CUDA: revert part of the RDNA1 optimizations (#8309)

The change on the launch_bounds was causing a small performance drop in perplexity of 25 t/s
ggerganov · Jul 5, 2024 · 0a42380 · 0a42380
1 parent d12f781
commit 0a42380
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/ggml/src/ggml-cuda/mmq.cuh b/ggml/src/ggml-cuda/mmq.cuh
@@ -2263,9 +2263,9 @@ static __device__ void mul_mat_q_process_tile(
 
 template <ggml_type type, int mmq_x, int nwarps, bool need_check>
 #if defined(GGML_USE_HIPBLAS) && defined(__HIP_PLATFORM_AMD__)
-#if defined(RDNA3) || defined(RDNA2) || defined(RDNA1)
+#if defined(RDNA3) || defined(RDNA2)
     __launch_bounds__(WARP_SIZE*nwarps, 2)
-#endif // defined(RDNA3) || defined(RDNA2) || defined(RDNA1)
+#endif // defined(RDNA3) || defined(RDNA2)
 #else
 #if __CUDA_ARCH__ >= CC_VOLTA
     __launch_bounds__(WARP_SIZE*nwarps, 1)