ywkang/kernbench2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

sweep: 6 short-context CSVs (3 variants x prefill+decode) + 6 wall/util figures

Browse Source
This commit is contained in:
eusonice
2026-06-26 15:11:01 -07:00
parent 3da116d40d
commit 3437d7e079
16 changed files with 455 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/sweeps/short_context_prefill_composite_sweep.csv
+17
View File
@@ -0,0 +1,17 @@
variant,mode,kv_per_cube,C,S_kv,wall_us,n_pe,gemm_util,math_count,math_pipeline_us,hbm_bw_util,hbm_read_mb,hbm_write_kb,ipcq_kb,kv_cache_per_cube_mb
composite,A1,1,8,8192,1101.224596999844,64,0.006144606666764116,5248,0.0,0.0018742770599413814,16.0625,64.0,114688.0,2.0
composite,A1,1,8,16384,2178.2218819663735,64,0.006212950164859459,10880,0.0,0.0018877782993750494,32.0625,64.0,229376.0,4.0
composite,A1,1,8,32768,4334.841731847132,64,0.006243911466154239,22144,0.0,0.0018934947358510517,64.0625,64.0,458752.0,8.0
composite,A1,1,8,65536,8649.585161613555,64,0.006258419909799432,44672,0.0,0.0018960446881062475,128.0625,64.0,917504.0,16.0
composite,A2,2,4,8192,1094.5704665014161,32,0.007139940496760185,2624,0.0,0.0037713423907684606,16.0625,64.0,49152.0,4.0
composite,A2,2,4,16384,2177.5659939366815,32,0.007177893135813299,5440,0.0,0.0037766938053309506,32.0625,64.0,98304.0,8.0
composite,A2,2,4,32768,4341.645937350417,32,0.007200189155116074,11072,0.0,0.0037810545209999826,64.0625,64.0,196608.0,16.0
composite,A2,2,4,65536,8671.42409207618,32,0.007210043393449057,22336,0.0,0.003782539021470782,128.0625,64.0,393216.0,32.0
composite,A4,4,2,8192,1104.2310135028845,16,0.008976672344028575,1312,0.0,0.007476696360673657,16.0625,64.0,16384.0,8.0
composite,A4,4,2,16384,2197.6415934265688,16,0.009020870400324496,2720,0.0,0.0074843869215062645,32.0625,64.0,32768.0,16.0
composite,A4,4,2,32768,4384.414073368468,16,0.00904323344692278,5536,0.0,0.007488343813013936,64.0625,64.0,65536.0,32.0
composite,A4,4,2,65536,8757.965852885032,16,0.009054449551299243,11168,0.0,0.0074903237922982055,128.0625,64.0,131072.0,64.0
composite,B,8,1,8192,1125.5021760018114,8,0.020408994750147753,656,0.0,0.014670784608037422,16.0625,64.0,0.0,16.0
composite,B,8,1,16384,2242.2356159431683,8,0.02048880843562789,1360,0.0,0.014671071927542597,32.0625,64.0,0.0,32.0
composite,B,8,1,32768,4475.702495825993,8,0.020528949826292484,2768,0.0,0.014671216431663579,64.0625,64.0,0.0,64.0
composite,B,8,1,65536,8942.63625560376,8,0.020549079566244906,5584,0.0,0.014671288896245289,128.0625,64.0,0.0,128.0
1 variant mode kv_per_cube C S_kv wall_us n_pe gemm_util math_count math_pipeline_us hbm_bw_util hbm_read_mb hbm_write_kb ipcq_kb kv_cache_per_cube_mb
2 composite A1 1 8 8192 1101.224596999844 64 0.006144606666764116 5248 0.0 0.0018742770599413814 16.0625 64.0 114688.0 2.0
3 composite A1 1 8 16384 2178.2218819663735 64 0.006212950164859459 10880 0.0 0.0018877782993750494 32.0625 64.0 229376.0 4.0
4 composite A1 1 8 32768 4334.841731847132 64 0.006243911466154239 22144 0.0 0.0018934947358510517 64.0625 64.0 458752.0 8.0
5 composite A1 1 8 65536 8649.585161613555 64 0.006258419909799432 44672 0.0 0.0018960446881062475 128.0625 64.0 917504.0 16.0
6 composite A2 2 4 8192 1094.5704665014161 32 0.007139940496760185 2624 0.0 0.0037713423907684606 16.0625 64.0 49152.0 4.0
7 composite A2 2 4 16384 2177.5659939366815 32 0.007177893135813299 5440 0.0 0.0037766938053309506 32.0625 64.0 98304.0 8.0
8 composite A2 2 4 32768 4341.645937350417 32 0.007200189155116074 11072 0.0 0.0037810545209999826 64.0625 64.0 196608.0 16.0
9 composite A2 2 4 65536 8671.42409207618 32 0.007210043393449057 22336 0.0 0.003782539021470782 128.0625 64.0 393216.0 32.0
10 composite A4 4 2 8192 1104.2310135028845 16 0.008976672344028575 1312 0.0 0.007476696360673657 16.0625 64.0 16384.0 8.0
11 composite A4 4 2 16384 2197.6415934265688 16 0.009020870400324496 2720 0.0 0.0074843869215062645 32.0625 64.0 32768.0 16.0
12 composite A4 4 2 32768 4384.414073368468 16 0.00904323344692278 5536 0.0 0.007488343813013936 64.0625 64.0 65536.0 32.0
13 composite A4 4 2 65536 8757.965852885032 16 0.009054449551299243 11168 0.0 0.0074903237922982055 128.0625 64.0 131072.0 64.0
14 composite B 8 1 8192 1125.5021760018114 8 0.020408994750147753 656 0.0 0.014670784608037422 16.0625 64.0 0.0 16.0
15 composite B 8 1 16384 2242.2356159431683 8 0.02048880843562789 1360 0.0 0.014671071927542597 32.0625 64.0 0.0 32.0
16 composite B 8 1 32768 4475.702495825993 8 0.020528949826292484 2768 0.0 0.014671216431663579 64.0625 64.0 0.0 64.0
17 composite B 8 1 65536 8942.63625560376 8 0.020549079566244906 5584 0.0 0.014671288896245289 128.0625 64.0 0.0 128.0