m53297601
/
Paddle
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

add the jit back

Browse Source 
fix compile error on windows
local_add_cudnn_lstm
peizhilin 6 years ago
parent 1cc23ef67d
commit a3e952f41d
9 changed files with 241 additions and 258 deletions
Show Stats Download Patch File Download Diff File

5
CMakeLists.txt
Unescape View File

@ -130,6 +130,11 @@ if (APPLE OR WIN32)
"Disable MKL for building on mac and windows" FORCE)
endif()
if (WIN32)
set(WITH_AVX OFF CACHE STRING
"Disable AVX when compiling for Windows" FORCE)
endif()
set(THIRD_PARTY_PATH "${CMAKE_BINARY_DIR}/third_party" CACHE STRING
"A path setting third party libraries download & build directories.")

5
cmake/operators.cmake
Unescape View File

@ -84,9 +84,8 @@ function(op_library TARGET)
endif()
if (WIN32)
# remove windows unsupported op, because windows has no nccl, no warpctc such ops.
foreach(windows_unsupport_op "nccl_op" "gen_nccl_id_op" "warpctc_op" "hierarchical_sigmoid_op"
"crf_decoding_op" "select_op" "lstmp_op" "gru_op" "fusion_gru_op" "lstm_op" "fusion_lstm_op" "cumsum_op"
"fusion_seqconv_eltadd_relu_op" "channel_send_op" "channel_create_op" "channel_close_op" "channel_recv_op")
foreach(windows_unsupport_op "nccl_op" "gen_nccl_id_op" "warpctc_op"
"channel_send_op" "channel_create_op" "channel_close_op" "channel_recv_op")
if ("${TARGET}" STREQUAL "${windows_unsupport_op}")
return()
endif()

25
cmake/simd.cmake
Unescape View File

@ -70,17 +70,20 @@ int main()
return 0;
}" AVX_FOUND)
# Check AVX 2
set(CMAKE_REQUIRED_FLAGS ${AVX2_FLAG})
set(AVX2_FOUND_EXITCODE 1 CACHE STRING "Result from TRY_RUN" FORCE)
CHECK_CXX_SOURCE_RUNS("
#include <immintrin.h>
int main()
{
__m256i a = _mm256_set_epi32 (-1, 2, -3, 4, -1, 2, -3, 4);
__m256i result = _mm256_abs_epi32 (a);
return 0;
}" AVX2_FOUND)
# disable AVX2 by default on windows
if(NOT WIN32)
# Check AVX 2
set(CMAKE_REQUIRED_FLAGS ${AVX2_FLAG})
set(AVX2_FOUND_EXITCODE 1 CACHE STRING "Result from TRY_RUN" FORCE)
CHECK_CXX_SOURCE_RUNS("
#include <immintrin.h>
int main()
{
__m256i a = _mm256_set_epi32 (-1, 2, -3, 4, -1, 2, -3, 4);
__m256i result = _mm256_abs_epi32 (a);
return 0;
}" AVX2_FOUND)
endif(NOT WIN32)
# Check AVX512F
set(CMAKE_REQUIRED_FLAGS ${AVX512F_FLAG})

9
paddle/fluid/operators/CMakeLists.txt
Unescape View File

@ -22,9 +22,7 @@ if(WITH_DISTRIBUTE)
add_subdirectory(distributed_ops)
endif()
if (NOT WIN32)
add_subdirectory(reader)
endif()
add_subdirectory(reader)
if (NOT WIN32)
add_subdirectory(nccl)
@ -49,9 +47,10 @@ endif()
set(COMMON_OP_DEPS "")
set(COMMON_OP_DEPS ${COMMON_OP_DEPS} xxhash selected_rows_functor selected_rows lod_tensor maxouting unpooling pooling lod_rank_table context_project sequence_pooling executor dynload_warpctc sequence_padding sequence_scale cos_sim_functor memory jit_kernel concat_and_split cross_entropy softmax vol2col im2col sampler)
set(COMMON_OP_DEPS ${COMMON_OP_DEPS} xxhash selected_rows_functor selected_rows lod_tensor maxouting unpooling pooling lod_rank_table context_project sequence_pooling executor sequence_padding sequence_scale cos_sim_functor memory concat_and_split cross_entropy softmax vol2col im2col sampler)
set(COMMON_OP_DEPS ${COMMON_OP_DEPS} lstm_compute matrix_bit_code sequence2batch gru_compute activation_functions jit_kernel)
if (NOT WIN32)
set(COMMON_OP_DEPS ${COMMON_OP_DEPS} sequence2batch lstm_compute matrix_bit_code gru_compute activation_functions)
set(COMMON_OP_DEPS ${COMMON_OP_DEPS} dynload_warpctc)
endif()
if (WITH_GPU)
set(COMMON_OP_DEPS ${COMMON_OP_DEPS} depthwise_conv cub)

2
paddle/fluid/operators/hierarchical_sigmoid_op.h
Unescape View File

@ -111,7 +111,7 @@ class HierarchicalSigmoidGradOpKernel : public framework::OpKernel<T> {
auto pre_out_mat = EigenMatrix<T>::From(*pre_out);
auto pre_out_grad_mat = EigenMatrix<T>::From(pre_out_grad);
auto out_grad_mat = EigenMatrix<T>::From(*out_grad);
Eigen::array<int, 2> bcast({{1, static_cast<int>(pre_out_grad.dims()[1])}});
Eigen::array<int, 2> bcast{1, static_cast<int>(pre_out_grad.dims()[1])};
// softrelu derivative
pre_out_grad_mat.device(place) =

