From f4b23d9f05dbb46813cba6a2ee8951f8d8f289bc Mon Sep 17 00:00:00 2001 From: admin Date: Fri, 4 Sep 2026 11:09:49 +0800 Subject: [PATCH] Expand cases_demo to 44 cases (B 4..128 x M 1..131072 x N/K 128..8192 incl 7168) + regenerate examples outputs --- BMM/BMM_Theory/examples/cases_demo.csv | 56 ++++++++++++++++---- BMM/BMM_Theory/examples/plans.csv | 34 ++++++++++++ BMM/BMM_Theory/examples/result_evaluate.csv | 34 ++++++++++++ BMM/BMM_Theory/examples/result_recommend.csv | 34 ++++++++++++ 4 files changed, 147 insertions(+), 11 deletions(-) diff --git a/BMM/BMM_Theory/examples/cases_demo.csv b/BMM/BMM_Theory/examples/cases_demo.csv index c04c1cd..b5a9e30 100644 --- a/BMM/BMM_Theory/examples/cases_demo.csv +++ b/BMM/BMM_Theory/examples/cases_demo.csv @@ -1,11 +1,45 @@ -case_id,batch_a,batch_b,m,n,k,dtype_a,dtype_b,dtype_c,trans_a,trans_b,has_bias,deterministic_level -to_matmul_demo,1,1,2048,2048,2048,bf16,bf16,bf16,0,0,0,0 -special_k0_demo,128,128,256,256,0,bf16,bf16,bf16,0,0,0,0 -special_k1_demo,128,128,256,256,1,bf16,bf16,bf16,0,0,0,0 -merge_demo_k_trunc,2048,2048,32,32,256,bf16,bf16,bf16,0,0,0,0 -merge_iter_arbitrate,128,128,64,64,512,bf16,bf16,bf16,0,0,0,0 -iter_demo_form_b,128,128,64,64,256,bf16,bf16,bf16,0,0,0,0 -iter_demo_form_d,64,64,64,64,8192,bf16,bf16,bf16,0,0,0,0 -streamk_demo,4,4,128,128,10240,bf16,bf16,bf16,0,0,0,0 -asw_demo_full,2,2,8192,8192,1024,bf16,bf16,bf16,0,0,0,0 -asw_demo_reduce_core,16,16,256,256,128,bf16,bf16,bf16,0,0,0,0 +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 +to_matmul_demo,1,1,2048,2048,2048,bf16,bf16,bf16,0,0,0,,0 +special_k0_demo,128,128,256,256,0,bf16,bf16,bf16,0,0,0,,0 +special_k1_demo,128,128,256,256,1,bf16,bf16,bf16,0,0,0,,0 +merge_demo_k_trunc,2048,2048,32,32,256,bf16,bf16,bf16,0,0,0,,0 +merge_iter_arbitrate,128,128,64,64,512,bf16,bf16,bf16,0,0,0,,0 +iter_demo_form_b,128,128,64,64,256,bf16,bf16,bf16,0,0,0,,0 +iter_demo_form_d,64,64,64,64,8192,bf16,bf16,bf16,0,0,0,,0 +streamk_demo,4,4,128,128,10240,bf16,bf16,bf16,0,0,0,,0 +asw_demo_full,2,2,8192,8192,1024,bf16,bf16,bf16,0,0,0,,0 +asw_demo_reduce_core,16,16,256,256,128,bf16,bf16,bf16,0,0,0,,0 +b4_m1_n128_k256,4,4,1,128,256,bf16,bf16,bf16,0,0,0,1,0 +b8_m2_n192_k128,8,8,2,192,128,bf16,bf16,bf16,0,0,0,1,0 +b16_m4_n256_k192,16,16,4,256,192,bf16,bf16,bf16,0,0,0,1,0 +b32_m8_n128_k256,32,32,8,128,256,bf16,bf16,bf16,0,0,0,1,0 +b64_m16_n256_k512,64,64,16,256,512,bf16,bf16,bf16,0,0,0,1,0 +b128_m8_n192_k256,128,128,8,192,256,bf16,bf16,bf16,0,0,0,1,0 +b32_m16_n8192_k7168,32,32,16,8192,7168,bf16,bf16,bf16,0,0,0,1,0 +b4_m1_n8192_k8192,4,4,1,8192,8192,bf16,bf16,bf16,0,0,0,1,0 +b16_m2_n4096_k7168,16,16,2,4096,7168,bf16,bf16,bf16,0,0,0,1,0 +b32_m64_n64_k7168,32,32,64,64,7168,bf16,bf16,bf16,0,0,0,1,0 +b64_m1024_n1024_k7168,64,64,1024,1024,7168,bf16,bf16,bf16,0,0,0,1,0 +b128_m2048_n2048_k1536,128,128,2048,2048,1536,bf16,bf16,bf16,0,0,0,1,0 +b64_m1024_n8192_k2048,64,64,1024,8192,2048,bf16,bf16,bf16,0,0,0,1,0 +b32_m1024_n1024_k512,32,32,1024,1024,512,bf16,bf16,bf16,0,0,0,1,0 +b128_m4096_n4096_k8192,128,128,4096,4096,8192,bf16,bf16,bf16,0,0,0,1,0 +b32_m8192_n4096_k7168,32,32,8192,4096,7168,bf16,bf16,bf16,0,0,0,1,0 +b32_m2048_n2048_k8192,32,32,2048,2048,8192,bf16,bf16,bf16,0,0,0,1,0 +b64_m4096_n2048_k128,64,64,4096,2048,128,bf16,bf16,bf16,0,0,0,1,0 +b16_m1024_n1024_k8192,16,16,1024,1024,8192,bf16,bf16,bf16,0,0,0,1,0 +b4_m32768_n128_k128,4,4,32768,128,128,bf16,bf16,bf16,0,0,0,1,0 +b8_m32768_n2048_k512,8,8,32768,2048,512,bf16,bf16,bf16,0,0,0,1,0 +b4_m131072_n128_k128,4,4,131072,128,128,bf16,bf16,bf16,0,0,0,1,0 +b8_m131072_n1024_k256,8,8,131072,1024,256,bf16,bf16,bf16,0,0,0,1,0 +b16_m32768_n8192_k7168,16,16,32768,8192,7168,bf16,bf16,bf16,0,0,0,1,0 +b4_m32768_n128_k8192,4,4,32768,128,8192,bf16,bf16,bf16,0,0,0,1,0 +b32_m131072_n8192_k128,32,32,131072,8192,128,bf16,bf16,bf16,0,0,0,1,0 +b64_m32768_n8192_k1536,64,64,32768,8192,1536,bf16,bf16,bf16,0,0,0,1,0 +b8_m131072_n8192_k8192,8,8,131072,8192,8192,bf16,bf16,bf16,0,0,0,1,0 +b8_m16_n7168_k1536,8,8,16,7168,1536,bf16,bf16,bf16,0,0,0,1,0 +b64_m1024_n7168_k7168,64,64,1024,7168,7168,bf16,bf16,bf16,0,0,0,1,0 +b32_m8192_n8192_k7168,32,32,8192,8192,7168,bf16,bf16,bf16,0,0,0,1,0 +b8_m4096_n4096_k128,8,8,4096,4096,128,bf16,bf16,bf16,0,0,0,1,0 +b128_m8192_n8192_k7168,128,128,8192,8192,7168,bf16,bf16,bf16,0,0,0,1,0 +special_k1_b64,64,64,8192,512,1,bf16,bf16,bf16,0,0,0,1,0 diff --git a/BMM/BMM_Theory/examples/plans.csv b/BMM/BMM_Theory/examples/plans.csv index 368bed0..29ed469 100644 --- a/BMM/BMM_Theory/examples/plans.csv +++ b/BMM/BMM_Theory/examples/plans.csv @@ -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=0.06L1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=0.50M->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=0.38M->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)" diff --git a/BMM/BMM_Theory/examples/result_evaluate.csv b/BMM/BMM_Theory/examples/result_evaluate.csv index 7297103..4056fd8 100644 --- a/BMM/BMM_Theory/examples/result_evaluate.csv +++ b/BMM/BMM_Theory/examples/result_evaluate.csv @@ -9,3 +9,37 @@ iter_demo_form_d,64,64,64,64,8192,bf16,bf16,bf16,False,False,False,True,0,iter_d 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",327680.0,0.0,6.5536e-06,0.0,6.5536e-06,0.0,0.0,41943040.0,2.761681646090535e-06,0.0,0.0,3.4067453613053613e-06,6.5536e-06,3.4067453613053613e-06,9.960345361305361e-06,MTE2_GM,True,,访存Bound(GM),"瓶颈在 GM 搬入: 可考虑增大 tile 提升 dValue/单核搬移量, 或利用 L2 驻留吸收重复读 (MergeBatch/ASW swizzle 方向)" 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_v3,32,1,47,47,1,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=0.06L1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 <= L1,69632,0.0,1.39264e-06,0.0,1.44264e-06,1,5.0000000000000004e-08,524288.0,3.452102057613169e-08,2048,4.096e-08,0.0,1.44264e-06,7.548102057613169e-08,1.5181210205761316e-06,MTE2_GM,True,,访存Bound(GM),"瓶颈在 GM 搬入: 可考虑增大 tile 提升 dValue/单核搬移量, 或利用 L2 驻留吸收重复读 (MergeBatch/ASW swizzle 方向)" +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),"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",557056,0.0,1.56672e-05,0.0,1.5967200000000002e-05,6,3.0000000000000004e-07,8388608.0,5.52336329218107e-07,16384,3.2768e-07,0.0,1.5967200000000002e-05,2.932938271604938e-07,1.6260493827160496e-05,MTE2_GM,True,,访存Bound(GM),"瓶颈在 GM 搬入: 可考虑增大 tile 提升 dValue/单核搬移量, 或利用 L2 驻留吸收重复读 (MergeBatch/ASW swizzle 方向)" +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),"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 <= L1,409600,0.0,8.192e-06,0.0,8.392e-06,4,2.0000000000000002e-07,3145728.0,2.0712612345679012e-07,12288,2.4576e-07,0.0,8.392e-06,1.1322153086419754e-07,8.505221530864198e-06,MTE2_GM,True,,访存Bound(GM),"瓶颈在 