Commit Graph

502 Commits

Author SHA1 Message Date
b9e07edc1d Fix #27-#30: dtype感知算力(Cube/AIV速率表) / GM首读下限与整芯片字节列口径+设计文档 / Fixpipe输出落点R4(整case驻留L2否则直写GM) / MergeBatch Cube公式复核注释
- docs/05_L2驻留GM读写与dtype算力口径_设计分析.md: R1-R6公理、S_A/S_B/S_C场景、输出落点R4、dtype速率表(白皮书出处+待标定假设)、逐分支GM/L2归属表 (issue#29/#30 先文档后代码)
- hardware: CUBE_DTYPE_FACTOR(f16/bf16=1, fp8=2x, fp4=4x, fp32=1/2假设) + AIV_DTYPE_FACTOR + q_cube/aiv_elem_rate (issue#28)
- 全分支 t_mmad/t_comp/drain/尾轮主导项/θ_c/R16 语义按输入dtype取算力; 混精度取慢侧; StreamK归约保持fp32(AIV fp32部分和)
- Fixpipe输出落点R4: to_l2 <=> V_in+V_out(+workspace)<=L2; 否则直写GM计入共享总线; ASW场景改S_A整case全驻留(原单batch驻留判定漏计整case输出累积逐出)
- 字节列统一整芯片口径(gm/l2/fix/cube_flops), dma_cmd_count注明单核; GM>=V_in不变量入测试; MergeBatch每步flops=2(b0M)(b0N)K公式注释显式化(#27复核与CSV一致无数值改动)
- tests 39->49 全过; 双压力seed7/6000+seed2024/4000: 0违规/0占位/0NaN/0GM<输入; examples三件套重生成且可复现0diff
2026-09-04 16:26:10 +08:00
4843053ad3 Fix issues #23-#25 (+#26 标注): GM读写共享总线累加计时 / ASW-切M/N 共享块 GM首读1次+L2重复读(n-1)次、场景按单batch判定、分组预算不再除B / StreamK 按plan实际tile芯片口径评估 / 降核线性带宽假设文档标注 2026-09-04 11:43:23 +08:00
f4b23d9f05 Expand cases_demo to 44 cases (B 4..128 x M 1..131072 x N/K 128..8192 incl 7168) + regenerate examples outputs 2026-09-04 11:09:49 +08:00
5051e00fa0 T_cmd=0 仲裁改为策略优先 MergeBatch: K截断即优先(指令/命令次数省b0倍,未量化收益), L1绑定恒劣; 路由层以策略覆盖时延模型差额并显式标注 2026-09-04 10:47:02 +08:00
a071d87831 Fix T_cmd=0 robustness: beats_iterbatch 阈值除零防护 (T_cmd<=0 判 MergeBatch 不胜出, 无命令节省) + 3 条回归测试 2026-09-04 10:31:53 +08:00
9afe6eec02 Fix review issues #17-#22: 恢复 #11/#12/#14 (StreamK fixpipe 单次计账/K=1 AIV单缓冲/advice) + 占位方案不可评估 + 转置 dValue 判据三处同源(form c 双缓冲适配修复) + 恢复 #13/#15 回归测试 + 清理临时 csv/.gitignore + 文档同步 2026-09-03 21:10:05 +08:00
f5a0b6fe81 Update BMM_Theory: tests/test_branches.py 2026-09-03 12:44:22 +00:00
08bf74d8b8 Update BMM_Theory: examples/result_recommend.csv 2026-09-03 12:44:20 +00:00
2d9d9f3116 Update BMM_Theory: examples/result_evaluate.csv 2026-09-03 12:44:18 +00:00
c9edf8d6b0 Update BMM_Theory: examples/plans.csv 2026-09-03 12:44:16 +00:00
e0ee3d1c94 Update BMM_Theory: examples/cases_demo.csv 2026-09-03 12:44:15 +00:00
3ff9f7d205 Update BMM_Theory: docs/02_分支理论/07_尾轮处理策略.md 2026-09-03 12:44:14 +00:00
588e8928c0 Update BMM_Theory: docs/02_分支理论/06_ASW_Basic分支.md 2026-09-03 12:44:13 +00:00
a51571b20d Update BMM_Theory: docs/02_分支理论/05_StreamK分支.md 2026-09-03 12:44:11 +00:00
6d5e452fbc Update BMM_Theory: docs/02_分支理论/04_特殊分支.md 2026-09-03 12:44:10 +00:00
5888333298 Update BMM_Theory: docs/02_分支理论/03_转Matmul分支.md 2026-09-03 12:44:09 +00:00
7ebe391b8f Update BMM_Theory: docs/02_分支理论/02_IterBatch分支.md 2026-09-03 12:44:08 +00:00
