## ncu_5120x12288.ncu-rep
served_M8    void exl3_gemm_kernel<4, 0, 2, 16, 32, 256, 4, 3> dur=  40.90us dram= 78.7% (  773GB/s rd=  31.6MB) sm= 38.2% issue= 38.2% tensor= 16.1% alu= 36.2% fma= 16.2% occ= 33.1/  33% l2hit= 16.5% regs=128 smem= 91.0K grid=128x512 bankcf=70863 stalls=barrier:3.2,math_pipe_throttle:1.6,wait:1.1,not_selected:1.1
mma_M8       void ag_mma_kernel<4, 2, 1, 1, 1>(const void *, const unsign dur=  42.53us dram= 75.8% (  744GB/s rd=  31.6MB) sm= 43.0% issue= 43.0% tensor=  7.3% alu= 41.0% fma= 17.1% occ= 61.1/  67% l2hit= 33.2% regs=64 smem=  9.0K grid=960x256 bankcf=522240 stalls=long_scoreboard:9.2,wait:1.6,not_selected:1.3,selected:1.0
up_gemv_M8   void exl3_gemv_kernel<4, 0, 2, 1, 1, 0> dur=  40.19us dram= 80.1% (  786GB/s rd=  31.6MB) sm= 28.5% issue= 28.5% tensor= 15.1% alu= 22.7% fma= 15.2% occ= 24.8/  50% l2hit= 27.9% regs=80 smem= 17.0K grid=192x256 bankcf=73728 stalls=long_scoreboard:6.0,selected:1.0,wait:0.8,barrier:0.7
simt_M8      void ag_gemv_kernel<Exl3GemvLoader<4, 2, 8>, 4, 0, 8, 4>(con dur=  64.35us dram= 50.0% (  491GB/s rd=  31.6MB) sm= 89.3% issue= 62.4% tensor=  0.0% alu= 21.0% fma= 37.9% occ= 52.4/  67% l2hit= 24.9% regs=64 smem= 21.0K grid=768x256 bankcf=7570 stalls=mio_throttle:2.8,not_selected:2.2,barrier:1.2,selected:1.0
simt_M8      void ag_gemv_reduce_kernel<Exl3GemvLoader<4, 2, 8>, 8> dur=   6.14us dram= 54.0% (  527GB/s rd=   3.2MB) sm=  8.2% issue=  8.2% tensor=  0.0% alu=  8.1% fma=  3.6% occ= 53.9/  83% l2hit= 25.4% regs=44 smem=  5.0K grid=768x256 bankcf=0 stalls=long_scoreboard:34.3,imc_miss:10.0,barrier:6.8,wait:2.2
served_M16   void exl3_gemm_kernel<4, 0, 2, 16, 32, 256, 4, 3> dur=  41.82us dram= 77.2% (  758GB/s rd=  31.7MB) sm= 36.0% issue= 36.0% tensor= 15.2% alu= 34.1% fma= 15.3% occ= 33.0/  33% l2hit= 27.7% regs=128 smem= 91.0K grid=128x512 bankcf=141769 stalls=barrier:3.3,math_pipe_throttle:1.6,wait:1.2,not_selected:1.1
mma_M16      void ag_mma_prestage_kernel<2, 1>(const void *, const __half dur=   2.37us dram=  8.1% (   77GB/s rd=   0.2MB) sm=  4.7% issue=  4.7% tensor=  0.0% alu= 10.7% fma=  5.0% occ= 15.9/ 100% l2hit= 60.7% regs=24 smem=  1.0K grid=80x256 bankcf=0 stalls=long_scoreboard:5.9,imc_miss:3.5,wait:1.4,selected:1.0
mma_M16      void ag_mma_kernel<4, 2, 2, 1, 1>(const void *, const unsign dur=  43.39us dram= 74.4% (  731GB/s rd=  31.7MB) sm= 32.9% issue= 32.9% tensor= 15.7% alu= 34.1% fma= 13.8% occ= 60.4/  67% l2hit= 51.1% regs=64 smem= 17.0K grid=960x256 bankcf=207583 stalls=long_scoreboard:10.8,wait:1.6,math_pipe_throttle:1.4,barrier:1.2
served_M32   void exl3_gemm_kernel<4, 0, 2, 16, 32, 256, 4, 3> dur=  71.10us dram= 45.6% (  448GB/s rd=  31.9MB) sm= 42.0% issue= 42.0% tensor= 16.9% alu= 37.9% fma= 17.1% occ= 33.3/  33% l2hit= 63.4% regs=128 smem= 91.0K grid=128x512 bankcf=283127 stalls=barrier:2.8,math_pipe_throttle:1.6,wait:1.2,not_selected:1.1
mma_M32      void ag_mma_prestage_kernel<4, 1>(const void *, const __half dur=   2.50us dram= 14.4% (  139GB/s rd=   0.3MB) sm=  8.8% issue=  8.8% tensor=  0.0% alu= 13.0% fma=  6.1% occ= 20.4/ 100% l2hit= 59.6% regs=24 smem=  1.0K grid=160x256 bankcf=0 stalls=long_scoreboard:6.1,imc_miss:5.1,wait:1.4,selected:1.0
mma_M32      void ag_mma_kernel<4, 2, 4, 1, 1>(const void *, const unsign dur=  48.54us dram= 66.9% (  657GB/s rd=  31.9MB) sm= 33.3% issue= 33.3% tensor= 27.5% alu= 31.8% fma= 12.8% occ= 43.2/  50% l2hit= 67.2% regs=64 smem= 33.0K grid=960x256 bankcf=442687 stalls=long_scoreboard:4.9,math_pipe_throttle:3.0,wait:1.7,barrier:1.0