GM 搬入: 可考虑增大 tile 提升 dValue/单核搬移量, 或利用 L2 驻留吸收重复读 (MergeBatch/ASW swizzle 方向)" +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_v3,32,1,1,47,1,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",4103077888.0000005,0.0,0.0025644236800000005,0.0,0.0025644236800000005,0.0,0.0,60129542144.0,0.00012372333774485596,8388608,5.24288e-06,0.0,0.0025644236800000005,0.0,0.0025644236800000005,MTE2_GM,True,,访存Bound(GM),"瓶颈在 GM 搬入: 可考虑增大 tile 提升 dValue/单核搬移量, 或利用 L2 驻留吸收重复读 (MergeBatch/ASW swizzle 方向)" +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",262144.0,0.0,5.24288e-06,0.0,5.24288e-06,0.0,0.0,33554432.0,2.209345316872428e-06,0.0,0.0,3.4067453613053613e-06,5.24288e-06,3.4067453613053613e-06,8.64962536130536e-06,MTE2_GM,True,,访存Bound(GM),"瓶颈在 GM 搬入: 可考虑增大 tile 提升 dValue/单核搬移量, 或利用 L2 驻留吸收重复读 (MergeBatch/ASW swizzle 方向)" +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",458752.0,0.0,9.17504e-06,0.0,9.17504e-06,0.0,0.0,58720256.0,3.866354304526749e-06,0.0,0.0,1.7159757575757577e-06,9.17504e-06,1.7159757575757577e-06,1.0891015757575759e-05,MTE2_GM,True,,访存Bound(GM),"瓶颈在 GM 搬入: 可考虑增大 tile 提升 dValue/单核搬移量, 或利用 L2 驻留吸收重复读 (MergeBatch/ASW swizzle 方向)" +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),"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",1835008,0.0,3.6700159999999995e-05,0.0,3.705016e-05,7,3.5000000000000004e-07,58720256.0,3.866354304526749e-06,8192,1.6384e-07,0.0,3.705016e-05,7.16176329218107e-07,3.77663363292181e-05,MTE2_GM,True,,访存Bound(GM),"瓶颈在 GM 搬入: 可考虑增大 tile 提升 dValue/单核搬移量, 或利用 L2 驻留吸收重复读 (MergeBatch/ASW swizzle 方向)" +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(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",58720256,0.0,0.0011744051199999998,0.0,0.00118560512,224,1.1200000000000001e-05,30064771072.0,0.0019795734039176954,4194304,8.388608e-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_v3,32,1,12,12,1,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",19327352832.0,0.0,0.01207959552,0.0,0.01207959552,0.0,0.0,1649267441664.0,0.0033935544067160493,1073741824,0.00067108864,0.0,0.01207959552,0.0,0.01207959552,MTE2_GM,True,,访存Bound(GM),"瓶颈在 GM 搬入: 可考虑增大 tile 提升 dValue/单核搬移量, 或利用 L2 驻留吸收重复读 (MergeBatch/ASW swizzle 方向)" +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_v3,32,1,6,47,1,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",25501368320.0,0.0,0.0159383552,0.0,0.0159383552,0.0,0.0,2199023255552.0,0.004524739208954733,1073741824,0.00067108864,0.0,0.0159383552,0.0,0.0159383552,MTE2_GM,True,,访存Bound(GM),"瓶颈在 GM 搬入: 可考虑增大 tile 提升 dValue/单核搬移量, 或利用 L2 驻留吸收重复读 (MergeBatch/ASW swizzle 方向)" +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),"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",2097152,0.0,4.194304e-05,0.0,4.234304e-05,8,4.0000000000000003e-07,1073741824.0,7.06990501399177e-05,2097152,4.194304e-05,0.0,7.06990501399177e-05,5.078042126748971e-05,0.0001214794714074074,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_v3,32,1,24,24,1,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",412316860416.0,0.0,0.25769803776,0.0,0.25769803776,0.0,0.0,35184372088832.0,0.07239582734327572,4294967296,0.00268435456,0.0,0.25769803776,0.0,0.25769803776,MTE2_GM,True,,访存Bound(GM),"瓶颈在 GM 搬入: 可考虑增大 tile 提升 dValue/单核搬移量, 或利用 L2 驻留吸收重复读 (MergeBatch/ASW