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_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
A1,1,8,8192,1103.359903999566,64,0.0019006962210579498,5248,0.001870649814732448,16.0625,64.0,114688.0,2.0
A1,1,8,16384,2182.457823968016,64,0.0019218259129421755,10880,0.0018841143021603984,32.0625,64.0,229376.0,4.0
A1,1,8,32768,4343.2822238495155,64,0.0019313983221991736,22144,0.0018898150239762977,64.0625,64.0,458752.0,8.0
A1,1,8,65536,8666.440783650422,64,0.001935883071136998,44672,0.0018923570136126979,128.0625,64.0,917504.0,16.0
A2,2,4,8192,1097.2535885006619,32,0.003822547535007557,2624,0.0037621203004135906,16.0625,64.0,49152.0,4.0
A2,2,4,16384,2179.78425743804,32,0.003848366172648072,5440,0.003772850442394648,32.0625,64.0,98304.0,8.0
A2,2,4,32768,4344.834905351148,32,0.003861416225357031,11072,0.003778279349528763,64.0625,64.0,196608.0,16.0
A2,2,4,65536,8674.946611121853,32,0.003867969856656271,22336,0.003781003096658628,128.0625,64.0,393216.0,32.0
A4,4,2,8192,1103.675383502932,16,0.007600611670231015,1312,0.007480460399321815,16.0625,64.0,16384.0,8.0
A4,4,2,16384,2197.0616234262543,16,0.00763620638634706,2720,0.007486362614786297,32.0625,64.0,32768.0,16.0
A4,4,2,32768,4383.834103368879,16,0.007654129058897454,5536,0.007489334501679554,64.0625,64.0,65536.0,32.0
A4,4,2,65536,8757.379062883949,16,0.007663121981838932,11168,0.007490825682997995,128.0625,64.0,131072.0,64.0
B,8,1,8192,1125.9457520018113,8,0.014900554462921552,656,0.01466500492643045,16.0625,64.0,0.0,16.0
B,8,1,16384,2242.543191943168,8,0.014962669223294344,1360,0.014669059716747552,32.0625,64.0,0.0,32.0
B,8,1,32768,4475.650071825993,8,0.014994216018466134,2768,0.014671388277951352,64.0625,64.0,0.0,64.0
B,8,1,65536,8942.79183160376,8,0.015008481750139946,5584,0.014671033662702533,128.0625,64.0,0.0,128.0
A1,1,8,8192,1100.677128999906,64,0.0019053289513740923,5248,0.001875209310359147,16.0625,64.0,114688.0,2.0
A1,1,8,16384,2177.674413966317,64,0.0019260473343055045,10880,0.0018882528874050511,32.0625,64.0,229376.0,4.0
A1,1,8,32768,4334.294263847072,64,0.001935403433484189,22144,0.0018937339046091134,64.0625,64.0,458752.0,8.0
A1,1,8,65536,8649.037693613021,64,0.0019397783423315907,44672,0.0018961647042087428,128.0625,64.0,917504.0,16.0
A2,2,4,8192,1093.6804565019731,32,0.003835036070239803,2624,0.003774411415563731,16.0625,64.0,49152.0,4.0
A2,2,4,16384,2175.2205604341793,32,0.0038564401939640384,5440,0.0037807660287830624,32.0625,64.0,98304.0,8.0
A2,2,4,32768,4338.30076834928,32,0.003867232102121915,11072,0.003783970009586559,64.0625,64.0,196608.0,16.0
A2,2,4,65536,8664.461183990821,32,0.003872650738157816,22336,0.0037855787340364574,128.0625,64.0,393216.0,32.0
A4,4,2,8192,1103.915289502884,16,0.0075989598837576024,1312,0.007478834724463186,16.0625,64.0,16384.0,8.0
A4,4,2,16384,2197.52387042685,16,0.007634600117789289,2720,0.007484787865719574,32.0625,64.0,32768.0,16.0
A4,4,2,32768,4384.131109368463,16,0.0076536105246211355,5536,0.007488827131524694,64.0625,64.0,65536.0,32.0
A4,4,2,65536,8757.668308885037,16,0.007662868886230499,11168,0.007490578277947104,128.0625,64.0,131072.0,64.0
