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

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
@@ -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_fused,A1,1,8,8192,1101.4436329998505,64,0.011331194467560951,4800,97.32531200143696,0.0018739043362378583,16.0625,64.0,114688.0,2.0
composite_fused,A1,1,8,16384,2178.44091796638,64,0.012139279878164511,9920,208.55424000307917,0.0018875884886695197,32.0625,64.0,229376.0,4.0
composite_fused,A1,1,8,32768,4335.060767847123,64,0.012542561892233649,20160,431.01209600543973,0.0018933990639481287,64.0625,64.0,458752.0,8.0
composite_fused,A1,1,8,65536,8649.804197613514,64,0.012743513431742019,40640,875.9278079059123,0.0018959966752224023,128.0625,64.0,917504.0,16.0
composite_fused,A2,2,4,8192,1093.9720835019473,32,0.01853321150177446,2400,96.40870400077105,0.0037734052470386023,16.0625,64.0,49152.0,4.0
composite_fused,A2,2,4,16384,2175.4760434340433,32,0.019695389489835093,4960,206.59008000165224,0.00378032202414797,32.0625,64.0,98304.0,8.0
composite_fused,A2,2,4,32768,4338.482933349601,32,0.020281493171481216,10080,426.9528320015669,0.003783811127574436,64.0625,64.0,196608.0,16.0
composite_fused,A2,2,4,65536,8664.499802991075,32,0.020575802877008553,20320,867.678335950613,0.0037855618611332994,128.0625,64.0,393216.0,32.0
composite_fused,A4,4,2,8192,1102.9720360028073,16,0.03256574312686088,1200,92.28038400042057,0.007485230568419403,16.0625,64.0,16384.0,8.0
composite_fused,A4,4,2,16384,2196.357595426575,16,0.03449854256839416,2480,197.74368000090124,0.007488762319145705,32.0625,64.0,32768.0,16.0
composite_fused,A4,4,2,32768,4383.130075368471,16,0.03547127219906801,5040,408.6702720000148,0.00749053745507198,64.0625,64.0,65536.0,32.0
composite_fused,A4,4,2,65536,8756.675034884938,16,0.03595923415220853,10160,830.5234559737444,0.007491427937962982,128.0625,64.0,131072.0,64.0
composite_fused,B,8,1,8192,1125.1019960018205,8,0.12366810519999533,712,121.6138560003899,0.014676002761240575,16.0625,64.0,0.0,16.0
composite_fused,B,8,1,16384,2241.8354359431773,8,0.13192705729555512,1480,260.6011200008355,0.0146736907948643,32.0625,64.0,0.0,32.0
composite_fused,B,8,1,32768,4475.302315825972,8,0.1360796989728368,3016,538.575647996068,0.014672528326811126,64.0625,64.0,0.0,64.0
composite_fused,B,8,1,65536,8942.236075603707,8,0.13816184916758104,6088,1094.5247039788662,0.014671945460927953,128.0625,64.0,0.0,128.0
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_fused A1 1 8 8192 1101.4436329998505 64 0.011331194467560951 4800 97.32531200143696 0.0018739043362378583 16.0625 64.0 114688.0 2.0
3 composite_fused A1 1 8 16384 2178.44091796638 64 0.012139279878164511 9920 208.55424000307917 0.0018875884886695197 32.0625 64.0 229376.0 4.0
4 composite_fused A1 1 8 32768 4335.060767847123 64 0.012542561892233649 20160 431.01209600543973 0.0018933990639481287 64.0625 64.0 458752.0 8.0
5 composite_fused A1 1 8 65536 8649.804197613514 64 0.012743513431742019 40640 875.9278079059123 0.0018959966752224023 128.0625 64.0 917504.0 16.0
6 composite_fused A2 2 4 8192 1093.9720835019473 32 0.01853321150177446 2400 96.40870400077105 0.0037734052470386023 16.0625 64.0 49152.0 4.0
7 composite_fused A2 2 4 16384 2175.4760434340433 32 0.019695389489835093 4960 206.59008000165224 0.00378032202414797 32.0625 64.0 98304.0 8.0
8 composite_fused A2 2 4 32768 4338.482933349601 32 0.020281493171481216 10080 426.9528320015669 0.003783811127574436 64.0625 64.0 196608.0 16.0
9 composite_fused A2 2 4 65536 8664.499802991075 32 0.020575802877008553 20320 867.678335950613 0.0037855618611332994 128.0625 64.0 393216.0 32.0
10 composite_fused A4 4 2 8192 1102.9720360028073 16 0.03256574312686088 1200 92.28038400042057 0.007485230568419403 16.0625 64.0 16384.0 8.0
11 composite_fused A4 4 2 16384 2196.357595426575 16 0.03449854256839416 2480 197.74368000090124 0.007488762319145705 32.0625 64.0 32768.0 16.0
12 composite_fused A4 4 2 32768 4383.130075368471 16 0.03547127219906801 5040 408.6702720000148 0.00749053745507198 64.0625 64.0 65536.0 32.0
13 composite_fused A4 4 2 65536 8756.675034884938 16 0.03595923415220853 10160 830.5234559737444 0.007491427937962982 128.0625 64.0 131072.0 64.0
14 composite_fused B 8 1 8192 1125.1019960018205 8 0.12366810519999533 712 121.6138560003899 0.014676002761240575 16.0625 64.0 0.0 16.0
15 composite_fused B 8 1 16384 2241.8354359431773 8 0.13192705729555512 1480 260.6011200008355 0.0146736907948643 32.0625 64.0 0.0 32.0
16 composite_fused B 8 1 32768 4475.302315825972 8 0.1360796989728368 3016 538.575647996068 0.014672528326811126 64.0625 64.0 0.0 64.0
17 composite_fused B 8 1 65536 8942.236075603707 8 0.13816184916758104 6088 1094.5247039788662 0.014671945460927953 128.0625 64.0 0.0 128.0