摘要: 被打桩的函数是STUB_FUN, 可以替换成如__cudaRegisterFunction, 另外插入的函数zwl_profiler可另外定义, .text .section .rodata .LC0: .string "STUB_FUN" .text .globl STUB_FUN .type S 阅读全文
posted @ 2025-01-05 22:33 zwlwf 阅读(26) 评论(0) 推荐(0)
摘要: 原始代码 // Type your code here, or load an example. extern "C" __global__ void square(int* array, int n) { int tid = blockDim.x * blockIdx.x + threadIdx. 阅读全文
posted @ 2025-01-05 21:43 zwlwf 阅读(80) 评论(0) 推荐(0)