diff --git a/BMM/BMM_Theory/README.md b/BMM/BMM_Theory/README.md index 50d8d4e..f1ad30d 100644 --- a/BMM/BMM_Theory/README.md +++ b/BMM/BMM_Theory/README.md @@ -52,12 +52,12 @@ python -m unittest discover -s tests -v - **GM 是读写共享总线 (1.6TB/s)**: MTE2 的 GM 读与 Fixpipe 直写 GM 并发时按 **(读+写)/1.6TB/s 累加**计入 MTE2 搬移链 (issue#23); - **搬入 MTE2 分两段、同链相加**: `t_mte2_gm` (首读按 GM 带宽; 随路驻留 L2 不重复累加) + `t_mte2_l2` (共享块驻留 L2 后被其它核重复读, 按 L2 读口 5.2TB/s) + DMA 命令开销 (issue#24; **T_cmd 默认 0**, 未标定按 0 处理, issue#36); - **搬移效率模型 (issue#36)**: 切B 两分支 (IterBatch/MergeBatch) 的 GM→L1 数据时延按单命令 tile 效率加权 —— eff = min(1, tile/min_TileSize), tile = nValue×dValue×dtype 达 16KB 饱和; **MergeBatch 合并 b0 个 batch 使单块 tile 放大 b0 倍, 即便 T_cmd=0 也比 IterBatch 逐 batch 搬移效率高** (堆叠方向视转置: A ND 非转置沿 M(nValue), B ND 非转置沿 N(dValue)); 只影响时间列, GM 字节量不变; -- **Cube 计算** `t_mmad`: 芯片算力 ≈486 TFLOPS (单核 ≈15.2 TFLOPS), MergeBatch 冗余计算计入; +- **Cube 计算** `t_mmad`: 芯片算力 = 白皮书 Cube-only 432 TFLOPS (单核 13.5 TFLOPS, issue#40), MergeBatch 冗余计算计入; - **Fixpipe 搬出**: 直写 GM 计入 GM 共享总线; 驻留 L2 走 5.2TB/s 写口 (独立计时); 数据量按 **C 矩阵 dtype** 计 (fp16/fp8 随路转换减半); StreamK 部分和按 4B (L0C dtype); - **总时延** `t_total = max(MTE2搬移链, MMAD, Fixpipe-L2) + t_drain` (稳态取最大 + 末级排空暴露; REDUCE 串行追加); - **GM 读取下限**: 每输入字节至少从 GM 读一次 (R1); L2 只吸收"驻留后的再次读取"; 整 case 输入+输出 ≤ L2 时 GM 恰读一次、输出全驻留 L2 (issue#29 设计文档 docs/05); - **Fixpipe 输出落点**: 整 case (输入+输出+workspace) 可驻留 L2 → 输出写 L2 写口 5.2TB/s、GM 写流量 0; 否则输入优先保 L2, 输出直写 GM 计入共享总线 (issue#30); -- **算力按输入 dtype**: Cube BF16/FP16 486TFLOPS 为基准, fp8=2x/fp4=4x (白皮书), fp32=1/2 (假设待标定); AIV 逐元素通量同理 (issue#28); +- **算力按输入 dtype**: Cube BF16/FP16 432TFLOPS 为基准 (Cube-only 口径, 白皮书表3-1 "Cube算力" 单行, issue#40), fp8=2x/fp4=4x (白皮书), fp32=1/2 (假设待标定); AIV 逐元素通量同理 (issue#28); - **瓶颈交换**: 搬移瓶颈可牺牲算力换搬移效率 (MergeBatch), 计算瓶颈可牺牲搬移换计算效率 (ASW_Basic 切 M/N). ## 目录结构 diff --git a/BMM/BMM_Theory/bmm_theory/hardware/ascend950dt.py b/BMM/BMM_Theory/bmm_theory/hardware/ascend950dt.py index 6dc9a5f..1617fd8 100644 --- a/BMM/BMM_Theory/bmm_theory/hardware/ascend950dt.py +++ b/BMM/BMM_Theory/bmm_theory/hardware/ascend950dt.py @@ -9,9 +9,9 @@ - L2 128MB 全档一致 (950PR 28 核降 112MB). 共架构的交叉验证 (表3-1/表4-2 反推, 与 950PR 单核速率一致): - - Cube: 432T/32核 = 486T/36核 = 13.5T/核 (= 16^3 MAC/拍 @ ~1.65GHz); - 本表 cube_peak_tflops 沿用 NpuSpec 现行口径 (= 白皮书 "Cube+Vector - 总算力" 行, 单核 15.1875T 全系列一致, 口径说明见 ascend950pr.py); + - Cube: 432T/32核 = 486T/36核 = 13.5T/核 (= 16^3 MAC/拍 @ ~1.65GHz), + cube_peak_tflops 取白皮书表3-1 "Cube算力" 单行 (Cube-only 口径, + issue#40 用户裁决), 单核 13.5T 全系列精确一致; - Vector fp32: 27T/64核 ≈ 30T/72核 -> 128 lane/拍 @ 1.65GHz (乘加计 2 次), 即 aiv_freq_ghz / aiv_fp32_per_cycle 默认值直接适用; - L1 512KB / L0A/L0B 64KB / L0C 256KB / UB 512KB 每核一致 (表4-2); @@ -24,33 +24,33 @@ from __future__ import annotations from .ascend950pr import NpuSpec -# 950DT 36 核主 bin (白皮书表3-1: 36 AIC / 72 AIV, HBM 4TB/s 144GB, L2 128MB; -# L2 带宽 7.5TB/s 读写各自独享, issue#39) +# 950DT 36 核主 bin (白皮书表3-1: 36 AIC / 72 AIV, Cube BF16 486 TFLOPS, +# HBM 4TB/s 144GB, L2 128MB; L2 带宽 7.5TB/s 读写各自独享, issue#39) ASCEND950DT = NpuSpec( name="Ascend950DT", aic_num=36, aiv_num=72, - cube_peak_tflops=547.0, - bw_gm=4.0e12, - bw_l2=7.5e12, - gm_capacity_gb=144.0, -) - -# 950DT 32 核档 (HBM 4TB/s 不变; 容量表3-1 仅给 144/96 两档, 32 核档映射待确认) -ASCEND950DT_C32 = NpuSpec( - name="Ascend950DT_C32", - aic_num=32, aiv_num=64, cube_peak_tflops=486.0, bw_gm=4.0e12, bw_l2=7.5e12, gm_capacity_gb=144.0, ) -# 950DT 28 核档 (HBM 4TB/s 不变, 容量 96GB; 总算力 425 为白皮书取整值, -# 单核 15.179T 与主 bin 15.1875T 差 0.06% 属取整误差) +# 950DT 32 核档 (Cube BF16 432 TFLOPS; HBM 4TB/s 不变; +# 容量表3-1 仅给 144/96 两档, 32 核档映射待确认) +ASCEND950DT_C32 = NpuSpec( + name="Ascend950DT_C32", + aic_num=32, aiv_num=64, + cube_peak_tflops=432.0, + bw_gm=4.0e12, + bw_l2=7.5e12, + gm_capacity_gb=144.0, +) + +# 950DT 28 核档 (Cube BF16 378 TFLOPS; HBM 4TB/s 不变, 容量 96GB) ASCEND950DT_C28 = NpuSpec( name="Ascend950DT_C28", aic_num=28, aiv_num=56, - cube_peak_tflops=425.0, + cube_peak_tflops=378.0, bw_gm=4.0e12, bw_l2=7.5e12, gm_capacity_gb=96.0, diff --git a/BMM/BMM_Theory/bmm_theory/hardware/ascend950pr.py b/BMM/BMM_Theory/bmm_theory/hardware/ascend950pr.py index a080514..f5dca9d 100644 --- a/BMM/BMM_Theory/bmm_theory/hardware/ascend950pr.py +++ b/BMM/BMM_Theory/bmm_theory/hardware/ascend950pr.py @@ -12,10 +12,12 @@ dtype 感知算力 (issue#28, 设计文档 docs/05 §2): (按 DaVinci 惯例 = 1/2, 白皮书未给同代比值), int8 假设同 FP8, 均待实测标定. AIV 逐元素通量按 lane 位宽等比假设 (16bit x2 / 8bit x4 / 4bit x8, 待标定). -口径注意 (issue#38): cube_peak_tflops 沿用 v0.98/用户澄清口径 = 白皮书表3-1 - "Cube+Vector 总算力" 行 (950PR 32核 = 486), 单核 15.1875T; 白皮书 "Cube算力" - 单行为 Cube 单元独立口径 (950PR 32核 = 432, 单核 13.5T)。两者差 12.5%, - 是否切换全模型口径待用户裁决 (本字段语义不变, 新增 SKU 同口径). +口径 (issue#40 用户裁决): cube_peak_tflops 采用白皮书表3-1 **"Cube算力"单行** + (Cube-only, 不含 Vector): 950PR 32核 = 432, 单核 13.5T = 16³ MAC/拍 × 1.65GHz; + 全系列 SKU 单核精确统一 13.5T (432/32 = 378/28 = 486/36)。2026-09 前曾沿用 + v0.98 的 "Cube+Vector 总算力" 口径 (486, 单核 15.1875T), 切换后全模型 MMAD + 时延 ×486/432 (+12.5%), R16 607.5→540, StreamK θ_c 12.24→10.9, + ASW 面积/周长分界 93.5→83.1。 """ from __future__ import annotations @@ -48,7 +50,8 @@ class NpuSpec: # ---- 核数与算力 ---- aic_num: int = 32 # C: AIC (Cube) 核数 aiv_num: int = 64 # AIV (Vector) 核数 - cube_peak_tflops: float = 486.0 # 全芯片 Cube BF16 标称算力 (乘加各计一次) + cube_peak_tflops: float = 432.0 # 全芯片 Cube BF16 标称算力 (乘加各计一次, + # 白皮书表3-1 Cube 单行, issue#40) aiv_freq_ghz: float = 1.65 aiv_fp32_per_cycle: int = 128 # 单 AIV 每拍 fp32 求和吞吐 @@ -90,7 +93,7 @@ class NpuSpec: # ---- 派生量 (属性) ---- @property def q16(self) -> float: - """单核 Cube BF16/FP16 峰值算力 (FLOP/s) = 15.1875T.""" + """单核 Cube BF16/FP16 峰值算力 (FLOP/s) = 13.5T (issue#40 Cube-only).""" return self.cube_peak_tflops * 1e12 / self.aic_num @staticmethod @@ -147,10 +150,10 @@ class NpuSpec: @property def r16(self) -> float: - """16bit 位宽平衡点算存比 R_16 = Cube峰值 / (GM带宽/2B) ≈ 607.5 FLOP/元素. + """16bit 位宽平衡点算存比 R_16 = Cube峰值 / (GM带宽/2B) = 540 FLOP/元素. 按 issue#28 速率表该比值对全 dtype 不变 (Cube 因子与元素字节数互成反比), - 故入口条件沿用单一 R_16. + 故入口条件沿用单一 R_16. (issue#40 Cube-only 口径: 607.5 -> 540) """ return self.cube_peak_tflops * 1e12 / (self.bw_gm / 2) @@ -173,12 +176,11 @@ class NpuSpec: ASCEND950PR = NpuSpec() # 950PR 28 核衍生版 (白皮书表3-1: 28 AIC / 56 AIV, HBM 1.4TB/s 112GB, -# L2 112MB; L2 带宽未分档, 沿用 5.2TB/s 待标定; 总算力 425 为白皮书取整值, -# 单核 15.179T 与主 bin 15.1875T 差 0.06% 属取整误差) +# L2 112MB; L2 带宽未分档, 沿用 5.2TB/s 待标定) ASCEND950PR_C28 = NpuSpec( name="Ascend950PR_C28", aic_num=28, aiv_num=56, - cube_peak_tflops=425.0, + cube_peak_tflops=378.0, l2_bytes=112 * 1024 * 1024, bw_gm=1.4e12, gm_capacity_gb=112.0, diff --git a/BMM/BMM_Theory/docs/02_分支理论/00_总纲_分支决策树.md b/BMM/BMM_Theory/docs/02_分支理论/00_总纲_分支决策树.md index 70460be..3f7acd7 100644 --- a/BMM/BMM_Theory/docs/02_分支理论/00_总纲_分支决策树.md +++ b/BMM/BMM_Theory/docs/02_分支理论/00_总纲_分支决策树.md @@ -18,7 +18,9 @@ $$T_{total} = \max\big(T_{MMAD},\; T_{MTE2},\; T_{MTE1},\; T_{Fixpipe}\;[,\;T_{R case 固有算存比与 16bit 位宽平衡点： -$$AI = \frac{2MN}{M+N},\qquad R_{16} = \frac{486\ \text{TFLOPS}}{1.6\ \text{TB/s}\,/\,2\ \text{B}} \approx 607.5$$ +$$AI = \frac{2MN}{M+N},\qquad R_{16} = \frac{432\ \text{TFLOPS}}{1.6\ \text{TB/s}\,/2\ \text{B}} = 540$$ + +（Cube 算力为白皮书 Cube-only 口径 432 TFLOPS，issue#40；此前 v0.98 沿用总算力 486 → R₁₆=607.5。） AI < R₁₆ → 访存 Bound；反之计算 Bound。 @@ -66,7 +68,7 @@ case (B, M, N, K, dtype) │ ▼ P ≤ C/2 (B/M/N 都买不满) StreamK: 核间切 K + 归约 - 进入: P ≤ C/2, K/grid_K ≥ 256B/dtype, K > grid_K²/(grid_K-1)·θ_c (θ_c≈12) + 进入: P ≤ C/2, K/grid_K ≥ 256B/dtype, K > grid_K²/(grid_K-1)·θ_c (θ_c≈10.9, issue#40 Cube-only 口径) ``` ## 4. 重叠区仲裁 diff --git a/BMM/BMM_Theory/docs/02_分支理论/05_StreamK分支.md b/BMM/BMM_Theory/docs/02_分支理论/05_StreamK分支.md index 68c3f36..528f3bd 100644 --- a/BMM/BMM_Theory/docs/02_分支理论/05_StreamK分支.md +++ b/BMM/BMM_Theory/docs/02_分支理论/05_StreamK分支.md @@ -16,7 +16,7 @@ |---|---|---| | 1 | `P ≤ C/2` | **并行缺口**：不切 K 时至多一半核有事做，K 是唯一剩余的并行维度。阈值取 C/2 而非 C：StreamK 定义即 grid_K≥2（至少 2 路切 K），grid_K=2 时每块需 2 核，总核数需求 = ⌈P⌉×2 ≤ C | | 2 | `K/grid_K ≥ 256B/dtype` | **单核 K 段下限**：每核 K 段内轴连续长度不小于 dValue 推荐值，保证段内搬移效率不崩。grid_K = ⌊C/⌈P⌉⌋ | -| 3 | `K > grid_K²/(grid_K-1)·θ_c`，θ_c≈12 | **归约代价可接受**：切 K 后总时延须小于不切 K（降核 ASW），推导见 §3 | +| 3 | `K > grid_K²/(grid_K-1)·θ_c`，θ_c≈10.9 | **归约代价可接受**：切 K 后总时延须小于不切 K（降核 ASW），推导见 §3 | | 4 | 确定性等级 ≤ 1 且 ND 格式 | 归约顺序不定引入浮点非确定性，确定性等级 2/3 的业务禁用 | ## 3. 归约代价与 θ_c 推导（条件 3 的来源） @@ -34,13 +34,13 @@ $$T_{Reduce}^t = \underbrace{\frac{grid_K\cdot M^t N^t\cdot 4B}{W_{L2}}}_{\text{ **计算 Bound 情形**（T_pipe = T_MMAD^t）代入判据，两边除以 L0C/4B 后 **tile 尺寸消去**——K 阈值不依赖 M/N 具体值： -$$K > \frac{grid_K^2}{grid_K-1}\cdot\theta_c,\qquad \theta_c = \frac{Q_{16}}{2}\Big(\frac{8B}{W_{L2}}+\frac{1}{Q_{AIV}}\Big) \approx 12$$ +$$K > \frac{grid_K^2}{grid_K-1}\cdot\theta_c,\qquad \theta_c = \frac{Q_{16}}{2}\Big(\frac{8B}{W_{L2}}+\frac{1}{Q_{AIV}}\Big) \approx 10.9$$ -代入数值：grid_K=2 → K>49；grid_K=4 → K>66；grid_K=8 → K>112。L2 读写（1.54 ps/元素）是主导项，AIV 求和仅占 5%。 +（Q16 为 Cube-only 口径 13.5T，issue#40；旧总算力口径 15.1875T 时 θ_c≈12。）代入数值：grid_K=2 → K>44；grid_K=4 → K>58；grid_K=8 → K>100。L2 读写（1.54 ps/元素）是主导项，AIV 求和仅占 5%。 -访存 Bound 情形阈值恒低于计算 Bound（θ_m·[M^tN^t/(M^t+N^t)]/θ_c ≤ 128/304 ≈ 0.42 < 1），故**汇总条件取计算 Bound 阈值**（保守，覆盖两种情形）。 +访存 Bound 情形阈值恒低于计算 Bound（θ_m·[M^tN^t/(M^t+N^t)]/θ_c ≤ 128/270 ≈ 0.47 < 1），故**汇总条件取计算 Bound 阈值**（保守，覆盖两种情形）。 -> **注意**：θ_c 对 workspace 落点敏感——部分和落 GM 时读写带宽从 5.2TB/s 降到 ~0.64TB/s，θ_c 升至约 97。**设计时应优先保证 workspace 驻留 L2**。 +> **注意**：θ_c 对 workspace 落点敏感——部分和落 GM 时读写带宽从 5.2TB/s 降到 ~0.64TB/s，θ_c 升至约 86。**设计时应优先保证 workspace 驻留 L2**。 ## 4. 实现方案 @@ -70,4 +70,4 @@ $$T_{SK} = \max\Big(\frac{T_{MMAD}}{grid_K},\; \frac{T_{MTE2}}{grid_K}\Big) + T_ - `8192` = C×512B = dValue 推荐值在最大 grid_K=C 下的保障（同为条件 2，取推荐值）； - max 取更严的 8192。 -修正后的归约阈值（θ_c≈12，grid_K=32 时 K>396）远低于 8192，说明 **8192 的绑定约束是 dValue（条件 2），不是归约代价（条件 3）**。源码不动态算 grid_K，用固定阈值保守合并两条条件。本软件按理论动态计算 grid_K 与 θ_c，进入条件更精细。 +修正后的归约阈值（θ_c≈10.9，grid_K=32 时 K>360）远低于 8192，说明 **8192 的绑定约束是 dValue（条件 2），不是归约代价（条件 3）**。源码不动态算 grid_K，用固定阈值保守合并两条条件。本软件按理论动态计算 grid_K 与 θ_c，进入条件更精细。 diff --git a/BMM/BMM_Theory/docs/02_分支理论/06_ASW_Basic分支.md b/BMM/BMM_Theory/docs/02_分支理论/06_ASW_Basic分支.md index 20029ee..bae05da 100644 --- a/BMM/BMM_Theory/docs/02_分支理论/06_ASW_Basic分支.md +++ b/BMM/BMM_Theory/docs/02_分支理论/06_ASW_Basic分支.md @@ -172,7 +172,7 @@ A 行块 block_a = a_b/m_cnt、B 列块 block_b = b_b/n_cnt。 - A1b 与方案 B **理论时延严格相等**（总量守恒 `T = c·B·M·N/C`）； - **默认选方案 B（工程简洁：一套 tile、无尾轮分支）**；追求搬移下限选 A1b（周长和恒 ≤ 方案 B，均值不等式）； -- r 小（ρ < (187/s)²）时 A1b 尾轮翻出为周长型，**方案 B 微优 ~6%**； +- r 小（ρ < (166/s)²，Cube-only 口径下由 187 修正，issue#40）时 A1b 尾轮翻出为周长型，**方案 B 微优 ~6%**； - A1a 是 A1b 真子集，仅在 r | C 且 s*=⌊C/r⌋ 完美时打平，工程上可不单列。 **边角场景（周长型主导，小 tile 或工作集超 L2 的 GM 直读）**： diff --git a/BMM/BMM_Theory/docs/02_分支理论/07_尾轮处理策略.md b/BMM/BMM_Theory/docs/02_分支理论/07_尾轮处理策略.md index 2e59089..33af896 100644 --- a/BMM/BMM_Theory/docs/02_分支理论/07_尾轮处理策略.md +++ b/BMM/BMM_Theory/docs/02_分支理论/07_尾轮处理策略.md @@ -17,12 +17,14 @@ $$T_{MMAD} = \frac{2\cdot sM\cdot sN\cdot K}{Q_{16}},\qquad T_{MTE2} = \frac{K(s | 对比 | 判据 | 决定因素 | |---|---|---| | MMAD vs MTE2 | `sM·sN/(sM+sN)` ⋛ `dt·Q16/(2·BW_eff)` | **tile 尺寸**（K 约掉） | -| MMAD vs FIX | `K` ⋛ `outB·Q16/(2·BW_pc)` ≈ 304 | **K** | +| MMAD vs FIX | `K` ⋛ `outB·Q16/(2·BW_pc)` ≈ 270 | **K** | + +（Q16 为 Cube-only 口径 13.5T（issue#40）：MMAD/MTE2 分界 93.5→**83.1**，MMAD/FIX 分界 304→**270**。） **缩放类型二分**：MMAD 与 FIX 都 ∝ 面积 sM·sN，MTE2 ∝ 周长 (sM+sN)。 -- **面积型主导**（MMAD 或 FIX 最大）：tile 大（sM·sN/(sM+sN)≥93.5，L2 命中）且（K≥304 时 MMAD、K<304 时 FIX）——**主流 prefill/decode case 均属此类**； -- **周长型主导**（MTE2 最大）：tile 小（<93.5，L2 命中）或工作集超 L2 的 GM 直读（<304）——边角 case。 +- **面积型主导**（MMAD 或 FIX 最大）：tile 大（sM·sN/(sM+sN)≥83.1，L2 命中）且（K≥270 时 MMAD、K<270 时 FIX）——**主流 prefill/decode case 均属此类**； +- **周长型主导**（MTE2 最大）：tile 小（<83.1，L2 命中）或工作集超 L2 的 GM 直读（<270）——边角 case。 ## 2. 四种策略定义 @@ -54,7 +56,7 @@ $$\big(n_{wave}-1+\sqrt{\rho}\big)^2 \le n_{wave}(n_{wave}-1+\rho) \iff (\sqrt{\ **A1b 周长和恒 ≤ 方案 B**（搬入总量少、L2 重复读少、掩盖余量大）。离散 16 对齐后时延互有胜负（<3%，数值依赖、无系统性方向）。 -**尾轮翻出修正**（§7.2.4）：面积型主导但 r 小（ρ < (187/s)²）时 A1b 尾轮 tile 缩得太小，周长/面积比上升使主导项翻转为周长型（搬入翻出），方案 B 的全局 tile 缩得温和（1/√g > √ρ 恒成立）不翻出——**r 小的面积型 case 方案 B 可微优 ~6%**。 +**尾轮翻出修正**（§7.2.4）：面积型主导但 r 小（ρ < (166/s)²，Cube-only 口径下 187→166，issue#40）时 A1b 尾轮 tile 缩得太小，周长/面积比上升使主导项翻转为周长型（搬入翻出），方案 B 的全局 tile 缩得温和（1/√g > √ρ 恒成立）不翻出——**r 小的面积型 case 方案 B 可微优 ~6%**。 ## 4. 周长型主导（边角场景） @@ -79,7 +81,7 @@ $$\big(n_{wave}-1+\sqrt{\rho}\big)^2 \le n_{wave}(n_{wave}-1+\rho) \iff (\sqrt{\ | 1 | r = 0 | A0 | n_wave·T_block | | 2 | 面积型，0C/2，无翻出 | A1b 或方案 B（严格打平） | T_block(n_wave−1+ρ) | -| 4 | 面积型，ρ<(187/s)²（翻出） | 方案 B | T_block·n_wave/g | +| 4 | 面积型，ρ<(166/s)²（翻出，issue#40 口径） | 方案 B | T_block·n_wave/g | | 5 | 周长型，ρ≥ρ_dv，B 可行 | A1b | T_load(n_wave−1+√ρ) | | 6 | 周长型，ρ<ρ_dv 且分界成立且 B 可行 | 方案 B | T_load·n_wave/√g | | 7 | 周长型，广义 B 损失>0 | A1b（恒不劣） | 广义枚举 min w×T_block | diff --git a/BMM/BMM_Theory/docs/04_差异对照_bmmv3_vs_BMM_Theory.md b/BMM/BMM_Theory/docs/04_差异对照_bmmv3_vs_BMM_Theory.md index 9376a8c..7d9e4dc 100644 --- a/BMM/BMM_Theory/docs/04_差异对照_bmmv3_vs_BMM_Theory.md +++ b/BMM/BMM_Theory/docs/04_差异对照_bmmv3_vs_BMM_Theory.md @@ -44,7 +44,7 @@ | M≤N 约束 | 有（条件 13） | 无 | bmmv3 源码特有（实现限制，非理论必要） | | 转置 view | 非连续转置 view 排除 | 不建模 | bmmv3 源码特有 | | bias | `has_bias=false` | 不建模 | bmmv3 源码特有 | -| 访存 Bound | `2MN/(M+N) < 607/2`（经验常数） | `2MN/(M+N) < R16/b0`（R16=算存比） | **我们更通用**——607.5 是 R16 在 fp16 下的数值实例，fp32 时 R16 减半但 bmmv3 不会 | +| 访存 Bound | `2MN/(M+N) < 607/2`（经验常数） | `2MN/(M+N) < R16/b0`（R16=算存比） | **我们更通用**——bmmv3 的 607 对应旧总算力口径 R16=607.5；现行 Cube-only 口径 R16=540（issue#40），fp32 时 R16 再减半但 bmmv3 不会 | ### 2.2 b0 计算 diff --git a/BMM/BMM_Theory/docs/05_L2驻留GM读写与dtype算力口径_设计分析.md b/BMM/BMM_Theory/docs/05_L2驻留GM读写与dtype算力口径_设计分析.md index a494639..fa0eb12 100644 --- a/BMM/BMM_Theory/docs/05_L2驻留GM读写与dtype算力口径_设计分析.md +++ b/BMM/BMM_Theory/docs/05_L2驻留GM读写与dtype算力口径_设计分析.md @@ -25,7 +25,9 @@ - L2: 128MB, **5.2TB/s, 读口/写口各自独享** —— L2 重复读(读口)与 Fixpipe→L2 写(写口)互不竞争 (issue#23 已落地)。 - 输入首访一律走 GM 带宽计一次, 不叠加 L2 (issue#24 已落地); L2 只吸收"驻留后的再次读取"。 - Cube 算力分精度 (白皮书: FP8/MXFP8/HiF8 = 2×FP16, MXFP4 = 4×FP16; 16bit 档 = 基准): - BF16 486 TFLOPS/芯片 (=15.1875 TFLOPS/核)。FP32/TF32 同代比值白皮书未给 → **假设 ½, 待实测标定** (见 §2 假设表)。 + BF16 **432 TFLOPS/芯片 (=13.5 TFLOPS/核, Cube-only 口径 = 白皮书表3-1 "Cube算力" 单行, + issue#40 用户裁决; 486 为 Cube+Vector 总算力, 不作为 Cube 时延基准)**。 + FP32/TF32 同代比值白皮书未给 → **假设 ½, 待实测标定** (见 §2 假设表)。 - AIV (Vector): 64 核 × 128 fp32 lane/拍 × 1.65GHz = 13.5T 元素/s (fp32 档)。 --- @@ -201,7 +203,8 @@ dma_cmd_count 为**单核**命令数 (各核 DMA 引擎并行执行, 墙钟 T_cm CSV 证据 (merge_demo_k_trunc, B=2048 M=N=32 K=256, b0=4, b_core=64): flops_step = 2·128·128·256 = 8,388,608; 步数 16; 合计 134,217,728 = 代码值 = CSV cube_flops 列; -t_mmad = 134,217,728 / 15.1875e12 = 8.837us = CSV t_mmad。**结论: 无需数值修改**; +t_mmad = 134,217,728 / 13.5e12 = 9.942us = CSV t_mmad (Cube-only 口径 issue#40; +旧总算力口径 15.1875T 时为 8.837us)。**结论: 无需数值修改** (指 flops 公式); 若意图是"只算对角块"则与全网格 GEMM 语义冲突 (冗余消失, v0.98 §五 理论前提需另行裁决)。 --- diff --git a/BMM/BMM_Theory/examples/plans.csv b/BMM/BMM_Theory/examples/plans.csv index 0c8da55..49744d9 100644 --- a/BMM/BMM_Theory/examples/plans.csv +++ b/BMM/BMM_Theory/examples/plans.csv @@ -2,7 +2,7 @@ to_matmul_demo,转Matmul,Ascend950PR,batch_mat_mul_v3,32,1,0,0,1,"折叠为 Matmul [2048,2048]x[2048,2048], 复用 Matmul 切分体系",0,1,0,0,2048,0,1,,0,0,0,,,0,0,转Matmul后由 Matmul 体系决定,1,1,1,0,0,0,0,True,2,"BatchB=1免费折叠: 左矩阵 [1,2048,2048] 视图折叠为 [2048,2048], 零重排零 split" special_k0_demo,特殊分支,Ascend950PR,batch_mat_mul_v3,64,1,1,1,1,AIV 核间按行均分 (无 Cube tile 概念),0,1,0,0,0,0,1,UB驻留(AIV),0,0,0,allocate,direct_gm,0,0,不涉及(AIV逐元素),1,1,1,0,0,0,0,False,2,"K=0纯写值: 无任何计算, C=bias 或 0, 纯 AIV 写值; 按行均分到 AIV 核" special_k1_demo,特殊分支,Ascend950PR,batch_mat_mul_v3,64,1,1,1,1,AIV 核间按行均分 (无 Cube tile 概念),0,1,0,0,1,0,1,UB驻留(AIV) UB乒乓,0,0,0,allocate,direct_gm,0,0,不涉及(AIV逐元素),1,1,1,0,0,0,0,False,2,"K=1逐元素乘: 退化为 C=A⊙B 无累加深度, Cube 16x16x16 粒度浪费 15/16; 走 AIV 通路 GM->UB->Mul->GM, UB乒乓 (B>=2*AIV 双batch乒乓流水)" -merge_demo_k_trunc,MergeBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B均分(核间零重复读零依赖),64,4,64,256,128,128,12,合并驻留,64,256,64,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"b0=4 (L0C上限5.7/算存比上限23.7/b_core=64); K截断; 合并后单次DMA搬入 A'[64,128]+B'[128,256]; 输出落点: L2驻留 (整case V_in+V_out=40.0MB vs L2=128MB)" +merge_demo_k_trunc,MergeBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B均分(核间零重复读零依赖),64,4,64,256,128,128,12,合并驻留,64,256,64,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"b0=4 (L0C上限5.7/算存比上限21.1/b_core=64); K截断; 合并后单次DMA搬入 A'[64,128]+B'[128,256]; 输出落点: L2驻留 (整case V_in+V_out=40.0MB vs L2=128MB)" merge_iter_arbitrate,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),4,1,64,64,512,512,2,b_双batch乒乓,64,64,256,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,双batch乒乓: 2*(MK+KN)*dtype=256KB <= L1; 输出落点: L2驻留 iter_demo_form_b,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),4,1,64,64,256,256,2,b_双batch乒乓,64,64,256,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,双batch乒乓: 2*(MK+KN)*dtype=128KB <= L1; 输出落点: L2驻留 iter_demo_form_d,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),2,1,64,64,8192,1024,1,d_两侧都切K,64,64,256,allocate(GM->L1随路驻留L2),"direct_gm(整case超L2: 输入优先驻留L2, 输出直写GM不占L2)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"两侧都切K: k_L1=1024, K段成对流水, batch边界天然无缝; dValueA=2048B/dValueB=128B; 输出落点: 直写GM" diff --git a/BMM/BMM_Theory/examples/result_evaluate.csv b/BMM/BMM_Theory/examples/result_evaluate.csv index 8a9fe22..b023d87 100644 --- a/BMM/BMM_Theory/examples/result_evaluate.csv +++ b/BMM/BMM_Theory/examples/result_evaluate.csv @@ -1,45 +1,45 @@ case_id,batch_a,batch_b,m,n,k,dtype_a,dtype_b,dtype_c,trans_a,trans_b,has_bias,out_nd,deterministic_level,plan_case_id,plan_branch,plan_npu,plan_op,plan_used_core_num,plan_split_b,plan_m_cnt,plan_n_cnt,plan_grid_k,plan_core_map,plan_b_core,plan_merge_b0,plan_single_core_m,plan_single_core_n,plan_single_core_k,plan_k_l1,plan_b_l1,plan_l1_form,plan_base_m,plan_base_n,plan_base_k,plan_l2_policy_in,plan_l2_policy_out,plan_swizzle_w,plan_workspace_bytes,plan_tail_strategy,plan_tail_m_cnt,plan_tail_n_cnt,plan_tail_k_cnt,plan_tail_m_main,plan_tail_n_main,plan_tail_block_cnt,plan_tail_wave_num,plan_fixpipe_unitflag,plan_out_dtype_bytes,plan_note,gm_read_bytes,l2_read_bytes,t_mte2_gm,t_mte2_l2,t_mte2,dma_cmd_count,t_dma_cmd,cube_flops,t_mmad,fixpipe_bytes,t_fixpipe,t_reduce,t_steady,t_drain,t_total,bottleneck,feasible,violations,bound_type,advice -to_matmul_demo,1,1,2048,2048,2048,bf16,bf16,bf16,False,False,False,True,0,to_matmul_demo,转Matmul,Ascend950PR,batch_mat_mul_v3,32,1,0,0,1,"折叠为 Matmul [2048,2048]x[2048,2048], 复用 Matmul 切分体系",0,1,0,0,2048,0,1,,0,0,0,,,0,0,转Matmul后由 Matmul 体系决定,1,1,1,0,0,0,0,True,2,"BatchB=1免费折叠: 左矩阵 [1,2048,2048] 视图折叠为 [2048,2048], 零重排零 split",16777216,0.0,1.048576e-05,0.0,1.048576e-05,0.0,0.0,17179869184.0,3.534952506995885e-05,8388608,1.6131938461538462e-06,0.0,3.534952506995885e-05,0.0,3.534952506995885e-05,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" +to_matmul_demo,1,1,2048,2048,2048,bf16,bf16,bf16,False,False,False,True,0,to_matmul_demo,转Matmul,Ascend950PR,batch_mat_mul_v3,32,1,0,0,1,"折叠为 Matmul [2048,2048]x[2048,2048], 复用 Matmul 切分体系",0,1,0,0,2048,0,1,,0,0,0,,,0,0,转Matmul后由 Matmul 体系决定,1,1,1,0,0,0,0,True,2,"BatchB=1免费折叠: 左矩阵 [1,2048,2048] 视图折叠为 [2048,2048], 零重排零 split",16777216,0.0,1.048576e-05,0.0,1.048576e-05,0.0,0.0,17179869184.0,3.97682157037037e-05,8388608,1.6131938461538462e-06,0.0,3.97682157037037e-05,0.0,3.97682157037037e-05,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" special_k0_demo,128,128,256,256,0,bf16,bf16,bf16,False,False,False,True,0,special_k0_demo,特殊分支,Ascend950PR,batch_mat_mul_v3,64,1,1,1,1,AIV 核间按行均分 (无 Cube tile 概念),0,1,0,0,0,0,1,UB驻留(AIV),0,0,0,allocate,direct_gm,0,0,不涉及(AIV逐元素),1,1,1,0,0,0,0,False,2,"K=0纯写值: 无任何计算, C=bias 或 0, 纯 AIV 写值; 按行均分到 AIV 核",0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,16777216,3.2263876923076923e-06,0.0,3.2263876923076923e-06,0.0,3.2263876923076923e-06,FIXPIPE,True,,写出Bound(L2写口),"瓶颈在 Fixpipe 写出: 检查输出 dtype (fp16/fp8 可减半写出量), 或评估输出驻留 L2 异步回写策略" special_k1_demo,128,128,256,256,1,bf16,bf16,bf16,False,False,False,True,0,special_k1_demo,特殊分支,Ascend950PR,batch_mat_mul_v3,64,1,1,1,1,AIV 核间按行均分 (无 Cube tile 概念),0,1,0,0,1,0,1,UB驻留(AIV) UB乒乓,0,0,0,allocate,direct_gm,0,0,不涉及(AIV逐元素),1,1,1,0,0,0,0,False,2,"K=1逐元素乘: 退化为 C=A⊙B 无累加深度, Cube 16x16x16 粒度浪费 15/16; 走 AIV 通路 GM->UB->Mul->GM, UB乒乓 (B>=2*AIV 双batch乒乓流水)",131072,0.0,8.192e-08,0.0,8.192e-08,0.0,0.0,8388608.0,3.103030303030303e-07,16777216,3.2263876923076923e-06,0.0,3.2263876923076923e-06,0.0,3.2263876923076923e-06,FIXPIPE,True,,写出Bound(L2写口),"瓶颈在 Fixpipe 写出: 检查输出 dtype (fp16/fp8 可减半写出量), 或评估输出驻留 L2 异步回写策略" -merge_demo_k_trunc,2048,2048,16,64,128,bf16,bf16,bf16,False,False,False,True,0,merge_demo_k_trunc,MergeBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B均分(核间零重复读零依赖),64,4,64,256,128,128,12,合并驻留,64,256,64,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"b0=4 (L0C上限5.7/算存比上限23.7/b_core=64); K截断; 合并后单次DMA搬入 A'[64,128]+B'[128,256]; 输出落点: L2驻留 (整case V_in+V_out=40.0MB vs L2=128MB)",41943040,0.0,2.62144e-05,0.0,2.62144e-05,16,0.0,2147483648.0,4.418690633744856e-06,4194304,8.065969230769231e-07,0.0,2.62144e-05,1.1945434884457107e-07,2.6333854348844573e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" -merge_iter_arbitrate,128,128,64,64,512,bf16,bf16,bf16,False,False,False,True,0,merge_iter_arbitrate,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),4,1,64,64,512,512,2,b_双batch乒乓,64,64,256,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,双batch乒乓: 2*(MK+KN)*dtype=256KB <= L1; 输出落点: L2驻留,16777216,0.0,1.048576e-05,0.0,1.048576e-05,4,0.0,536870912.0,1.104672658436214e-06,1048576,2.0164923076923077e-07,0.0,1.048576e-05,3.265804723013612e-07,1.081234047230136e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" -iter_demo_form_b,128,128,64,64,256,bf16,bf16,bf16,False,False,False,True,0,iter_demo_form_b,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),4,1,64,64,256,256,2,b_双batch乒乓,64,64,256,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,双batch乒乓: 2*(MK+KN)*dtype=128KB <= L1; 输出落点: L2驻留,8388608,0.0,5.24288e-06,0.0,5.24288e-06,4,0.0,268435456.0,5.52336329218107e-07,1048576,2.0164923076923077e-07,0.0,5.24288e-06,1.8849638999683443e-07,5.431376389996834e-06,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" -iter_demo_form_d,64,64,64,64,8192,bf16,bf16,bf16,False,False,False,True,0,iter_demo_form_d,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),2,1,64,64,8192,1024,1,d_两侧都切K,64,64,256,allocate(GM->L1随路驻留L2),"direct_gm(整case超L2: 输入优先驻留L2, 输出直写GM不占L2)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"两侧都切K: k_L1=1024, K段成对流水, batch边界天然无缝; dValueA=2048B/dValueB=128B; 输出落点: 直写GM",134217728,0.0,8.388608e-05,0.0,8.388608e-05,16,0.0,4294967296.0,8.837381267489712e-06,524288,3.2768e-07,0.0,8.421376e-05,7.16176329218107e-07,8.492993632921811e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" -streamk_demo,4,4,128,128,10240,bf16,bf16,bf16,False,False,False,True,0,streamk_demo,StreamK,Ascend950PR,batch_mat_mul_v3,32,1,1,1,32,"B/M/N切出4块, 每块32核切K归约 (归约组内核c负责K段[c*K/32,(c+1)*K/32))",1,1,128,128,320,256,1,K段标准分块流水,128,128,64,allocate(部分和驻留L2),"resident(部分和4B驻留L2, 防精度丢失不随C的fp16/fp8转换)",0,8388608,grid_K=32路切K+归约,1,1,32,0,0,0,0,True,4,"P=1.00, grid_K=32, 部分和驻留L2按4B写出, AIV归约后按C dtype=2B写最终",20971520,0,1.31072e-05,0.0,1.31072e-05,0.0,0.0,1342177280.0,2.761681646090535e-06,0.0,0.0,3.4067453613053613e-06,1.31072e-05,3.4067453613053613e-06,1.651394536130536e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" -asw_demo_full,2,2,8192,8192,1024,bf16,bf16,bf16,False,False,False,True,0,asw_demo_full,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,16,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,1024,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,16,True,2,"tile枚举: P=16, 有界枚举最优 mCnt=16 x nCnt=16 (tile 512x512, 每batch搬入512.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=64.0MB, V_out=256.0MB, L2=128MB); 尾轮: r=0 无尾轮",67108864,1006632960,4.194304e-05,0.00019358326153846154,0.00023552630153846153,0.0,0.0,274877906944.0,0.0005655924011193416,268435456,0.00016777216,0.0,0.0005655924011193416,0.0,0.0005655924011193416,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" -asw_demo_reduce_core,16,16,256,256,128,bf16,bf16,bf16,False,False,False,True,0,asw_demo_reduce_core,ASW_Basic_降核,Ascend950PR,batch_mat_mul_v3,16,1,1,1,1,"降核: 只用16核, 每核一个L0C满载输出块, 其余核闲置",0,1,256,256,128,128,1,标准核内流水,256,256,64,allocate,resident(整case全驻留S_A),0,0,不涉及(每核一块无尾轮),1,1,1,0,0,0,0,True,2,"P=16.00L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,单batch全驻留: (MK+KN)*dtype=68KB <= L1; 输出落点: L2驻留,2228224,0.0,1.6384e-06,0.0,1.6384e-06,1,0.0,16777216.0,3.452102057613169e-08,65536,1.2603076923076923e-08,0.0,1.6384e-06,4.712409749920861e-08,1.6855240974992087e-06,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" -b64_m16_n256_k512,64,64,16,256,512,bf16,bf16,bf16,False,False,False,True,0,b64_m16_n256_k512,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),2,1,16,256,512,240,1,c_一侧驻留+对侧切K,16,256,64,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"一侧驻留(A)+对侧切K: A驻留16KB, 预算L1/2, k_L1=240, dValueA=480B/dValueB=512B; 输出落点: L2驻留",17825792,0.0,1.114112e-05,0.0,1.114112e-05,6,0.0,268435456.0,5.52336329218107e-07,524288,1.0082461538461538e-07,0.0,1.114112e-05,1.798661348528015e-07,1.1320986134852803e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" -b128_m8_n192_k256,128,128,8,192,256,bf16,bf16,bf16,False,False,False,True,0,b128_m8_n192_k256,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),4,1,8,192,256,256,2,b_双batch乒乓,8,192,80,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,双batch乒乓: 2*(MK+KN)*dtype=200KB <= L1; 输出落点: L2驻留,13107200,0.0,9.17504e-06,0.0,9.17504e-06,4,0.0,100663296.0,2.0712612345679012e-07,393216,7.561846153846153e-08,0.0,9.17504e-06,7.068614624881291e-08,9.245726146248813e-06,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" -b32_m16_n8192_k7168,32,32,16,8192,7168,bf16,bf16,bf16,False,False,False,True,0,b32_m16_n8192_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,1,8,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,16,1024,7168,112,1,双缓冲驻留当前tile输入,16,1024,16,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,8,True,2,"tile枚举: 效率降级(放开约束4, dValue 按 128B 硬下限, 搬移效率低于模型假设, 时延可能低估): P=1, mCnt=1 x nCnt=8 (tile 16x1024, 每batch搬入113.8MB, r=0); Base tile 16x1024 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=3591.0MB, V_out=8.0MB, L2=128MB); 尾轮: r=0 无尾轮",3765436416,51380224,0.00235339776,9.880812307692307e-06,0.0023632785723076925,0.0,0.0,60129542144.0,0.00012372333774485596,8388608,5.24288e-06,0.0,0.0023685214523076923,0.0,0.0023685214523076923,MTE2,True,,访存Bound(GM读写共享+L2重复读),"效率降级标注 (plan.note): 搬移效率下限不满足 —— 方案照常给出 (兜底), 但实际效率低于模型假设, 时延可能低估; 建议调整 dtype/布局 | 瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" -b4_m1_n8192_k8192,4,4,1,8192,8192,bf16,bf16,bf16,False,False,False,True,0,b4_m1_n8192_k8192,StreamK,Ascend950PR,batch_mat_mul_v3,32,1,1,1,32,"B/M/N切出4块, 每块32核切K归约 (归约组内核c负责K段[c*K/32,(c+1)*K/32))",1,1,1,8192,256,256,1,K段标准分块流水,1,128,64,allocate(部分和驻留L2),"resident(部分和4B驻留L2, 防精度丢失不随C的fp16/fp8转换)",0,4194304,grid_K=32路切K+归约,1,1,32,0,0,0,0,True,4,"P=0.50, grid_K=32, 部分和驻留L2按4B写出, AIV归约后按C dtype=2B写最终",536936448,0.0,0.00033558528,0.0,0.00033558528,0.0,0.0,536870912.0,1.104672658436214e-06,0.0,0.0,1.731729603729604e-06,0.00033558528,1.731729603729604e-06,0.0003373170096037296,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" -b16_m2_n4096_k7168,16,16,2,4096,7168,bf16,bf16,bf16,False,False,False,True,0,b16_m2_n4096_k7168,StreamK,Ascend950PR,batch_mat_mul_v3,32,1,1,1,16,"B/M/N切出16块, 每块16核切K归约 (归约组内核c负责K段[c*K/16,(c+1)*K/16))",1,1,2,4096,448,256,1,K段标准分块流水,2,128,64,allocate(部分和驻留L2),"resident(部分和4B驻留L2, 防精度丢失不随C的fp16/fp8转换)",0,8388608,grid_K=16路切K+归约,1,1,16,0,0,0,0,True,4,"P=2.00, grid_K=16, 部分和驻留L2按4B写出, AIV归约后按C dtype=2B写最终",939982848,0,0.00058748928,0.0,0.00058748928,0.0,0.0,1879048192.0,3.866354304526749e-06,0.0,0.0,1.7726896037296038e-06,0.00058748928,1.7726896037296038e-06,0.0005892619696037297,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" -b32_m64_n64_k7168,32,32,64,64,7168,bf16,bf16,bf16,False,False,False,True,0,b32_m64_n64_k7168,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),1,1,64,64,7168,1024,1,d_两侧都切K,64,64,256,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"两侧都切K: k_L1=1024, K段成对流水, batch边界天然无缝; dValueA=2048B/dValueB=128B; 输出落点: L2驻留",58720256,0.0,3.670016e-05,0.0,3.670016e-05,7,0.0,1879048192.0,3.866354304526749e-06,262144,5.041230769230769e-08,0.0,3.670016e-05,6.027486369104147e-07,3.730290863691042e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" -b64_m1024_n1024_k7168,64,64,1024,1024,7168,bf16,bf16,bf16,False,False,False,True,0,b64_m1024_n1024_k7168,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),2,1,1024,1024,7168,64,1,d_两侧都切K,176,176,64,allocate(GM->L1随路驻留L2),"direct_gm(整case超L2: 输入优先驻留L2, 输出直写GM不占L2)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"两侧都切K: k_L1=64, K段成对流水, batch边界天然无缝; dValueA=128B/dValueB=2048B; 输出落点: 直写GM",1879048192,0.0,0.00117440512,0.0,0.00117440512,224,0.0,962072674304.0,0.0019795734039176954,134217728,8.388608e-05,0.0,0.0019795734039176954,5.078042126748971e-05,0.0020303538251851853,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" -b128_m2048_n2048_k1536,128,128,2048,2048,1536,bf16,bf16,bf16,False,False,False,True,0,b128_m2048_n2048_k1536,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,4,4,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,1536,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,64,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=4 x nCnt=4 (tile 512x512, 每batch搬入48.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=1536.0MB, V_out=1024.0MB, L2=128MB); 尾轮: r=0 无尾轮",1610612736,4831838208,0.00100663296,0.0009291996553846154,0.0019358326153846154,0.0,0.0,1649267441664.0,0.0033935544067160493,1073741824,0.00067108864,0.0,0.0033935544067160493,0.0,0.0033935544067160493,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" -b64_m1024_n8192_k2048,64,64,1024,8192,2048,bf16,bf16,bf16,False,False,False,True,0,b64_m1024_n8192_k2048,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,2,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,2048,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,64,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=2 x nCnt=16 (tile 512x512, 每batch搬入128.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=2304.0MB, V_out=1024.0MB, L2=128MB); 尾轮: r=0 无尾轮",2415919104,6174015488,0.00150994944,0.0011873106707692308,0.0026972601107692305,0.0,0.0,2199023255552.0,0.004524739208954733,1073741824,0.00067108864,0.0,0.004524739208954733,0.0,0.004524739208954733,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" -b32_m1024_n1024_k512,32,32,1024,1024,512,bf16,bf16,bf16,False,False,False,True,0,b32_m1024_n1024_k512,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),1,1,1024,1024,512,64,1,d_两侧都切K,176,176,64,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"两侧都切K: k_L1=64, K段成对流水, batch边界天然无缝; dValueA=128B/dValueB=2048B; 输出落点: L2驻留",67108864,0.0,4.194304e-05,0.0,4.194304e-05,8,0.0,34359738368.0,7.06990501399177e-05,67108864,1.290555076923077e-05,0.0,7.06990501399177e-05,2.1742932036720483e-05,9.244198217663819e-05,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" -b128_m4096_n4096_k8192,128,128,4096,4096,8192,bf16,bf16,bf16,False,False,False,True,0,b128_m4096_n4096_k8192,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,8,8,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,8192,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,256,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=8 x nCnt=8 (tile 512x512, 每batch搬入1024.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=16384.0MB, V_out=4096.0MB, L2=128MB); 尾轮: r=0 无尾轮",17179869184,120259084288,0.01073741824,0.023126746978461538,0.033864165218461535,0.0,0.0,35184372088832.0,0.07239582734327572,4294967296,0.00268435456,0.0,0.07239582734327572,0.0,0.07239582734327572,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" -b32_m8192_n4096_k7168,32,32,8192,4096,7168,bf16,bf16,bf16,False,False,False,True,0,b32_m8192_n4096_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,16,8,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,7168,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,128,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=16 x nCnt=8 (tile 512x512, 每batch搬入1792.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=5376.0MB, V_out=2048.0MB, L2=128MB); 尾轮: r=0 无尾轮",5637144576,54492397568,0.00352321536,0.010479307224615384,0.014002522584615384,0.0,0.0,15393162788864.0,0.031673174462683126,2147483648,0.00134217728,0.0,0.031673174462683126,0.0,0.031673174462683126,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" -b32_m2048_n2048_k8192,32,32,2048,2048,8192,bf16,bf16,bf16,False,False,False,True,0,b32_m2048_n2048_k8192,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,4,4,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,8192,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,16,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=4 x nCnt=4 (tile 512x512, 每batch搬入256.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=2048.0MB, V_out=256.0MB, L2=128MB); 尾轮: r=0 无尾轮",2147483648,6442450944,0.00134217728,0.0012389328738461537,0.002581110153846154,0.0,0.0,2199023255552.0,0.004524739208954733,268435456,0.00016777216,0.0,0.004524739208954733,0.0,0.004524739208954733,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" -b64_m4096_n2048_k128,64,64,4096,2048,128,bf16,bf16,bf16,False,False,False,True,0,b64_m4096_n2048_k128,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,8,4,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,128,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,64,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=8 x nCnt=4 (tile 512x512, 每batch搬入8.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=96.0MB, V_out=1024.0MB, L2=128MB); 尾轮: r=0 无尾轮",100663296,436207616,6.291456e-05,8.388608e-05,0.00014680063999999998,0.0,0.0,137438953472.0,0.0002827962005596708,1073741824,0.00067108864,0.0,0.00081788928,0.0,0.00081788928,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" -b16_m1024_n1024_k8192,16,16,1024,1024,8192,bf16,bf16,bf16,False,False,False,True,0,b16_m1024_n1024_k8192,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,2,2,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,8192,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,2,True,2,"tile枚举: P=2, 有界枚举最优 mCnt=2 x nCnt=2 (tile 512x512, 每batch搬入64.