From cad4d1618fee74471d335314cb77070fee951a42 Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Sun, 25 Feb 2018 13:29:44 +0000
Subject: [PATCH] Added support for Tensor Cores CC >= 7.0 (V100). For FP16/32 (mixed precision) define CUDNN_HALF should be used.
---
src/cuda.h | 2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/src/cuda.h b/src/cuda.h
index 31f9092..0bc0557 100644
--- a/src/cuda.h
+++ b/src/cuda.h
@@ -26,6 +26,7 @@
void cuda_push_array(float *x_gpu, float *x, size_t n);
void cuda_pull_array(float *x_gpu, float *x, size_t n);
void cuda_set_device(int n);
+int cuda_get_device();
void cuda_free(float *x_gpu);
void cuda_random(float *x_gpu, size_t n);
float cuda_compare(float *x_gpu, float *x, size_t n, char *s);
@@ -34,6 +35,7 @@
#ifdef CUDNN
cudnnHandle_t cudnn_handle();
+enum {cudnn_fastest, cudnn_smallest};
#endif
#endif
--
Gitblit v1.10.0