mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-05 14:11:29 +00:00
712e464c4e
* Suppress additional warnings for googltest. * Rename file conv_fwd_util to conv_util. * Update includes and ConvParams member access. * Formatting. * Change conv_fwd_util target to conv_util * Fix compiler errors. * Fix leftovers. Co-authored-by: Adam Osewski <aosewski@amd.com> Co-authored-by: Chao Liu <chao.liu2@amd.com>
Instructions for example_conv_xdl_bias_relu_add
Run example_conv_xdl_bias_relu_add
#arg1: verification (0=no, 1=yes)
#arg2: initialization (0=no init, 1=integer value, 2=decimal value)
#arg3: run kernel # of times (>1)
#arg4 to 18: N, K, C, Y, X, Hi, Wi, Sy, Sx, Dy, Dx, LeftPy, LeftPx, RightPy, RightPx
./bin/example_conv_xdl_bias_relu_add 0 1 5
Result (MI100 @ 1087Mhz, 133.5TFlops peak FP16)
in_n_c_hi_wi: dim 4, lengths {128, 192, 71, 71}, strides {967872, 1, 13632, 192}
wei_k_c_y_x: dim 4, lengths {256, 192, 3, 3}, strides {1728, 1, 576, 192}
out_n_k_ho_wo: dim 4, lengths {128, 256, 36, 36}, strides {331776, 1, 9216, 256}
bias_k: dim 1, lengths {256}, strides {1}
resi_n_k_ho_wo: dim 4, lengths {128, 256, 36, 36}, strides {331776, 1, 9216, 256}
launch_and_time_kernel: grid_dim {1296, 1, 1}, block_dim {256, 1, 1}
Warm up
Start running 5 times...
Perf: 1.44711 ms, 101.421 TFlops, 289.218 GB/s