swizzle 方向)" +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_v3,32,1,47,24,1,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",178509578240.0,0.0,0.1115684864,0.0,0.1115684864,0.0,0.0,15393162788864.0,0.031673174462683126,2147483648,0.00134217728,0.0,0.1115684864,0.0,0.1115684864,MTE2_GM,True,,访存Bound(GM),"瓶颈在 GM 搬入: 可考虑增大 tile 提升 dValue/单核搬移量, 或利用 L2 驻留吸收重复读 (MergeBatch/ASW swizzle 方向)" +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_v3,32,1,12,12,1,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",25769803776.0,0.0,0.01610612736,0.0,0.01610612736,0.0,0.0,2199023255552.0,0.004524739208954733,268435456,0.00016777216,0.0,0.01610612736,0.0,0.01610612736,MTE2_GM,True,,访存Bound(GM),"瓶颈在 GM 搬入: 可考虑增大 tile 提升 dValue/单核搬移量, 或利用 L2 驻留吸收重复读 (MergeBatch/ASW swizzle 方向)" +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_v3,32,1,24,12,1,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",100663296.0,0.0,6.291456e-05,0.0,6.291456e-05,0.0,0.0,137438953472.0,0.0002827962005596708,1073741824,0.00067108864,0.0,0.00067108864,0.0,0.00067108864,FIXPIPE,True,,写出Bound,"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" +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_v3,32,1,6,6,1,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",3221225472.0,0.0,0.00201326592,0.0,0.00201326592,0.0,0.0,274877906944.0,0.0005655924011193416,33554432,2.097152e-05,0.0,0.00201326592,0.0,0.00201326592,MTE2_GM,True,,访存Bound(GM),"瓶颈在 GM 搬入: 可考虑增大 tile 提升 dValue/单核搬移量, 或利用 L2 驻留吸收重复读 (MergeBatch/ASW swizzle 方向)" +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_v3,32,1,187,1,1,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)",33685504.0,0.0,2.105344e-05,0.0,2.105344e-05,0.0,0.0,4294967296.0,8.837381267489712e-06,33554432,6.452775384615385e-06,0.0,2.105344e-05,0.0,2.105344e-05,MTE2_GM,True,,访存Bound(GM),"瓶颈在 GM 搬入: 可考虑增大 tile 提升 dValue/单核搬移量, 或利用 L2 驻留吸收重复读 (MergeBatch/ASW swizzle 方向)" +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_v3,32,1,187,12,1,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",352321536.0,0.0,0.00022020096,0.0,0.00022020096,0.0,0.0,549755813888.0,0.0011311848022386832,1073741824,0.00067108864,0.0,0.0011311848022386832,0.0,0.0011311848022386832,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_v3,32,1,745,1,1,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)",134610944.0,0.0,8.413184e-05,0.0,8.413184e-05,0.0,0.0,17179869184.0,3.534952506995885e-05,134217728,8.388608e-05,0.0,8.413184e-05,0.0,8.413184e-05,MTE2_GM,True,,访存Bound(GM),"瓶颈在 GM 搬入: 可考虑增大 tile 提升 dValue/单核搬移量, 或利用 L2 驻留吸收重复读 (MergeBatch/ASW swizzle 方向)" +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_v3,32,1,745,6,1,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)",574619648.0,0.0,0.00035913728,0.0,0.00035913728,0.0,0.0,549755813888.0,0.0011311848022386832,2147483648,0.00134217728,0.0,0.00134217728,0.0,0.00134217728,FIXPIPE,True,,写出Bound,"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" +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_v3,32,1,187,47,1,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=0.50M->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=0.38M->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",3288334336.0,0.0,0.00205520896,0.0,0.00205520896,0.0,0.0,8796093022208.0,0.01809895683581893,68719476736,0.04294967296,0.0,0.04294967296,0.0,0.04294967296,FIXPIPE,True,,写出Bound,"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" +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_v3,32,1,187,47,1,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",603979776000.0,0.0,0.37748736,0.0,0.37748736,0.0,0.0,52776558133248.0,0.10859374101491358,34359738368,0.02147483648,0.0,0.37748736,0.0,0.37748736,MTE2_GM,True,,访存Bound(GM),"瓶颈在 