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

Expand cases_demo to 44 cases (B 4..128 x M 1..131072 x N/K 128..8192 incl 7168) + regenerate examples outputs

Browse Source
This commit is contained in:
admin
2026-09-04 11:09:49 +08:00
parent 5051e00fa0
commit f4b23d9f05
4 changed files with 147 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
BMM/BMM_Theory/examples/plans.csv
View File

@@ -9,3 +9,37 @@ iter_demo_form_d,IterBatch,Ascend950PR,batch_mat_mul_v3,32,32,1,1,1,切B轮转
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"
asw_demo_full,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,47,47,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,176,176,1024,256,1,双缓冲驻留当前tile输入,176,176,80,allocate(输入驻留L2吸收重复读),direct_gm(输出直写GM不占L2),4,0,方案B,52,52,1,52,52,2,139,True,2,"L2场景B_输入驻留输出直写GM, r_in=1.00; 尾轮: 周长型主导, rho=0.06<rho_dv=0.53, A1b被dValue卡死, 方案B反超"
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,direct_gm,0,0,不涉及(每核一块无尾轮),1,1,1,0,0,0,0,True,2,"P=16.00<C, 降核是理性选择 (强切则 tile 跌破搬移效率下限反而更慢)"
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,direct_gm,0,0,不涉及(每核一块无尾轮),1,1,1,0,0,0,0,True,2,"P=0.01<C, 降核是理性选择 (强切则 tile 跌破搬移效率下限反而更慢)"
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,direct_gm,0,0,不涉及(每核一块无尾轮),1,1,1,0,0,0,0,True,2,"P=0.05<C, 降核是理性选择 (强切则 tile 跌破搬移效率下限反而更慢)"
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,direct_gm,0,0,不涉及(每核一块无尾轮),1,1,1,0,0,0,0,True,2,"P=0.25<C, 降核是理性选择 (强切则 tile 跌破搬移效率下限反而更慢)"
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),"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,单batch全驻留: (MK+KN)*dtype=68KB <= L1
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),"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,"一侧驻留(A)+对侧切K: A驻留16KB, 预算L1/2, k_L1=240, dValueA=480B/dValueB=512B"
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),"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=200KB <= L1
b32_m16_n8192_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,1,47,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,176,176,7168,256,1,双缓冲驻留当前tile输入,176,176,80,allocate(输入驻留L2吸收重复读),direct_gm(输出直写GM不占L2),4,0,A0,1,1,1,0,0,0,47,True,2,"L2场景C_输入超L2分组执行, r_in=1.09; 尾轮: r=0 无尾轮"
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"
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"
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),"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,"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"
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(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,"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"
b128_m2048_n2048_k1536,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,12,12,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,176,176,1536,256,1,双缓冲驻留当前tile输入,176,176,80,allocate(输入驻留L2吸收重复读),direct_gm(输出直写GM不占L2),4,0,A0,1,1,1,0,0,0,576,True,2,"L2场景C_输入超L2分组执行, r_in=12.00; 尾轮: r=0 无尾轮"
