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_decode_sweep.csv
+16 -16
View File
@@ -1,17 +1,17 @@
mode,kv_per_cube,C,S_kv,wall_us,n_pe,gemm_util,math_count,hbm_bw_util,hbm_read_mb,hbm_write_kb,ipcq_kb,kv_cache_per_cube_mb
A1,1,8,8192,149.2685345000007,64,0.001756190618994587,656,0.013780533230866485,16.0625,8.0,57.75,2.0
A1,1,8,16384,282.2252665000025,64,0.0018576933472394743,1360,0.014545118695104373,32.0625,8.0,57.75,4.0
A1,1,8,32768,548.138730500006,64,0.0019129755692392889,2768,0.014961540835691614,64.0625,8.0,57.75,8.0
A1,1,8,65536,1080.073058500367,64,0.0019416760593127277,5584,0.01517767698303756,128.0625,8.0,57.75,16.0
A2,2,4,8192,142.16883275000066,32,0.0036877843748065785,656,0.028881154333033524,16.03125,8.0,24.75,4.0
A2,2,4,16384,277.0102967500018,32,0.0037853322143696724,1360,0.029609007665885423,32.03125,8.0,24.75,8.0
A2,2,4,32768,546.8006247504073,32,0.0038353138330044275,2768,0.02998167752182655,64.03125,8.0,24.75,16.0
A2,2,4,65536,1087.0962007518285,32,0.003858263874988177,5584,0.03015188534127058,128.03125,8.0,24.75,32.0
A4,4,2,8192,142.21417550000066,16,0.007373217165681769,656,0.05768763888097753,16.015625,8.0,8.25,8.0
A4,4,2,16384,280.8788035001758,16,0.007466394665122732,1360,0.058373931374247456,32.015625,8.0,8.25,16.0
A4,4,2,32768,558.5655195010398,16,0.007509063580845671,2768,0.058686042828569145,64.015625,8.0,8.25,32.0
A4,4,2,65536,1114.319951501857,16,0.007528006645388841,5584,0.05882332081702009,128.015625,8.0,8.25,64.0
B,8,1,8192,147.93485600006025,8,0.014176185766516818,656,0.11085960701508589,16.0078125,8.0,0.0,16.0
B,8,1,16384,294.3171420004266,8,0.014250967413897551,1360,0.1113900460475132,32.0078125,8.0,0.0,32.0
B,8,1,32768,587.2722140010417,8,0.01428401991446495,2768,0.11162115018757507,64.0078125,8.0,0.0,64.0
B,8,1,65536,1173.1823580017838,8,0.014300603725891686,5584,0.11173710472707321,128.0078125,8.0,0.0,128.0
A1,1,8,8192,146.95153450000072,64,0.0017838806576053131,656,0.013997812319543966,16.0625,8.0,57.75,2.0
A1,1,8,16384,279.3832665000025,64,0.0018765905580817512,1360,0.014693077546933053,32.0625,8.0,57.75,4.0
A1,1,8,32768,544.246730500006,64,0.0019266555796063503,2768,0.015068533333155061,64.0625,8.0,57.75,8.0
A1,1,8,65536,1074.081058500367,64,0.0019525081309290412,5584,0.01526234902874828,128.0625,8.0,57.75,16.0
A2,2,4,8192,139.87083275000066,32,0.003748372621310069,656,0.029355655637933423,16.03125,8.0,24.75,4.0
A2,2,4,16384,273.6622967500018,32,0.0038316421825465713,1360,0.029971245938539923,32.03125,8.0,24.75,8.0
A2,2,4,32768,541.3526247504072,32,0.0038739112070761647,2768,0.030283403553383558,64.03125,8.0,24.75,16.0
A2,2,4,65536,1077.4482007518286,32,0.003892812663356761,5584,0.030421880121130614,128.03125,8.0,24.75,32.0
A4,4,2,8192,139.89951550000075,16,0.007495208230366452,656,0.05864209015076937,16.015625,8.0,8.25,8.0
A4,4,2,16384,276.4641435001754,16,0.007585620230706115,1360,0.05930606331952627,32.015625,8.0,8.25,16.0
A4,4,2,32768,549.9508595010393,16,0.007626688689616412,2768,0.059605325518975856,64.015625,8.0,8.25,32.0
A4,4,2,65536,1097.305291501857,16,0.0076447348472311214,5584,0.059735426874945555,128.015625,8.0,8.25,64.0