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=512.0MB, V_out=32.0MB, L2=128MB); 尾轮: r=0 无尾轮",536870912,536870912,0.00033554432,0.00010324440615384615,0.0004387887261538461,0.0,0.0,274877906944.0,0.0005655924011193416,33554432,2.097152e-05,0.0,0.0005655924011193416,0.0,0.0005655924011193416,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" -b4_m32768_n128_k128,4,4,32768,128,128,bf16,bf16,bf16,False,False,False,True,0,b4_m32768_n128_k128,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,64,1,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,128,128,128,1,双缓冲驻留当前tile输入,512,128,32,allocate(输入驻留L2吸收重复读),"resident(整case全驻留S_A: 输出驻留L2异步回写, GM写=0)",4,0,A0,1,1,1,0,0,0,8,True,2,"tile枚举: P=8, 有界枚举最优 mCnt=64 x nCnt=1 (tile 512x128, 每batch搬入10.0MB, r=0); Base tile 512x128 (L0C 单缓冲方形用满); L2场景: A_整case全驻留(输入+输出<=L2) (V_in=32.1MB, V_out=32.0MB, L2=128MB); 尾轮: r=0 无尾轮",33685504,8257536,2.105344e-05,1.5879876923076922e-06,2.2641427692307692e-05,0.0,0.0,4294967296.0,8.837381267489712e-06,33554432,6.452775384615385e-06,0.0,2.2641427692307692e-05,0.0,2.2641427692307692e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" -b8_m32768_n2048_k512,8,8,32768,2048,512,bf16,bf16,bf16,False,False,False,True,0,b8_m32768_n2048_k512,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,64,4,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,512,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,64,True,2,"tile枚举: P=4, 有界枚举最优 mCnt=64 x nCnt=4 (tile 512x512, 每batch搬入256.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=272.0MB, V_out=1024.0MB, L2=128MB); 尾轮: r=0 无尾轮",285212672,1862270976,0.00017825792,0.00035812903384615385,0.0005363869538461539,0.0,0.0,549755813888.0,0.0011311848022386832,1073741824,0.00067108864,0.0,0.0012074755938461538,0.0,0.0012074755938461538,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" -b4_m131072_n128_k128,4,4,131072,128,128,bf16,bf16,bf16,False,False,False,True,0,b4_m131072_n128_k128,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,256,1,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,128,128,128,1,双缓冲驻留当前tile输入,512,128,32,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,32,True,2,"tile枚举: P=8, 有界枚举最优 mCnt=256 x nCnt=1 (tile 512x128, 每batch搬入40.0MB, r=0); Base tile 512x128 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=128.1MB, V_out=128.0MB, L2=128MB); 尾轮: r=0 无尾轮",134348800,33423360,8.3968e-05,6.427569230769231e-06,9.039556923076924e-05,0.0,0.0,17179869184.0,3.534952506995885e-05,134217728,8.388608e-05,0.0,0.00017428164923076922,0.0,0.00017428164923076922,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" -b8_m131072_n1024_k256,8,8,131072,1024,256,bf16,bf16,bf16,False,False,False,True,0,b8_m131072_n1024_k256,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,256,2,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,256,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,128,True,2,"tile枚举: P=4, 有界枚举最优 mCnt=256 x nCnt=2 (tile 512x512, 每batch搬入256.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=516.0MB, V_out=2048.0MB, L2=128MB); 尾轮: r=0 无尾轮",541065216,1606418432,0.00033816576,0.00030892662153846154,0.0006470923815384616,0.0,0.0,549755813888.0,0.0011311848022386832,2147483648,0.00134217728,0.0,0.0019892696615384617,0.0,0.0019892696615384617,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" -b16_m32768_n8192_k7168,16,16,32768,8192,7168,bf16,bf16,bf16,False,False,False,True,0,b16_m32768_n8192_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,64,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,7168,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,512,True,2,"tile枚举: P=2, 有界枚举最优 mCnt=64 x nCnt=16 (tile 512x512, 每batch搬入14336.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=8960.0MB, V_out=8192.0MB, L2=128MB); 尾轮: r=0 无尾轮",9395240960,231122927616,0.0058720256,0.044446716849230766,0.05031874244923076,0.0,0.0,61572651155456.0,0.1266926978507325,8589934592,0.00536870912,0.0,0.1266926978507325,0.0,0.1266926978507325,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" -b4_m32768_n128_k8192,4,4,32768,128,8192,bf16,bf16,bf16,False,False,False,True,0,b4_m32768_n128_k8192,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,64,1,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,128,8192,192,1,双缓冲驻留当前tile输入,512,128,32,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,8,True,2,"tile枚举: P=8, 有界枚举最优 mCnt=64 x nCnt=1 (tile 512x128, 每batch搬入640.0MB, r=0); Base tile 512x128 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=2056.0MB, V_out=32.0MB, L2=128MB); 尾轮: r=0 无尾轮",2155872256,528482304,0.00134742016,0.0001016312123076923,0.0014490513723076923,0.0,0.0,274877906944.0,0.0005655924011193416,33554432,2.097152e-05,0.0,0.0014700228923076922,0.0,0.0014700228923076922,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" -b32_m131072_n8192_k128,32,32,131072,8192,128,bf16,bf16,bf16,False,False,False,True,0,b32_m131072_n8192_k128,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,256,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,128,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,4096,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=256 x nCnt=16 (tile 512x512, 每batch搬入1024.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=1088.0MB, V_out=65536.0MB, L2=128MB); 尾轮: r=0 无尾轮",1140850688,33218887680,0.00071303168,0.006388247630769231,0.007101279310769231,0.0,0.0,8796093022208.0,0.01809895683581893,68719476736,0.04294967296,0.0,0.05005095227076922,0.0,0.05005095227076922,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" -b64_m32768_n8192_k1536,64,64,32768,8192,1536,bf16,bf16,bf16,False,False,False,True,0,b64_m32768_n8192_k1536,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,64,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,1536,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,2048,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=64 x nCnt=16 (tile 512x512, 每batch搬入3072.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=7680.0MB, V_out=32768.0MB, L2=128MB); 尾轮: r=0 无尾轮",8053063680,198105366528,0.0050331648,0.03809718587076923,0.04313035067076923,0.0,0.0,52776558133248.0,0.10859374101491358,34359738368,0.02147483648,0.0,0.10859374101491358,0.0,0.10859374101491358,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" -b8_m131072_n8192_k8192,8,8,131072,8192,8192,bf16,bf16,bf16,False,False,False,True,0,b8_m131072_n8192_k8192,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,256,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,8192,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,1024,True,2,"tile枚举: P=4, 有界枚举最优 mCnt=256 x nCnt=16 (tile 512x512, 每batch搬入65536.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: C_双侧超L2: 最小替换2D分组(组间落空GM, 窗口L2) (V_in=17408.0MB, V_out=16384.0MB, L2=128MB); 最小替换分组 m_grp=8x n_grp=8 (GM倍率3.76, 窗口L2/batch=57344.0MB); 尾轮: r=0 无尾轮",68719476736,481036337152,0.04294967296,0.09250698791384615,0.13545666087384614,0.0,0.0,140737488355328.0,0.2895833093731029,17179869184,0.01073741824,0.0,0.2895833093731029,0.0,0.2895833093731029,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" -b8_m16_n7168_k1536,8,8,16,7168,1536,bf16,bf16,bf16,False,False,False,True,0,b8_m16_n7168_k1536,StreamK,Ascend950PR,batch_mat_mul_v3,32,1,1,2,2,"B/M/N切出16块, 每块2核切K归约 (归约组内核c负责K段[c*K/2,(c+1)*K/2))",1,1,16,3584,768,256,1,K段标准分块流水,16,128,64,allocate(部分和驻留L2),"resident(部分和4B驻留L2, 防精度丢失不随C的fp16/fp8转换)",0,3670016,grid_K=2路切K+归约,1,1,2,0,0,0,0,True,4,"P=14.00, grid_K=2, 部分和驻留L2按4B写出, AIV归约后按C dtype=2B写最终",176553984,393216,0.00011034624,7.561846153846153e-08,0.00011042185846153846,0.0,0.0,2818572288.0,5.799531456790123e-06,0.0,0.0,2.566079254079254e-07,0.00011042185846153846,2.566079254079254e-07,0.00011067846638694638,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" -b64_m1024_n7168_k7168,64,64,1024,7168,7168,bf16,bf16,bf16,False,False,False,True,0,b64_m1024_n7168_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,2,14,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,7168,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,56,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=2 x nCnt=14 (tile 512x512, 每batch搬入392.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=7168.0MB, V_out=896.0MB, L2=128MB); 尾轮: r=0 无尾轮",7516192768,18790481920,0.00469762048,0.0036135542153846152,0.008311174695384616,0.0,0.0,6734508720128.0,0.013857013827423869,939524096,0.00058720256,0.0,0.013857013827423869,0.0,0.013857013827423869,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" -b32_m8192_n8192_k7168,32,32,8192,8192,7168,bf16,bf16,bf16,False,False,False,True,0,b32_m8192_n8192_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,16,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,7168,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,256,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=16 x nCnt=16 (tile 512x512, 每batch搬入3584.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=7168.0MB, V_out=4096.0MB, L2=128MB); 尾轮: r=0 无尾轮",7516192768,112742891520,0.00469762048,0.021681325292307693,0.026378945772307694,0.0,0.0,30786325577728.0,0.06334634892536625,4294967296,0.00268435456,0.0,0.06334634892536625,0.0,0.06334634892536625,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" -b8_m4096_n4096_k128,8,8,4096,4096,128,bf16,bf16,bf16,False,False,False,True,0,b8_m4096_n4096_k128,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,8,8,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,128,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,16,True,2,"tile枚举: P=4, 有界枚举最优 mCnt=8 x nCnt=8 (tile 512x512, 每batch搬入16.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=16.0MB, V_out=256.0MB, L2=128MB); 尾轮: r=0 无尾轮",16777216,117440512,1.048576e-05,2.2584713846153845e-05,3.307047384615384e-05,0.0,0.0,34359738368.0,7.06990501399177e-05,268435456,0.00016777216,0.0,0.00020084263384615383,0.0,0.00020084263384615383,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" -b128_m8192_n8192_k7168,128,128,8192,8192,7168,bf16,bf16,bf16,False,False,False,True,0,b128_m8192_n8192_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,16,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,7168,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,1024,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=16 x nCnt=16 (tile 512x512, 每batch搬入3584.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=28672.0MB, V_out=16384.0MB, L2=128MB); 尾轮: r=0 无尾轮",30064771072,450971566080,0.01879048192,0.08672530116923077,0.10551578308923078,0.0,0.0,123145302310912.0,0.253385395701465,17179869184,0.01073741824,0.0,0.253385395701465,0.0,0.253385395701465,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" +merge_demo_k_trunc,2048,2048,16,64,128,bf16,bf16,bf16,False,False,False,True,0,merge_demo_k_trunc,MergeBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B均分(核间零重复读零依赖),64,4,64,256,128,128,12,合并驻留,64,256,64,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"b0=4 (L0C上限5.7/算存比上限21.1/b_core=64); K截断; 合并后单次DMA搬入 A'[64,128]+B'[128,256]; 输出落点: L2驻留 (整case V_in+V_out=40.0MB vs L2=128MB)",41943040,0.0,2.62144e-05,0.0,2.62144e-05,16,0.0,2147483648.0,4.971026962962963e-06,4194304,8.065969230769231e-07,0.0,2.62144e-05,1.2808460398860398e-07,2.6342484603988603e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" +merge_iter_arbitrate,128,128,64,64,512,bf16,bf16,bf16,False,False,False,True,0,merge_iter_arbitrate,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),4,1,64,64,512,512,2,b_双batch乒乓,64,64,256,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,双batch乒乓: 2*(MK+KN)*dtype=256KB <= L1; 输出落点: L2驻留,16777216,0.0,1.048576e-05,0.0,1.048576e-05,4,0.0,536870912.0,1.2427567407407407e-06,1048576,2.0164923076923077e-07,0.0,1.048576e-05,3.6110149287749287e-07,1.0846861492877492e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" +iter_demo_form_b,128,128,64,64,256,bf16,bf16,bf16,False,False,False,True,0,iter_demo_form_b,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),4,1,64,64,256,256,2,b_双batch乒乓,64,64,256,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,双batch乒乓: 2*(MK+KN)*dtype=128KB <= L1; 输出落点: L2驻留,8388608,0.0,5.24288e-06,0.0,5.24288e-06,4,0.0,268435456.0,6.213783703703703e-07,1048576,2.0164923076923077e-07,0.0,5.24288e-06,2.0575690028490026e-07,5.4486369002849e-06,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" +iter_demo_form_d,64,64,64,64,8192,bf16,bf16,bf16,False,False,False,True,0,iter_demo_form_d,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),2,1,64,64,8192,1024,1,d_两侧都切K,64,64,256,allocate(GM->L1随路驻留L2),"direct_gm(整case超L2: 输入优先驻留L2, 输出直写GM不占L2)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"两侧都切K: k_L1=1024, K段成对流水, batch边界天然无缝; dValueA=2048B/dValueB=128B; 输出落点: 直写GM",134217728,0.0,8.388608e-05,0.0,8.388608e-05,16,0.0,4294967296.0,9.942053925925925e-06,524288,3.2768e-07,0.0,8.421376e-05,7.852183703703703e-07,8.499897837037037e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" +streamk_demo,4,4,128,128,10240,bf16,bf16,bf16,False,False,False,True,0,streamk_demo,StreamK,Ascend950PR,batch_mat_mul_v3,32,1,1,1,32,"B/M/N切出4块, 每块32核切K归约 (归约组内核c负责K段[c*K/32,(c+1)*K/32))",1,1,128,128,320,256,1,K段标准分块流水,128,128,64,allocate(部分和驻留L2),"resident(部分和4B驻留L2, 防精度丢失不随C的fp16/fp8转换)",0,8388608,grid_K=32路切K+归约,1,1,32,0,0,0,0,True,4,"P=1.00, grid_K=32, 部分和驻留L2按4B写出, AIV归约后按C dtype=2B写最终",20971520,0,1.31072e-05,0.0,1.31072e-05,0.0,0.0,1342177280.0,3.1068918518518518e-06,0.0,0.0,3.4067453613053613e-06,1.31072e-05,3.4067453613053613e-06,1.651394536130536e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" +asw_demo_full,2,2,8192,8192,1024,bf16,bf16,bf16,False,False,False,True,0,asw_demo_full,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,16,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,1024,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,16,True,2,"tile枚举: P=16, 有界枚举最优 mCnt=16 x nCnt=16 (tile 512x512, 每batch搬入512.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=64.0MB, V_out=256.0MB, L2=128MB); 尾轮: r=0 无尾轮",67108864,1006632960,4.194304e-05,0.00019358326153846154,0.00023552630153846153,0.0,0.0,274877906944.0,0.0006362914512592592,268435456,0.00016777216,0.0,0.0006362914512592592,0.0,0.0006362914512592592,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" +asw_demo_reduce_core,16,16,256,256,128,bf16,bf16,bf16,False,False,False,True,0,asw_demo_reduce_core,ASW_Basic_降核,Ascend950PR,batch_mat_mul_v3,16,1,1,1,1,"降核: 只用16核, 每核一个L0C满载输出块, 其余核闲置",0,1,256,256,128,128,1,标准核内流水,256,256,64,allocate,resident(整case全驻留S_A),0,0,不涉及(每核一块无尾轮),1,1,1,0,0,0,0,True,2,"P=16.00L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,单batch全驻留: (MK+KN)*dtype=68KB <= L1; 输出落点: L2驻留,2228224,0.0,1.6384e-06,0.0,1.6384e-06,1,0.0,16777216.0,3.8836148148148146e-08,65536,1.2603076923076923e-08,0.0,1.6384e-06,5.1439225071225065e-08,1.689839225071225e-06,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" +b64_m16_n256_k512,64,64,16,256,512,bf16,bf16,bf16,False,False,False,True,0,b64_m16_n256_k512,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),2,1,16,256,512,240,1,c_一侧驻留+对侧切K,16,256,64,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"一侧驻留(A)+对侧切K: A驻留16KB, 预算L1/2, k_L1=240, dValueA=480B/dValueB=512B; 输出落点: L2驻留",17825792,0.0,1.114112e-05,0.0,1.114112e-05,6,0.0,268435456.0,6.213783703703703e-07,524288,1.0082461538461538e-07,0.0,1.114112e-05,1.9604786324786327e-07,1.1337167863247863e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" +b128_m8_n192_k256,128,128,8,192,256,bf16,bf16,bf16,False,False,False,True,0,b128_m8_n192_k256,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),4,1,8,192,256,256,2,b_双batch乒乓,8,192,80,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,双batch乒乓: 2*(MK+KN)*dtype=200KB <= L1; 输出落点: L2驻留,13107200,0.0,9.17504e-06,0.0,9.17504e-06,4,0.0,100663296.0,2.330168888888889e-07,393216,7.561846153846153e-08,0.0,9.17504e-06,7.71588376068376e-08,9.252198837606838e-06,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" +b32_m16_n8192_k7168,32,32,16,8192,7168,bf16,bf16,bf16,False,False,False,True,0,b32_m16_n8192_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,1,8,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,16,1024,7168,112,1,双缓冲驻留当前tile输入,16,1024,16,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,8,True,2,"tile枚举: 效率降级(放开约束4, dValue 按 128B 硬下限, 搬移效率低于模型假设, 时延可能低估): P=1, mCnt=1 x nCnt=8 (tile 16x1024, 每batch搬入113.8MB, r=0); Base tile 16x1024 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=3591.0MB, V_out=8.0MB, L2=128MB); 尾轮: r=0 无尾轮",3765436416,51380224,0.00235339776,9.880812307692307e-06,0.0023632785723076925,0.0,0.0,60129542144.0,0.00013918875496296296,8388608,5.24288e-06,0.0,0.0023685214523076923,0.0,0.0023685214523076923,MTE2,True,,访存Bound(GM读写共享+L2重复读),"效率降级标注 (plan.note): 搬移效率下限不满足 —— 方案照常给出 (兜底), 但实际效率低于模型假设, 时延可能低估; 建议调整 dtype/布局 | 瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" +b4_m1_n8192_k8192,4,4,1,8192,8192,bf16,bf16,bf16,False,False,False,True,0,b4_m1_n8192_k8192,StreamK,Ascend950PR,batch_mat_mul_v3,32,1,1,1,32,"B/M/N切出4块, 每块32核切K归约 (归约组内核c负责K段[c*K/32,(c+1)*K/32))",1,1,1,8192,256,256,1,K段标准分块流水,1,128,64,allocate(部分和驻留L2),"resident(部分和4B驻留L2, 防精度丢失不随C的fp16/fp8转换)",0,4194304,grid_K=32路切K+归约,1,1,32,0,0,0,0,True,4,"P=0.50, grid_K=32, 部分和驻留L2按4B写出, AIV归约后按C dtype=2B写最终",536936448,0.0,0.00033558528,0.0,0.00033558528,0.0,0.0,536870912.0,1.2427567407407407e-06,0.0,0.0,1.731729603729604e-06,0.00033558528,1.731729603729604e-06,0.0003373170096037296,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" +b16_m2_n4096_k7168,16,16,2,4096,7168,bf16,bf16,bf16,False,False,False,True,0,b16_m2_n4096_k7168,StreamK,Ascend950PR,batch_mat_mul_v3,32,1,1,1,16,"B/M/N切出16块, 每块16核切K归约 (归约组内核c负责K段[c*K/16,(c+1)*K/16))",1,1,2,4096,448,256,1,K段标准分块流水,2,128,64,allocate(部分和驻留L2),"resident(部分和4B驻留L2, 防精度丢失不随C的fp16/fp8转换)",0,8388608,grid_K=16路切K+归约,1,1,16,0,0,0,0,True,4,"P=2.00, grid_K=16, 部分和驻留L2按4B写出, AIV归约后按C dtype=2B写最终",939982848,0,0.00058748928,0.0,0.00058748928,0.0,0.0,1879048192.0,4.349648592592593e-06,0.0,0.0,1.7726896037296038e-06,0.00058748928,1.7726896037296038e-06,0.0005892619696037297,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" +b32_m64_n64_k7168,32,32,64,64,7168,bf16,bf16,bf16,False,False,False,True,0,b32_m64_n64_k7168,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),1,1,64,64,7168,1024,1,d_两侧都切K,64,64,256,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"两侧都切K: k_L1=1024, K段成对流水, batch边界天然无缝; dValueA=2048B/dValueB=128B; 输出落点: L2驻留",58720256,0.0,3.670016e-05,0.0,3.670016e-05,7,0.0,1879048192.0,4.349648592592593e-06,262144,5.041230769230769e-08,0.0,3.670016e-05,6.71790678062678e-07,3.737195067806268e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" +b64_m1024_n1024_k7168,64,64,1024,1024,7168,bf16,bf16,bf16,False,False,False,True,0,b64_m1024_n1024_k7168,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),2,1,1024,1024,7168,64,1,d_两侧都切K,176,176,64,allocate(GM->L1随路驻留L2),"direct_gm(整case超L2: 输入优先驻留L2, 输出直写GM不占L2)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"两侧都切K: k_L1=64, K段成对流水, batch边界天然无缝; dValueA=128B/dValueB=2048B; 输出落点: 直写GM",1879048192,0.0,0.00117440512,0.0,0.00117440512,224,0.0,962072674304.0,0.0022270200794074074,134217728,8.388608e-05,0.0,0.0022270200794074074,5.1885093925925924e-05,0.0022789051733333333,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" +b128_m2048_n2048_k1536,128,128,2048,2048,1536,bf16,bf16,bf16,False,False,False,True,0,b128_m2048_n2048_k1536,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,4,4,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,1536,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,64,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=4 x nCnt=4 (tile 512x512, 每batch搬入48.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=1536.0MB, V_out=1024.0MB, L2=128MB); 尾轮: r=0 无尾轮",1610612736,4831838208,0.00100663296,0.0009291996553846154,0.0019358326153846154,0.0,0.0,1649267441664.0,0.0038177487075555555,1073741824,0.00067108864,0.0,0.0038177487075555555,0.0,0.0038177487075555555,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" +b64_m1024_n8192_k2048,64,64,1024,8192,2048,bf16,bf16,bf16,False,False,False,True,0,b64_m1024_n8192_k2048,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,2,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,2048,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,64,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=2 x nCnt=16 (tile 512x512, 每batch搬入128.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=2304.0MB, V_out=1024.0MB, L2=128MB); 尾轮: r=0 无尾轮",2415919104,6174015488,0.00150994944,0.0011873106707692308,0.0026972601107692305,0.0,0.0,2199023255552.0,0.005090331610074074,1073741824,0.00067108864,0.0,0.005090331610074074,0.0,0.005090331610074074,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" +b32_m1024_n1024_k512,32,32,1024,1024,512,bf16,bf16,bf16,False,False,False,True,0,b32_m1024_n1024_k512,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),1,1,1024,1024,512,64,1,d_两侧都切K,176,176,64,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"两侧都切K: k_L1=64, K段成对流水, batch边界天然无缝; dValueA=128B/dValueB=2048B; 输出落点: L2驻留",67108864,0.0,4.194304e-05,0.0,4.194304e-05,8,0.0,34359738368.0,7.95364314074074e-05,67108864,1.290555076923077e-05,0.0,7.95364314074074e-05,2.2847604695156693e-05,0.0001023840361025641,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" +b128_m4096_n4096_k8192,128,128,4096,4096,8192,bf16,bf16,bf16,False,False,False,True,0,b128_m4096_n4096_k8192,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,8,8,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,8192,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,256,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=8 x nCnt=8 (tile 512x512, 每batch搬入1024.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=16384.0MB, V_out=4096.0MB, L2=128MB); 尾轮: r=0 无尾轮",17179869184,120259084288,0.01073741824,0.023126746978461538,0.033864165218461535,0.0,0.0,35184372088832.0,0.08144530576118518,4294967296,0.00268435456,0.0,0.08144530576118518,0.0,0.08144530576118518,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" +b32_m8192_n4096_k7168,32,32,8192,4096,7168,bf16,bf16,bf16,False,False,False,True,0,b32_m8192_n4096_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,16,8,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,7168,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,128,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=16 x nCnt=8 (tile 512x512, 每batch搬入1792.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=5376.0MB, V_out=2048.0MB, L2=128MB); 尾轮: r=0 无尾轮",5637144576,54492397568,0.00352321536,0.010479307224615384,0.014002522584615384,0.0,0.0,15393162788864.0,0.03563232127051852,2147483648,0.00134217728,0.0,0.03563232127051852,0.0,0.03563232127051852,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" +b32_m2048_n2048_k8192,32,32,2048,2048,8192,bf16,bf16,bf16,False,False,False,True,0,b32_m2048_n2048_k8192,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,4,4,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,8192,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,16,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=4 x nCnt=4 (tile 512x512, 每batch搬入256.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=2048.0MB, V_out=256.0MB, L2=128MB); 尾轮: r=0 无尾轮",2147483648,6442450944,0.00134217728,0.0012389328738461537,0.002581110153846154,0.0,0.0,2199023255552.0,0.005090331610074074,268435456,0.00016777216,0.0,0.005090331610074074,0.0,0.005090331610074074,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" +b64_m4096_n2048_k128,64,64,4096,2048,128,bf16,bf16,bf16,False,False,False,True,0,b64_m4096_n2048_k128,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,8,4,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,128,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,64,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=8 x nCnt=4 (tile 512x512, 每batch搬入8.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=96.0MB, V_out=1024.0MB, L2=128MB); 尾轮: r=0 无尾轮",100663296,436207616,6.291456e-05,8.388608e-05,0.00014680063999999998,0.0,0.0,137438953472.0,0.0003181457256296296,1073741824,0.00067108864,0.0,0.00081788928,0.0,0.00081788928,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" +b16_m1024_n1024_k8192,16,16,1024,1024,8192,bf16,bf16,bf16,False,False,False,True,0,b16_m1024_n1024_k8192,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,2,2,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,8192,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,2,True,2,"tile枚举: P=2, 有界枚举最优 mCnt=2 x nCnt=2 (tile 512x512, 每batch搬入64.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=512.0MB, V_out=32.0MB, L2=128MB); 尾轮: r=0 无尾轮",536870912,536870912,0.00033554432,0.00010324440615384615,0.0004387887261538461,0.0,0.0,274877906944.0,0.0006362914512592592,33554432,2.097152e-05,0.0,0.0006362914512592592,0.0,0.0006362914512592592,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" +b4_m32768_n128_k128,4,4,32768,128,128,bf16,bf16,bf16,False,False,False,True,0,b4_m32768_n128_k128,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,64,1,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,128,128,128,1,双缓冲驻留当前tile输入,512,128,32,allocate(输入驻留L2吸收重复读),"resident(整case全驻留S_A: 输出驻留L2异步回写, GM写=0)",4,0,A0,1,1,1,0,0,0,8,True,2,"tile枚举: P=8, 有界枚举最优 mCnt=64 x nCnt=1 (tile 512x128, 每batch搬入10.0MB, r=0); Base tile 512x128 (L0C 单缓冲方形用满); L2场景: A_整case全驻留(输入+输出<=L2) (V_in=32.1MB, V_out=32.0MB, L2=128MB); 尾轮: r=0 无尾轮",33685504,8257536,2.105344e-05,1.5879876923076922e-06,2.2641427692307692e-05,0.0,0.0,4294967296.0,9.942053925925925e-06,33554432,6.452775384615385e-06,0.0,2.2641427692307692e-05,0.0,2.2641427692307692e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" +b8_m32768_n2048_k512,8,8,32768,2048,512,bf16,bf16,bf16,False,False,False,True,0,b8_m32768_n2048_k512,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,64,4,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,512,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,64,True,2,"tile枚举: P=4, 有界枚举最优 mCnt=64 x nCnt=4 (tile 512x512, 每batch搬入256.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=272.0MB, V_out=1024.0MB, L2=128MB); 尾轮: r=0 无尾轮",285212672,1862270976,0.00017825792,0.00035812903384615385,0.0005363869538461539,0.0,0.0,549755813888.0,0.0012725829025185184,1073741824,0.00067108864,0.0,0.0012725829025185184,0.0,0.0012725829025185184,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" +b4_m131072_n128_k128,4,4,131072,128,128,bf16,bf16,bf16,False,False,False,True,0,b4_m131072_n128_k128,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,256,1,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,128,128,128,1,双缓冲驻留当前tile输入,512,128,32,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,32,True,2,"tile枚举: P=8, 有界枚举最优 mCnt=256 x nCnt=1 (tile 512x128, 每batch搬入40.0MB, r=0); Base tile 512x128 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=128.1MB, V_out=128.0MB, L2=128MB); 尾轮: r=0 无尾轮",134348800,33423360,8.3968e-05,6.427569230769231e-06,9.039556923076924e-05,0.0,0.0,17179869184.0,3.97682157037037e-05,134217728,8.388608e-05,0.0,0.00017428164923076922,0.0,0.00017428164923076922,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" +b8_m131072_n1024_k256,8,8,131072,1024,256,bf16,bf16,bf16,False,False,False,True,0,b8_m131072_n1024_k256,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,256,2,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,256,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,128,True,2,"tile枚举: P=4, 有界枚举最优 mCnt=256 x nCnt=2 (tile 512x512, 每batch搬入256.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=516.0MB, V_out=2048.0MB, L2=128MB); 尾轮: r=0 无尾轮",541065216,1606418432,0.00033816576,0.00030892662153846154,0.0006470923815384616,0.0,0.0,549755813888.0,0.0012725829025185184,2147483648,0.00134217728,0.0,0.0019892696615384617,0.0,0.0019892696615384617,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" +b16_m32768_n8192_k7168,16,16,32768,8192,7168,bf16,bf16,bf16,False,False,False,True,0,b16_m32768_n8192_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,64,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,7168,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,512,True,2,"tile枚举: P=2, 有界枚举最优 mCnt=64 x nCnt=16 (tile 512x512, 每batch搬入14336.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=8960.0MB, V_out=8192.0MB, L2=128MB); 尾轮: r=0 无尾轮",9395240960,231122927616,0.0058720256,0.044446716849230766,0.05031874244923076,0.0,0.0,61572651155456.0,0.14252928508207408,8589934592,0.00536870912,0.0,0.14252928508207408,0.0,0.14252928508207408,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" +b4_m32768_n128_k8192,4,4,32768,128,8192,bf16,bf16,bf16,False,False,False,True,0,b4_m32768_n128_k8192,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,64,1,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,128,8192,192,1,双缓冲驻留当前tile输入,512,128,32,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,8,True,2,"tile枚举: P=8, 有界枚举最优 mCnt=64 x nCnt=1 (tile 512x128, 每batch搬入640.0MB, r=0); Base tile 512x128 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=2056.0MB, V_out=32.0MB, L2=128MB); 尾轮: r=0 无尾轮",2155872256,528482304,0.00134742016,0.0001016312123076923,0.0014490513723076923,0.0,0.0,274877906944.0,0.0006362914512592592,33554432,2.097152e-05,0.0,0.0014700228923076922,0.0,0.0014700228923076922,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" +b32_m131072_n8192_k128,32,32,131072,8192,128,bf16,bf16,bf16,False,False,False,True,0,b32_m131072_n8192_k128,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,256,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,128,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,4096,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=256 x nCnt=16 (tile 512x512, 每batch搬入1024.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=1088.0MB, V_out=65536.0MB, L2=128MB); 尾轮: r=0 无尾轮",1140850688,33218887680,0.00071303168,0.006388247630769231,0.007101279310769231,0.0,0.0,8796093022208.0,0.020361326440296295,68719476736,0.04294967296,0.0,0.05005095227076922,0.0,0.05005095227076922,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" +b64_m32768_n8192_k1536,64,64,32768,8192,1536,bf16,bf16,bf16,False,False,False,True,0,b64_m32768_n8192_k1536,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,64,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,1536,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,2048,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=64 x nCnt=16 (tile 512x512, 每batch搬入3072.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=7680.0MB, V_out=32768.0MB, L2=128MB); 尾轮: r=0 无尾轮",8053063680,198105366528,0.0050331648,0.03809718587076923,0.04313035067076923,0.0,0.0,52776558133248.0,0.12216795864177778,34359738368,0.02147483648,0.0,0.12216795864177778,0.0,0.12216795864177778,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" +b8_m131072_n8192_k8192,8,8,131072,8192,8192,bf16,bf16,bf16,False,False,False,True,0,b8_m131072_n8192_k8192,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,256,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,8192,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,1024,True,2,"tile枚举: P=4, 有界枚举最优 mCnt=256 x nCnt=16 (tile 512x512, 每batch搬入65536.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: C_双侧超L2: 最小替换2D分组(组间落空GM, 窗口L2) (V_in=17408.0MB, V_out=16384.0MB, L2=128MB); 最小替换分组 m_grp=8x n_grp=8 (GM倍率3.76, 窗口L2/batch=57344.0MB); 尾轮: r=0 无尾轮",68719476736,481036337152,0.04294967296,0.09250698791384615,0.13545666087384614,0.0,0.0,140737488355328.0,0.3257812230447407,17179869184,0.01073741824,0.0,0.3257812230447407,0.0,0.3257812230447407,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" +b8_m16_n7168_k1536,8,8,16,7168,1536,bf16,bf16,bf16,False,False,False,True,0,b8_m16_n7168_k1536,StreamK,Ascend950PR,batch_mat_mul_v3,32,1,1,2,2,"B/M/N切出16块, 每块2核切K归约 (归约组内核c负责K段[c*K/2,(c+1)*K/2))",1,1,16,3584,768,256,1,K段标准分块流水,16,128,64,allocate(部分和驻留L2),"resident(部分和4B驻留L2, 防精度丢失不随C的fp16/fp8转换)",0,3670016,grid_K=2路切K+归约,1,1,2,0,0,0,0,True,4,"P=14.00, grid_K=2, 部分和驻留L2按4B写出, AIV归约后按C dtype=2B写最终",176553984,393216,0.00011034624,7.561846153846153e-08,0.00011042185846153846,0.0,0.0,2818572288.0,6.524472888888889e-06,0.0,0.0,2.566079254079254e-07,0.00011042185846153846,2.566079254079254e-07,0.00011067846638694638,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" +b64_m1024_n7168_k7168,64,64,1024,7168,7168,bf16,bf16,bf16,False,False,False,True,0,b64_m1024_n7168_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,2,14,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,7168,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,56,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=2 x nCnt=14 (tile 512x512, 每batch搬入392.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=7168.0MB, V_out=896.0MB, L2=128MB); 尾轮: r=0 无尾轮",7516192768,18790481920,0.00469762048,0.0036135542153846152,0.008311174695384616,0.0,0.0,6734508720128.0,0.015589140555851852,939524096,0.00058720256,0.0,0.015589140555851852,0.0,0.015589140555851852,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" +b32_m8192_n8192_k7168,32,32,8192,8192,7168,bf16,bf16,bf16,False,False,False,True,0,b32_m8192_n8192_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,16,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,7168,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,256,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=16 x nCnt=16 (tile 512x512, 每batch搬入3584.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=7168.0MB, V_out=4096.0MB, L2=128MB); 尾轮: r=0 无尾轮",7516192768,112742891520,0.00469762048,0.021681325292307693,0.026378945772307694,0.0,0.0,30786325577728.0,0.07126464254103704,4294967296,0.00268435456,0.0,0.07126464254103704,0.0,0.07126464254103704,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" +b8_m4096_n4096_k128,8,8,4096,4096,128,bf16,bf16,bf16,False,False,False,True,0,b8_m4096_n4096_k128,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,8,8,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,128,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,16,True,2,"tile枚举: P=4, 有界枚举最优 mCnt=8 x nCnt=8 (tile 512x512, 每batch搬入16.