GM 搬入: 可考虑增大 tile 提升 dValue/单核搬移量, 或利用 L2 驻留吸收重复读 (MergeBatch/ASW swizzle 方向)" +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_v3,32,1,745,47,1,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)",812822560768.0,0.0,0.50801410048,0.0,0.50801410048,0.0,0.0,140737488355328.0,0.2895833093731029,17179869184,0.01073741824,0.0,0.50801410048,0.0,0.50801410048,MTE2_GM,True,,访存Bound(GM),"瓶颈在 GM 搬入: 可考虑增大 tile 提升 dValue/单核搬移量, 或利用 L2 驻留吸收重复读 (MergeBatch/ASW swizzle 方向)" +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",786432.0,0.0,1.572864e-05,0.0,1.572864e-05,0.0,0.0,100663296.0,6.628035950617284e-06,0.0,0.0,2.3655235431235433e-07,1.572864e-05,2.3655235431235433e-07,1.5965192354312353e-05,MTE2_GM,True,,访存Bound(GM),"瓶颈在 GM 搬入: 可考虑增大 tile 提升 dValue/单核搬移量, 或利用 L2 驻留吸收重复读 (MergeBatch/ASW swizzle 方向)" +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_v3,32,1,6,41,1,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",77980499968.0,0.0,0.04873781248,0.0,0.04873781248,0.0,0.0,6734508720128.0,0.013857013827423869,939524096,0.00058720256,0.0,0.04873781248,0.0,0.04873781248,MTE2_GM,True,,访存Bound(GM),"瓶颈在 GM 搬入: 可考虑增大 tile 提升 dValue/单核搬移量, 或利用 L2 驻留吸收重复读 (MergeBatch/ASW swizzle 方向)" +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_v3,32,1,47,47,1,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",353261060096.0,0.0,0.22078816256,0.0,0.22078816256,0.0,0.0,30786325577728.0,0.06334634892536625,4294967296,0.00268435456,0.0,0.22078816256,0.0,0.22078816256,MTE2_GM,True,,访存Bound(GM),"瓶颈在 GM 搬入: 可考虑增大 tile 提升 dValue/单核搬移量, 或利用 L2 驻留吸收重复读 (MergeBatch/ASW swizzle 方向)" +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_v3,32,1,24,24,1,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",16777216.0,0.0,1.048576e-05,0.0,1.048576e-05,0.0,0.0,34359738368.0,7.06990501399177e-05,268435456,0.00016777216,0.0,0.00016777216,0.0,0.00016777216,FIXPIPE,True,,写出Bound,"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" +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_v3,32,1,47,47,1,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",1413044240384.0,0.0,0.88315265024,0.0,0.88315265024,0.0,0.0,123145302310912.0,0.253385395701465,17179869184,0.01073741824,0.0,0.88315265024,0.0,0.88315265024,MTE2_GM,True,,访存Bound(GM),"瓶颈在 GM 搬入: 可考虑增大 tile 提升 dValue/单核搬移量, 或利用 L2 驻留吸收重复读 (MergeBatch/ASW swizzle 方向)" +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-07,0.0,0.0,268435456.0,1.985939393939394e-05,536870912,0.00033554432,0.0,0.00033554432,0.0,0.00033554432,FIXPIPE,True,,写出Bound,"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" diff --git a/BMM/BMM_Theory/examples/result_recommend.csv b/BMM/BMM_Theory/examples/result_recommend.csv index f66fca8..10b6edb 100644 --- a/BMM/BMM_Theory/examples/result_recommend.csv +++ b/BMM/BMM_Theory/examples/result_recommend.csv @@ -9,3 +9,37 @@ iter_demo_form_d,64,64,64,64,8192,bf16,bf16,bf16,False,False,False,True,0,iter_d 