B,8,1,8192,144.06747100006032,8,0.014556735017573057,656,0.11383555139933797,16.0078125,8.0,0.0,16.0
B,8,1,16384,286.24975700042637,8,0.014652602831705778,1360,0.1145293548666704,32.0078125,8.0,0.0,32.0
B,8,1,32768,570.8048290010414,8,0.014696105522939606,2768,0.11484135499470417,64.0078125,8.0,0.0,64.0
B,8,1,65536,1139.9149730017834,8,0.014717953880200899,5584,0.11499805082373886,128.0078125,8.0,0.0,128.0
1 mode kv_per_cube C S_kv wall_us n_pe gemm_util math_count hbm_bw_util hbm_read_mb hbm_write_kb ipcq_kb kv_cache_per_cube_mb
2 A1 1 8 8192 149.2685345000007 146.95153450000072 64 0.001756190618994587 0.0017838806576053131 656 0.013780533230866485 0.013997812319543966 16.0625 8.0 57.75 2.0
3 A1 1 8 16384 282.2252665000025 279.3832665000025 64 0.0018576933472394743 0.0018765905580817512 1360 0.014545118695104373 0.014693077546933053 32.0625 8.0 57.75 4.0
4 A1 1 8 32768 548.138730500006 544.246730500006 64 0.0019129755692392889 0.0019266555796063503 2768 0.014961540835691614 0.015068533333155061 64.0625 8.0 57.75 8.0
5 A1 1 8 65536 1080.073058500367 1074.081058500367 64 0.0019416760593127277 0.0019525081309290412 5584 0.01517767698303756 0.01526234902874828 128.0625 8.0 57.75 16.0
6 A2 2 4 8192 142.16883275000066 139.87083275000066 32 0.0036877843748065785 0.003748372621310069 656 0.028881154333033524 0.029355655637933423 16.03125 8.0 24.75 4.0
7 A2 2 4 16384 277.0102967500018 273.6622967500018 32 0.0037853322143696724 0.0038316421825465713 1360 0.029609007665885423 0.029971245938539923 32.03125 8.0 24.75 8.0
8 A2 2 4 32768 546.8006247504073 541.3526247504072 32 0.0038353138330044275 0.0038739112070761647 2768 0.02998167752182655 0.030283403553383558 64.03125 8.0 24.75 16.0
9 A2 2 4 65536 1087.0962007518285 1077.4482007518286 32 0.003858263874988177 0.003892812663356761 5584 0.03015188534127058 0.030421880121130614 128.03125 8.0 24.75 32.0
10 A4 4 2 8192 142.21417550000066 139.89951550000075 16 0.007373217165681769 0.007495208230366452 656 0.05768763888097753 0.05864209015076937 16.015625 8.0 8.25 8.0
11 A4 4 2 16384 280.8788035001758 276.4641435001754 16 0.007466394665122732 0.007585620230706115 1360 0.058373931374247456 0.05930606331952627 32.015625 8.0 8.25 16.0
12 A4 4 2 32768 558.5655195010398 549.9508595010393 16 0.007509063580845671 0.007626688689616412 2768 0.058686042828569145 0.059605325518975856 64.015625 8.0 8.25 32.0
13 A4 4 2 65536 1114.319951501857 1097.305291501857 16 0.007528006645388841 0.0076447348472311214 5584 0.05882332081702009 0.059735426874945555 128.015625 8.0 8.25 64.0
14 B 8 1 8192 147.93485600006025 144.06747100006032 8 0.014176185766516818 0.014556735017573057 656 0.11085960701508589 0.11383555139933797 16.0078125 8.0 0.0 16.0
15 B 8 1 16384 294.3171420004266 286.24975700042637 8 0.014250967413897551 0.014652602831705778 1360 0.1113900460475132 0.1145293548666704 32.0078125 8.0 0.0 32.0
16 B 8 1 32768 587.2722140010417 570.8048290010414 8 0.01428401991446495 0.014696105522939606 2768 0.11162115018757507 0.11484135499470417 64.0078125 8.0 0.0 64.0
17 B 8 1 65536 1173.1823580017838 1139.9149730017834 8 0.014300603725891686 0.014717953880200899 5584 0.11173710472707321 0.11499805082373886 128.0078125 8.0 0.0 128.0