admin/matmul-analysis
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Remove mistakenly pushed temp file: t_out.csv

Browse Source
This commit is contained in:
admin
2026-09-03 11:35:02 +00:00
parent fbd6954d61
commit 2d06aa939f
1 changed files with 0 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
BMM/BMM_Theory/t_out.csv
View File

@@ -1,4 +0,0 @@
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
x,51,51,255,42,682,fp32,fp32,fp32,False,False,False,True,0,x,StreamK,Ascend950PR,batch_mat_mul_v3,32,1,1,1,3,"B/M/N切出51块, 每块3核切K归约 (归约组内核c负责K段[c*K/3,(c+1)*K/3))",1,1,255,42,228,128,1,K段标准分块流水,128,42,64,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)",0,6554520,grid_K=3路切K+归约,1,1,3,0,0,0,0,True,4,"P=8.33, grid_K=3, 部分和驻留L2按4B写出, AIV归约后按C dtype=4B写最终",465578.6666666667,0.0,9.311573333333333e-06,0.0,9.311573333333333e-06,0.0,0.0,29797034.666666668,1.9619446694101507e-06,262144,1.6131938461538462e-06,3.674316083916084e-07,9.311573333333333e-06,3.674316083916084e-07,9.679004941724942e-06,MTE2_GM,True,,访存Bound(GM),"切B分支条件不满足, 落 StreamK"
y,2,2,64,16,32,fp16,fp16,fp16,False,False,False,True,0,y,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",0,1,64,16,32,32,1,标准核内流水,64,16,32,allocate,direct_gm,0,0,不涉及(每核一块无尾轮),1,1,1,0,0,0,0,True,2,"P=0.03<C, 降核是理性选择 (强切则 tile 跌破搬移效率下限反而更慢)",10240.0,0.0,2.048e-07,0.0,2.048e-07,0.0,0.0,131072.0,8.630255144032922e-09,4096,8.192e-08,0.0,2.048e-07,0.0,2.048e-07,MTE2_GM,True,,访存Bound(GM),"ASW_Basic兜底 (StreamK未过: 2_单核K段下限: K/grid_K >= 256B/dtype 且 grid_K>=2; 3_归约代价可接受: K > grid_K^2/(grid_K-1)*theta_c) [自检违规: dValue=64B < 下限 128B, K 段连续维搬移效率崩塌] —— 方案生成存在缺陷, 需人工复核"
z,256,256,128,1024,8,bf16,bf16,bf16,False,False,False,True,0,z,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),8,1,128,1024,8,8,2,b_双batch乒乓,128,256,16,allocate(GM->L1随路驻留L2),"direct_gm(输出仅写一次,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,双batch乒乓: 2*(MK+KN)*dtype=36KB <= L1,147456,0.0,2.94912e-06,0.0,3.34912e-06,8,4.0000000000000003e-07,16777216.0,1.104672658436214e-06,2097152,4.194304e-05,0.0,4.194304e-05,5.380964082304527e-06,4.7324004082304525e-05,FIXPIPE,True,,写出Bound,仅 IterBatch 条件满足
1 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
2 x 51 51 255 42 682 fp32 fp32 fp32 False False False True 0 x StreamK Ascend950PR batch_mat_mul_v3 32 1 1 1 3 B/M/N切出51块, 每块3核切K归约 (归约组内核c负责K段[c*K/3,(c+1)*K/3)) 1 1 255 42 228 128 1 K段标准分块流水 128 42 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 6554520 grid_K=3路切K+归约 1 1 3 0 0 0 0 True 4 P=8.33, grid_K=3, 部分和驻留L2按4B写出, AIV归约后按C dtype=4B写最终 465578.6666666667 0.0 9.311573333333333e-06 0.0 9.311573333333333e-06 0.0 0.0 29797034.666666668 1.9619446694101507e-06 262144 1.6131938461538462e-06 3.674316083916084e-07 9.311573333333333e-06 3.674316083916084e-07 9.679004941724942e-06 MTE2_GM True 访存Bound(GM) 切B分支条件不满足, 落 StreamK
3 y 2 2 64 16 32 fp16 fp16 fp16 False False False True 0 y 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 64 16 32 32 1 标准核内流水 64 16 32 allocate direct_gm 0 0 不涉及(每核一块无尾轮) 1 1 1 0 0 0 0 True 2 P=0.03<C, 降核是理性选择 (强切则 tile 跌破搬移效率下限反而更慢) 10240.0 0.0 2.048e-07 0.0 2.048e-07 0.0 0.0 131072.0 8.630255144032922e-09 4096 8.192e-08 0.0 2.048e-07 0.0 2.048e-07 MTE2_GM True 访存Bound(GM) ASW_Basic兜底 (StreamK未过: 2_单核K段下限: K/grid_K >= 256B/dtype 且 grid_K>=2; 3_归约代价可接受: K > grid_K^2/(grid_K-1)*theta_c) [自检违规: dValue=64B < 下限 128B, K 段连续维搬移效率崩塌] —— 方案生成存在缺陷, 需人工复核
4 z 256 256 128 1024 8 bf16 bf16 bf16 False False False True 0 z 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) 8 1 128 1024 8 8 2 b_双batch乒乓 128 256 16 allocate(GM->L1随路驻留L2) direct_gm(输出仅写一次,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 双batch乒乓: 2*(MK+KN)*dtype=36KB <= L1 147456 0.0 2.94912e-06 0.0 3.34912e-06 8 4.0000000000000003e-07 16777216.0 1.104672658436214e-06 2097152 4.194304e-05 0.0 4.194304e-05 5.380964082304527e-06 4.7324004082304525e-05 FIXPIPE True 写出Bound 仅 IterBatch 条件满足