[libc-commits] [libc] [libc] Add Kernel Resource Usage to nvptx-loader (PR #97503)

[via libc-commits]

================
@@ -229,6 +229,17 @@ CUresult launch_kernel(CUmodule binary, CUstream stream,
   return CUDA_SUCCESS;
 }
 
+void print_resource_usage(CUmodule binary, const char *kernel_name) {
+  CUfunction function;
+  if (CUresult err = cuModuleGetFunction(&function, binary, kernel_name))
+    handle_error(err);
+  int num_regs;
+  if (CUresult err =
+          cuFuncGetAttribute(&num_regs, CU_FUNC_ATTRIBUTE_NUM_REGS, function))
+    handle_error(err);
+  fprintf(stderr, "%6s registers: %d\n", kernel_name, num_regs);
----------------
jameshu15869 wrote:

Ah yeah, I don't think there's a specific reason I put it in `stderr`. 

https://github.com/llvm/llvm-project/pull/97503