From a284a7da8d1facbf984a22302665a2a50295a687 Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Wed, 08 Aug 2018 16:08:58 +0000
Subject: [PATCH] Try to use avx_hs() - slow and requires alignment 4096 bits < (l.size*l.size*l.c) May be faster only from 8192 bits and more.
---
src/cuda.c | 8 ++++----
1 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/src/cuda.c b/src/cuda.c
index 688e1c5..2284dad 100644
--- a/src/cuda.c
+++ b/src/cuda.c
@@ -29,23 +29,23 @@
//cudaDeviceSynchronize();
cudaError_t status2 = cudaGetLastError();
if (status != cudaSuccess)
- {
+ {
const char *s = cudaGetErrorString(status);
char buffer[256];
printf("CUDA Error: %s\n", s);
assert(0);
snprintf(buffer, 256, "CUDA Error: %s", s);
error(buffer);
- }
+ }
if (status2 != cudaSuccess)
- {
+ {
const char *s = cudaGetErrorString(status);
char buffer[256];
printf("CUDA Error Prev: %s\n", s);
assert(0);
snprintf(buffer, 256, "CUDA Error Prev: %s", s);
error(buffer);
- }
+ }
}
dim3 cuda_gridsize(size_t n){
--
Gitblit v1.10.0