| [general] | |
| name = "gemm" | |
| universal = false | |
| [torch] | |
| src = [ | |
| "torch-ext/torch_binding.cpp", | |
| "torch-ext/torch_binding.h", | |
| ] | |
| [kernel.gemm] | |
| backend = "rocm" | |
| rocm-archs = [ | |
| #"gfx908", | |
| # "gfx90a", | |
| # "gfx940", | |
| # "gfx941", | |
| "gfx942", | |
| # "gfx1100", | |
| # "gfx1101", | |
| # "gfx1102", | |
| # "gfx1200", | |
| # "gfx1201", | |
| ] | |
| depends = ["torch"] | |
| src = [ | |
| "include/clangd_workaround.h", | |
| "include/gpu_libs.h", | |
| "include/gpu_types.h", | |
| "include/timer.h", | |
| "gemm/gemm_kernel.h", | |
| "gemm/gemm_kernel_legacy.h", | |
| "gemm/gemm_launcher.hip", | |
| "gemm/transpose_kernel.h", | |
| "src/utils/arithmetic.h", | |
| "src/utils/timer.hip", | |
| "tests/checker/metrics.h", | |
| ] | |
| include = ["include"] | |