From 5ae119ee950c036619342b462aacff23769e2343 Mon Sep 17 00:00:00 2001 From: Damian Broncel Date: Fri, 9 Mar 2018 14:26:17 +0100 Subject: [PATCH 1/3] eigen_archive url changed --- tensorflow/workspace.bzl | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/tensorflow/workspace.bzl b/tensorflow/workspace.bzl index 14a4281fae..aa4b05af55 100644 --- a/tensorflow/workspace.bzl +++ b/tensorflow/workspace.bzl @@ -120,11 +120,11 @@ def tf_workspace(path_prefix="", tf_repo_name=""): tf_http_archive( name = "eigen_archive", urls = [ - "https://mirror.bazel.build/bitbucket.org/eigen/eigen/get/2355b229ea4c.tar.gz", - "https://bitbucket.org/eigen/eigen/get/2355b229ea4c.tar.gz", + "https://mirror.bazel.build/bitbucket.org/dtrebbien/eigen/get/374842a18727.tar.gz", + "https://bitbucket.org/dtrebbien/eigen/get/374842a18727.tar.gz", ], - sha256 = "0cadb31a35b514bf2dfd6b5d38205da94ef326ec6908fc3fd7c269948467214f", - strip_prefix = "eigen-eigen-2355b229ea4c", + sha256 = "fa26e9b9ff3a2692b092d154685ec88d6cb84d4e1e895006541aff8603f15c16", + strip_prefix = "dtrebbien-eigen-374842a18727", build_file = str(Label("//third_party:eigen.BUILD")), ) @@ -353,11 +353,11 @@ def tf_workspace(path_prefix="", tf_repo_name=""): tf_http_archive( name = "protobuf_archive", urls = [ - "https://mirror.bazel.build/github.com/google/protobuf/archive/396336eb961b75f03b25824fe86cf6490fb75e3a.tar.gz", - "https://github.com/google/protobuf/archive/396336eb961b75f03b25824fe86cf6490fb75e3a.tar.gz", + "https://mirror.bazel.build/github.com/dtrebbien/protobuf/archive/50f552646ba1de79e07562b41f3999fe036b4fd0.tar.gz", + "https://github.com/dtrebbien/protobuf/archive/50f552646ba1de79e07562b41f3999fe036b4fd0.tar.gz", ], - sha256 = "846d907acf472ae233ec0882ef3a2d24edbbe834b80c305e867ac65a1f2c59e3", - strip_prefix = "protobuf-396336eb961b75f03b25824fe86cf6490fb75e3a", + sha256 = "eb16b33431b91fe8cee479575cee8de202f3626aaf00d9bf1783c6e62b4ffbc7", + strip_prefix = "protobuf-50f552646ba1de79e07562b41f3999fe036b4fd0", ) # We need to import the protobuf library under the names com_google_protobuf -- 2.11.0 (Apple Git-81) From 067ab153a782ded0d812e832b957b6072223825a Mon Sep 17 00:00:00 2001 From: Damian Broncel Date: Fri, 9 Mar 2018 14:29:08 +0100 Subject: [PATCH 2/3] remove __align__(sizeof(T)) entries --- tensorflow/core/kernels/concat_lib_gpu_impl.cu.cc | 2 +- tensorflow/core/kernels/depthwise_conv_op_gpu.cu.cc | 8 ++++---- tensorflow/core/kernels/split_lib_gpu.cu.cc | 2 +- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/tensorflow/core/kernels/concat_lib_gpu_impl.cu.cc b/tensorflow/core/kernels/concat_lib_gpu_impl.cu.cc index 0f7adaf24a..8d89c66f3f 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(smem); if (useSmem) { diff --git a/tensorflow/core/kernels/depthwise_conv_op_gpu.cu.cc b/tensorflow/core/kernels/depthwise_conv_op_gpu.cu.cc index 505d33046e..9bed380f38 100644 --- a/tensorflow/core/kernels/depthwise_conv_op_gpu.cu.cc +++ b/tensorflow/core/kernels/depthwise_conv_op_gpu.cu.cc @@ -172,7 +172,7 @@ __global__ __launch_bounds__(1024, 2) void DepthwiseConv2dGPUKernelNHWCSmall( const DepthwiseArgs args, const T* input, const T* filter, T* output) { assert(CanLaunchDepthwiseConv2dGPUSmall(args)); // Holds block plus halo and filter data for blockDim.x depths. - extern __shared__ __align__(sizeof(T)) unsigned char shared_memory[]; + extern __shared__ unsigned char shared_memory[]; T* const shared_data = reinterpret_cast(shared_memory); const int num_batches = args.batch; @@ -450,7 +450,7 @@ __global__ __launch_bounds__(1024, 2) void DepthwiseConv2dGPUKernelNCHWSmall( const DepthwiseArgs args, const T* input, const T* filter, T* output) { assert(CanLaunchDepthwiseConv2dGPUSmall(args)); // Holds block plus halo and filter data for blockDim.z depths. - extern __shared__ __align__(sizeof(T)) unsigned char shared_memory[]; + extern __shared__ unsigned char shared_memory[]; T* const shared_data = reinterpret_cast(shared_memory); const int num_batches = args.batch; @@ -1099,7 +1099,7 @@ __launch_bounds__(1024, 2) void DepthwiseConv2dBackpropFilterGPUKernelNHWCSmall( const DepthwiseArgs args, const T* output, const T* input, T* filter) { assert(CanLaunchDepthwiseConv2dBackpropFilterGPUSmall(args, blockDim.z)); // Holds block plus halo and filter data for blockDim.x depths. - extern __shared__ __align__(sizeof(T)) unsigned char shared_memory[]; + extern __shared__ unsigned char shared_memory[]; T* const shared_data = reinterpret_cast(shared_memory); const int num_batches = args.batch; @@ -1367,7 +1367,7 @@ __launch_bounds__(1024, 2) void DepthwiseConv2dBackpropFilterGPUKernelNCHWSmall( const DepthwiseArgs args, const T* output, const T* input, T* filter) { assert(CanLaunchDepthwiseConv2dBackpropFilterGPUSmall(args, blockDim.x)); // Holds block plus halo and filter data for blockDim.z depths. - extern __shared__ __align__(sizeof(T)) unsigned char shared_memory[]; + extern __shared__ unsigned char shared_memory[]; T* const shared_data = reinterpret_cast(shared_memory); const int num_batches = args.batch; diff --git a/tensorflow/core/kernels/split_lib_gpu.cu.cc b/tensorflow/core/kernels/split_lib_gpu.cu.cc index 9f234fc093..5115a96d17 100644 --- a/tensorflow/core/kernels/split_lib_gpu.cu.cc +++ b/tensorflow/core/kernels/split_lib_gpu.cu.cc @@ -119,7 +119,7 @@ __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(smem); if (useSmem) { -- 2.11.0 (Apple Git-81) From 7f108ef6b616b29607b30db10e436cee02e371e8 Mon Sep 17 00:00:00 2001 From: Damian Broncel Date: Fri, 9 Mar 2018 14:30:39 +0100 Subject: [PATCH 3/3] comment out lgomp --- third_party/gpus/cuda/BUILD.tpl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/third_party/gpus/cuda/BUILD.tpl b/third_party/gpus/cuda/BUILD.tpl index 2a37c65bc7..61b203e005 100644 --- a/third_party/gpus/cuda/BUILD.tpl +++ b/third_party/gpus/cuda/BUILD.tpl @@ -110,7 +110,7 @@ cc_library( ".", "cuda/include", ], - linkopts = ["-lgomp"], + # linkopts = ["-lgomp"], linkstatic = 1, visibility = ["//visibility:public"], ) -- 2.11.0 (Apple Git-81)