b64_m1024_n8192_k2048,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,6,47,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,176,176,2048,256,1,双缓冲驻留当前tile输入,176,176,80,allocate(输入驻留L2吸收重复读),direct_gm(输出直写GM不占L2),4,0,A0,1,1,1,0,0,0,564,True,2,"L2场景C_输入超L2分组执行, r_in=10.56; 尾轮: r=0 无尾轮"
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),"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,"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"
b128_m4096_n4096_k8192,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,24,24,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,176,176,8192,256,1,双缓冲驻留当前tile输入,176,176,80,allocate(输入驻留L2吸收重复读),direct_gm(输出直写GM不占L2),4,0,A0,1,1,1,0,0,0,2304,True,2,"L2场景C_输入超L2分组执行, r_in=24.00; 尾轮: r=0 无尾轮"
b32_m8192_n4096_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,47,24,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,176,176,7168,256,1,双缓冲驻留当前tile输入,176,176,80,allocate(输入驻留L2吸收重复读),direct_gm(输出直写GM不占L2),4,0,A0,1,1,1,0,0,0,1128,True,2,"L2场景C_输入超L2分组执行, r_in=31.67; 尾轮: r=0 无尾轮"
b32_m2048_n2048_k8192,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,12,12,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,176,176,8192,256,1,双缓冲驻留当前tile输入,176,176,80,allocate(输入驻留L2吸收重复读),direct_gm(输出直写GM不占L2),4,0,A0,1,1,1,0,0,0,144,True,2,"L2场景C_输入超L2分组执行, r_in=12.00; 尾轮: r=0 无尾轮"
b64_m4096_n2048_k128,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,24,12,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,176,176,128,128,1,双缓冲驻留当前tile输入,176,176,80,allocate(输入驻留L2吸收重复读),direct_gm(输出直写GM不占L2),4,0,A0,1,1,1,0,0,0,576,True,2,"L2场景B_输入驻留输出直写GM, r_in=1.00; 尾轮: r=0 无尾轮"
b16_m1024_n1024_k8192,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,6,6,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,176,176,8192,256,1,双缓冲驻留当前tile输入,176,176,80,allocate(输入驻留L2吸收重复读),direct_gm(输出直写GM不占L2),4,0,A0,1,1,1,0,0,0,18,True,2,"L2场景C_输入超L2分组执行, r_in=6.00; 尾轮: r=0 无尾轮"
b4_m32768_n128_k128,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,187,1,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,176,176,128,128,1,双缓冲驻留当前tile输入,176,176,80,allocate(输入驻留L2吸收重复读),resident(输出驻留L2异步回写),4,0,方案B,205,1,1,205,1,12,24,True,2,"L2场景A_全驻留, r_in=1.00; 尾轮: 面积型主导, A1b与方案B严格打平(T=28.96us), 选方案B工程简洁 (一套tile)"
b8_m32768_n2048_k512,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,187,12,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,176,176,512,256,1,双缓冲驻留当前tile输入,176,176,80,allocate(输入驻留L2吸收重复读),direct_gm(输出直写GM不占L2),4,0,A0,1,1,1,0,0,0,561,True,2,"L2场景C_输入超L2分组执行, r_in=1.24; 尾轮: r=0 无尾轮"
b4_m131072_n128_k128,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,745,1,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,176,176,128,128,1,双缓冲驻留当前tile输入,176,176,80,allocate(输入驻留L2吸收重复读),direct_gm(输出直写GM不占L2),4,0,方案B,820,1,1,820,1,4,94,True,2,"L2场景C_输入超L2分组执行, r_in=1.00; 尾轮: 面积型主导, A1b与方案B严格打平(T=115.39us), 选方案B工程简洁 (一套tile)"
