From dda993f3dd3c753dfd580d485b39c1001830fee4 Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Thu, 22 Feb 2018 19:54:40 +0000
Subject: [PATCH] Use half_float16 instead of float32 if defined both CUDNN and CUDNN_HALF. Use Tensor Cores.
---
src/cuda.h | 3 +++
1 files changed, 3 insertions(+), 0 deletions(-)
diff --git a/src/cuda.h b/src/cuda.h
index 32aaabb..0bc0557 100644
--- a/src/cuda.h
+++ b/src/cuda.h
@@ -26,13 +26,16 @@
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);
dim3 cuda_gridsize(size_t n);
+cudaStream_t get_cuda_stream();
#ifdef CUDNN
cudnnHandle_t cudnn_handle();
+enum {cudnn_fastest, cudnn_smallest};
#endif
#endif
--
Gitblit v1.10.0