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/avgpool_layer_kernels.cu | 4 ++++
1 files changed, 4 insertions(+), 0 deletions(-)
diff --git a/src/avgpool_layer_kernels.cu b/src/avgpool_layer_kernels.cu
index 1bd2a2a..b7e2770 100644
--- a/src/avgpool_layer_kernels.cu
+++ b/src/avgpool_layer_kernels.cu
@@ -1,3 +1,7 @@
+#include "cuda_runtime.h"
+#include "curand.h"
+#include "cublas_v2.h"
+
extern "C" {
#include "avgpool_layer.h"
#include "cuda.h"
--
Gitblit v1.10.0