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",327680.0,0.0,6.5536e-06,0.0,6.5536e-06,0.0,0.0,41943040.0,2.761681646090535e-06,0.0,0.0,3.4067453613053613e-06,6.5536e-06,3.4067453613053613e-06,9.960345361305361e-06,MTE2_GM,True,,访存Bound(GM),"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_v3,32,1,47,47,1,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= 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,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= 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,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= 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,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= 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,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= 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),"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 <= L1,69632,0.0,1.39264e-06,0.0,1.44264e-06,1,5.0000000000000004e-08,524288.0,3.452102057613169e-08,2048,4.096e-08,0.0,1.44264e-06,7.548102057613169e-08,1.5181210205761316e-06,MTE2_GM,True,,访存Bound(GM),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),"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",557056,0.0,1.56672e-05,0.0,1.5967200000000002e-05,6,3.0000000000000004e-07,8388608.0,5.52336329218107e-07,16384,3.2768e-07,0.0,1.5967200000000002e-05,2.932938271604938e-07,1.6260493827160496e-05,MTE2_GM,True,,访存Bound(GM),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),"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 <= L1,409600,0.0,8.192e-06,0.0,8.392e-06,4,2.0000000000000002e-07,3145728.0,2.0712612345679012e-07,12288,2.4576e-07,0.0,8.392e-06,1.1322153086419754e-07,8.505221530864198e-06,MTE2_GM,True,,访存Bound(GM),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_v3,32,1,1,47,1,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",4103077888.0000005,0.0,0.0025644236800000005,0.0,0.0025644236800000005,0.0,0.0,60129542144.0,0.00012372333774485596,8388608,5.24288e-06,0.0,0.0025644236800000005,0.0,0.0025644236800000005,MTE2_GM,True,,访存Bound(GM),"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" +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",262144.0,0.0,5.24288e-06,0.0,5.24288e-06,0.0,0.0,33554432.0,2.209345316872428e-06,0.0,0.0,3.4067453613053613e-06,5.24288e-06,3.4067453613053613e-06,8.64962536130536e-06,MTE2_GM,True,,访存Bound(GM),"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",458752.0,0.0,9.17504e-06,0.0,9.17504e-06,0.0,0.0,58720256.0,3.866354304526749e-06,0.0,0.0,1.7159757575757577e-06,9.17504e-06,1.7159757575757577e-06,1.0891015757575759e-05,MTE2_GM,True,,访存Bound(GM),"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),"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",1835008,0.0,3.6700159999999995e-05,0.0,3.705016e-05,7,3.5000000000000004e-07,58720256.0,3.866354304526749e-06,8192,1.6384e-07,0.0,3.705016e-05,7.16176329218107e-07,3.77663363292181e-05,MTE2_GM,True,,访存Bound(GM),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(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",58720256,0.0,0.0011744051199999998,0.0,0.00118560512,224,1.1200000000000001e-05,30064771072.0,0.0019795734039176954,4194304,8.388608e-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