B,8,1,8192,1125.2657520018113,8,0.014909558893223249,656,0.014673867013748253,16.0625,64.0,0.0,16.0
B,8,1,16384,2241.999191943168,8,0.01496629977413786,1360,0.014672619026008048,32.0625,64.0,0.0,32.0
B,8,1,32768,4475.466071825993,8,0.014994832476216706,2768,0.014671991463273241,64.0625,64.0,0.0,64.0
B,8,1,65536,8942.39983160376,8,0.01500913966355881,5584,0.014671676783710771,128.0625,64.0,0.0,128.0
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 1103.359903999566 1100.677128999906 64 0.0019006962210579498 0.0019053289513740923 5248 0.001870649814732448 0.001875209310359147 16.0625 64.0 114688.0 2.0
3 A1 1 8 16384 2182.457823968016 2177.674413966317 64 0.0019218259129421755 0.0019260473343055045 10880 0.0018841143021603984 0.0018882528874050511 32.0625 64.0 229376.0 4.0
4 A1 1 8 32768 4343.2822238495155 4334.294263847072 64 0.0019313983221991736 0.001935403433484189 22144 0.0018898150239762977 0.0018937339046091134 64.0625 64.0 458752.0 8.0
5 A1 1 8 65536 8666.440783650422 8649.037693613021 64 0.001935883071136998 0.0019397783423315907 44672 0.0018923570136126979 0.0018961647042087428 128.0625 64.0 917504.0 16.0
6 A2 2 4 8192 1097.2535885006619 1093.6804565019731 32 0.003822547535007557 0.003835036070239803 2624 0.0037621203004135906 0.003774411415563731 16.0625 64.0 49152.0 4.0
7 A2 2 4 16384 2179.78425743804 2175.2205604341793 32 0.003848366172648072 0.0038564401939640384 5440 0.003772850442394648 0.0037807660287830624 32.0625 64.0 98304.0 8.0
8 A2 2 4 32768 4344.834905351148 4338.30076834928 32 0.003861416225357031 0.003867232102121915 11072 0.003778279349528763 0.003783970009586559 64.0625 64.0 196608.0 16.0
9 A2 2 4 65536 8674.946611121853 8664.461183990821 32 0.003867969856656271 0.003872650738157816 22336 0.003781003096658628 0.0037855787340364574 128.0625 64.0 393216.0 32.0
10 A4 4 2 8192 1103.675383502932 1103.915289502884 16 0.007600611670231015 0.0075989598837576024 1312 0.007480460399321815 0.007478834724463186 16.0625 64.0 16384.0 8.0
11 A4 4 2 16384 2197.0616234262543 2197.52387042685 16 0.00763620638634706 0.007634600117789289 2720 0.007486362614786297 0.007484787865719574 32.0625 64.0 32768.0 16.0
12 A4 4 2 32768 4383.834103368879 4384.131109368463 16 0.007654129058897454 0.0076536105246211355 5536 0.007489334501679554 0.007488827131524694 64.0625 64.0 65536.0 32.0
13 A4 4 2 65536 8757.379062883949 8757.668308885037 16 0.007663121981838932 0.007662868886230499 11168 0.007490825682997995 0.007490578277947104 128.0625 64.0 131072.0 64.0
14 B 8 1 8192 1125.9457520018113 1125.2657520018113 8 0.014900554462921552 0.014909558893223249 656 0.01466500492643045 0.014673867013748253 16.0625 64.0 0.0 16.0
15 B 8 1 16384 2242.543191943168 2241.999191943168 8 0.014962669223294344 0.01496629977413786 1360 0.014669059716747552 0.014672619026008048 32.0625 64.0 0.0 32.0
16 B 8 1 32768 4475.650071825993 4475.466071825993 8 0.014994216018466134 0.014994832476216706 2768 0.014671388277951352 0.014671991463273241 64.0625 64.0 0.0 64.0
17 B 8 1 65536 8942.79183160376 8942.39983160376 8 0.015008481750139946 0.01500913966355881 5584 0.014671033662702533 0.014671676783710771 128.0625 64.0 0.0 128.0