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

This commit is contained in:
2026-09-04 11:09:49 +08:00
parent 5051e00fa0
commit f4b23d9f05
4 changed files with 147 additions and 11 deletions

View File

@@ -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
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
2 to_matmul_demo 1 1 2048 2048 2048 bf16 bf16 bf16 0 0 0 0
3 special_k0_demo 128 128 256 256 0 bf16 bf16 bf16 0 0 0 0
4 special_k1_demo 128 128 256 256 1 bf16 bf16 bf16 0 0 0 0
5 merge_demo_k_trunc 2048 2048 32 32 256 bf16 bf16 bf16 0 0 0 0
6 merge_iter_arbitrate 128 128 64 64 512 bf16 bf16 bf16 0 0 0 0
7 iter_demo_form_b 128 128 64 64 256 bf16 bf16 bf16 0 0 0 0
8 iter_demo_form_d 64 64 64 64 8192 bf16 bf16 bf16 0 0 0 0
9 streamk_demo 4 4 128 128 10240 bf16 bf16 bf16 0 0 0 0
10 asw_demo_full 2 2 8192 8192 1024 bf16 bf16 bf16 0 0 0 0
11 asw_demo_reduce_core 16 16 256 256 128 bf16 bf16 bf16 0 0 0 0
12 b4_m1_n128_k256 4 4 1 128 256 bf16 bf16 bf16 0 0 0 1 0
13 b8_m2_n192_k128 8 8 2 192 128 bf16 bf16 bf16 0 0 0 1 0
14 b16_m4_n256_k192 16 16 4 256 192 bf16 bf16 bf16 0 0 0 1 0
15 b32_m8_n128_k256 32 32 8 128 256 bf16 bf16 bf16 0 0 0 1 0
16 b64_m16_n256_k512 64 64 16 256 512 bf16 bf16 bf16 0 0 0 1 0
17 b128_m8_n192_k256 128 128 8 192 256 bf16 bf16 bf16 0 0 0 1 0
18 b32_m16_n8192_k7168 32 32 16 8192 7168 bf16 bf16 bf16 0 0 0 1 0
19 b4_m1_n8192_k8192 4 4 1 8192 8192 bf16 bf16 bf16 0 0 0 1 0
20 b16_m2_n4096_k7168 16 16 2 4096 7168 bf16 bf16 bf16 0 0 0 1 0
21 b32_m64_n64_k7168 32 32 64 64 7168 bf16 bf16 bf16 0 0 0 1 0
22 b64_m1024_n1024_k7168 64 64 1024 1024 7168 bf16 bf16 bf16 0 0 0 1 0
23 b128_m2048_n2048_k1536 128 128 2048 2048 1536 bf16 bf16 bf16 0 0 0 1 0
24 b64_m1024_n8192_k2048 64 64 1024 8192 2048 bf16 bf16 bf16 0 0 0 1 0
25 b32_m1024_n1024_k512 32 32 1024 1024 512 bf16 bf16 bf16 0 0 0 1 0
26 b128_m4096_n4096_k8192 128 128 4096 4096 8192 bf16 bf16 bf16 0 0 0 1 0
27 b32_m8192_n4096_k7168 32 32 8192 4096 7168 bf16 bf16 bf16 0 0 0 1 0
28 b32_m2048_n2048_k8192 32 32 2048 2048 8192 bf16 bf16 bf16 0 0 0 1 0
29 b64_m4096_n2048_k128 64 64 4096 2048 128 bf16 bf16 bf16 0 0 0 1 0
30 b16_m1024_n1024_k8192 16 16 1024 1024 8192 bf16 bf16 bf16 0 0 0 1 0
31 b4_m32768_n128_k128 4 4 32768 128 128 bf16 bf16 bf16 0 0 0 1 0
32 b8_m32768_n2048_k512 8 8 32768 2048 512 bf16 bf16 bf16 0 0 0 1 0
33 b4_m131072_n128_k128 4 4 131072 128 128 bf16 bf16 bf16 0 0 0 1 0
34 b8_m131072_n1024_k256 8 8 131072 1024 256 bf16 bf16 bf16 0 0 0 1 0
35 b16_m32768_n8192_k7168 16 16 32768 8192 7168 bf16 bf16 bf16 0 0 0 1 0
36 b4_m32768_n128_k8192 4 4 32768 128 8192 bf16 bf16 bf16 0 0 0 1 0
37 b32_m131072_n8192_k128 32 32 131072 8192 128 bf16 bf16 bf16 0 0 0 1 0
38 b64_m32768_n8192_k1536 64 64 32768 8192 1536 bf16 bf16 bf16 0 0 0 1 0
39 b8_m131072_n8192_k8192 8 8 131072 8192 8192 bf16 bf16 bf16 0 0 0 1 0
40 b8_m16_n7168_k1536 8 8 16 7168 1536 bf16 bf16 bf16 0 0 0 1 0
41 b64_m1024_n7168_k7168 64 64 1024 7168 7168 bf16 bf16 bf16 0 0 0 1 0
42 b32_m8192_n8192_k7168 32 32 8192 8192 7168 bf16 bf16 bf16 0 0 0 1 0
43 b8_m4096_n4096_k128 8 8 4096 4096 128 bf16 bf16 bf16 0 0 0 1 0
44 b128_m8192_n8192_k7168 128 128 8192 8192 7168 bf16 bf16 bf16 0 0 0 1 0
45 special_k1_b64 64 64 8192 512 1 bf16 bf16 bf16 0 0 0 1 0