|
|
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 |
|
|
|
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 |
|
|
|
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 |
|
|
|
4bedf0a109
|
Fix review issues #11-#16: StreamK fixpipe 单次计账 / K=1 AIV单缓冲方案 / MergeBatch b0 L0A/L0B 上限+路由可行回退 / advice-StreamK / 输入校验 / .gitignore+死代码清理
|
2026-09-03 20:05:14 +08:00 |
|
|
|
f756729e43
|
Update BMM_Theory: bmm_theory/branches/stream_k.py (fix review issues #4-#10)
|
2026-09-03 11:34:27 +00:00 |
|
|
|
1385d01816
|
Update BMM_Theory: bmm_theory/branches/merge_batch.py (fix review issues #4-#10)
|
2026-09-03 11:34:26 +00:00 |
|
|
|
c0b358fa94
|
Update BMM_Theory: bmm_theory/branches/iter_batch.py (fix review issues #4-#10)
|
2026-09-03 11:34:25 +00:00 |
|
|
|
e6aa792cc2
|
Update BMM_Theory: bmm_theory/branches/asw_basic.py (fix review issues #4-#10)
|
2026-09-03 11:34:23 +00:00 |
|
|
|
149de60c3d
|
Add BMM_Theory: bmm_theory/branches/to_matmul.py
|
2026-09-03 09:25:44 +00:00 |
|
|
|
ee2ea4d33c
|
Add BMM_Theory: bmm_theory/branches/stream_k.py
|
2026-09-03 09:25:43 +00:00 |
|
|
|
e7da2e0a0b
|
Add BMM_Theory: bmm_theory/branches/special.py
|
2026-09-03 09:25:42 +00:00 |
|
|
|
6a24b5d945
|
Add BMM_Theory: bmm_theory/branches/asw_basic.py
|
2026-09-03 09:25:40 +00:00 |
|
|
|
113769b657
|
Update BMM_Theory: bmm_theory/branches/__init__.py
|
2026-09-03 09:25:39 +00:00 |
|
|
|
2550c0e9ac
|
Add BMM_Theory: bmm_theory/branches/merge_batch.py
|
2026-09-03 08:09:31 +00:00 |
|
|
|
d93ae35729
|
Add BMM_Theory: bmm_theory/branches/iter_batch.py
|
2026-09-03 08:09:31 +00:00 |
|
|
|
87e945c5a8
|
Add BMM_Theory: bmm_theory/branches/base.py
|
2026-09-03 08:09:30 +00:00 |
|
|
|
ea846dc363
|
Add BMM_Theory: bmm_theory/branches/__init__.py
|
2026-09-03 08:09:29 +00:00 |
|