b8_m131072_n1024_k256,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,745,6,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,176,176,256,256,1,双缓冲驻留当前tile输入,176,176,80,allocate(输入驻留L2吸收重复读),direct_gm(输出直写GM不占L2),4,0,方案B,820,7,1,820,7,16,1118,True,2,"L2场景C_输入超L2分组执行, r_in=1.06; 尾轮: 面积型主导, A1b与方案B严格打平(T=1384.63us), 选方案B工程简洁 (一套tile)"
b16_m32768_n8192_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,187,47,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,176,176,7168,256,1,双缓冲驻留当前tile输入,176,176,80,allocate(输入驻留L2吸收重复读),direct_gm(输出直写GM不占L2),4,0,方案B,205,52,1,205,52,16,4395,True,2,"L2场景C_输入超L2分组执行, r_in=75.00; 尾轮: 周长型主导, rho=0.50<rho_dv=0.53, A1b被dValue卡死, 方案B反超"
b4_m32768_n128_k8192,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,187,1,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,176,176,8192,256,1,双缓冲驻留当前tile输入,176,176,80,allocate(输入驻留L2吸收重复读),direct_gm(输出直写GM不占L2),4,0,方案B,205,1,1,205,1,12,24,True,2,"L2场景C_输入超L2分组执行, r_in=1.14; 尾轮: 周长型主导, rho=0.38<rho_dv=0.53, A1b被dValue卡死, 方案B反超"
b32_m131072_n8192_k128,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,745,47,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,176,176,128,128,1,双缓冲驻留当前tile输入,176,176,80,allocate(输入驻留L2吸收重复读),direct_gm(输出直写GM不占L2),4,0,A0,1,1,1,0,0,0,35015,True,2,"L2场景C_输入超L2分组执行, r_in=2.88; 尾轮: r=0 无尾轮"
b64_m32768_n8192_k1536,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,187,47,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,176,176,1536,256,1,双缓冲驻留当前tile输入,176,176,80,allocate(输入驻留L2吸收重复读),direct_gm(输出直写GM不占L2),4,0,A0,1,1,1,0,0,0,17578,True,2,"L2场景C_输入超L2分组执行, r_in=75.00; 尾轮: r=0 无尾轮"
b8_m131072_n8192_k8192,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,745,47,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,176,176,8192,256,1,双缓冲驻留当前tile输入,176,176,80,allocate(输入驻留L2吸收重复读),direct_gm(输出直写GM不占L2),4,0,A1b,2,2,1,2,2,24,8754,True,2,"L2场景C_输入超L2分组执行, r_in=44.53; 尾轮: 周长型主导, rho=0.75>=rho_dv=0.53, A1b恒优 (尾轮tile缩√rho=0.87倍凑满核)"
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"
b64_m1024_n7168_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,6,41,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,176,176,7168,256,1,双缓冲驻留当前tile输入,176,176,80,allocate(输入驻留L2吸收重复读),direct_gm(输出直写GM不占L2),4,0,A0,1,1,1,0,0,0,492,True,2,"L2场景C_输入超L2分组执行, r_in=10.38; 尾轮: r=0 无尾轮"
b32_m8192_n8192_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,47,47,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,176,176,7168,256,1,双缓冲驻留当前tile输入,176,176,80,allocate(输入驻留L2吸收重复读),direct_gm(输出直写GM不占L2),4,0,A0,1,1,1,0,0,0,2209,True,2,"L2场景C_输入超L2分组执行, r_in=47.00; 尾轮: r=0 无尾轮"
b8_m4096_n4096_k128,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,24,24,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,176,176,128,128,1,双缓冲驻留当前tile输入,176,176,80,allocate(输入驻留L2吸收重复读),direct_gm(输出直写GM不占L2),4,0,A0,1,1,1,0,0,0,144,True,2,"L2场景B_输入驻留输出直写GM, r_in=1.00; 尾轮: r=0 无尾轮"