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=16.0MB, V_out=256.0MB, L2=128MB); 尾轮: r=0 无尾轮",16777216,117440512,1.048576e-05,2.2584713846153845e-05,3.307047384615384e-05,0.0,0.0,34359738368.0,7.95364314074074e-05,268435456,0.00016777216,0.0,0.00020084263384615383,0.0,0.00020084263384615383,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" +b128_m8192_n8192_k7168,128,128,8192,8192,7168,bf16,bf16,bf16,False,False,False,True,0,b128_m8192_n8192_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,16,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,7168,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,1024,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=16 x nCnt=16 (tile 512x512, 每batch搬入3584.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=28672.0MB, V_out=16384.0MB, L2=128MB); 尾轮: r=0 无尾轮",30064771072,450971566080,0.01879048192,0.08672530116923077,0.10551578308923078,0.0,0.0,123145302310912.0,0.28505857016414815,17179869184,0.01073741824,0.0,0.28505857016414815,0.0,0.28505857016414815,MMAD,True,,计算Bound,"瓶颈在 Cube 计算: 已接近理论算力上限, 检查是否有冗余计算 (MergeBatch 交叉项) 可消除" special_k1_b64,64,64,8192,512,1,bf16,bf16,bf16,False,False,False,True,0,special_k1_b64,特殊分支,Ascend950PR,batch_mat_mul_v3,64,1,1,1,1,AIV 核间按行均分 (无 Cube tile 概念),0,1,0,0,1,0,1,UB驻留(AIV) AIV单缓冲,0,0,0,allocate,direct_gm,0,0,不涉及(AIV逐元素),1,1,1,0,0,0,0,False,2,"K=1逐元素乘: 退化为 C=A⊙B 无累加深度, Cube 16x16x16 粒度浪费 15/16; 走 AIV 通路 GM->UB->Mul->GM, AIV单缓冲 (B<2*AIV 逐batch单缓冲串行)",1114112,0.0,6.9632e-07,0.0,6.9632e-07,0.0,0.0,268435456.0,9.92969696969697e-06,536870912,0.00033554432,0.0,0.00033624063999999996,0.0,0.00033624063999999996,MTE2,True,,访存Bound(GM读写共享+L2重复读),"瓶颈在 MTE2 搬移链 (GM 读写共享总线 + L2 重复读): 可增大 tile 提升 dValue/单核搬移量、利用 L2 驻留吸收重复读 (ASW swizzle/分组方向), 或评估输出驻留 L2 以减少 GM 直写与读竞争" diff --git a/BMM/BMM_Theory/examples/result_recommend.csv b/BMM/BMM_Theory/examples/result_recommend.csv index 1221fec..9884769 100644 --- a/BMM/BMM_Theory/examples/result_recommend.csv +++ b/BMM/BMM_Theory/examples/result_recommend.csv @@ -1,45 +1,45 @@ case_id,batch_a,batch_b,m,n,k,dtype_a,dtype_b,dtype_c,trans_a,trans_b,has_bias,out_nd,deterministic_level,plan_case_id,plan_branch,plan_npu,plan_op,plan_used_core_num,plan_split_b,plan_m_cnt,plan_n_cnt,plan_grid_k,plan_core_map,plan_b_core,plan_merge_b0,plan_single_core_m,plan_single_core_n,plan_single_core_k,plan_k_l1,plan_b_l1,plan_l1_form,plan_base_m,plan_base_n,plan_base_k,plan_l2_policy_in,plan_l2_policy_out,plan_swizzle_w,plan_workspace_bytes,plan_tail_strategy,plan_tail_m_cnt,plan_tail_n_cnt,plan_tail_k_cnt,plan_tail_m_main,plan_tail_n_main,plan_tail_block_cnt,plan_tail_wave_num,plan_fixpipe_unitflag,plan_out_dtype_bytes,plan_note,gm_read_bytes,l2_read_bytes,t_mte2_gm,t_mte2_l2,t_mte2,dma_cmd_count,t_dma_cmd,cube_flops,t_mmad,fixpipe_bytes,t_fixpipe,t_reduce,t_steady,t_drain,t_total,bottleneck,feasible,violations,bound_type,advice -to_matmul_demo,1,1,2048,2048,2048,bf16,bf16,bf16,False,False,False,True,0,to_matmul_demo,转Matmul,Ascend950PR,batch_mat_mul_v3,32,1,0,0,1,"折叠为 Matmul [2048,2048]x[2048,2048], 复用 Matmul 切分体系",0,1,0,0,2048,0,1,,0,0,0,,,0,0,转Matmul后由 Matmul 体系决定,1,1,1,0,0,0,0,True,2,"BatchB=1免费折叠: 左矩阵 [1,2048,2048] 视图折叠为 [2048,2048], 零重排零 split",16777216,0.0,1.048576e-05,0.0,1.048576e-05,0.0,0.0,17179869184.0,3.534952506995885e-05,8388608,1.6131938461538462e-06,0.0,3.534952506995885e-05,0.0,3.534952506995885e-05,MMAD,True,,计算Bound,"BatchA=1或BatchB=1, 折叠转普通Matmul" +to_matmul_demo,1,1,2048,2048,2048,bf16,bf16,bf16,False,False,False,True,0,to_matmul_demo,转Matmul,Ascend950PR,batch_mat_mul_v3,32,1,0,0,1,"折叠为 Matmul [2048,2048]x[2048,2048], 复用 Matmul 切分体系",0,1,0,0,2048,0,1,,0,0,0,,,0,0,转Matmul后由 Matmul 体系决定,1,1,1,0,0,0,0,True,2,"BatchB=1免费折叠: 左矩阵 [1,2048,2048] 视图折叠为 [2048,2048], 零重排零 split",16777216,0.0,1.048576e-05,0.0,1.048576e-05,0.0,0.0,17179869184.0,3.97682157037037e-05,8388608,1.6131938461538462e-06,0.0,3.97682157037037e-05,0.0,3.97682157037037e-05,MMAD,True,,计算Bound,"BatchA=1或BatchB=1, 折叠转普通Matmul" special_k0_demo,128,128,256,256,0,bf16,bf16,bf16,False,False,False,True,0,special_k0_demo,特殊分支,Ascend950PR,batch_mat_mul_v3,64,1,1,1,1,AIV 核间按行均分 (无 Cube tile 概念),0,1,0,0,0,0,1,UB驻留(AIV),0,0,0,allocate,direct_gm,0,0,不涉及(AIV逐元素),1,1,1,0,0,0,0,False,2,"K=0纯写值: 无任何计算, C=bias 或 0, 纯 AIV 写值; 按行均分到 AIV 核",0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,16777216,3.2263876923076923e-06,0.0,3.2263876923076923e-06,0.0,3.2263876923076923e-06,FIXPIPE,True,,写出Bound(L2写口),K=0纯写值 special_k1_demo,128,128,256,256,1,bf16,bf16,bf16,False,False,False,True,0,special_k1_demo,特殊分支,Ascend950PR,batch_mat_mul_v3,64,1,1,1,1,AIV 核间按行均分 (无 Cube tile 概念),0,1,0,0,1,0,1,UB驻留(AIV) UB乒乓,0,0,0,allocate,direct_gm,0,0,不涉及(AIV逐元素),1,1,1,0,0,0,0,False,2,"K=1逐元素乘: 退化为 C=A⊙B 无累加深度, Cube 16x16x16 粒度浪费 15/16; 走 AIV 通路 GM->UB->Mul->GM, UB乒乓 (B>=2*AIV 双batch乒乓流水)",131072,0.0,8.192e-08,0.0,8.192e-08,0.0,0.0,8388608.0,3.103030303030303e-07,16777216,3.2263876923076923e-06,0.0,3.2263876923076923e-06,0.0,3.2263876923076923e-06,FIXPIPE,True,,写出Bound(L2写口),"K=1逐元素乘, 走AIV向量通路" -merge_demo_k_trunc,2048,2048,16,64,128,bf16,bf16,bf16,False,False,False,True,0,merge_demo_k_trunc,MergeBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B均分(核间零重复读零依赖),64,4,64,256,128,128,12,合并驻留,64,256,64,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"b0=4 (L0C上限5.7/算存比上限23.7/b_core=64); K截断; 合并后单次DMA搬入 A'[64,128]+B'[128,256]; 输出落点: L2驻留 (整case V_in+V_out=40.0MB vs L2=128MB)",41943040,0.0,2.62144e-05,0.0,2.62144e-05,16,0.0,2147483648.0,4.418690633744856e-06,4194304,8.065969230769231e-07,0.0,2.62144e-05,1.1945434884457107e-07,2.6333854348844573e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),"两分支均合法, 仲裁: [分界条件] MergeBatch最优=True (K截断(k_l1^m=128>=K); 每核命令数 MergeBatch=16 vs IterBatch=64 (命令节省=0.00us) + 搬移效率节省=15.73us vs drain惩罚=(b0-1)*(T_comp+T_write)=0.17us -> MergeBatch优); [时延模型] T_MergeBatch=26.33us vs T_IterBatch=41.97us -> MergeBatch更优; [裁决] MergeBatch" -merge_iter_arbitrate,128,128,64,64,512,bf16,bf16,bf16,False,False,False,True,0,merge_iter_arbitrate,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),4,1,64,64,512,512,2,b_双batch乒乓,64,64,256,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,双batch乒乓: 2*(MK+KN)*dtype=256KB <= L1; 输出落点: L2驻留,16777216,0.0,1.048576e-05,0.0,1.048576e-05,4,0.0,536870912.0,1.104672658436214e-06,1048576,2.0164923076923077e-07,0.0,1.048576e-05,3.265804723013612e-07,1.081234047230136e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),"两分支均合法, 仲裁: [分界条件] MergeBatch最优=False (L1绑定(k_l1^m=256 IterBatch优); [时延模型] T_MergeBatch=10.86us vs T_IterBatch=10.81us -> IterBatch更优; [裁决] IterBatch" -iter_demo_form_b,128,128,64,64,256,bf16,bf16,bf16,False,False,False,True,0,iter_demo_form_b,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),4,1,64,64,256,256,2,b_双batch乒乓,64,64,256,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,双batch乒乓: 2*(MK+KN)*dtype=128KB <= L1; 输出落点: L2驻留,8388608,0.0,5.24288e-06,0.0,5.24288e-06,4,0.0,268435456.0,5.52336329218107e-07,1048576,2.0164923076923077e-07,0.0,5.24288e-06,1.8849638999683443e-07,5.431376389996834e-06,MTE2,True,,访存Bound(GM读写共享+L2重复读),仅 IterBatch 条件满足 -iter_demo_form_d,64,64,64,64,8192,bf16,bf16,bf16,False,False,False,True,0,iter_demo_form_d,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),2,1,64,64,8192,1024,1,d_两侧都切K,64,64,256,allocate(GM->L1随路驻留L2),"direct_gm(整case超L2: 输入优先驻留L2, 输出直写GM不占L2)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"两侧都切K: k_L1=1024, K段成对流水, batch边界天然无缝; dValueA=2048B/dValueB=128B; 输出落点: 直写GM",134217728,0.0,8.388608e-05,0.0,8.388608e-05,16,0.0,4294967296.0,8.837381267489712e-06,524288,3.2768e-07,0.0,8.421376e-05,7.16176329218107e-07,8.492993632921811e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),仅 IterBatch 条件满足 -streamk_demo,4,4,128,128,10240,bf16,bf16,bf16,False,False,False,True,0,streamk_demo,StreamK,Ascend950PR,batch_mat_mul_v3,32,1,1,1,32,"B/M/N切出4块, 每块32核切K归约 (归约组内核c负责K段[c*K/32,(c+1)*K/32))",1,1,128,128,320,256,1,K段标准分块流水,128,128,64,allocate(部分和驻留L2),"resident(部分和4B驻留L2, 防精度丢失不随C的fp16/fp8转换)",0,8388608,grid_K=32路切K+归约,1,1,32,0,0,0,0,True,4,"P=1.00, grid_K=32, 部分和驻留L2按4B写出, AIV归约后按C dtype=2B写最终",20971520,0,1.31072e-05,0.0,1.31072e-05,0.0,0.0,1342177280.0,2.761681646090535e-06,0.0,0.0,3.4067453613053613e-06,1.31072e-05,3.4067453613053613e-06,1.651394536130536e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),"P<=C/2, B/M/N并行度买不满, 切K (grid_K=32)" -asw_demo_full,2,2,8192,8192,1024,bf16,bf16,bf16,False,False,False,True,0,asw_demo_full,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,16,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,1024,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,16,True,2,"tile枚举: P=16, 有界枚举最优 mCnt=16 x nCnt=16 (tile 512x512, 每batch搬入512.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=64.0MB, V_out=256.0MB, L2=128MB); 尾轮: r=0 无尾轮",67108864,1006632960,4.194304e-05,0.00019358326153846154,0.00023552630153846153,0.0,0.0,274877906944.0,0.0005655924011193416,268435456,0.00016777216,0.0,0.0005655924011193416,0.0,0.0005655924011193416,MMAD,True,,计算Bound,ASW_Basic兜底 (StreamK未过: 1_并行缺口: P=B*MN*4B/L0C <= C/2; 2_单核K段下限: K/grid_K >= 256B/dtype 且 grid_K>=2; 3_归约代价可接受) -asw_demo_reduce_core,16,16,256,256,128,bf16,bf16,bf16,False,False,False,True,0,asw_demo_reduce_core,ASW_Basic_降核,Ascend950PR,batch_mat_mul_v3,16,1,1,1,1,"降核: 只用16核, 每核一个L0C满载输出块, 其余核闲置",0,1,256,256,128,128,1,标准核内流水,256,256,64,allocate,resident(整case全驻留S_A),0,0,不涉及(每核一块无尾轮),1,1,1,0,0,0,0,True,2,"P=16.00= 256B/dtype 且 grid_K>=2) -b4_m1_n128_k256,4,4,1,128,256,bf16,bf16,bf16,False,False,False,True,0,b4_m1_n128_k256,ASW_Basic_降核,Ascend950PR,batch_mat_mul_v3,1,1,1,1,1,"降核: 只用1核, 每核一个L0C满载输出块, 其余核闲置",0,1,1,128,256,256,1,标准核内流水,1,128,128,allocate,resident(整case全驻留S_A),0,0,不涉及(每核一块无尾轮),1,1,1,0,0,0,0,True,2,"P=0.01= 256B/dtype 且 grid_K>=2; 3_归约代价可接受: K > grid_K^2/(grid_K-1)*theta_c) -b8_m2_n192_k128,8,8,2,192,128,bf16,bf16,bf16,False,False,False,True,0,b8_m2_n192_k128,ASW_Basic_降核,Ascend950PR,batch_mat_mul_v3,1,1,1,1,1,"降核: 只用1核, 每核一个L0C满载输出块, 其余核闲置",0,1,2,192,128,128,1,标准核内流水,2,192,80,allocate,resident(整case全驻留S_A),0,0,不涉及(每核一块无尾轮),1,1,1,0,0,0,0,True,2,"P=0.05= 256B/dtype 且 grid_K>=2; 3_归约代价可接受: K > grid_K^2/(grid_K-1)*theta_c) -b16_m4_n256_k192,16,16,4,256,192,bf16,bf16,bf16,False,False,False,True,0,b16_m4_n256_k192,ASW_Basic_降核,Ascend950PR,batch_mat_mul_v3,1,1,1,1,1,"降核: 只用1核, 每核一个L0C满载输出块, 其余核闲置",0,1,4,256,192,192,1,标准核内流水,4,256,64,allocate,resident(整case全驻留S_A),0,0,不涉及(每核一块无尾轮),1,1,1,0,0,0,0,True,2,"P=0.25= 256B/dtype 且 grid_K>=2; 3_归约代价可接受: K > grid_K^2/(grid_K-1)*theta_c) -b32_m8_n128_k256,32,32,8,128,256,bf16,bf16,bf16,False,False,False,True,0,b32_m8_n128_k256,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),1,1,8,128,256,256,1,a_单batch全驻留,8,128,128,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,单batch全驻留: (MK+KN)*dtype=68KB <= L1; 输出落点: L2驻留,2228224,0.0,1.6384e-06,0.0,1.6384e-06,1,0.0,16777216.0,3.452102057613169e-08,65536,1.2603076923076923e-08,0.0,1.6384e-06,4.712409749920861e-08,1.6855240974992087e-06,MTE2,True,,访存Bound(GM读写共享+L2重复读),仅 IterBatch 条件满足 -b64_m16_n256_k512,64,64,16,256,512,bf16,bf16,bf16,False,False,False,True,0,b64_m16_n256_k512,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),2,1,16,256,512,240,1,c_一侧驻留+对侧切K,16,256,64,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"一侧驻留(A)+对侧切K: A驻留16KB, 预算L1/2, k_L1=240, dValueA=480B/dValueB=512B; 输出落点: L2驻留",17825792,0.0,1.114112e-05,0.0,1.114112e-05,6,0.0,268435456.0,5.52336329218107e-07,524288,1.0082461538461538e-07,0.0,1.114112e-05,1.798661348528015e-07,1.1320986134852803e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),仅 IterBatch 条件满足 -b128_m8_n192_k256,128,128,8,192,256,bf16,bf16,bf16,False,False,False,True,0,b128_m8_n192_k256,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),4,1,8,192,256,256,2,b_双batch乒乓,8,192,80,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,双batch乒乓: 2*(MK+KN)*dtype=200KB <= L1; 输出落点: L2驻留,13107200,0.0,9.17504e-06,0.0,9.17504e-06,4,0.0,100663296.0,2.0712612345679012e-07,393216,7.561846153846153e-08,0.0,9.17504e-06,7.068614624881291e-08,9.245726146248813e-06,MTE2,True,,访存Bound(GM读写共享+L2重复读),仅 IterBatch 条件满足 -b32_m16_n8192_k7168,32,32,16,8192,7168,bf16,bf16,bf16,False,False,False,True,0,b32_m16_n8192_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,1,8,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,16,1024,7168,112,1,双缓冲驻留当前tile输入,16,1024,16,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,8,True,2,"tile枚举: 效率降级(放开约束4, dValue 按 128B 硬下限, 搬移效率低于模型假设, 时延可能低估): P=1, mCnt=1 x nCnt=8 (tile 16x1024, 每batch搬入113.8MB, r=0); Base tile 16x1024 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=3591.0MB, V_out=8.0MB, L2=128MB); 尾轮: r=0 无尾轮",3765436416,51380224,0.00235339776,9.880812307692307e-06,0.0023632785723076925,0.0,0.0,60129542144.0,0.00012372333774485596,8388608,5.24288e-06,0.0,0.0023685214523076923,0.0,0.0023685214523076923,MTE2,True,,访存Bound(GM读写共享+L2重复读),"IterBatch/MergeBatch 进入条件均不满足, 回落 ASW_Basic; IterBatch未过: 3_L1驻留形态(四选一, 核心要求: 单batch核内零重复读); MergeBatch未过: 1_batch关系与每核份额: BatchA==BatchB 且 b_core=B/C>=2*b0; 2_L0C容量: 2*(b0*M)*(b0*N)*4B <= L0C; 2b_L0AB容量: 合并后 b0*M/b0*N 在最小K粒度下可驻留 L0A/L0B [效率降级标注: 搬移效率低于模型假设, 时延可能低估, 见 plan.note]" -b4_m1_n8192_k8192,4,4,1,8192,8192,bf16,bf16,bf16,False,False,False,True,0,b4_m1_n8192_k8192,StreamK,Ascend950PR,batch_mat_mul_v3,32,1,1,1,32,"B/M/N切出4块, 每块32核切K归约 (归约组内核c负责K段[c*K/32,(c+1)*K/32))",1,1,1,8192,256,256,1,K段标准分块流水,1,128,64,allocate(部分和驻留L2),"resident(部分和4B驻留L2, 防精度丢失不随C的fp16/fp8转换)",0,4194304,grid_K=32路切K+归约,1,1,32,0,0,0,0,True,4,"P=0.50, grid_K=32, 部分和驻留L2按4B写出, AIV归约后按C dtype=2B写最终",536936448,0.0,0.00033558528,0.0,0.00033558528,0.0,0.0,536870912.0,1.104672658436214e-06,0.0,0.0,1.731729603729604e-06,0.00033558528,1.731729603729604e-06,0.0003373170096037296,MTE2,True,,访存Bound(GM读写共享+L2重复读),"P<=C/2, B/M/N并行度买不满, 切K (grid_K=32)" -b16_m2_n4096_k7168,16,16,2,4096,7168,bf16,bf16,bf16,False,False,False,True,0,b16_m2_n4096_k7168,StreamK,Ascend950PR,batch_mat_mul_v3,32,1,1,1,16,"B/M/N切出16块, 每块16核切K归约 (归约组内核c负责K段[c*K/16,(c+1)*K/16))",1,1,2,4096,448,256,1,K段标准分块流水,2,128,64,allocate(部分和驻留L2),"resident(部分和4B驻留L2, 防精度丢失不随C的fp16/fp8转换)",0,8388608,grid_K=16路切K+归约,1,1,16,0,0,0,0,True,4,"P=2.00, grid_K=16, 部分和驻留L2按4B写出, AIV归约后按C dtype=2B写最终",939982848,0,0.00058748928,0.0,0.00058748928,0.0,0.0,1879048192.0,3.866354304526749e-06,0.0,0.0,1.7726896037296038e-06,0.00058748928,1.7726896037296038e-06,0.0005892619696037297,MTE2,True,,访存Bound(GM读写共享+L2重复读),"P<=C/2, B/M/N并行度买不满, 切K (grid_K=16)" -b32_m64_n64_k7168,32,32,64,64,7168,bf16,bf16,bf16,False,False,False,True,0,b32_m64_n64_k7168,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),1,1,64,64,7168,1024,1,d_两侧都切K,64,64,256,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"两侧都切K: k_L1=1024, K段成对流水, batch边界天然无缝; dValueA=2048B/dValueB=128B; 输出落点: L2驻留",58720256,0.0,3.670016e-05,0.0,3.670016e-05,7,0.0,1879048192.0,3.866354304526749e-06,262144,5.041230769230769e-08,0.0,3.670016e-05,6.027486369104147e-07,3.730290863691042e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),仅 IterBatch 条件满足 -b64_m1024_n1024_k7168,64,64,1024,1024,7168,bf16,bf16,bf16,False,False,False,True,0,b64_m1024_n1024_k7168,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),2,1,1024,1024,7168,64,1,d_两侧都切K,176,176,64,allocate(GM->L1随路驻留L2),"direct_gm(整case超L2: 输入优先驻留L2, 输出直写GM不占L2)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"两侧都切K: k_L1=64, K段成对流水, batch边界天然无缝; dValueA=128B/dValueB=2048B; 输出落点: 直写GM",1879048192,0.0,0.00117440512,0.0,0.00117440512,224,0.0,962072674304.0,0.0019795734039176954,134217728,8.388608e-05,0.0,0.0019795734039176954,5.078042126748971e-05,0.0020303538251851853,MMAD,True,,计算Bound,仅 IterBatch 条件满足 -b128_m2048_n2048_k1536,128,128,2048,2048,1536,bf16,bf16,bf16,False,False,False,True,0,b128_m2048_n2048_k1536,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,4,4,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,1536,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,64,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=4 x nCnt=4 (tile 512x512, 每batch搬入48.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=1536.0MB, V_out=1024.0MB, L2=128MB); 尾轮: r=0 无尾轮",1610612736,4831838208,0.00100663296,0.0009291996553846154,0.0019358326153846154,0.0,0.0,1649267441664.0,0.0033935544067160493,1073741824,0.00067108864,0.0,0.0033935544067160493,0.0,0.0033935544067160493,MMAD,True,,计算Bound,"IterBatch/MergeBatch 进入条件均不满足, 回落 ASW_Basic; IterBatch未过: 3_L1驻留形态(四选一, 核心要求: 单batch核内零重复读); MergeBatch未过: 2_L0C容量: 2*(b0*M)*(b0*N)*4B <= L0C; 2b_L0AB容量: 合并后 b0*M/b0*N 在最小K粒度下可驻留 L0A/L0B; 5_访存Bound: 2MN/(M+N) < R16/b0" -b64_m1024_n8192_k2048,64,64,1024,8192,2048,bf16,bf16,bf16,False,False,False,True,0,b64_m1024_n8192_k2048,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,2,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,2048,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,64,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=2 x nCnt=16 (tile 512x512, 每batch搬入128.