35
paddle/fluid/operators/math/CMakeLists.txt
Unescape View File

@ -1,6 +1,4 @@
if (NOT WIN32)
add_subdirectory(detail)
endif(NOT WIN32)
add_subdirectory(detail)
function(math_library TARGET)
# math_library is a function to create math library.
@ -43,10 +41,8 @@ math_library(depthwise_conv)
math_library(im2col)
math_library(sampler)
if (NOT WIN32) # windows do not support avx functions yet.
math_library(gru_compute DEPS activation_functions math_function)
math_library(lstm_compute DEPS activation_functions)
endif (NOT WIN32)
math_library(gru_compute DEPS activation_functions math_function)
math_library(lstm_compute DEPS activation_functions)
cc_library(blas SRCS blas.cc DEPS cblas framework_proto device_context)
math_library(math_function DEPS blas)
@ -58,9 +54,9 @@ math_library(sequence_padding)
math_library(sequence_pooling DEPS math_function)
math_library(sequence_scale)
math_library(softmax DEPS math_function)
if (NOT WIN32)
math_library(matrix_bit_code)
endif (NOT WIN32)
math_library(matrix_bit_code)
math_library(unpooling)
math_library(vol2col)
@ -76,13 +72,12 @@ if(WITH_GPU)
endif()
cc_test(concat_test SRCS concat_test.cc DEPS concat_and_split)
cc_test(cpu_vec_test SRCS cpu_vec_test.cc DEPS blas cpu_info)
if (NOT WIN32)
set(JIT_KERNEL_SRCS jit_kernel.cc jit_kernel_blas.cc jit_kernel_exp.cc jit_kernel_rnn.cc jit_kernel_crf_decode.cc)
set(JIT_KERNEL_DEPS cpu_info cblas gflags enforce)
if(WITH_XBYAK)
list(APPEND JIT_KERNEL_SRCS jit_gen.cc jit_code.cc)
list(APPEND JIT_KERNEL_DEPS xbyak)
endif()
cc_library(jit_kernel SRCS ${JIT_KERNEL_SRCS} DEPS ${JIT_KERNEL_DEPS})
cc_test(jit_kernel_test SRCS jit_kernel_test.cc DEPS jit_kernel)
endif (NOT WIN32)
set(JIT_KERNEL_SRCS jit_kernel.cc jit_kernel_blas.cc jit_kernel_exp.cc jit_kernel_rnn.cc jit_kernel_crf_decode.cc)
set(JIT_KERNEL_DEPS cpu_info cblas gflags enforce)
if(WITH_XBYAK)
list(APPEND JIT_KERNEL_SRCS jit_gen.cc jit_code.cc)
list(APPEND JIT_KERNEL_DEPS xbyak)
endif()
cc_library(jit_kernel SRCS ${JIT_KERNEL_SRCS} DEPS ${JIT_KERNEL_DEPS})
cc_test(jit_kernel_test SRCS jit_kernel_test.cc DEPS jit_kernel)

3
paddle/fluid/operators/math/matrix_bit_code.h
Unescape View File

@ -67,7 +67,7 @@ inline constexpr size_t FindLastSet(size_t x) {
: (std::is_same<size_t, unsigned long>::value // NOLINT
? (x ? 8 * sizeof(x) - __builtin_clzl(x) : 0)
: (x ? 8 * sizeof(x) - __builtin_clzll(x) : 0));
}
#else
// windows don't have built-in clz, ctz function
template <typename T>
@ -92,7 +92,6 @@ inline int clz(const T& value) {
inline size_t FindLastSet(size_t x) { return sizeof(size_t) * 8 - clz(x); }
#endif // !_WIN32
}
struct SimpleCode {
SimpleCode(size_t code, size_t num_classes) : c_(code + num_classes) {}

374
python/paddle/fluid/layers/nn.py
View File

File diff suppressed because it is too large Load Diff

41
python/paddle/fluid/layers/ops.py
Unescape View File

@ -100,26 +100,27 @@ Examples:
>>> result = fluid.layers.hard_shrink(x=data, threshold=0.3)
"""
if os.name != 'nt':
__all__ += ['cumsum']
_cum_sum_ = generate_layer_fn('cumsum')
def cumsum(x, axis=None, exclusive=None, reverse=None):
locals_var = locals().keys()
kwargs = dict()
for name in locals_var:
val = locals()[name]
if val is not None:
kwargs[name] = val
return _cum_sum_(**kwargs)
cumsum.__doc__ = _cum_sum_.__doc__ + """
Examples:
>>> data = fluid.layers.data(name="input", shape=[32, 784])
>>> result = fluid.layers.cumsum(data, axis=0)
"""
__all__ += ['cumsum']
_cum_sum_ = generate_layer_fn('cumsum')
def cumsum(x, axis=None, exclusive=None, reverse=None):
locals_var = locals().keys()
kwargs = dict()
for name in locals_var:
val = locals()[name]
if val is not None:
kwargs[name] = val
return _cum_sum_(**kwargs)
cumsum.__doc__ = _cum_sum_.__doc__ + """
Examples:
>>> data = fluid.layers.data(name="input", shape=[32, 784])
>>> result = fluid.layers.cumsum(data, axis=0)
"""
__all__ += ['thresholded_relu']

Write Preview
Loading…
Cancel
Save