b128_m8192_n8192_k7168,ASW_Basic,Ascend950PR,batch_mat_mul_v3,32,1,47,47,1,B->M->N线性映射+ASW滑窗蛇形(W=4),0,1,176,176,7168,256,1,双缓冲驻留当前tile输入,176,176,80,allocate(输入驻留L2吸收重复读),direct_gm(输出直写GM不占L2),4,0,A0,1,1,1,0,0,0,8836,True,2,"L2场景C_输入超L2分组执行, r_in=47.00; 尾轮: r=0 无尾轮"
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)"
1 case_id branch npu op used_core_num split_b m_cnt n_cnt grid_k core_map b_core merge_b0 single_core_m single_core_n single_core_k k_l1 b_l1 l1_form base_m base_n base_k l2_policy_in l2_policy_out swizzle_w workspace_bytes tail_strategy tail_m_cnt tail_n_cnt tail_k_cnt tail_m_main tail_n_main tail_block_cnt tail_wave_num fixpipe_unitflag out_dtype_bytes note
9 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
10 asw_demo_full ASW_Basic Ascend950PR batch_mat_mul_v3 32 1 47 47 1 B->M->N线性映射+ASW滑窗蛇形(W=4) 0 1 176 176 1024 256 1 双缓冲驻留当前tile输入 176 176 80 allocate(输入驻留L2吸收重复读) direct_gm(输出直写GM不占L2) 4 0 方案B 52 52 1 52 52 2 139 True 2 L2场景B_输入驻留输出直写GM, r_in=1.00; 尾轮: 周长型主导, rho=0.06<rho_dv=0.53, A1b被dValue卡死, 方案B反超
11 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 direct_gm 0 0 不涉及(每核一块无尾轮) 1 1 1 0 0 0 0 True 2 P=16.00<C, 降核是理性选择 (强切则 tile 跌破搬移效率下限反而更慢)
12 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 direct_gm 0 0 不涉及(每核一块无尾轮) 1 1 1 0 0 0 0 True 2 P=0.01<C, 降核是理性选择 (强切则 tile 跌破搬移效率下限反而更慢)
13 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 direct_gm 0 0 不涉及(每核一块无尾轮) 1 1 1 0 0 0 0 True 2 P=0.05<C, 降核是理性选择 (强切则 tile 跌破搬移效率下限反而更慢)
14 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 direct_gm 0 0 不涉及(每核一块无尾轮) 1 1 1 0 0 0 0 True 2 P=0.25<C, 降核是理性选择 (强切则 tile 跌破搬移效率下限反而更慢)
15 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) 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 单batch全驻留: (MK+KN)*dtype=68KB <= L1
16 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) 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 一侧驻留(A)+对侧切K: A驻留16KB, 预算L1/2, k_L1=240, dValueA=480B/dValueB=512B
17 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) 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=200KB <= L1
18 b32_m16_n8192_k7168 ASW_Basic Ascend950PR batch_mat_mul_v3 32 1 1 47 1 B->M->N线性映射+ASW滑窗蛇形(W=4) 0 1 176 176 7168 256 1 双缓冲驻留当前tile输入 176 176 80 allocate(输入驻留L2吸收重复读) direct_gm(输出直写GM不占L2) 4 0 A0 1 1 1 0 0 0 47 True 2 L2场景C_输入超L2分组执行, r_in=1.09; 尾轮: r=0 无尾轮
19 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
20 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
21 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) 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 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
22 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(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 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