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=2304.0MB, V_out=1024.0MB, L2=128MB); 尾轮: r=0 无尾轮",2415919104,6174015488,0.00150994944,0.0011873106707692308,0.0026972601107692305,0.0,0.0,2199023255552.0,0.004524739208954733,1073741824,0.00067108864,0.0,0.004524739208954733,0.0,0.004524739208954733,MMAD,True,,计算Bound,"IterBatch/MergeBatch 进入条件均不满足, 回落 ASW_Basic; IterBatch未过: 3_L1驻留形态(四选一, 核心要求: 单batch核内零重复读); MergeBatch未过: 1_batch关系与每核份额: BatchA==BatchB 且 b_core=B/C>=2*b0; 2_L0C容量: 2*(b0*M)*(b0*N)*4B <= L0C; 2b_L0AB容量: 合并后 b0*M/b0*N 在最小K粒度下可驻留 L0A/L0B; 5_访存Bound: 2MN/(M+N) < R16/b0" -b32_m1024_n1024_k512,32,32,1024,1024,512,bf16,bf16,bf16,False,False,False,True,0,b32_m1024_n1024_k512,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),1,1,1024,1024,512,64,1,d_两侧都切K,176,176,64,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"两侧都切K: k_L1=64, K段成对流水, batch边界天然无缝; dValueA=128B/dValueB=2048B; 输出落点: L2驻留",67108864,0.0,4.194304e-05,0.0,4.194304e-05,8,0.0,34359738368.0,7.06990501399177e-05,67108864,1.290555076923077e-05,0.0,7.06990501399177e-05,2.1742932036720483e-05,9.244198217663819e-05,MMAD,True,,计算Bound,仅 IterBatch 条件满足 -b128_m4096_n4096_k8192,128,128,4096,4096,8192,bf16,bf16,bf16,False,False,False,True,0,b128_m4096_n4096_k8192,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,8,8,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,8192,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,256,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=8 x nCnt=8 (tile 512x512, 每batch搬入1024.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=16384.0MB, V_out=4096.0MB, L2=128MB); 尾轮: r=0 无尾轮",17179869184,120259084288,0.01073741824,0.023126746978461538,0.033864165218461535,0.0,0.0,35184372088832.0,0.07239582734327572,4294967296,0.00268435456,0.0,0.07239582734327572,0.0,0.07239582734327572,MMAD,True,,计算Bound,"IterBatch/MergeBatch 进入条件均不满足, 回落 ASW_Basic; IterBatch未过: 3_L1驻留形态(四选一, 核心要求: 单batch核内零重复读); MergeBatch未过: 2_L0C容量: 2*(b0*M)*(b0*N)*4B <= L0C; 2b_L0AB容量: 合并后 b0*M/b0*N 在最小K粒度下可驻留 L0A/L0B; 5_访存Bound: 2MN/(M+N) < R16/b0" -b32_m8192_n4096_k7168,32,32,8192,4096,7168,bf16,bf16,bf16,False,False,False,True,0,b32_m8192_n4096_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,16,8,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,7168,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,128,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=16 x nCnt=8 (tile 512x512, 每batch搬入1792.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=5376.0MB, V_out=2048.0MB, L2=128MB); 尾轮: r=0 无尾轮",5637144576,54492397568,0.00352321536,0.010479307224615384,0.014002522584615384,0.0,0.0,15393162788864.0,0.031673174462683126,2147483648,0.00134217728,0.0,0.031673174462683126,0.0,0.031673174462683126,MMAD,True,,计算Bound,"IterBatch/MergeBatch 进入条件均不满足, 回落 ASW_Basic; IterBatch未过: 3_L1驻留形态(四选一, 核心要求: 单batch核内零重复读); MergeBatch未过: 1_batch关系与每核份额: BatchA==BatchB 且 b_core=B/C>=2*b0; 2_L0C容量: 2*(b0*M)*(b0*N)*4B <= L0C; 2b_L0AB容量: 合并后 b0*M/b0*N 在最小K粒度下可驻留 L0A/L0B; 5_访存Bound: 2MN/(M+N) < R16/b0" -b32_m2048_n2048_k8192,32,32,2048,2048,8192,bf16,bf16,bf16,False,False,False,True,0,b32_m2048_n2048_k8192,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,4,4,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,8192,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,16,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=4 x nCnt=4 (tile 512x512, 每batch搬入256.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=2048.0MB, V_out=256.0MB, L2=128MB); 尾轮: r=0 无尾轮",2147483648,6442450944,0.00134217728,0.0012389328738461537,0.002581110153846154,0.0,0.0,2199023255552.0,0.004524739208954733,268435456,0.00016777216,0.0,0.004524739208954733,0.0,0.004524739208954733,MMAD,True,,计算Bound,"IterBatch/MergeBatch 进入条件均不满足, 回落 ASW_Basic; IterBatch未过: 3_L1驻留形态(四选一, 核心要求: 单batch核内零重复读); MergeBatch未过: 1_batch关系与每核份额: BatchA==BatchB 且 b_core=B/C>=2*b0; 2_L0C容量: 2*(b0*M)*(b0*N)*4B <= L0C; 2b_L0AB容量: 合并后 b0*M/b0*N 在最小K粒度下可驻留 L0A/L0B; 5_访存Bound: 2MN/(M+N) < R16/b0" -b64_m4096_n2048_k128,64,64,4096,2048,128,bf16,bf16,bf16,False,False,False,True,0,b64_m4096_n2048_k128,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,8,4,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,128,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,64,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=8 x nCnt=4 (tile 512x512, 每batch搬入8.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=96.0MB, V_out=1024.0MB, L2=128MB); 尾轮: r=0 无尾轮",100663296,436207616,6.291456e-05,8.388608e-05,0.00014680063999999998,0.0,0.0,137438953472.0,0.0002827962005596708,1073741824,0.00067108864,0.0,0.00081788928,0.0,0.00081788928,MTE2,True,,访存Bound(GM读写共享+L2重复读),"IterBatch/MergeBatch 进入条件均不满足, 回落 ASW_Basic; IterBatch未过: 3_L1驻留形态(四选一, 核心要求: 单batch核内零重复读); MergeBatch未过: 1_batch关系与每核份额: BatchA==BatchB 且 b_core=B/C>=2*b0; 2_L0C容量: 2*(b0*M)*(b0*N)*4B <= L0C; 2b_L0AB容量: 合并后 b0*M/b0*N 在最小K粒度下可驻留 L0A/L0B; 5_访存Bound: 2MN/(M+N) < R16/b0" -b16_m1024_n1024_k8192,16,16,1024,1024,8192,bf16,bf16,bf16,False,False,False,True,0,b16_m1024_n1024_k8192,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,2,2,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,8192,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,2,True,2,"tile枚举: P=2, 有界枚举最优 mCnt=2 x nCnt=2 (tile 512x512, 每batch搬入64.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=512.0MB, V_out=32.0MB, L2=128MB); 尾轮: r=0 无尾轮",536870912,536870912,0.00033554432,0.00010324440615384615,0.0004387887261538461,0.0,0.0,274877906944.0,0.0005655924011193416,33554432,2.097152e-05,0.0,0.0005655924011193416,0.0,0.0005655924011193416,MMAD,True,,计算Bound,ASW_Basic兜底 (StreamK未过: 1_并行缺口: P=B*MN*4B/L0C <= C/2; 2_单核K段下限: K/grid_K >= 256B/dtype 且 grid_K>=2; 3_归约代价可接受) -b4_m32768_n128_k128,4,4,32768,128,128,bf16,bf16,bf16,False,False,False,True,0,b4_m32768_n128_k128,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,64,1,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,128,128,128,1,双缓冲驻留当前tile输入,512,128,32,allocate(输入驻留L2吸收重复读),"resident(整case全驻留S_A: 输出驻留L2异步回写, GM写=0)",4,0,A0,1,1,1,0,0,0,8,True,2,"tile枚举: P=8, 有界枚举最优 mCnt=64 x nCnt=1 (tile 512x128, 每batch搬入10.0MB, r=0); Base tile 512x128 (L0C 单缓冲方形用满); L2场景: A_整case全驻留(输入+输出<=L2) (V_in=32.1MB, V_out=32.0MB, L2=128MB); 尾轮: r=0 无尾轮",33685504,8257536,2.105344e-05,1.5879876923076922e-06,2.2641427692307692e-05,0.0,0.0,4294967296.0,8.837381267489712e-06,33554432,6.452775384615385e-06,0.0,2.2641427692307692e-05,0.0,2.2641427692307692e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),ASW_Basic兜底 (StreamK未过: 1_并行缺口: P=B*MN*4B/L0C <= C/2; 2_单核K段下限: K/grid_K >= 256B/dtype 且 grid_K>=2; 3_归约代价可接受) -b8_m32768_n2048_k512,8,8,32768,2048,512,bf16,bf16,bf16,False,False,False,True,0,b8_m32768_n2048_k512,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,64,4,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,512,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,64,True,2,"tile枚举: P=4, 有界枚举最优 mCnt=64 x nCnt=4 (tile 512x512, 每batch搬入256.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=272.0MB, V_out=1024.0MB, L2=128MB); 尾轮: r=0 无尾轮",285212672,1862270976,0.00017825792,0.00035812903384615385,0.0005363869538461539,0.0,0.0,549755813888.0,0.0011311848022386832,1073741824,0.00067108864,0.0,0.0012074755938461538,0.0,0.0012074755938461538,MTE2,True,,访存Bound(GM读写共享+L2重复读),ASW_Basic兜底 (StreamK未过: 1_并行缺口: P=B*MN*4B/L0C <= C/2; 2_单核K段下限: K/grid_K >= 256B/dtype 且 grid_K>=2; 3_归约代价可接受) -b4_m131072_n128_k128,4,4,131072,128,128,bf16,bf16,bf16,False,False,False,True,0,b4_m131072_n128_k128,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,256,1,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,128,128,128,1,双缓冲驻留当前tile输入,512,128,32,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,32,True,2,"tile枚举: P=8, 有界枚举最优 mCnt=256 x nCnt=1 (tile 512x128, 每batch搬入40.0MB, r=0); Base tile 512x128 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=128.1MB, V_out=128.0MB, L2=128MB); 尾轮: r=0 无尾轮",134348800,33423360,8.3968e-05,6.427569230769231e-06,9.039556923076924e-05,0.0,0.0,17179869184.0,3.534952506995885e-05,134217728,8.388608e-05,0.0,0.00017428164923076922,0.0,0.00017428164923076922,MTE2,True,,访存Bound(GM读写共享+L2重复读),ASW_Basic兜底 (StreamK未过: 1_并行缺口: P=B*MN*4B/L0C <= C/2; 2_单核K段下限: K/grid_K >= 256B/dtype 且 grid_K>=2; 3_归约代价可接受) -b8_m131072_n1024_k256,8,8,131072,1024,256,bf16,bf16,bf16,False,False,False,True,0,b8_m131072_n1024_k256,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,256,2,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,256,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,128,True,2,"tile枚举: P=4, 有界枚举最优 mCnt=256 x nCnt=2 (tile 512x512, 每batch搬入256.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=516.0MB, V_out=2048.0MB, L2=128MB); 尾轮: r=0 无尾轮",541065216,1606418432,0.00033816576,0.00030892662153846154,0.0006470923815384616,0.0,0.0,549755813888.0,0.0011311848022386832,2147483648,0.00134217728,0.0,0.0019892696615384617,0.0,0.0019892696615384617,MTE2,True,,访存Bound(GM读写共享+L2重复读),ASW_Basic兜底 (StreamK未过: 1_并行缺口: P=B*MN*4B/L0C <= C/2; 2_单核K段下限: K/grid_K >= 256B/dtype 且 grid_K>=2; 3_归约代价可接受) -b16_m32768_n8192_k7168,16,16,32768,8192,7168,bf16,bf16,bf16,False,False,False,True,0,b16_m32768_n8192_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,64,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,7168,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,512,True,2,"tile枚举: P=2, 有界枚举最优 mCnt=64 x nCnt=16 (tile 512x512, 每batch搬入14336.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=8960.0MB, V_out=8192.0MB, L2=128MB); 尾轮: r=0 无尾轮",9395240960,231122927616,0.0058720256,0.044446716849230766,0.05031874244923076,0.0,0.0,61572651155456.0,0.1266926978507325,8589934592,0.00536870912,0.0,0.1266926978507325,0.0,0.1266926978507325,MMAD,True,,计算Bound,ASW_Basic兜底 (StreamK未过: 1_并行缺口: P=B*MN*4B/L0C <= C/2; 2_单核K段下限: K/grid_K >= 256B/dtype 且 grid_K>=2; 3_归约代价可接受) -b4_m32768_n128_k8192,4,4,32768,128,8192,bf16,bf16,bf16,False,False,False,True,0,b4_m32768_n128_k8192,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,64,1,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,128,8192,192,1,双缓冲驻留当前tile输入,512,128,32,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,8,True,2,"tile枚举: P=8, 有界枚举最优 mCnt=64 x nCnt=1 (tile 512x128, 每batch搬入640.0MB, r=0); Base tile 512x128 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=2056.0MB, V_out=32.0MB, L2=128MB); 尾轮: r=0 无尾轮",2155872256,528482304,0.00134742016,0.0001016312123076923,0.0014490513723076923,0.0,0.0,274877906944.0,0.0005655924011193416,33554432,2.097152e-05,0.0,0.0014700228923076922,0.0,0.0014700228923076922,MTE2,True,,访存Bound(GM读写共享+L2重复读),ASW_Basic兜底 (StreamK未过: 1_并行缺口: P=B*MN*4B/L0C <= C/2; 2_单核K段下限: K/grid_K >= 256B/dtype 且 grid_K>=2; 3_归约代价可接受) -b32_m131072_n8192_k128,32,32,131072,8192,128,bf16,bf16,bf16,False,False,False,True,0,b32_m131072_n8192_k128,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,256,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,128,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,4096,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=256 x nCnt=16 (tile 512x512, 每batch搬入1024.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=1088.0MB, V_out=65536.0MB, L2=128MB); 尾轮: r=0 无尾轮",1140850688,33218887680,0.00071303168,0.006388247630769231,0.007101279310769231,0.0,0.0,8796093022208.0,0.01809895683581893,68719476736,0.04294967296,0.0,0.05005095227076922,0.0,0.05005095227076922,MTE2,True,,访存Bound(GM读写共享+L2重复读),"IterBatch/MergeBatch 进入条件均不满足, 回落 ASW_Basic; IterBatch未过: 3_L1驻留形态(四选一, 核心要求: 单batch核内零重复读); MergeBatch未过: 1_batch关系与每核份额: BatchA==BatchB 且 b_core=B/C>=2*b0; 2_L0C容量: 2*(b0*M)*(b0*N)*4B <= L0C; 2b_L0AB容量: 合并后 b0*M/b0*N 在最小K粒度下可驻留 L0A/L0B; 5_访存Bound: 2MN/(M+N) < R16/b0" -b64_m32768_n8192_k1536,64,64,32768,8192,1536,bf16,bf16,bf16,False,False,False,True,0,b64_m32768_n8192_k1536,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,64,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,1536,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,2048,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=64 x nCnt=16 (tile 512x512, 每batch搬入3072.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=7680.0MB, V_out=32768.0MB, L2=128MB); 尾轮: r=0 无尾轮",8053063680,198105366528,0.0050331648,0.03809718587076923,0.04313035067076923,0.0,0.0,52776558133248.0,0.10859374101491358,34359738368,0.02147483648,0.0,0.10859374101491358,0.0,0.10859374101491358,MMAD,True,,计算Bound,"IterBatch/MergeBatch 进入条件均不满足, 回落 ASW_Basic; IterBatch未过: 3_L1驻留形态(四选一, 核心要求: 单batch核内零重复读); MergeBatch未过: 1_batch关系与每核份额: BatchA==BatchB 且 b_core=B/C>=2*b0; 2_L0C容量: 2*(b0*M)*(b0*N)*4B <= L0C; 2b_L0AB容量: 合并后 b0*M/b0*N 在最小K粒度下可驻留 L0A/L0B; 5_访存Bound: 2MN/(M+N) < R16/b0" -b8_m131072_n8192_k8192,8,8,131072,8192,8192,bf16,bf16,bf16,False,False,False,True,0,b8_m131072_n8192_k8192,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,256,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,8192,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,1024,True,2,"tile枚举: P=4, 有界枚举最优 mCnt=256 x nCnt=16 (tile 512x512, 每batch搬入65536.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: C_双侧超L2: 最小替换2D分组(组间落空GM, 窗口L2) (V_in=17408.0MB, V_out=16384.0MB, L2=128MB); 最小替换分组 m_grp=8x n_grp=8 (GM倍率3.76, 窗口L2/batch=57344.0MB); 尾轮: r=0 无尾轮",68719476736,481036337152,0.04294967296,0.09250698791384615,0.13545666087384614,0.0,0.0,140737488355328.0,0.2895833093731029,17179869184,0.01073741824,0.0,0.2895833093731029,0.0,0.2895833093731029,MMAD,True,,计算Bound,ASW_Basic兜底 (StreamK未过: 1_并行缺口: P=B*MN*4B/L0C <= C/2; 2_单核K段下限: K/grid_K >= 256B/dtype 且 grid_K>=2; 3_归约代价可接受) -b8_m16_n7168_k1536,8,8,16,7168,1536,bf16,bf16,bf16,False,False,False,True,0,b8_m16_n7168_k1536,StreamK,Ascend950PR,batch_mat_mul_v3,32,1,1,2,2,"B/M/N切出16块, 每块2核切K归约 (归约组内核c负责K段[c*K/2,(c+1)*K/2))",1,1,16,3584,768,256,1,K段标准分块流水,16,128,64,allocate(部分和驻留L2),"resident(部分和4B驻留L2, 防精度丢失不随C的fp16/fp8转换)",0,3670016,grid_K=2路切K+归约,1,1,2,0,0,0,0,True,4,"P=14.00, grid_K=2, 部分和驻留L2按4B写出, AIV归约后按C dtype=2B写最终",176553984,393216,0.00011034624,7.561846153846153e-08,0.00011042185846153846,0.0,0.0,2818572288.0,5.799531456790123e-06,0.0,0.0,2.566079254079254e-07,0.00011042185846153846,2.566079254079254e-07,0.00011067846638694638,MTE2,True,,访存Bound(GM读写共享+L2重复读),"P<=C/2, B/M/N并行度买不满, 切K (grid_K=2)" -b64_m1024_n7168_k7168,64,64,1024,7168,7168,bf16,bf16,bf16,False,False,False,True,0,b64_m1024_n7168_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,2,14,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,7168,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,56,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=2 x nCnt=14 (tile 512x512, 每batch搬入392.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=7168.0MB, V_out=896.0MB, L2=128MB); 尾轮: r=0 无尾轮",7516192768,18790481920,0.00469762048,0.0036135542153846152,0.008311174695384616,0.0,0.0,6734508720128.0,0.013857013827423869,939524096,0.00058720256,0.0,0.013857013827423869,0.0,0.013857013827423869,MMAD,True,,计算Bound,"IterBatch/MergeBatch 进入条件均不满足, 回落 ASW_Basic; IterBatch未过: 3_L1驻留形态(四选一, 核心要求: 单batch核内零重复读); MergeBatch未过: 1_batch关系与每核份额: BatchA==BatchB 且 b_core=B/C>=2*b0; 2_L0C容量: 2*(b0*M)*(b0*N)*4B <= L0C; 2b_L0AB容量: 合并后 b0*M/b0*N 在最小K粒度下可驻留 L0A/L0B; 5_访存Bound: 2MN/(M+N) < R16/b0" -b32_m8192_n8192_k7168,32,32,8192,8192,7168,bf16,bf16,bf16,False,False,False,True,0,b32_m8192_n8192_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,16,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,7168,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,256,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=16 x nCnt=16 (tile 512x512, 每batch搬入3584.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=7168.0MB, V_out=4096.0MB, L2=128MB); 尾轮: r=0 无尾轮",7516192768,112742891520,0.00469762048,0.021681325292307693,0.026378945772307694,0.0,0.0,30786325577728.0,0.06334634892536625,4294967296,0.00268435456,0.0,0.06334634892536625,0.0,0.06334634892536625,MMAD,True,,计算Bound,"IterBatch/MergeBatch 进入条件均不满足, 回落 ASW_Basic; IterBatch未过: 3_L1驻留形态(四选一, 核心要求: 单batch核内零重复读); MergeBatch未过: 1_batch关系与每核份额: BatchA==BatchB 且 b_core=B/C>=2*b0; 2_L0C容量: 2*(b0*M)*(b0*N)*4B <= L0C; 2b_L0AB容量: 合并后 b0*M/b0*N 在最小K粒度下可驻留 L0A/L0B; 5_访存Bound: 2MN/(M+N) < R16/b0" -b8_m4096_n4096_k128,8,8,4096,4096,128,bf16,bf16,bf16,False,False,False,True,0,b8_m4096_n4096_k128,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,8,8,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,128,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,16,True,2,"tile枚举: P=4, 有界枚举最优 mCnt=8 x nCnt=8 (tile 512x512, 每batch搬入16.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=16.0MB, V_out=256.0MB, L2=128MB); 尾轮: r=0 无尾轮",16777216,117440512,1.048576e-05,2.2584713846153845e-05,3.307047384615384e-05,0.0,0.0,34359738368.0,7.06990501399177e-05,268435456,0.00016777216,0.0,0.00020084263384615383,0.0,0.00020084263384615383,MTE2,True,,访存Bound(GM读写共享+L2重复读),ASW_Basic兜底 (StreamK未过: 1_并行缺口: P=B*MN*4B/L0C <= C/2; 2_单核K段下限: K/grid_K >= 256B/dtype 且 grid_K>=2; 3_归约代价可接受) -b128_m8192_n8192_k7168,128,128,8192,8192,7168,bf16,bf16,bf16,False,False,False,True,0,b128_m8192_n8192_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,16,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,7168,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,1024,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=16 x nCnt=16 (tile 512x512, 每batch搬入3584.