diff options
Diffstat (limited to 'third_party')
3 files changed, 28 insertions, 22 deletions
diff --git a/third_party/eigen3/Eigen/src/Core/util/Macros.h b/third_party/eigen3/Eigen/src/Core/util/Macros.h index 729a451324..b531327afb 100644 --- a/third_party/eigen3/Eigen/src/Core/util/Macros.h +++ b/third_party/eigen3/Eigen/src/Core/util/Macros.h @@ -296,10 +296,14 @@ // 16 byte alignment on all platforms where vectorization might be enabled. In theory we could always // enable alignment, but it can be a cause of problems on some platforms, so we just disable it in // certain common platform (compiler+architecture combinations) to avoid these problems. -// Only static alignment is really problematic (relies on nonstandard compiler extensions that don't -// work everywhere, for example don't work on GCC/ARM), try to keep heap alignment even -// when we have to disable static alignment. -#if EIGEN_COMP_GNUC && !(EIGEN_ARCH_i386_OR_x86_64 || EIGEN_ARCH_PPC || EIGEN_ARCH_IA64) +// Only static alignment is really problematic (relies on nonstandard compiler extensions), +// try to keep heap alignment even when we have to disable static alignment. +#if EIGEN_COMP_GNUC && !(EIGEN_ARCH_i386_OR_x86_64 || EIGEN_ARCH_ARM_OR_ARM64 || EIGEN_ARCH_PPC || EIGEN_ARCH_IA64) +#define EIGEN_GCC_AND_ARCH_DOESNT_WANT_STACK_ALIGNMENT 1 +#elif EIGEN_ARCH_ARM_OR_ARM64 && EIGEN_COMP_GNUC_STRICT && EIGEN_GNUC_AT_MOST(4, 6) +// Old versions of GCC on ARM, at least 4.4, were once seen to have buggy static alignment support. +// Not sure which version fixed it, hopefully it doesn't affect 4.7, which is still somewhat in use. +// 4.8 and newer seem definitely unaffected. #define EIGEN_GCC_AND_ARCH_DOESNT_WANT_STACK_ALIGNMENT 1 #else #define EIGEN_GCC_AND_ARCH_DOESNT_WANT_STACK_ALIGNMENT 0 diff --git a/third_party/eigen3/unsupported/Eigen/CXX11/src/Tensor/TensorDeviceType.h b/third_party/eigen3/unsupported/Eigen/CXX11/src/Tensor/TensorDeviceType.h index b6eeb73832..a62682c728 100644 --- a/third_party/eigen3/unsupported/Eigen/CXX11/src/Tensor/TensorDeviceType.h +++ b/third_party/eigen3/unsupported/Eigen/CXX11/src/Tensor/TensorDeviceType.h @@ -760,11 +760,15 @@ struct GpuDevice { GpuDevice() : stream_(perftools::gputools::MachineManager::singleton()->stream_for_device(0)), allocator_(nullptr), - stream_exec_(stream_->parent()) {} + stream_exec_(stream_->parent()), + device_descr_(&(stream_exec_->GetDeviceDescription())) {} GpuDevice(perftools::gputools::Stream* stream, const Allocator* alloc = nullptr) - : stream_(stream), allocator_(alloc), stream_exec_(stream_->parent()) { } + : stream_(stream), + allocator_(alloc), + stream_exec_(stream_->parent()), + device_descr_(&(stream_exec_->GetDeviceDescription())) {} EIGEN_STRONG_INLINE perftools::gputools::Stream* stream() const { return stream_; @@ -873,28 +877,25 @@ struct GpuDevice { stream_->BlockHostUntilDone(); } - // A gpu::DeviceDescription is cached inside a StreamExecutor, so these calls - // aren't expensive/wasteful. EIGEN_DEVICE_FUNC inline int getNumCudaMultiProcessors() const { - return stream_exec_->GetDeviceDescription().core_count(); + return device_descr_->core_count(); } EIGEN_DEVICE_FUNC inline int maxCudaThreadsPerBlock() const { - return stream_exec_->GetDeviceDescription().threads_per_block_limit(); + return device_descr_->threads_per_block_limit(); } EIGEN_DEVICE_FUNC inline int maxCudaThreadsPerMultiProcessor() const { - return stream_exec_->GetDeviceDescription().threads_per_core_limit(); + return device_descr_->threads_per_core_limit(); } EIGEN_DEVICE_FUNC inline int sharedMemPerBlock() const { - return stream_exec_->GetDeviceDescription().shared_memory_per_block(); + return device_descr_->shared_memory_per_block(); } EIGEN_DEVICE_FUNC inline int majorDeviceVersion() const { int major, minor; - if (stream_exec_->GetDeviceDescription().cuda_compute_capability(&major, - &minor)) { + if (device_descr_->cuda_compute_capability(&major, &minor)) { return major; } else { return 0; @@ -906,6 +907,7 @@ struct GpuDevice { private: perftools::gputools::Stream* stream_; perftools::gputools::StreamExecutor* stream_exec_; + const perftools::gputools::DeviceDescription* device_descr_; const Allocator* allocator_; }; diff --git a/third_party/eigen3/unsupported/Eigen/CXX11/src/Tensor/TensorIntDiv.h b/third_party/eigen3/unsupported/Eigen/CXX11/src/Tensor/TensorIntDiv.h index 3e90b08c99..6d63b23b2f 100644 --- a/third_party/eigen3/unsupported/Eigen/CXX11/src/Tensor/TensorIntDiv.h +++ b/third_party/eigen3/unsupported/Eigen/CXX11/src/Tensor/TensorIntDiv.h @@ -115,7 +115,7 @@ namespace { } -template <typename T> +template <typename T, bool div_gt_one = false> struct TensorIntDivisor { public: EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE TensorIntDivisor() { @@ -166,7 +166,7 @@ struct TensorIntDivisor { // Optimized version for signed 32 bit integers. // Derived from Hacker's Delight. template <> -class TensorIntDivisor<int32_t> { +class TensorIntDivisor<int32_t, true> { public: EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE TensorIntDivisor() { magic = 0; @@ -225,15 +225,15 @@ private: }; -template <typename T> -static EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE T operator / (const T& numerator, const TensorIntDivisor<T>& divisor) { +template <typename T, bool div_gt_one> +static EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE T operator / (const T& numerator, const TensorIntDivisor<T, div_gt_one>& divisor) { return divisor.divide(numerator); } #else // Reverse to the old code since gcudacc doesn't support the code above. -template <typename T> +template <typename T, bool div_gt_one = false> struct TensorIntDivisor { public: EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE TensorIntDivisor() { @@ -285,7 +285,7 @@ struct TensorIntDivisor { // Optimized version for signed 32 bit integers. // Derived from Hacker's Delight. template <> -class TensorIntDivisor<int> { +class TensorIntDivisor<int, true> { public: EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE TensorIntDivisor() { magic = 0; @@ -344,8 +344,8 @@ private: }; -template <typename T> -static EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE T operator / (const T& numerator, const TensorIntDivisor<T>& divisor) { +template <typename T, bool div_gt_one> +static EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE T operator / (const T& numerator, const TensorIntDivisor<T, div_gt_one>& divisor) { return divisor.divide(numerator); } |