23 b128_m2048_n2048_k1536 ASW_Basic Ascend950PR batch_mat_mul_v3 32 1 12 12 1 B->M->N线性映射+ASW滑窗蛇形(W=4) 0 1 176 176 1536 256 1 双缓冲驻留当前tile输入 176 176 80 allocate(输入驻留L2吸收重复读) direct_gm(输出直写GM不占L2) 4 0 A0 1 1 1 0 0 0 576 True 2 L2场景C_输入超L2分组执行, r_in=12.00; 尾轮: r=0 无尾轮
24 b64_m1024_n8192_k2048 ASW_Basic Ascend950PR batch_mat_mul_v3 32 1 6 47 1 B->M->N线性映射+ASW滑窗蛇形(W=4) 0 1 176 176 2048 256 1 双缓冲驻留当前tile输入 176 176 80 allocate(输入驻留L2吸收重复读) direct_gm(输出直写GM不占L2) 4 0 A0 1 1 1 0 0 0 564 True 2 L2场景C_输入超L2分组执行, r_in=10.56; 尾轮: r=0 无尾轮
25 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) 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 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
26 b128_m4096_n4096_k8192 ASW_Basic Ascend950PR batch_mat_mul_v3 32 1 24 24 1 B->M->N线性映射+ASW滑窗蛇形(W=4) 0 1 176 176 8192 256 1 双缓冲驻留当前tile输入 176 176 80 allocate(输入驻留L2吸收重复读) direct_gm(输出直写GM不占L2) 4 0 A0 1 1 1 0 0 0 2304 True 2 L2场景C_输入超L2分组执行, r_in=24.00; 尾轮: r=0 无尾轮
27 b32_m8192_n4096_k7168 ASW_Basic Ascend950PR batch_mat_mul_v3 32 1 47 24 1 B->M->N线性映射+ASW滑窗蛇形(W=4) 0 1 176 176 7168 256 1 双缓冲驻留当前tile输入 176 176 80 allocate(输入驻留L2吸收重复读) direct_gm(输出直写GM不占L2) 4 0 A0 1 1 1 0 0 0 1128 True 2 L2场景C_输入超L2分组执行, r_in=31.67; 尾轮: r=0 无尾轮
28 b32_m2048_n2048_k8192 ASW_Basic Ascend950PR batch_mat_mul_v3 32 1 12 12 1 B->M->N线性映射+ASW滑窗蛇形(W=4) 0 1 176 176 8192 256 1 双缓冲驻留当前tile输入 176 176 80 allocate(输入驻留L2吸收重复读) direct_gm(输出直写GM不占L2) 4 0 A0 1 1 1 0 0 0 144 True 2 L2场景C_输入超L2分组执行, r_in=12.00; 尾轮: r=0 无尾轮
29 b64_m4096_n2048_k128 ASW_Basic Ascend950PR batch_mat_mul_v3 32 1 24 12 1 B->M->N线性映射+ASW滑窗蛇形(W=4) 0 1 176 176 128 128 1 双缓冲驻留当前tile输入 176 176 80 allocate(输入驻留L2吸收重复读) direct_gm(输出直写GM不占L2) 4 0 A0 1 1 1 0 0 0 576 True 2 L2场景B_输入驻留输出直写GM, r_in=1.00; 尾轮: r=0 无尾轮
30 b16_m1024_n1024_k8192 ASW_Basic Ascend950PR batch_mat_mul_v3 32 1 6 6 1 B->M->N线性映射+ASW滑窗蛇形(W=4) 0 1 176 176 8192 256 1 双缓冲驻留当前tile输入 176 176 80 allocate(输入驻留L2吸收重复读) direct_gm(输出直写GM不占L2) 4 0 A0 1 1 1 0 0 0 18 True 2 L2场景C_输入超L2分组执行, r_in=6.00; 尾轮: r=0 无尾轮
31 b4_m32768_n128_k128 ASW_Basic Ascend950PR batch_mat_mul_v3 32 1 187 1 1 B->M->N线性映射+ASW滑窗蛇形(W=4) 0 1 176 176 128 128 1 双缓冲驻留当前tile输入 176 176 80 allocate(输入驻留L2吸收重复读) resident(输出驻留L2异步回写) 4 0 方案B 205 1 1 205 1 12 24 True 2 L2场景A_全驻留, r_in=1.00; 尾轮: 面积型主导, A1b与方案B严格打平(T=28.96us), 选方案B工程简洁 (一套tile)
32 b8_m32768_n2048_k512 ASW_Basic Ascend950PR batch_mat_mul_v3 32 1 187 12 1 B->M->N线性映射+ASW滑窗蛇形(W=4) 0 1 176 176 512 256 1 双缓冲驻留当前tile输入 176 176 80 allocate(输入驻留L2吸收重复读) direct_gm(输出直写GM不占L2) 4 0 A0 1 1 1 0 0 0 561 True 2 L2场景C_输入超L2分组执行, r_in=1.24; 尾轮: r=0 无尾轮
33 b4_m131072_n128_k128 ASW_Basic Ascend950PR batch_mat_mul_v3 32 1 745 1 1 B->M->N线性映射+ASW滑窗蛇形(W=4) 0 1 176 176 128 128 1 双缓冲驻留当前tile输入 176 176 80 allocate(输入驻留L2吸收重复读) direct_gm(输出直写GM不占L2) 4 0 方案B 820 1 1 820 1 4 94 True 2 L2场景C_输入超L2分组执行, r_in=1.00; 尾轮: 面积型主导, A1b与方案B严格打平(T=115.39us), 选方案B工程简洁 (一套tile)
