AI TOPS of Thor-U measured based on CUTLASS

AI & Data Science Computer Vision & Image Processing
, ,
1

DRIVE OS Version: 7.0.4

Issue Description: s8 vs u8 Performance Gap

=============================
Problem ID: 1

    Provider: CUTLASS

OperationKind: gemm
Operation: cutlass_tensorop_i16832gemm_u8_256x128_64x3_tn_align16

      Status: Success
Verification: ON
 Disposition: Passed

reference_device: Passed
cuBLAS: Not run
cuDNN: Not run

   Arguments: --gemm_kind=universal --m=8192 --n=8192 --k=8192 --A=u8:row --B=u8:column --C=s32:column --D=s32:column  \
              --alpha=1 --beta=0 --split_k_mode=serial --split_k_slices=1 --batch_count=1 --raster_order=heuristic  \
              --runtime_input_datatype_a=invalid --runtime_input_datatype_b=invalid --use_pdl=false --enable_sm90_mixed_dtype_shuffle_test=false  \
              --swizzle_size=1 --op_class=tensorop --accum=s32 --cta_m=256 --cta_n=128 --cta_k=64 --cluster_m=1 --cluster_n=1  \
              --cluster_k=1 --cluster_m_fallback=1 --cluster_n_fallback=1 --cluster_k_fallback=1 --stages=3 --warps_m=4  \
              --warps_n=2 --warps_k=1 --inst_m=16 --inst_n=8 --inst_k=32 --min_cc=80 --max_cc=1024

       Bytes: 402653184  bytes
       FLOPs: 1099645845504  flops
       FLOPs/Byte: 2731

     Runtime: 14.102  ms
      Memory: 26.5919 GiB/s

        Math: 77977.8 GFLOP/s

=============================