59a7f8df44 Update BMM_Theory: docs/02_分支理论/01_MergeBatch分支.md 2026-09-03 12:44:06 +00:00
9c96fab9f6 Update BMM_Theory: docs/02_分支理论/00_总纲_分支决策树.md 2026-09-03 12:44:05 +00:00
1d1a9187c9 Update BMM_Theory: docs/04_差异对照_bmmv3_vs_BMM_Theory.md 2026-09-03 12:44:04 +00:00
759a51e92a Update BMM_Theory: docs/01_软件架构.md 2026-09-03 12:44:01 +00:00
1e8f9102d0 Update BMM_Theory: bmm_theory/hardware/ascend950pr.py 2026-09-03 12:43:59 +00:00
6a33c3b1f9 Update BMM_Theory: bmm_theory/hardware/__init__.py 2026-09-03 12:43:58 +00:00
657cc6639f Update BMM_Theory: bmm_theory/branches/to_matmul.py 2026-09-03 12:43:56 +00:00
c05cbeafad Update BMM_Theory: bmm_theory/branches/stream_k.py 2026-09-03 12:43:55 +00:00
49397260f6 Update BMM_Theory: bmm_theory/branches/special.py 2026-09-03 12:43:54 +00:00
4f90f76db9 Update BMM_Theory: bmm_theory/branches/merge_batch.py 2026-09-03 12:43:53 +00:00
af0a90bc25 Update BMM_Theory: bmm_theory/branches/iter_batch.py 2026-09-03 12:43:52 +00:00
517441de6e Update BMM_Theory: bmm_theory/branches/base.py 2026-09-03 12:43:50 +00:00
27e0fd85ba Update BMM_Theory: bmm_theory/branches/asw_basic.py 2026-09-03 12:43:49 +00:00
2881fdca38 Update BMM_Theory: bmm_theory/branches/__init__.py 2026-09-03 12:43:47 +00:00
9cb1eb91c3 Update BMM_Theory: bmm_theory/timing.py 2026-09-03 12:43:46 +00:00
c14310d9cb Update BMM_Theory: bmm_theory/router.py 2026-09-03 12:43:44 +00:00
d27278bbb6 Update BMM_Theory: bmm_theory/models.py 2026-09-03 12:43:42 +00:00
e7db521122 Update BMM_Theory: bmm_theory/io_csv.py 2026-09-03 12:43:40 +00:00
a7356fec99 Update BMM_Theory: bmm_theory/evaluator.py 2026-09-03 12:43:38 +00:00
4d5c95c3e2 Update BMM_Theory: bmm_theory/constraints.py 2026-09-03 12:43:37 +00:00
eb16b71387 Update BMM_Theory: bmm_theory/__main__.py 2026-09-03 12:43:34 +00:00
ff0bac9b45 Update BMM_Theory: bmm_theory/__init__.py 2026-09-03 12:43:33 +00:00
db8399b62c Update models.py: fp4 support 2026-09-03 12:42:35 +00:00
c2028a41ed Add BMM_Theory: t_p.csv 2026-09-03 12:37:18 +00:00
f3d6bc7003 Add BMM_Theory: t_out.csv 2026-09-03 12:37:16 +00:00
ebf77d9b48 Add BMM_Theory: t.csv 2026-09-03 12:37:14 +00:00
98223e0e12 Add BMM_Theory: p2.csv 2026-09-03 12:37:12 +00:00
32febc1f62 Add BMM_Theory: bug_test.csv 2026-09-03 12:37:11 +00:00
ed084a4be0 Add BMM_Theory: bug2.csv 2026-09-03 12:37:10 +00:00
340ae2c0d4 Add BMM_Theory: bug1_p.csv 2026-09-03 12:37:09 +00:00
b4003d8246 Add BMM_Theory: bug1_out.csv 2026-09-03 12:37:08 +00:00
7309215720 Add BMM_Theory: bug1.csv 2026-09-03 12:37:06 +00:00
d8457be420 Remove mistakenly pushed temp file: t_p.csv 2026-09-03 12:36:42 +00:00