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=28672.0MB, V_out=16384.0MB, L2=128MB); 尾轮: r=0 无尾轮",30064771072,450971566080,0.01879048192,0.08672530116923077,0.10551578308923078,0.0,0.0,123145302310912.0,0.253385395701465,17179869184,0.01073741824,0.0,0.253385395701465,0.0,0.253385395701465,MMAD,True,,计算Bound,"IterBatch/MergeBatch 进入条件均不满足, 回落 ASW_Basic; IterBatch未过: 3_L1驻留形态(四选一, 核心要求: 单batch核内零重复读); MergeBatch未过: 2_L0C容量: 2*(b0*M)*(b0*N)*4B <= L0C; 2b_L0AB容量: 合并后 b0*M/b0*N 在最小K粒度下可驻留 L0A/L0B; 5_访存Bound: 2MN/(M+N) < R16/b0" +merge_demo_k_trunc,2048,2048,16,64,128,bf16,bf16,bf16,False,False,False,True,0,merge_demo_k_trunc,MergeBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B均分(核间零重复读零依赖),64,4,64,256,128,128,12,合并驻留,64,256,64,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"b0=4 (L0C上限5.7/算存比上限21.1/b_core=64); K截断; 合并后单次DMA搬入 A'[64,128]+B'[128,256]; 输出落点: L2驻留 (整case V_in+V_out=40.0MB vs L2=128MB)",41943040,0.0,2.62144e-05,0.0,2.62144e-05,16,0.0,2147483648.0,4.971026962962963e-06,4194304,8.065969230769231e-07,0.0,2.62144e-05,1.2808460398860398e-07,2.6342484603988603e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),"两分支均合法, 仲裁: [分界条件] MergeBatch最优=True (K截断(k_l1^m=128>=K); 每核命令数 MergeBatch=16 vs IterBatch=64 (命令节省=0.00us) + 搬移效率节省=15.73us vs drain惩罚=(b0-1)*(T_comp+T_write)=0.18us -> MergeBatch优); [时延模型] T_MergeBatch=26.34us vs T_IterBatch=41.98us -> MergeBatch更优; [裁决] MergeBatch" +merge_iter_arbitrate,128,128,64,64,512,bf16,bf16,bf16,False,False,False,True,0,merge_iter_arbitrate,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),4,1,64,64,512,512,2,b_双batch乒乓,64,64,256,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,双batch乒乓: 2*(MK+KN)*dtype=256KB <= L1; 输出落点: L2驻留,16777216,0.0,1.048576e-05,0.0,1.048576e-05,4,0.0,536870912.0,1.2427567407407407e-06,1048576,2.0164923076923077e-07,0.0,1.048576e-05,3.6110149287749287e-07,1.0846861492877492e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),"两分支均合法, 仲裁: [分界条件] MergeBatch最优=False (L1绑定(k_l1^m=256 IterBatch优); [时延模型] T_MergeBatch=10.90us vs T_IterBatch=10.85us -> IterBatch更优; [裁决] IterBatch" +iter_demo_form_b,128,128,64,64,256,bf16,bf16,bf16,False,False,False,True,0,iter_demo_form_b,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),4,1,64,64,256,256,2,b_双batch乒乓,64,64,256,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,双batch乒乓: 2*(MK+KN)*dtype=128KB <= L1; 输出落点: L2驻留,8388608,0.0,5.24288e-06,0.0,5.24288e-06,4,0.0,268435456.0,6.213783703703703e-07,1048576,2.0164923076923077e-07,0.0,5.24288e-06,2.0575690028490026e-07,5.4486369002849e-06,MTE2,True,,访存Bound(GM读写共享+L2重复读),仅 IterBatch 条件满足 +iter_demo_form_d,64,64,64,64,8192,bf16,bf16,bf16,False,False,False,True,0,iter_demo_form_d,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),2,1,64,64,8192,1024,1,d_两侧都切K,64,64,256,allocate(GM->L1随路驻留L2),"direct_gm(整case超L2: 输入优先驻留L2, 输出直写GM不占L2)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"两侧都切K: k_L1=1024, K段成对流水, batch边界天然无缝; dValueA=2048B/dValueB=128B; 输出落点: 直写GM",134217728,0.0,8.388608e-05,0.0,8.388608e-05,16,0.0,4294967296.0,9.942053925925925e-06,524288,3.2768e-07,0.0,8.421376e-05,7.852183703703703e-07,8.499897837037037e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),仅 IterBatch 条件满足 +streamk_demo,4,4,128,128,10240,bf16,bf16,bf16,False,False,False,True,0,streamk_demo,StreamK,Ascend950PR,batch_mat_mul_v3,32,1,1,1,32,"B/M/N切出4块, 每块32核切K归约 (归约组内核c负责K段[c*K/32,(c+1)*K/32))",1,1,128,128,320,256,1,K段标准分块流水,128,128,64,allocate(部分和驻留L2),"resident(部分和4B驻留L2, 防精度丢失不随C的fp16/fp8转换)",0,8388608,grid_K=32路切K+归约,1,1,32,0,0,0,0,True,4,"P=1.00, grid_K=32, 部分和驻留L2按4B写出, AIV归约后按C dtype=2B写最终",20971520,0,1.31072e-05,0.0,1.31072e-05,0.0,0.0,1342177280.0,3.1068918518518518e-06,0.0,0.0,3.4067453613053613e-06,1.31072e-05,3.4067453613053613e-06,1.651394536130536e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),"P<=C/2, B/M/N并行度买不满, 切K (grid_K=32)" +asw_demo_full,2,2,8192,8192,1024,bf16,bf16,bf16,False,False,False,True,0,asw_demo_full,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,16,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,1024,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,16,True,2,"tile枚举: P=16, 有界枚举最优 mCnt=16 x nCnt=16 (tile 512x512, 每batch搬入512.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=64.0MB, V_out=256.0MB, L2=128MB); 尾轮: r=0 无尾轮",67108864,1006632960,4.194304e-05,0.00019358326153846154,0.00023552630153846153,0.0,0.0,274877906944.0,0.0006362914512592592,268435456,0.00016777216,0.0,0.0006362914512592592,0.0,0.0006362914512592592,MMAD,True,,计算Bound,ASW_Basic兜底 (StreamK未过: 1_并行缺口: P=B*MN*4B/L0C <= C/2; 2_单核K段下限: K/grid_K >= 256B/dtype 且 grid_K>=2; 3_归约代价可接受) +asw_demo_reduce_core,16,16,256,256,128,bf16,bf16,bf16,False,False,False,True,0,asw_demo_reduce_core,ASW_Basic_降核,Ascend950PR,batch_mat_mul_v3,16,1,1,1,1,"降核: 只用16核, 每核一个L0C满载输出块, 其余核闲置",0,1,256,256,128,128,1,标准核内流水,256,256,64,allocate,resident(整case全驻留S_A),0,0,不涉及(每核一块无尾轮),1,1,1,0,0,0,0,True,2,"P=16.00= 256B/dtype 且 grid_K>=2) +b4_m1_n128_k256,4,4,1,128,256,bf16,bf16,bf16,False,False,False,True,0,b4_m1_n128_k256,ASW_Basic_降核,Ascend950PR,batch_mat_mul_v3,1,1,1,1,1,"降核: 只用1核, 每核一个L0C满载输出块, 其余核闲置",0,1,1,128,256,256,1,标准核内流水,1,128,128,allocate,resident(整case全驻留S_A),0,0,不涉及(每核一块无尾轮),1,1,1,0,0,0,0,True,2,"P=0.01= 256B/dtype 且 grid_K>=2; 3_归约代价可接受: K > grid_K^2/(grid_K-1)*theta_c) +b8_m2_n192_k128,8,8,2,192,128,bf16,bf16,bf16,False,False,False,True,0,b8_m2_n192_k128,ASW_Basic_降核,Ascend950PR,batch_mat_mul_v3,1,1,1,1,1,"降核: 只用1核, 每核一个L0C满载输出块, 其余核闲置",0,1,2,192,128,128,1,标准核内流水,2,192,80,allocate,resident(整case全驻留S_A),0,0,不涉及(每核一块无尾轮),1,1,1,0,0,0,0,True,2,"P=0.05= 256B/dtype 且 grid_K>=2; 3_归约代价可接受: K > grid_K^2/(grid_K-1)*theta_c) +b16_m4_n256_k192,16,16,4,256,192,bf16,bf16,bf16,False,False,False,True,0,b16_m4_n256_k192,ASW_Basic_降核,Ascend950PR,batch_mat_mul_v3,1,1,1,1,1,"降核: 只用1核, 每核一个L0C满载输出块, 其余核闲置",0,1,4,256,192,192,1,标准核内流水,4,256,64,allocate,resident(整case全驻留S_A),0,0,不涉及(每核一块无尾轮),1,1,1,0,0,0,0,True,2,"P=0.25= 256B/dtype 且 grid_K>=2; 3_归约代价可接受: K > grid_K^2/(grid_K-1)*theta_c) +b32_m8_n128_k256,32,32,8,128,256,bf16,bf16,bf16,False,False,False,True,0,b32_m8_n128_k256,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),1,1,8,128,256,256,1,a_单batch全驻留,8,128,128,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,单batch全驻留: (MK+KN)*dtype=68KB <= L1; 输出落点: L2驻留,2228224,0.0,1.6384e-06,0.0,1.6384e-06,1,0.0,16777216.0,3.8836148148148146e-08,65536,1.2603076923076923e-08,0.0,1.6384e-06,5.1439225071225065e-08,1.689839225071225e-06,MTE2,True,,访存Bound(GM读写共享+L2重复读),仅 IterBatch 条件满足 +b64_m16_n256_k512,64,64,16,256,512,bf16,bf16,bf16,False,False,False,True,0,b64_m16_n256_k512,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),2,1,16,256,512,240,1,c_一侧驻留+对侧切K,16,256,64,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"一侧驻留(A)+对侧切K: A驻留16KB, 预算L1/2, k_L1=240, dValueA=480B/dValueB=512B; 输出落点: L2驻留",17825792,0.0,1.114112e-05,0.0,1.114112e-05,6,0.0,268435456.0,6.213783703703703e-07,524288,1.0082461538461538e-07,0.0,1.114112e-05,1.9604786324786327e-07,1.1337167863247863e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),仅 IterBatch 条件满足 +b128_m8_n192_k256,128,128,8,192,256,bf16,bf16,bf16,False,False,False,True,0,b128_m8_n192_k256,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),4,1,8,192,256,256,2,b_双batch乒乓,8,192,80,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,双batch乒乓: 2*(MK+KN)*dtype=200KB <= L1; 输出落点: L2驻留,13107200,0.0,9.17504e-06,0.0,9.17504e-06,4,0.0,100663296.0,2.330168888888889e-07,393216,7.561846153846153e-08,0.0,9.17504e-06,7.71588376068376e-08,9.252198837606838e-06,MTE2,True,,访存Bound(GM读写共享+L2重复读),仅 IterBatch 条件满足 +b32_m16_n8192_k7168,32,32,16,8192,7168,bf16,bf16,bf16,False,False,False,True,0,b32_m16_n8192_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,1,8,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,16,1024,7168,112,1,双缓冲驻留当前tile输入,16,1024,16,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,8,True,2,"tile枚举: 效率降级(放开约束4, dValue 按 128B 硬下限, 搬移效率低于模型假设, 时延可能低估): P=1, mCnt=1 x nCnt=8 (tile 16x1024, 每batch搬入113.8MB, r=0); Base tile 16x1024 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=3591.0MB, V_out=8.0MB, L2=128MB); 尾轮: r=0 无尾轮",3765436416,51380224,0.00235339776,9.880812307692307e-06,0.0023632785723076925,0.0,0.0,60129542144.0,0.00013918875496296296,8388608,5.24288e-06,0.0,0.0023685214523076923,0.0,0.0023685214523076923,MTE2,True,,访存Bound(GM读写共享+L2重复读),"IterBatch/MergeBatch 进入条件均不满足, 回落 ASW_Basic; IterBatch未过: 3_L1驻留形态(四选一, 核心要求: 单batch核内零重复读); MergeBatch未过: 1_batch关系与每核份额: BatchA==BatchB 且 b_core=B/C>=2*b0; 2_L0C容量: 2*(b0*M)*(b0*N)*4B <= L0C; 2b_L0AB容量: 合并后 b0*M/b0*N 在最小K粒度下可驻留 L0A/L0B [效率降级标注: 搬移效率低于模型假设, 时延可能低估, 见 plan.note]" +b4_m1_n8192_k8192,4,4,1,8192,8192,bf16,bf16,bf16,False,False,False,True,0,b4_m1_n8192_k8192,StreamK,Ascend950PR,batch_mat_mul_v3,32,1,1,1,32,"B/M/N切出4块, 每块32核切K归约 (归约组内核c负责K段[c*K/32,(c+1)*K/32))",1,1,1,8192,256,256,1,K段标准分块流水,1,128,64,allocate(部分和驻留L2),"resident(部分和4B驻留L2, 防精度丢失不随C的fp16/fp8转换)",0,4194304,grid_K=32路切K+归约,1,1,32,0,0,0,0,True,4,"P=0.50, grid_K=32, 部分和驻留L2按4B写出, AIV归约后按C dtype=2B写最终",536936448,0.0,0.00033558528,0.0,0.00033558528,0.0,0.0,536870912.0,1.2427567407407407e-06,0.0,0.0,1.731729603729604e-06,0.00033558528,1.731729603729604e-06,0.0003373170096037296,MTE2,True,,访存Bound(GM读写共享+L2重复读),"P<=C/2, B/M/N并行度买不满, 切K (grid_K=32)" +b16_m2_n4096_k7168,16,16,2,4096,7168,bf16,bf16,bf16,False,False,False,True,0,b16_m2_n4096_k7168,StreamK,Ascend950PR,batch_mat_mul_v3,32,1,1,1,16,"B/M/N切出16块, 每块16核切K归约 (归约组内核c负责K段[c*K/16,(c+1)*K/16))",1,1,2,4096,448,256,1,K段标准分块流水,2,128,64,allocate(部分和驻留L2),"resident(部分和4B驻留L2, 防精度丢失不随C的fp16/fp8转换)",0,8388608,grid_K=16路切K+归约,1,1,16,0,0,0,0,True,4,"P=2.00, grid_K=16, 部分和驻留L2按4B写出, AIV归约后按C dtype=2B写最终",939982848,0,0.00058748928,0.0,0.00058748928,0.0,0.0,1879048192.0,4.349648592592593e-06,0.0,0.0,1.7726896037296038e-06,0.00058748928,1.7726896037296038e-06,0.0005892619696037297,MTE2,True,,访存Bound(GM读写共享+L2重复读),"P<=C/2, B/M/N并行度买不满, 切K (grid_K=16)" +b32_m64_n64_k7168,32,32,64,64,7168,bf16,bf16,bf16,False,False,False,True,0,b32_m64_n64_k7168,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),1,1,64,64,7168,1024,1,d_两侧都切K,64,64,256,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"两侧都切K: k_L1=1024, K段成对流水, batch边界天然无缝; dValueA=2048B/dValueB=128B; 输出落点: L2驻留",58720256,0.0,3.670016e-05,0.0,3.670016e-05,7,0.0,1879048192.0,4.349648592592593e-06,262144,5.041230769230769e-08,0.0,3.670016e-05,6.71790678062678e-07,3.737195067806268e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),仅 IterBatch 条件满足 +b64_m1024_n1024_k7168,64,64,1024,1024,7168,bf16,bf16,bf16,False,False,False,True,0,b64_m1024_n1024_k7168,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),2,1,1024,1024,7168,64,1,d_两侧都切K,176,176,64,allocate(GM->L1随路驻留L2),"direct_gm(整case超L2: 输入优先驻留L2, 输出直写GM不占L2)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"两侧都切K: k_L1=64, K段成对流水, batch边界天然无缝; dValueA=128B/dValueB=2048B; 输出落点: 直写GM",1879048192,0.0,0.00117440512,0.0,0.00117440512,224,0.0,962072674304.0,0.0022270200794074074,134217728,8.388608e-05,0.0,0.0022270200794074074,5.1885093925925924e-05,0.0022789051733333333,MMAD,True,,计算Bound,仅 IterBatch 条件满足 +b128_m2048_n2048_k1536,128,128,2048,2048,1536,bf16,bf16,bf16,False,False,False,True,0,b128_m2048_n2048_k1536,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,4,4,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,1536,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,64,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=4 x nCnt=4 (tile 512x512, 每batch搬入48.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=1536.0MB, V_out=1024.0MB, L2=128MB); 尾轮: r=0 无尾轮",1610612736,4831838208,0.00100663296,0.0009291996553846154,0.0019358326153846154,0.0,0.0,1649267441664.0,0.0038177487075555555,1073741824,0.00067108864,0.0,0.0038177487075555555,0.0,0.0038177487075555555,MMAD,True,,计算Bound,"IterBatch/MergeBatch 进入条件均不满足, 回落 ASW_Basic; IterBatch未过: 3_L1驻留形态(四选一, 核心要求: 单batch核内零重复读); MergeBatch未过: 2_L0C容量: 2*(b0*M)*(b0*N)*4B <= L0C; 2b_L0AB容量: 合并后 b0*M/b0*N 在最小K粒度下可驻留 L0A/L0B; 5_访存Bound: 2MN/(M+N) < R16/b0" +b64_m1024_n8192_k2048,64,64,1024,8192,2048,bf16,bf16,bf16,False,False,False,True,0,b64_m1024_n8192_k2048,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,2,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,2048,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,64,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=2 x nCnt=16 (tile 512x512, 每batch搬入128.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=2304.0MB, V_out=1024.0MB, L2=128MB); 尾轮: r=0 无尾轮",2415919104,6174015488,0.00150994944,0.0011873106707692308,0.0026972601107692305,0.0,0.0,2199023255552.0,0.005090331610074074,1073741824,0.00067108864,0.0,0.005090331610074074,0.0,0.005090331610074074,MMAD,True,,计算Bound,"IterBatch/MergeBatch 进入条件均不满足, 回落 ASW_Basic; IterBatch未过: 3_L1驻留形态(四选一, 核心要求: 单batch核内零重复读); MergeBatch未过: 1_batch关系与每核份额: BatchA==BatchB 且 b_core=B/C>=2*b0; 2_L0C容量: 2*(b0*M)*(b0*N)*4B <= L0C; 2b_L0AB容量: 合并后 b0*M/b0*N 在最小K粒度下可驻留 L0A/L0B; 5_访存Bound: 2MN/(M+N) < R16/b0" +b32_m1024_n1024_k512,32,32,1024,1024,512,bf16,bf16,bf16,False,False,False,True,0,b32_m1024_n1024_k512,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转分配(核间零重复读零依赖),1,1,1024,1024,512,64,1,d_两侧都切K,176,176,64,allocate(GM->L1随路驻留L2),"resident(整case输入+输出<=L2: 输出驻留L2异步回写, GM写=0)",0,0,不涉及(核内不切M/N),1,1,1,0,0,0,0,True,2,"两侧都切K: k_L1=64, K段成对流水, batch边界天然无缝; dValueA=128B/dValueB=2048B; 输出落点: L2驻留",67108864,0.0,4.194304e-05,0.0,4.194304e-05,8,0.0,34359738368.0,7.95364314074074e-05,67108864,1.290555076923077e-05,0.0,7.95364314074074e-05,2.2847604695156693e-05,0.0001023840361025641,MMAD,True,,计算Bound,仅 IterBatch 条件满足 +b128_m4096_n4096_k8192,128,128,4096,4096,8192,bf16,bf16,bf16,False,False,False,True,0,b128_m4096_n4096_k8192,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,8,8,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,8192,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,256,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=8 x nCnt=8 (tile 512x512, 每batch搬入1024.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=16384.0MB, V_out=4096.0MB, L2=128MB); 尾轮: r=0 无尾轮",17179869184,120259084288,0.01073741824,0.023126746978461538,0.033864165218461535,0.0,0.0,35184372088832.0,0.08144530576118518,4294967296,0.00268435456,0.0,0.08144530576118518,0.0,0.08144530576118518,MMAD,True,,计算Bound,"IterBatch/MergeBatch 进入条件均不满足, 回落 ASW_Basic; IterBatch未过: 3_L1驻留形态(四选一, 核心要求: 单batch核内零重复读); MergeBatch未过: 2_L0C容量: 2*(b0*M)*(b0*N)*4B <= L0C; 2b_L0AB容量: 合并后 b0*M/b0*N 在最小K粒度下可驻留 L0A/L0B; 5_访存Bound: 2MN/(M+N) < R16/b0" +b32_m8192_n4096_k7168,32,32,8192,4096,7168,bf16,bf16,bf16,False,False,False,True,0,b32_m8192_n4096_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,16,8,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,7168,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,128,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=16 x nCnt=8 (tile 512x512, 每batch搬入1792.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=5376.0MB, V_out=2048.0MB, L2=128MB); 尾轮: r=0 无尾轮",5637144576,54492397568,0.00352321536,0.010479307224615384,0.014002522584615384,0.0,0.0,15393162788864.0,0.03563232127051852,2147483648,0.00134217728,0.0,0.03563232127051852,0.0,0.03563232127051852,MMAD,True,,计算Bound,"IterBatch/MergeBatch 进入条件均不满足, 回落 ASW_Basic; IterBatch未过: 3_L1驻留形态(四选一, 核心要求: 单batch核内零重复读); MergeBatch未过: 1_batch关系与每核份额: BatchA==BatchB 且 b_core=B/C>=2*b0; 2_L0C容量: 2*(b0*M)*(b0*N)*4B <= L0C; 2b_L0AB容量: 合并后 b0*M/b0*N 在最小K粒度下可驻留 L0A/L0B; 5_访存Bound: 2MN/(M+N) < R16/b0" +b32_m2048_n2048_k8192,32,32,2048,2048,8192,bf16,bf16,bf16,False,False,False,True,0,b32_m2048_n2048_k8192,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,4,4,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,8192,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,16,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=4 x nCnt=4 (tile 512x512, 每batch搬入256.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=2048.0MB, V_out=256.0MB, L2=128MB); 尾轮: r=0 无尾轮",2147483648,6442450944,0.00134217728,0.0012389328738461537,0.002581110153846154,0.0,0.0,2199023255552.0,0.005090331610074074,268435456,0.00016777216,0.0,0.005090331610074074,0.0,0.005090331610074074,MMAD,True,,计算Bound,"IterBatch/MergeBatch 进入条件均不满足, 回落 ASW_Basic; IterBatch未过: 3_L1驻留形态(四选一, 核心要求: 单batch核内零重复读); MergeBatch未过: 1_batch关系与每核份额: BatchA==BatchB 且 b_core=B/C>=2*b0; 2_L0C容量: 2*(b0*M)*(b0*N)*4B <= L0C; 2b_L0AB容量: 合并后 b0*M/b0*N 在最小K粒度下可驻留 L0A/L0B; 5_访存Bound: 2MN/(M+N) < R16/b0" +b64_m4096_n2048_k128,64,64,4096,2048,128,bf16,bf16,bf16,False,False,False,True,0,b64_m4096_n2048_k128,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,8,4,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,128,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,64,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=8 x nCnt=4 (tile 512x512, 每batch搬入8.