We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 5fce5f9 commit 2c2caa4Copy full SHA for 2c2caa4
ggml/src/ggml-cuda/common.cuh
@@ -262,11 +262,11 @@ static bool cp_async_available(const int cc) {
262
}
263
264
static constexpr __device__ int ggml_cuda_get_physical_warp_size() {
265
-#if defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__)
266
- return __AMDGCN_WAVEFRONT_SIZE;
+#if defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__) && (defined(__GFX9__) || defined(__GFX8__))
+ return 64;
267
#else
268
return 32;
269
-#endif // defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__)
+#endif // defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__) && (defined(__GFX9__) || defined(__GFX8__))
270
271
272
[[noreturn]]
0 commit comments