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,A1,1,8,8192,35.53158299944201,64,0.3512557265116541,4800,97.32531200143696,0.0290446,16.0625,64.0,114688.0,2.0 composite_fused,A1,1,8,16384,63.02314799463935,64,0.4196030322618738,9920,208.55424000307917,0.0326229,32.0625,64.0,229376.0,4.0 composite_fused,A1,1,8,32768,118.00299802135117,64,0.4607744625054221,20160,431.01209600543973,0.0347788,64.0625,64.0,458752.0,8.0 composite_fused,A1,1,8,65536,227.95666800683736,64,0.4835519703723695,40640,875.9278079059123,0.0359717,128.0625,64.0,917504.0,16.0 composite_fused,A2,2,4,8192,35.27508350025257,32,0.5747630902258046,2400,96.40870400077105,0.0585116,16.0625,64.0,49152.0,4.0 composite_fused,A2,2,4,16384,65.58160349091561,32,0.653336388872743,4960,206.59008000165224,0.0627005,32.0625,64.0,98304.0,8.0 composite_fused,A2,2,4,32768,126.19361352364719,32,0.69726913692688,10080,426.9528320015669,0.0650429,64.0625,64.0,196608.0,16.0 composite_fused,A2,2,4,65536,247.42072338639758,32,0.7205501525262498,20320,867.678335950613,0.0662839,128.0625,64.0,393216.0,32.0 composite_fused,A4,4,2,8192,45.62825600103196,16,0.7872118539828873,1200,92.28038400042057,0.0904703,16.0625,64.0,16384.0,8.0 composite_fused,A4,4,2,16384,87.81637548340065,16,0.8628360665552867,2480,197.74368000090124,0.09365,32.0625,64.0,32768.0,16.0 composite_fused,A4,4,2,32768,172.19397554247547,16,0.9029073142513345,5040,408.6702720000148,0.0953343,64.0625,64.0,65536.0,32.0 composite_fused,A4,4,2,65536,340.9491752808783,16,0.9235491703853554,10160,830.5234559737444,0.096202,128.0625,64.0,131072.0,64.0 composite_fused,B,8,1,8192,68.33786600000411,8,2.036048828365075,712,121.6138560003899,0.120811,16.0625,64.0,0.0,16.0 composite_fused,B,8,1,16384,133.87386600000133,8,2.209234414765302,1480,260.6011200008355,0.122862,32.0625,64.0,0.0,32.0 composite_fused,B,8,1,32768,264.9458659999771,8,2.2985744263323977,3016,538.575647996068,0.12392,64.0625,64.0,0.0,64.0 composite_fused,B,8,1,65536,527.0898659999762,8,2.3439567929361727,6088,1094.5247039788662,0.124457,128.0625,64.0,0.0,128.0