_v3,32,1,12,12,1,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",19327352832.0,0.0,0.01207959552,0.0,0.01207959552,0.0,0.0,1649267441664.0,0.0033935544067160493,1073741824,0.00067108864,0.0,0.01207959552,0.0,0.01207959552,MTE2_GM,True,,访存Bound(GM),"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_v3,32,1,6,47,1,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",25501368320.0,0.0,0.0159383552,0.0,0.0159383552,0.0,0.0,2199023255552.0,0.004524739208954733,1073741824,0.00067108864,0.0,0.0159383552,0.0,0.0159383552,MTE2_GM,True,,访存Bound(GM),"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),"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",2097152,0.0,4.194304e-05,0.0,4.234304e-05,8,4.0000000000000003e-07,1073741824.0,7.06990501399177e-05,2097152,4.194304e-05,0.0,7.06990501399177e-05,5.078042126748971e-05,0.0001214794714074074,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_v3,32,1,24,24,1,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",412316860416.0,0.0,0.25769803776,0.0,0.25769803776,0.0,0.0,35184372088832.0,0.07239582734327572,4294967296,0.00268435456,0.0,0.25769803776,0.0,0.25769803776,MTE2_GM,True,,访存Bound(GM),"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_v3,32,1,47,24,1,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",178509578240.0,0.0,0.1115684864,0.0,0.1115684864,0.0,0.0,15393162788864.0,0.031673174462683126,2147483648,0.00134217728,0.0,0.1115684864,0.0,0.1115684864,MTE2_GM,True,,访存Bound(GM),"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_v3,32,1,12,12,1,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",25769803776.0,0.0,0.01610612736,0.0,0.01610612736,0.0,0.0,2199023255552.0,0.004524739208954733,268435456,0.00016777216,0.0,0.01610612736,0.0,0.01610612736,MTE2_GM,True,,访存Bound(GM),"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_v3,32,1,24,12,1,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",100663296.0,0.0,6.291456e-05,0.0,6.291456e-05,0.0,0.0,137438953472.0,0.0002827962005596708,1073741824,0.00067108864,0.0,0.00067108864,0.0,0.00067108864,FIXPIPE,True,,写出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" +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_v3,32,1,6,6,1,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",3221225472.0,0.0,0.00201326592,0.0,0.00201326592,0.0,0.0,274877906944.0,0.0005655924011193416,33554432,2.097152e-05,0.0,0.00201326592,0.0,0.00201326592,MTE2_GM,True,,访存Bound(GM),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_v3,32,1,187,1,1,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)",33685504.0,0.0,2.105344e-05,0.0,2.105344e-05,0.0,0.0,4294967296.0,8.837381267489712e-06,33554432,6.452775384615385e-06,0.0,2.105344e-05,0.0,2.105344e-05,MTE2_GM,True,,访存Bound(GM),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_v3,32,1,187,12,1,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",352321536.0,0.0,0.00022020096,0.0,0.00022020096,0.0,0.0,549755813888.0,0.0011311848022386832,1073741824,0.00067108864,0.0,0.0011311848022386832,0.0,0.0011311848022386832,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_v3,32,1,745,1,1,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)",134610944.0,0.0,8.413184e-05,0.0,8.413184e-05,0.0,0.0,17179869184.0,3.534952506995885e-05,134217728,8.388608e-05,0.0,8.413184e-05,0.0,8.413184e-05,MTE2_GM,True,,访存Bound(GM),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_v3,32,1,745,6,1,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)",574619648.0,0.0,0.00035913728,0.0,0.00035913728,0.0,0.0,549755813888.0,0.0011311848022386832,2147483648,0.00134217728,0.0,0.00134217728,0.0,0.00134217728,FIXPIPE,True,,写出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) +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_v3,32,1,187,47,1,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= 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_v3,32,1,187,1,1,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= 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_v3,32,1,745,47,1,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",3288334336.0,0.0,0.00205520896,0.0,0.00205520896,0.0,0.0,8796093022208.0,0.01809895683581893,68719476736,0.04294967296,0.0,0.04294967296,0.0,0.04294967296,FIXPIPE,True,,写出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_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_v3,32,1,187,47,1,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",603979776000.0,0.0,0.37748736,0.0,0.37748736,0.0,0.0,52776558133248.0,0.10859374101491358,34359738368,0.02147483648,0.0,0.37748736,0.0,0.37748736,MTE2_GM,True,,访存Bound(GM),"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_v3,32,1,745,47,1,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)",812822560768.0,0.0,0.50801410048,0.0,0.50801410048,0.0,0.0,140737488355328.0,0.2895833093731029,17179869184,0.01073741824,0.0,0.50801410048,0.0,0.50801410048,MTE2_GM,True,,访存Bound(GM),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",786432.0,0.0,1.572864e-05,0.0,1.572864e-05,0.0,0.0,100663296.0,6.628035950617284e-06,0.0,0.0,2.3655235431235433e-07,1.572864e-05,2.3655235431235433e-07,1.5965192354312353e-05,MTE2_GM,True,,访存Bound(GM),"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_v3,32,1,6,41,1,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",77980499968.0,0.0,0.04873781248,0.0,0.04873781248,0.0,0.0,6734508720128.0,0.013857013827423869,939524096,0.00058720256,0.0,0.04873781248,0.0,0.04873781248,MTE2_GM,True,,访存Bound(GM),"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_v3,32,1,47,47,1,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",353261060096.0,0.0,0.22078816256,0.0,0.22078816256,0.0,0.0,30786325577728.0,0.06334634892536625,4294967296,0.00268435456,0.0,0.22078816256,0.0,0.22078816256,MTE2_GM,True,,访存Bound(GM),"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_v3,32,1,24,24,1,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",16777216.0,0.0,1.048576e-05,0.0,1.048576e-05,0.0,0.0,34359738368.0,7.06990501399177e-05,268435456,0.00016777216,0.0,0.00016777216,0.0,0.00016777216,FIXPIPE,True,,写出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) +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_v3,32,1,47,47,1,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",1413044240384.0,0.0,0.88315265024,0.0,0.88315265024,0.0,0.0,123145302310912.0,0.253385395701465,17179869184,0.01073741824,0.0,0.88315265024,0.0,0.88315265024,MTE2_GM,True,,访存Bound(GM),"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-07,0.0,0.0,268435456.0,1.985939393939394e-05,536870912,0.00033554432,0.0,0.00033554432,0.0,0.00033554432,FIXPIPE,True,,写出Bound,"K=1逐元素乘, 走AIV向量通路"