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=96.0MB, V_out=1024.0MB, L2=128MB); 尾轮: r=0 无尾轮",100663296,436207616,6.291456e-05,8.388608e-05,0.00014680063999999998,0.0,0.0,137438953472.0,0.0003181457256296296,1073741824,0.00067108864,0.0,0.00081788928,0.0,0.00081788928,MTE2,True,,访存Bound(GM读写共享+L2重复读),"IterBatch/MergeBatch 进入条件均不满足, 回落 ASW_Basic; IterBatch未过: 3_L1驻留形态(四选一, 核心要求: 单batch核内零重复读); MergeBatch未过: 1_batch关系与每核份额: BatchA==BatchB 且 b_core=B/C>=2*b0; 2_L0C容量: 2*(b0*M)*(b0*N)*4B <= L0C; 2b_L0AB容量: 合并后 b0*M/b0*N 在最小K粒度下可驻留 L0A/L0B; 5_访存Bound: 2MN/(M+N) < R16/b0" +b16_m1024_n1024_k8192,16,16,1024,1024,8192,bf16,bf16,bf16,False,False,False,True,0,b16_m1024_n1024_k8192,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,2,2,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,8192,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,2,True,2,"tile枚举: P=2, 有界枚举最优 mCnt=2 x nCnt=2 (tile 512x512, 每batch搬入64.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=512.0MB, V_out=32.0MB, L2=128MB); 尾轮: r=0 无尾轮",536870912,536870912,0.00033554432,0.00010324440615384615,0.0004387887261538461,0.0,0.0,274877906944.0,0.0006362914512592592,33554432,2.097152e-05,0.0,0.0006362914512592592,0.0,0.0006362914512592592,MMAD,True,,计算Bound,ASW_Basic兜底 (StreamK未过: 1_并行缺口: P=B*MN*4B/L0C <= C/2; 2_单核K段下限: K/grid_K >= 256B/dtype 且 grid_K>=2; 3_归约代价可接受) +b4_m32768_n128_k128,4,4,32768,128,128,bf16,bf16,bf16,False,False,False,True,0,b4_m32768_n128_k128,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,64,1,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,128,128,128,1,双缓冲驻留当前tile输入,512,128,32,allocate(输入驻留L2吸收重复读),"resident(整case全驻留S_A: 输出驻留L2异步回写, GM写=0)",4,0,A0,1,1,1,0,0,0,8,True,2,"tile枚举: P=8, 有界枚举最优 mCnt=64 x nCnt=1 (tile 512x128, 每batch搬入10.0MB, r=0); Base tile 512x128 (L0C 单缓冲方形用满); L2场景: A_整case全驻留(输入+输出<=L2) (V_in=32.1MB, V_out=32.0MB, L2=128MB); 尾轮: r=0 无尾轮",33685504,8257536,2.105344e-05,1.5879876923076922e-06,2.2641427692307692e-05,0.0,0.0,4294967296.0,9.942053925925925e-06,33554432,6.452775384615385e-06,0.0,2.2641427692307692e-05,0.0,2.2641427692307692e-05,MTE2,True,,访存Bound(GM读写共享+L2重复读),ASW_Basic兜底 (StreamK未过: 1_并行缺口: P=B*MN*4B/L0C <= C/2; 2_单核K段下限: K/grid_K >= 256B/dtype 且 grid_K>=2; 3_归约代价可接受) +b8_m32768_n2048_k512,8,8,32768,2048,512,bf16,bf16,bf16,False,False,False,True,0,b8_m32768_n2048_k512,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,64,4,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,512,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,64,True,2,"tile枚举: P=4, 有界枚举最优 mCnt=64 x nCnt=4 (tile 512x512, 每batch搬入256.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=272.0MB, V_out=1024.0MB, L2=128MB); 尾轮: r=0 无尾轮",285212672,1862270976,0.00017825792,0.00035812903384615385,0.0005363869538461539,0.0,0.0,549755813888.0,0.0012725829025185184,1073741824,0.00067108864,0.0,0.0012725829025185184,0.0,0.0012725829025185184,MMAD,True,,计算Bound,ASW_Basic兜底 (StreamK未过: 1_并行缺口: P=B*MN*4B/L0C <= C/2; 2_单核K段下限: K/grid_K >= 256B/dtype 且 grid_K>=2; 3_归约代价可接受) +b4_m131072_n128_k128,4,4,131072,128,128,bf16,bf16,bf16,False,False,False,True,0,b4_m131072_n128_k128,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,256,1,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,128,128,128,1,双缓冲驻留当前tile输入,512,128,32,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,32,True,2,"tile枚举: P=8, 有界枚举最优 mCnt=256 x nCnt=1 (tile 512x128, 每batch搬入40.0MB, r=0); Base tile 512x128 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=128.1MB, V_out=128.0MB, L2=128MB); 尾轮: r=0 无尾轮",134348800,33423360,8.3968e-05,6.427569230769231e-06,9.039556923076924e-05,0.0,0.0,17179869184.0,3.97682157037037e-05,134217728,8.388608e-05,0.0,0.00017428164923076922,0.0,0.00017428164923076922,MTE2,True,,访存Bound(GM读写共享+L2重复读),ASW_Basic兜底 (StreamK未过: 1_并行缺口: P=B*MN*4B/L0C <= C/2; 2_单核K段下限: K/grid_K >= 256B/dtype 且 grid_K>=2; 3_归约代价可接受) +b8_m131072_n1024_k256,8,8,131072,1024,256,bf16,bf16,bf16,False,False,False,True,0,b8_m131072_n1024_k256,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,256,2,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,256,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,128,True,2,"tile枚举: P=4, 有界枚举最优 mCnt=256 x nCnt=2 (tile 512x512, 每batch搬入256.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=516.0MB, V_out=2048.0MB, L2=128MB); 尾轮: r=0 无尾轮",541065216,1606418432,0.00033816576,0.00030892662153846154,0.0006470923815384616,0.0,0.0,549755813888.0,0.0012725829025185184,2147483648,0.00134217728,0.0,0.0019892696615384617,0.0,0.0019892696615384617,MTE2,True,,访存Bound(GM读写共享+L2重复读),ASW_Basic兜底 (StreamK未过: 1_并行缺口: P=B*MN*4B/L0C <= C/2; 2_单核K段下限: K/grid_K >= 256B/dtype 且 grid_K>=2; 3_归约代价可接受) +b16_m32768_n8192_k7168,16,16,32768,8192,7168,bf16,bf16,bf16,False,False,False,True,0,b16_m32768_n8192_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,64,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,7168,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,512,True,2,"tile枚举: P=2, 有界枚举最优 mCnt=64 x nCnt=16 (tile 512x512, 每batch搬入14336.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=8960.0MB, V_out=8192.0MB, L2=128MB); 尾轮: r=0 无尾轮",9395240960,231122927616,0.0058720256,0.044446716849230766,0.05031874244923076,0.0,0.0,61572651155456.0,0.14252928508207408,8589934592,0.00536870912,0.0,0.14252928508207408,0.0,0.14252928508207408,MMAD,True,,计算Bound,ASW_Basic兜底 (StreamK未过: 1_并行缺口: P=B*MN*4B/L0C <= C/2; 2_单核K段下限: K/grid_K >= 256B/dtype 且 grid_K>=2; 3_归约代价可接受) +b4_m32768_n128_k8192,4,4,32768,128,8192,bf16,bf16,bf16,False,False,False,True,0,b4_m32768_n128_k8192,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,64,1,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,128,8192,192,1,双缓冲驻留当前tile输入,512,128,32,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,8,True,2,"tile枚举: P=8, 有界枚举最优 mCnt=64 x nCnt=1 (tile 512x128, 每batch搬入640.0MB, r=0); Base tile 512x128 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=2056.0MB, V_out=32.0MB, L2=128MB); 尾轮: r=0 无尾轮",2155872256,528482304,0.00134742016,0.0001016312123076923,0.0014490513723076923,0.0,0.0,274877906944.0,0.0006362914512592592,33554432,2.097152e-05,0.0,0.0014700228923076922,0.0,0.0014700228923076922,MTE2,True,,访存Bound(GM读写共享+L2重复读),ASW_Basic兜底 (StreamK未过: 1_并行缺口: P=B*MN*4B/L0C <= C/2; 2_单核K段下限: K/grid_K >= 256B/dtype 且 grid_K>=2; 3_归约代价可接受) +b32_m131072_n8192_k128,32,32,131072,8192,128,bf16,bf16,bf16,False,False,False,True,0,b32_m131072_n8192_k128,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,256,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,128,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,4096,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=256 x nCnt=16 (tile 512x512, 每batch搬入1024.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=1088.0MB, V_out=65536.0MB, L2=128MB); 尾轮: r=0 无尾轮",1140850688,33218887680,0.00071303168,0.006388247630769231,0.007101279310769231,0.0,0.0,8796093022208.0,0.020361326440296295,68719476736,0.04294967296,0.0,0.05005095227076922,0.0,0.05005095227076922,MTE2,True,,访存Bound(GM读写共享+L2重复读),"IterBatch/MergeBatch 进入条件均不满足, 回落 ASW_Basic; IterBatch未过: 3_L1驻留形态(四选一, 核心要求: 单batch核内零重复读); MergeBatch未过: 1_batch关系与每核份额: BatchA==BatchB 且 b_core=B/C>=2*b0; 2_L0C容量: 2*(b0*M)*(b0*N)*4B <= L0C; 2b_L0AB容量: 合并后 b0*M/b0*N 在最小K粒度下可驻留 L0A/L0B; 5_访存Bound: 2MN/(M+N) < R16/b0" +b64_m32768_n8192_k1536,64,64,32768,8192,1536,bf16,bf16,bf16,False,False,False,True,0,b64_m32768_n8192_k1536,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,64,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,1536,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,2048,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=64 x nCnt=16 (tile 512x512, 每batch搬入3072.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=7680.0MB, V_out=32768.0MB, L2=128MB); 尾轮: r=0 无尾轮",8053063680,198105366528,0.0050331648,0.03809718587076923,0.04313035067076923,0.0,0.0,52776558133248.0,0.12216795864177778,34359738368,0.02147483648,0.0,0.12216795864177778,0.0,0.12216795864177778,MMAD,True,,计算Bound,"IterBatch/MergeBatch 进入条件均不满足, 回落 ASW_Basic; IterBatch未过: 3_L1驻留形态(四选一, 核心要求: 单batch核内零重复读); MergeBatch未过: 1_batch关系与每核份额: BatchA==BatchB 且 b_core=B/C>=2*b0; 2_L0C容量: 2*(b0*M)*(b0*N)*4B <= L0C; 2b_L0AB容量: 合并后 b0*M/b0*N 在最小K粒度下可驻留 L0A/L0B; 5_访存Bound: 2MN/(M+N) < R16/b0" +b8_m131072_n8192_k8192,8,8,131072,8192,8192,bf16,bf16,bf16,False,False,False,True,0,b8_m131072_n8192_k8192,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,256,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,8192,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,1024,True,2,"tile枚举: P=4, 有界枚举最优 mCnt=256 x nCnt=16 (tile 512x512, 每batch搬入65536.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: C_双侧超L2: 最小替换2D分组(组间落空GM, 窗口L2) (V_in=17408.0MB, V_out=16384.0MB, L2=128MB); 最小替换分组 m_grp=8x n_grp=8 (GM倍率3.76, 窗口L2/batch=57344.0MB); 尾轮: r=0 无尾轮",68719476736,481036337152,0.04294967296,0.09250698791384615,0.13545666087384614,0.0,0.0,140737488355328.0,0.3257812230447407,17179869184,0.01073741824,0.0,0.3257812230447407,0.0,0.3257812230447407,MMAD,True,,计算Bound,ASW_Basic兜底 (StreamK未过: 1_并行缺口: P=B*MN*4B/L0C <= C/2; 2_单核K段下限: K/grid_K >= 256B/dtype 且 grid_K>=2; 3_归约代价可接受) +b8_m16_n7168_k1536,8,8,16,7168,1536,bf16,bf16,bf16,False,False,False,True,0,b8_m16_n7168_k1536,StreamK,Ascend950PR,batch_mat_mul_v3,32,1,1,2,2,"B/M/N切出16块, 每块2核切K归约 (归约组内核c负责K段[c*K/2,(c+1)*K/2))",1,1,16,3584,768,256,1,K段标准分块流水,16,128,64,allocate(部分和驻留L2),"resident(部分和4B驻留L2, 防精度丢失不随C的fp16/fp8转换)",0,3670016,grid_K=2路切K+归约,1,1,2,0,0,0,0,True,4,"P=14.00, grid_K=2, 部分和驻留L2按4B写出, AIV归约后按C dtype=2B写最终",176553984,393216,0.00011034624,7.561846153846153e-08,0.00011042185846153846,0.0,0.0,2818572288.0,6.524472888888889e-06,0.0,0.0,2.566079254079254e-07,0.00011042185846153846,2.566079254079254e-07,0.00011067846638694638,MTE2,True,,访存Bound(GM读写共享+L2重复读),"P<=C/2, B/M/N并行度买不满, 切K (grid_K=2)" +b64_m1024_n7168_k7168,64,64,1024,7168,7168,bf16,bf16,bf16,False,False,False,True,0,b64_m1024_n7168_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,2,14,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,7168,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,56,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=2 x nCnt=14 (tile 512x512, 每batch搬入392.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=7168.0MB, V_out=896.0MB, L2=128MB); 尾轮: r=0 无尾轮",7516192768,18790481920,0.00469762048,0.0036135542153846152,0.008311174695384616,0.0,0.0,6734508720128.0,0.015589140555851852,939524096,0.00058720256,0.0,0.015589140555851852,0.0,0.015589140555851852,MMAD,True,,计算Bound,"IterBatch/MergeBatch 进入条件均不满足, 回落 ASW_Basic; IterBatch未过: 3_L1驻留形态(四选一, 核心要求: 单batch核内零重复读); MergeBatch未过: 1_batch关系与每核份额: BatchA==BatchB 且 b_core=B/C>=2*b0; 2_L0C容量: 2*(b0*M)*(b0*N)*4B <= L0C; 2b_L0AB容量: 合并后 b0*M/b0*N 在最小K粒度下可驻留 L0A/L0B; 5_访存Bound: 2MN/(M+N) < R16/b0" +b32_m8192_n8192_k7168,32,32,8192,8192,7168,bf16,bf16,bf16,False,False,False,True,0,b32_m8192_n8192_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,16,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,7168,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,256,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=16 x nCnt=16 (tile 512x512, 每batch搬入3584.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=7168.0MB, V_out=4096.0MB, L2=128MB); 尾轮: r=0 无尾轮",7516192768,112742891520,0.00469762048,0.021681325292307693,0.026378945772307694,0.0,0.0,30786325577728.0,0.07126464254103704,4294967296,0.00268435456,0.0,0.07126464254103704,0.0,0.07126464254103704,MMAD,True,,计算Bound,"IterBatch/MergeBatch 进入条件均不满足, 回落 ASW_Basic; IterBatch未过: 3_L1驻留形态(四选一, 核心要求: 单batch核内零重复读); MergeBatch未过: 1_batch关系与每核份额: BatchA==BatchB 且 b_core=B/C>=2*b0; 2_L0C容量: 2*(b0*M)*(b0*N)*4B <= L0C; 2b_L0AB容量: 合并后 b0*M/b0*N 在最小K粒度下可驻留 L0A/L0B; 5_访存Bound: 2MN/(M+N) < R16/b0" +b8_m4096_n4096_k128,8,8,4096,4096,128,bf16,bf16,bf16,False,False,False,True,0,b8_m4096_n4096_k128,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,8,8,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,128,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,16,True,2,"tile枚举: P=4, 有界枚举最优 mCnt=8 x nCnt=8 (tile 512x512, 每batch搬入16.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=16.0MB, V_out=256.0MB, L2=128MB); 尾轮: r=0 无尾轮",16777216,117440512,1.048576e-05,2.2584713846153845e-05,3.307047384615384e-05,0.0,0.0,34359738368.0,7.95364314074074e-05,268435456,0.00016777216,0.0,0.00020084263384615383,0.0,0.00020084263384615383,MTE2,True,,访存Bound(GM读写共享+L2重复读),ASW_Basic兜底 (StreamK未过: 1_并行缺口: P=B*MN*4B/L0C <= C/2; 2_单核K段下限: K/grid_K >= 256B/dtype 且 grid_K>=2; 3_归约代价可接受) +b128_m8192_n8192_k7168,128,128,8192,8192,7168,bf16,bf16,bf16,False,False,False,True,0,b128_m8192_n8192_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,16,16,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,512,512,7168,128,1,双缓冲驻留当前tile输入,256,256,64,allocate(输入驻留L2吸收重复读),"direct_gm(输出直写GM, 输入优先驻留L2)",4,0,A0,1,1,1,0,0,0,1024,True,2,"tile枚举: P=1, 有界枚举最优 mCnt=16 x nCnt=16 (tile 512x512, 每batch搬入3584.0MB, r=0); Base tile 256x256 (L0C 单缓冲方形用满); L2场景: B_单batch可驻留(全驻留或单侧驻留+对侧滑窗) (V_in=28672.0MB, V_out=16384.0MB, L2=128MB); 尾轮: r=0 无尾轮",30064771072,450971566080,0.01879048192,0.08672530116923077,0.10551578308923078,0.0,0.0,123145302310912.0,0.28505857016414815,17179869184,0.01073741824,0.0,0.28505857016414815,0.0,0.28505857016414815,MMAD,True,,计算Bound,"IterBatch/MergeBatch 进入条件均不满足, 回落 ASW_Basic; IterBatch未过: 3_L1驻留形态(四选一, 核心要求: 单batch核内零重复读); MergeBatch未过: 2_L0C容量: 2*(b0*M)*(b0*N)*4B <= L0C; 2b_L0AB容量: 合并后 b0*M/b0*N 在最小K粒度下可驻留 L0A/L0B; 5_访存Bound: 2MN/(M+N) < R16/b0" special_k1_b64,64,64,8192,512,1,bf16,bf16,bf16,False,False,False,True,0,special_k1_b64,特殊分支,Ascend950PR,batch_mat_mul_v3,64,1,1,1,1,AIV 核间按行均分 (无 Cube tile 概念),0,1,0,0,1,0,1,UB驻留(AIV) AIV单缓冲,0,0,0,allocate,direct_gm,0,0,不涉及(AIV逐元素),1,1,1,0,0,0,0,False,2,"K=1逐元素乘: 退化为 C=A⊙B 无累加深度, Cube 16x16x16 粒度浪费 15/16; 走 AIV 通路 GM->UB->Mul->GM, AIV单缓冲 (B<2*AIV 逐batch单缓冲串行)",1114112,0.0,6.9632e-07,0.0,6.9632e-07,0.0,0.0,268435456.0,9.92969696969697e-06,536870912,0.00033554432,0.0,0.00033624063999999996,0.0,0.00033624063999999996,MTE2,True,,访存Bound(GM读写共享+L2重复读),"K=1逐元素乘, 走AIV向量通路" diff --git a/BMM/BMM_Theory/tests/test_branches.py b/BMM/BMM_Theory/tests/test_branches.py index 97fbd4f..f36c2d8 100644 --- a/BMM/BMM_Theory/tests/test_branches.py +++ b/BMM/BMM_Theory/tests/test_branches.py @@ -1040,7 +1040,9 @@ class TestIssue38(unittest.TestCase): self.assertEqual(s.bw_gm, 1.6e12) self.assertEqual(s.bw_l2, 5.2e12) # PR 保持 5.2TB/s self.assertEqual(s.l2_bytes, 128 * 1024 * 1024) - self.assertAlmostEqual(s.q16, 486e12 / 32) + self.assertAlmostEqual(s.q16, 432e12 / 32) # 13.5T (issue#40 Cube-only) + self.assertEqual(s.cube_peak_tflops, 432.0) + self.assertAlmostEqual(s.r16, 540.0) # 432e12/(1.6e12/2) self.assertEqual(s.gm_capacity_gb, 128.0) self.assertIs(get_spec(), ASCEND950PR) # 默认 = 950PR 主bin self.assertIs(get_spec("Ascend950PR"), ASCEND950PR) @@ -1052,9 +1054,9 @@ class TestIssue38(unittest.TestCase): "Ascend950DT", "Ascend950DT_C28", "Ascend950DT_C32", "Ascend950PR", "Ascend950PR_C28"]) for s in SPECS.values(): - # 共架构: 单核 Cube 口径全系列一致 (白皮书总算力行取整, 28核档 - # 425/28=15.179T 与 15.1875T 差 0.06%, 容差 0.1%); AIV 恒为 AIC 两倍 - self.assertLess(abs(s.q16 / (486e12 / 32) - 1), 1e-3) + # 共架构 + Cube-only 口径 (issue#40): 单核 Cube 全系列精确 13.5T + # (432/32=378/28=486/36); AIV 恒为 AIC 两倍 + self.assertAlmostEqual(s.q16, 13.5e12, places=6) self.assertEqual(s.aiv_num, 2 * s.aic_num) self.assertEqual(s.l1_bytes, 512 * 1024) # 表4-2 各档一致 self.assertEqual(s.l0c_bytes, 256 * 1024) @@ -1066,20 +1068,20 @@ class TestIssue38(unittest.TestCase): self.assertEqual(ASCEND950DT.bw_gm, 4.0e12) # 4TB/s HBM self.assertEqual(ASCEND950DT.l2_bytes, 128 * 1024 * 1024) self.assertEqual(ASCEND950DT.gm_capacity_gb, 144.0) - self.assertEqual(ASCEND950DT.cube_peak_tflops, 547.0) + self.assertEqual(ASCEND950DT.cube_peak_tflops, 486.0) # Cube-only (issue#40) # L2 带宽: DT 三档 7.5TB/s 读写各自独享 (issue#39 用户澄清) for dt_spec in (ASCEND950DT, ASCEND950DT_C32, ASCEND950DT_C28): self.assertEqual(dt_spec.bw_l2, 7.5e12) self.assertAlmostEqual(ASCEND950DT.bw_l2_pc, 7.5e12 / 36) self.assertEqual((ASCEND950DT_C32.aic_num, - ASCEND950DT_C32.cube_peak_tflops), (32, 486.0)) + ASCEND950DT_C32.cube_peak_tflops), (32, 432.0)) self.assertEqual((ASCEND950DT_C28.aic_num, - ASCEND950DT_C28.cube_peak_tflops), (28, 425.0)) + ASCEND950DT_C28.cube_peak_tflops), (28, 378.0)) self.assertEqual(ASCEND950DT_C28.gm_capacity_gb, 96.0) # 派生量: 单核 GM 份额 4TB/36; r16 平衡点随带宽升至 4TB/s 而减半 self.assertAlmostEqual(ASCEND950DT.bw_pc, 4.0e12 / 36) - self.assertAlmostEqual(ASCEND950DT.r16, 547e12 / (4.0e12 / 2)) - self.assertAlmostEqual(ASCEND950DT_C32.r16, 486e12 / (4.0e12 / 2)) + self.assertAlmostEqual(ASCEND950DT.r16, 486e12 / (4.0e12 / 2)) # 243 + self.assertAlmostEqual(ASCEND950DT_C32.r16, 432e12 / (4.0e12 / 2)) # 216 # AIV 白皮书交叉验证: fp32 通量 72 核 x 128 lane x 1.65GHz x 2 ≈ 30T self.assertAlmostEqual(ASCEND950DT.aiv_elem_rate_fp32 * 2 / 1e12, 30.0, places=0)