34 b8_m131072_n1024_k256 ASW_Basic Ascend950PR batch_mat_mul_v3 32 1 745 6 1 B->M->N线性映射+ASW滑窗蛇形(W=4) 0 1 176 176 256 256 1 双缓冲驻留当前tile输入 176 176 80 allocate(输入驻留L2吸收重复读) direct_gm(输出直写GM不占L2) 4 0 方案B 820 7 1 820 7 16 1118 True 2 L2场景C_输入超L2分组执行, r_in=1.06; 尾轮: 面积型主导, A1b与方案B严格打平(T=1384.63us), 选方案B工程简洁 (一套tile)
35 b16_m32768_n8192_k7168 ASW_Basic Ascend950PR batch_mat_mul_v3 32 1 187 47 1 B->M->N线性映射+ASW滑窗蛇形(W=4) 0 1 176 176 7168 256 1 双缓冲驻留当前tile输入 176 176 80 allocate(输入驻留L2吸收重复读) direct_gm(输出直写GM不占L2) 4 0 方案B 205 52 1 205 52 16 4395 True 2 L2场景C_输入超L2分组执行, r_in=75.00; 尾轮: 周长型主导, rho=0.50<rho_dv=0.53, A1b被dValue卡死, 方案B反超
36 b4_m32768_n128_k8192 ASW_Basic Ascend950PR batch_mat_mul_v3 32 1 187 1 1 B->M->N线性映射+ASW滑窗蛇形(W=4) 0 1 176 176 8192 256 1 双缓冲驻留当前tile输入 176 176 80 allocate(输入驻留L2吸收重复读) direct_gm(输出直写GM不占L2) 4 0 方案B 205 1 1 205 1 12 24 True 2 L2场景C_输入超L2分组执行, r_in=1.14; 尾轮: 周长型主导, rho=0.38<rho_dv=0.53, A1b被dValue卡死, 方案B反超
37 b32_m131072_n8192_k128 ASW_Basic Ascend950PR batch_mat_mul_v3 32 1 745 47 1 B->M->N线性映射+ASW滑窗蛇形(W=4) 0 1 176 176 128 128 1 双缓冲驻留当前tile输入 176 176 80 allocate(输入驻留L2吸收重复读) direct_gm(输出直写GM不占L2) 4 0 A0 1 1 1 0 0 0 35015 True 2 L2场景C_输入超L2分组执行, r_in=2.88; 尾轮: r=0 无尾轮
38 b64_m32768_n8192_k1536 ASW_Basic Ascend950PR batch_mat_mul_v3 32 1 187 47 1 B->M->N线性映射+ASW滑窗蛇形(W=4) 0 1 176 176 1536 256 1 双缓冲驻留当前tile输入 176 176 80 allocate(输入驻留L2吸收重复读) direct_gm(输出直写GM不占L2) 4 0 A0 1 1 1 0 0 0 17578 True 2 L2场景C_输入超L2分组执行, r_in=75.00; 尾轮: r=0 无尾轮
39 b8_m131072_n8192_k8192 ASW_Basic Ascend950PR batch_mat_mul_v3 32 1 745 47 1 B->M->N线性映射+ASW滑窗蛇形(W=4) 0 1 176 176 8192 256 1 双缓冲驻留当前tile输入 176 176 80 allocate(输入驻留L2吸收重复读) direct_gm(输出直写GM不占L2) 4 0 A1b 2 2 1 2 2 24 8754 True 2 L2场景C_输入超L2分组执行, r_in=44.53; 尾轮: 周长型主导, rho=0.75>=rho_dv=0.53, A1b恒优 (尾轮tile缩√rho=0.87倍凑满核)
40 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
41 b64_m1024_n7168_k7168 ASW_Basic Ascend950PR batch_mat_mul_v3 32 1 6 41 1 B->M->N线性映射+ASW滑窗蛇形(W=4) 0 1 176 176 7168 256 1 双缓冲驻留当前tile输入 176 176 80 allocate(输入驻留L2吸收重复读) direct_gm(输出直写GM不占L2) 4 0 A0 1 1 1 0 0 0 492 True 2 L2场景C_输入超L2分组执行, r_in=10.38; 尾轮: r=0 无尾轮
42 b32_m8192_n8192_k7168 ASW_Basic Ascend950PR batch_mat_mul_v3 32 1 47 47 1 B->M->N线性映射+ASW滑窗蛇形(W=4) 0 1 176 176 7168 256 1 双缓冲驻留当前tile输入 176 176 80 allocate(输入驻留L2吸收重复读) direct_gm(输出直写GM不占L2) 4 0 A0 1 1 1 0 0 0 2209 True 2 L2场景C_输入超L2分组执行, r_in=47.00; 尾轮: r=0 无尾轮
43 b8_m4096_n4096_k128 ASW_Basic Ascend950PR batch_mat_mul_v3 32 1 24 24 1 B->M->N线性映射+ASW滑窗蛇形(W=4) 0 1 176 176 128 128 1 双缓冲驻留当前tile输入 176 176 80 allocate(输入驻留L2吸收重复读) direct_gm(输出直写GM不占L2) 4 0 A0 1 1 1 0 0 0 144 True 2 L2场景B_输入驻留输出直写GM, r_in=1.00; 尾轮: r=0 无尾轮
44 b128_m8192_n8192_k7168 ASW_Basic Ascend950PR batch_mat_mul_v3 32 1 47 47 1 B->M->N线性映射+ASW滑窗蛇形(W=4) 0 1 176 176 7168 256 1 双缓冲驻留当前tile输入 176 176 80 allocate(输入驻留L2吸收重复读) direct_gm(输出直写GM不占L2) 4 0 A0 1 1 1 0 0 0 8836 True 2 L2场景C_输入超L2分组执行, r_in=47.00; 尾轮: r=0 无尾轮
45 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)