Last active
August 15, 2018 20:21
-
-
Save rxwei/993deb4c9ed51c875e74f5ca4e074d3d to your computer and use it in GitHub Desktop.
TensorFlow macOS GPU patch (base: 8453e23a8b)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
diff --git a/tensorflow/core/kernels/concat_lib_gpu_impl.cu.cc b/tensorflow/core/kernels/concat_lib_gpu_impl.cu.cc | |
index a561d918bd..785e0ddf4e 100644 | |
--- a/tensorflow/core/kernels/concat_lib_gpu_impl.cu.cc | |
+++ b/tensorflow/core/kernels/concat_lib_gpu_impl.cu.cc | |
@@ -69,7 +69,7 @@ __global__ void concat_variable_kernel( | |
IntType num_inputs = input_ptr_data.size; | |
// verbose declaration needed due to template | |
- extern __shared__ __align__(sizeof(T)) unsigned char smem[]; | |
+ extern __shared__ unsigned char smem[]; | |
IntType* smem_col_scan = reinterpret_cast<IntType*>(smem); | |
if (useSmem) { | |
diff --git a/tensorflow/core/kernels/split_lib_gpu.cu.cc b/tensorflow/core/kernels/split_lib_gpu.cu.cc | |
index 393818730b..a7d9e02853 100644 | |
--- a/tensorflow/core/kernels/split_lib_gpu.cu.cc | |
+++ b/tensorflow/core/kernels/split_lib_gpu.cu.cc | |
@@ -121,7 +121,7 @@ __global__ void split_v_kernel(const T* input_ptr, | |
int num_outputs = output_ptr_data.size; | |
// verbose declaration needed due to template | |
- extern __shared__ __align__(sizeof(T)) unsigned char smem[]; | |
+ extern __shared__ unsigned char smem[]; | |
IntType* smem_col_scan = reinterpret_cast<IntType*>(smem); | |
if (useSmem) { |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment