Error building Tensorflow Lite on AARCH64

Question

Error building Tensorflow Lite on AARCH64

weihChen opened this issue 5 years ago · comments

System information

OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Linux Ubuntu 16.04
TensorFlow installed from (source or binary): N/A
TensorFlow version: the latest
Python version: N/A
Installed using virtualenv? pip? conda?: N/A
Bazel version (if compiling from source): N/A
GCC/Compiler version (if compiling from source): gcc version 5.4.0 20160609
CUDA/cuDNN version: N/A
GPU model and memory: N/A

Describe the problem
I am trying to build Tensorflow Lite for ARM64 boards.
I followed the instructions on https://tensorflow.google.cn/lite/guide/build_arm64 and executed the following commands:

sudo apt-get update
sudo apt-get install crossbuild-essential-arm64
./tensorflow/lite/tools/make/download_dependencies.sh
./tensorflow/lite/tools/make/build_aarch64_lib.sh

But at the last step got lots of errors such as:

./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:3823:22: note: use -flax-vector-conversions to permit conversions between vectors with differing element types or numbers of subparts
filter_reg_0_b = vdupq_n_u8(kSignBit);
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:3823:22: error: cannot convert ‘uint8x16_t {aka __vector(16) unsigned char}’ to ‘int8x16_t {aka __vector(16) signed char}’ in assignment
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:3824:22: error: cannot convert ‘uint8x16_t {aka __vector(16) unsigned char}’ to ‘int8x16_t {aka __vector(16) signed char}’ in assignment
filter_reg_1_b = vdupq_n_u8(kSignBit);
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:3825:22: error: cannot convert ‘uint8x16_t {aka __vector(16) unsigned char}’ to ‘int8x16_t {aka __vector(16) signed char}’ in assignment
filter_reg_2_b = vdupq_n_u8(kSignBit);
^
In file included from ./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8.h:21:0,
from tensorflow/lite/kernels/depthwise_conv.cc:25:
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:50:71: error: cannot convert ‘int8x16_t {aka __vector(16) signed char}’ to ‘uint64x2_t {aka __vector(2) long unsigned int}’ for argument ‘2’ to ‘uint64x2_t vld1q_lane_u64(const uint64_t*, uint64x2_t, int)’
vld1q_lane_u64(reinterpret_cast<const uint64_t*>(src), reg, lane_num)
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:3828:24: note: in expansion of macro ‘vld1q_lane_s8x8’
filter_reg_0_a = vld1q_lane_s8x8(filter_block_ptr, filter_reg_0_a, 0);
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:50:71: error: cannot convert ‘int8x16_t {aka __vector(16) signed char}’ to ‘uint64x2_t {aka __vector(2) long unsigned int}’ for argument ‘2’ to ‘uint64x2_t vld1q_lane_u64(const uint64_t*, uint64x2_t, int)’
vld1q_lane_u64(reinterpret_cast<const uint64_t*>(src), reg, lane_num)
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:3830:24: note: in expansion of macro ‘vld1q_lane_s8x8’
filter_reg_0_b = vld1q_lane_s8x8(filter_block_ptr, filter_reg_0_b, 0);
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:50:71: error: cannot convert ‘int8x16_t {aka __vector(16) signed char}’ to ‘uint64x2_t {aka __vector(2) long unsigned int}’ for argument ‘2’ to ‘uint64x2_t vld1q_lane_u64(const uint64_t*, uint64x2_t, int)’
vld1q_lane_u64(reinterpret_cast<const uint64_t*>(src), reg, lane_num)
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:3832:24: note: in expansion of macro ‘vld1q_lane_s8x8’
filter_reg_0_a = vld1q_lane_s8x8(filter_block_ptr, filter_reg_0_a, 1);
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:50:71: error: cannot convert ‘int8x16_t {aka __vector(16) signed char}’ to ‘uint64x2_t {aka __vector(2) long unsigned int}’ for argument ‘2’ to ‘uint64x2_t vld1q_lane_u64(const uint64_t*, uint64x2_t, int)’
vld1q_lane_u64(reinterpret_cast<const uint64_t*>(src), reg, lane_num)
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:3834:24: note: in expansion of macro ‘vld1q_lane_s8x8’
filter_reg_1_a = vld1q_lane_s8x8(filter_block_ptr, filter_reg_1_a, 0);
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:50:71: error: cannot convert ‘int8x16_t {aka __vector(16) signed char}’ to ‘uint64x2_t {aka __vector(2) long unsigned int}’ for argument ‘2’ to ‘uint64x2_t vld1q_lane_u64(const uint64_t*, uint64x2_t, int)’
vld1q_lane_u64(reinterpret_cast<const uint64_t*>(src), reg, lane_num)
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:3836:24: note: in expansion of macro ‘vld1q_lane_s8x8’
filter_reg_1_b = vld1q_lane_s8x8(filter_block_ptr, filter_reg_1_b, 0);
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:50:71: error: cannot convert ‘int8x16_t {aka __vector(16) signed char}’ to ‘uint64x2_t {aka __vector(2) long unsigned int}’ for argument ‘2’ to ‘uint64x2_t vld1q_lane_u64(const uint64_t*, uint64x2_t, int)’
vld1q_lane_u64(reinterpret_cast<const uint64_t*>(src), reg, lane_num)
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:3838:24: note: in expansion of macro ‘vld1q_lane_s8x8’
filter_reg_1_a = vld1q_lane_s8x8(filter_block_ptr, filter_reg_1_a, 1);
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:50:71: error: cannot convert ‘int8x16_t {aka __vector(16) signed char}’ to ‘uint64x2_t {aka __vector(2) long unsigned int}’ for argument ‘2’ to ‘uint64x2_t vld1q_lane_u64(const uint64_t*, uint64x2_t, int)’
vld1q_lane_u64(reinterpret_cast<const uint64_t*>(src), reg, lane_num)
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:3840:24: note: in expansion of macro ‘vld1q_lane_s8x8’
filter_reg_2_a = vld1q_lane_s8x8(filter_block_ptr, filter_reg_2_a, 0);
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:50:71: error: cannot convert ‘int8x16_t {aka __vector(16) signed char}’ to ‘uint64x2_t {aka __vector(2) long unsigned int}’ for argument ‘2’ to ‘uint64x2_t vld1q_lane_u64(const uint64_t*, uint64x2_t, int)’
vld1q_lane_u64(reinterpret_cast<const uint64_t*>(src), reg, lane_num)
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:3842:24: note: in expansion of macro ‘vld1q_lane_s8x8’
filter_reg_2_b = vld1q_lane_s8x8(filter_block_ptr, filter_reg_2_b, 0);
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:50:71: error: cannot convert ‘int8x16_t {aka __vector(16) signed char}’ to ‘uint64x2_t {aka __vector(2) long unsigned int}’ for argument ‘2’ to ‘uint64x2_t vld1q_lane_u64(const uint64_t*, uint64x2_t, int)’
vld1q_lane_u64(reinterpret_cast<const uint64_t*>(src), reg, lane_num)
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:3844:24: note: in expansion of macro ‘vld1q_lane_s8x8’
filter_reg_2_a = vld1q_lane_s8x8(filter_block_ptr, filter_reg_2_a, 1);
^
In file included from ./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8.h:21:0,
from tensorflow/lite/kernels/depthwise_conv.cc:25:
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:3846:57: error: cannot convert ‘const uint8x16_t {aka const __vector(16) unsigned char}’ to ‘int8x16_t {aka __vector(16) signed char}’ for argument ‘2’ to ‘int8x16_t veorq_s8(int8x16_t, int8x16_t)’
filter_reg_0_a = veorq_s8(filter_reg_0_a, sign_bit);
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:3847:57: error: cannot convert ‘const uint8x16_t {aka const __vector(16) unsigned char}’ to ‘int8x16_t {aka __vector(16) signed char}’ for argument ‘2’ to ‘int8x16_t veorq_s8(int8x16_t, int8x16_t)’
filter_reg_0_b = veorq_s8(filter_reg_0_b, sign_bit);
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:3848:57: error: cannot convert ‘const uint8x16_t {aka const __vector(16) unsigned char}’ to ‘int8x16_t {aka __vector(16) signed char}’ for argument ‘2’ to ‘int8x16_t veorq_s8(int8x16_t, int8x16_t)’
filter_reg_1_a = veorq_s8(filter_reg_1_a, sign_bit);
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:3849:57: error: cannot convert ‘const uint8x16_t {aka const __vector(16) unsigned char}’ to ‘int8x16_t {aka __vector(16) signed char}’ for argument ‘2’ to ‘int8x16_t veorq_s8(int8x16_t, int8x16_t)’
filter_reg_1_b = veorq_s8(filter_reg_1_b, sign_bit);
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:3850:57: error: cannot convert ‘const uint8x16_t {aka const __vector(16) unsigned char}’ to ‘int8x16_t {aka __vector(16) signed char}’ for argument ‘2’ to ‘int8x16_t veorq_s8(int8x16_t, int8x16_t)’
filter_reg_2_a = veorq_s8(filter_reg_2_a, sign_bit);
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:3851:57: error: cannot convert ‘const uint8x16_t {aka const __vector(16) unsigned char}’ to ‘int8x16_t {aka __vector(16) signed char}’ for argument ‘2’ to ‘int8x16_t veorq_s8(int8x16_t, int8x16_t)’
filter_reg_2_b = veorq_s8(filter_reg_2_b, sign_bit);
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h: In static member function ‘static void tflite::optimized_ops::depthwise_conv::PackMacroBlock<(tflite::DepthwiseConvImplementation)3, (tflite::DepthwiseConvDepthMultiplication)0, 0>::PackMacroBlockNeon(const uint8*, int8*, const tflite::optimized_ops::depthwise_conv::DepthwiseConvDotProdParams*)’:
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:3954:53: error: cannot convert ‘uint8x16_t {aka __vector(16) unsigned char}’ to ‘const int8x16_t {aka const __vector(16) signed char}’ in initialization
const int8x16_t perm_data_0 = vld1q_u8(perm_data);
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:3955:58: error: cannot convert ‘uint8x16_t {aka __vector(16) unsigned char}’ to ‘const int8x16_t {aka const __vector(16) signed char}’ in initialization
const int8x16_t perm_data_1 = vld1q_u8(perm_data + 16);
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:3956:58: error: cannot convert ‘uint8x16_t {aka __vector(16) unsigned char}’ to ‘const int8x16_t {aka const __vector(16) signed char}’ in initialization
const int8x16_t perm_data_2 = vld1q_u8(perm_data + 32);
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:3957:58: error: cannot convert ‘uint8x16_t {aka __vector(16) unsigned char}’ to ‘const int8x16_t {aka const __vector(16) signed char}’ in initialization
const int8x16_t perm_data_3 = vld1q_u8(perm_data + 48);

How can I fix it?

zjd1988 · Answer 1 · Sat Mar 16 2019 14:53:02 GMT+0800 (China Standard Time)

I build tensorflow-lite on raspberry-3B+，and met this problem。

Javier Bonilla · Answer 2 · Sat Mar 16 2019 20:16:25 GMT+0800 (China Standard Time)

It also happened to me when cross-compiling for Raspberry Pi

./tensorflow/lite/tools/make/build_rpi_lib.sh

Javier Bonilla · Answer 3 · Sat Mar 16 2019 20:31:45 GMT+0800 (China Standard Time)

I have been doing some testing, I share here this in case it helps.

I get the error during the compilation when executing.

arm-linux-gnueabihf-g++ -O3 -DNDEBUG -fPIC --std=c++11 -march=armv7-a -mfpu=neon-vfpv4 -funsafe-math-optimizations -ftree-vectorize -fPIC -I. -I/home/javi/Qt/tensorflow/tensorflow/lite/tools/make/../../../../../ -I/home/javi/Qt/tensorflow/tensorflow/lite/tools/make/../../../../../../ -I/home/javi/Qt/tensorflow/tensorflow/lite/tools/make/downloads/ -I/home/javi/Qt/tensorflow/tensorflow/lite/tools/make/downloads/eigen -I/home/javi/Qt/tensorflow/tensorflow/lite/tools/make/downloads/absl -I/home/javi/Qt/tensorflow/tensorflow/lite/tools/make/downloads/gemmlowp -I/home/javi/Qt/tensorflow/tensorflow/lite/tools/make/downloads/neon_2_sse -I/home/javi/Qt/tensorflow/tensorflow/lite/tools/make/downloads/farmhash/src -I/home/javi/Qt/tensorflow/tensorflow/lite/tools/make/downloads/flatbuffers/include -I -I/usr/local/include -c tensorflow/lite/kernels/depthwise_conv.cc -o /home/javi/Qt/tensorflow/tensorflow/lite/tools/make/gen/rpi_armv7l/obj/tensorflow/lite/kernels/depthwise_conv.o

But, if I remove mfpu=neon-vfpv4 from the previous command, it works.

I also noticed than when executing ./tensorflow/lite/tools/make/download_dependencies.sh, I get this warning.

cat: /home/javi/Qt/tensorflow/tensorflow/lite/tools/make/../../../../third_party/eigen3/gebp_neon.patch: No such file or directory

jrullan · Answer 4 · Thu Mar 21 2019 08:36:15 GMT+0800 (China Standard Time)

I had the exact same error on a Pine64 A64+ Board.

alexhegit · Answer 5 · Thu Mar 21 2019 15:39:23 GMT+0800 (China Standard Time)

Same problom with master branch of tensorflow for ARMv8 platform

teddylai · Answer 6 · Tue Mar 26 2019 11:11:57 GMT+0800 (China Standard Time)

It also happened to me when cross-compiling for ARMv8 platform

Jakub Kunert · Answer 7 · Tue Mar 26 2019 18:40:56 GMT+0800 (China Standard Time)

Same for me.

Koan-Sin Tan · Answer 8 · Wed Mar 27 2019 10:55:06 GMT+0800 (China Standard Time)

I think the code was not tested with newer gcc. If you build it with gcc or clang for android-arm64, e.g.,

bazel build  --config android_arm64 --cxxopt=-std=c++11 \
//tensorflow/lite/examples/label_image:label_image --config monolithic

It goes well.

To build it for aarch64 machines running Linux with gcc, either natively or cross-compiling, as suggested in the error message use -flax-vector-conversions is one of the possible answers. Other possible solutions include adding explicit type casting to make gcc happy. Or you can use clang instead of gcc. Tested on an internal dev board and Google's Coral Dev Board.

I'll submit a PR for this issue later.

Koan-Sin Tan · Answer 9 · Wed Mar 27 2019 17:39:41 GMT+0800 (China Standard Time)

it seem the problem is gone after 152095e. Those who met the problem may want to git pull and try again.

jrullan · Answer 10 · Thu Apr 18 2019 08:40:03 GMT+0800 (China Standard Time)

@freedomtan I tried it again in my Pine64 A64+ with the process described in the guide and this time it ended with a different error:

nnapi_delegate.cc:(.text+0x28): undefined reference to `NnApiImplementation()'
/home/pine/Downloads/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/lib/libtensorflow-lite.a(nnapi_delegate.o): In function `tflite::NNAPIAllocation::NNAPIAllocation(char const*, tflite::ErrorReporter*)':
nnapi_delegate.cc:(.text+0x18c): undefined reference to `NnApiImplementation()'
/home/pine/Downloads/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/lib/libtensorflow-lite.a(nnapi_delegate.o): In function `tflite::NNAPIDelegate::~NNAPIDelegate()':
nnapi_delegate.cc:(.text+0x200): undefined reference to `NnApiImplementation()'
nnapi_delegate.cc:(.text+0x21c): undefined reference to `NnApiImplementation()'
/home/pine/Downloads/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/lib/libtensorflow-lite.a(nnapi_delegate.o): In function `tflite::addTensorOperands(tflite::Subgraph*, ANeuralNetworksModel*, unsigned int*, std::vector<long, std::allocator<long> >*)':
nnapi_delegate.cc:(.text+0x298): undefined reference to `NnApiImplementation()'
/home/pine/Downloads/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/lib/libtensorflow-lite.a(nnapi_delegate.o):nnapi_delegate.cc:(.text+0x578): more undefined references to `NnApiImplementation()' follow
collect2: error: ld returned 1 exit status
tensorflow/lite/tools/make/Makefile:227: recipe for target '/home/pine/Downloads/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/bin/minimal' failed
make: *** [/home/pine/Downloads/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/bin/minimal] Error 1

Edit 1: Maybe this is the same as Issue 25120?

Edit 2: Indeed this appears to be issue 25120. I did as suggested there, modified the Makefile to set BUILD_WITH_NNAPI=true -> BUILD_WITH_NNAPI=false, deleted the /gen folder and re ran the build script and it finished without errors. Now I guess it's time to run some example to try it out. I'll do that next.

Kevin Mader · Answer 11 · Wed May 08 2019 17:24:35 GMT+0800 (China Standard Time)

I have a travis-ci build running to build tflite and can reproduce the error on the latest commit: https://travis-ci.org/kmader/tflite_lib_builder/jobs/529685375

PhilipXue · Answer 12 · Tue Jun 04 2019 13:40:20 GMT+0800 (China Standard Time)

Hi, I still have the same error under both the latest master branch and r1.14 tag. Any progress on a solution to it?

PhilipXue · Answer 13 · Thu Jun 06 2019 14:08:10 GMT+0800 (China Standard Time)

@freedomtan
Changed to clang, the mentioned error goes away, but the following error occurs at the end of the compilation.
Clang info: clang version 6.0.0-1ubuntu2 (tags/RELEASE_600/final) Target: aarch64-unknown-linux-gnu

/usr/bin/llvm-ar-6.0: creating /home/pi/code/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/lib/libtensorflow-lite.a
/usr/bin/clang++ -O3 -DNDEBUG -fPIC  --std=c++11 -march=armv8-a -funsafe-math-optimizations -ftree-vectorize -fPIC -I. -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/../../../../../ -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/../../../../../../ -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/ -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/eigen -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/absl -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/gemmlowp -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/neon_2_sse -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/farmhash/src -I -I/usr/local/include \
-o /home/pi/code/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/bin/minimal /home/pi/code/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/obj/tensorflow/lite/examples/minimal/minimal.o \
 /home/pi/code/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/lib/libtensorflow-lite.a -Wl,--no-export-dynamic -Wl,--exclude-libs,ALL -Wl,--gc-sections -Wl,--as-needed -lrt -lstdc++ -lpthread -lm -ldl/home/pi/code/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/lib/libtensorflow-lite.a(audio_spectrogram.o): In function `flexbuffers::Reference::AsUInt64() const':
audio_spectrogram.cc:(.text._ZNK11flexbuffers9Reference8AsUInt64Ev[_ZNK11flexbuffers9Reference8AsUInt64Ev]+0x2f0): undefined reference to `flatbuffers::ClassicLocale::instance_'
audio_spectrogram.cc:(.text._ZNK11flexbuffers9Reference8AsUInt64Ev[_ZNK11flexbuffers9Reference8AsUInt64Ev]+0x2f4): undefined reference to `flatbuffers::ClassicLocale::instance_'
/home/pi/code/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/lib/libtensorflow-lite.a(while.o): In function `flexbuffers::Reference::AsInt64() const':
while.cc:(.text._ZNK11flexbuffers9Reference7AsInt64Ev[_ZNK11flexbuffers9Reference7AsInt64Ev]+0x2f0): undefined reference to `flatbuffers::ClassicLocale::instance_'
while.cc:(.text._ZNK11flexbuffers9Reference7AsInt64Ev[_ZNK11flexbuffers9Reference7AsInt64Ev]+0x2f4): undefined reference to `flatbuffers::ClassicLocale::instance_'
clang: error: linker command failed with exit code 1 (use -v to see invocation)
tensorflow/lite/tools/make/Makefile_clang:264: recipe for target '/home/pi/code/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/bin/minimal' failed
make: *** [/home/pi/code/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/bin/minimal] Error 1
make: *** Waiting for unfinished jobs....

And adding -flax-vector-conversions flag end up with this error. gcc version gcc (Ubuntu/Linaro 7.4.0-1ubuntu1~18.04) 7.4.0

aarch64-linux-gnu-g++ -O3 -DNDEBUG -fPIC -flax-vector-conversions  --std=c++11 -march=armv8-a -funsafe-math-optimizations -ftree-vectorize -fPIC -I. -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/../../../../../ -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/../../../../../../ -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/ -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/eigen -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/absl -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/gemmlowp -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/neon_2_sse -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/farmhash/src -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/flatbuffers/include -I -I/usr/local/include -c tensorflow/lite/kernels/dequantize.cc -o /home/pi/code/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/obj/tensorflow/lite/kernels/dequantize.o
In file included from ./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8.h:23:0,
                 from ./tensorflow/lite/kernels/internal/optimized/depthwiseconv_multithread.h:22,
                 from tensorflow/lite/kernels/depthwise_conv.cc:28:
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h: In static member function ‘static void tflite::optimized_ops::depthwise_conv::KernelMacroBlock<(tflite::DepthwiseConvImplementation)3, (tflite::DepthwiseConvDepthMultiplication)0, 2>::Run(const int8*, const int8*, const int32*, uint8*, const tflite::optimized_ops::depthwise_conv::DepthwiseConvDotProdParams*)’:
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:8255:3: error: x29 cannot be used in asm here

Koan-Sin Tan · Answer 14 · Thu Jun 06 2019 14:37:54 GMT+0800 (China Standard Time)

@PhilipXue try adding -fomit-frame-pointer to see if it can make inline assembly happy

PhilipXue · Answer 15 · Thu Jun 06 2019 15:32:39 GMT+0800 (China Standard Time)

@freedomtan
Hi, thanks for reply, I add the suggested flag and the previous error is gone, but end up with the following error at the end, which is the same error as the clang compilation.

aarch64-linux-gnu-ar: creating /home/pi/code/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/lib/libtensorflow-lite.a
aarch64-linux-gnu-g++ -O3 -DNDEBUG -fPIC -flax-vector-conversions -fomit-frame-pointer  --std=c++11 -march=armv8-a -funsafe-math-optimizations -ftree-vectorize -fPIC -I. -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/../../../../../ -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/../../../../../../ -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/ -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/eigen -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/absl -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/gemmlowp -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/neon_2_sse -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/farmhash/src -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/flatbuffers/include -I -I/usr/local/include \
-o /home/pi/code/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/bin/minimal /home/pi/code/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/obj/tensorflow/lite/examples/minimal/minimal.o \
 /home/pi/code/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/lib/libtensorflow-lite.a -Wl,--no-export-dynamic -Wl,--exclude-libs,ALL -Wl,--gc-sections -Wl,--as-needed -lrt -lstdc++ -lpthread -lm -ldl/home/pi/code/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/lib/libtensorflow-lite.a(while.o): In function `tflite::ops::custom::while_kernel::Init(TfLiteContext*, char const*, unsigned long)':
while.cc:(.text+0x1a6c): undefined reference to `flatbuffers::ClassicLocale::instance_'
while.cc:(.text+0x1a7c): undefined reference to `flatbuffers::ClassicLocale::instance_'
while.cc:(.text+0x1db8): undefined reference to `flatbuffers::ClassicLocale::instance_'
while.cc:(.text+0x1dc8): undefined reference to `flatbuffers::ClassicLocale::instance_'
/home/pi/code/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/lib/libtensorflow-lite.a(audio_spectrogram.o): In function `tflite::ops::custom::audio_spectrogram::Init(TfLiteContext*, char const*, unsigned long)':
audio_spectrogram.cc:(.text+0xd94): undefined reference to `flatbuffers::ClassicLocale::instance_'
/home/pi/code/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/lib/libtensorflow-lite.a(audio_spectrogram.o):audio_spectrogram.cc:(.text+0xda4): more undefined references to `flatbuffers::ClassicLocale::instance_' follow
collect2: error: ld returned 1 exit status
tensorflow/lite/tools/make/Makefile:267: recipe for target '/home/pi/code/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/bin/minimal' failed

It seems that flatbuffer is to blame, I am trying both lasted github flatbuffer and one download by dowload_denpendencies.sh,
Also, I am trying a fresh reinstall of the OS.

leonard951 · Answer 16 · Fri Jun 07 2019 05:37:35 GMT+0800 (China Standard Time)

I turned in a pull request at #29515 that can hopefully resolve the two issues.

mrudulaathi · Answer 17 · Mon Jun 10 2019 22:02:24 GMT+0800 (China Standard Time)

@freedomtan
Hi, thanks for reply, I add the suggested flag and the previous error is gone, but end up with the following error at the end, which is the same error as the clang compilation.

aarch64-linux-gnu-ar: creating /home/pi/code/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/lib/libtensorflow-lite.a
aarch64-linux-gnu-g++ -O3 -DNDEBUG -fPIC -flax-vector-conversions -fomit-frame-pointer  --std=c++11 -march=armv8-a -funsafe-math-optimizations -ftree-vectorize -fPIC -I. -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/../../../../../ -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/../../../../../../ -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/ -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/eigen -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/absl -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/gemmlowp -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/neon_2_sse -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/farmhash/src -I/home/pi/code/tensorflow/tensorflow/lite/tools/make/downloads/flatbuffers/include -I -I/usr/local/include \
-o /home/pi/code/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/bin/minimal /home/pi/code/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/obj/tensorflow/lite/examples/minimal/minimal.o \
 /home/pi/code/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/lib/libtensorflow-lite.a -Wl,--no-export-dynamic -Wl,--exclude-libs,ALL -Wl,--gc-sections -Wl,--as-needed -lrt -lstdc++ -lpthread -lm -ldl/home/pi/code/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/lib/libtensorflow-lite.a(while.o): In function `tflite::ops::custom::while_kernel::Init(TfLiteContext*, char const*, unsigned long)':
while.cc:(.text+0x1a6c): undefined reference to `flatbuffers::ClassicLocale::instance_'
while.cc:(.text+0x1a7c): undefined reference to `flatbuffers::ClassicLocale::instance_'
while.cc:(.text+0x1db8): undefined reference to `flatbuffers::ClassicLocale::instance_'
while.cc:(.text+0x1dc8): undefined reference to `flatbuffers::ClassicLocale::instance_'
/home/pi/code/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/lib/libtensorflow-lite.a(audio_spectrogram.o): In function `tflite::ops::custom::audio_spectrogram::Init(TfLiteContext*, char const*, unsigned long)':
audio_spectrogram.cc:(.text+0xd94): undefined reference to `flatbuffers::ClassicLocale::instance_'
/home/pi/code/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/lib/libtensorflow-lite.a(audio_spectrogram.o):audio_spectrogram.cc:(.text+0xda4): more undefined references to `flatbuffers::ClassicLocale::instance_' follow
collect2: error: ld returned 1 exit status
tensorflow/lite/tools/make/Makefile:267: recipe for target '/home/pi/code/tensorflow/tensorflow/lite/tools/make/gen/aarch64_armv8-a/bin/minimal' failed

It seems that flatbuffer is to blame, I am trying both lasted github flatbuffer and one download by dowload_denpendencies.sh,
Also, I am trying a fresh reinstall of the OS.

I have the same issue. Any solutions yet?

vizero1 · Answer 18 · Tue Jun 11 2019 22:55:54 GMT+0800 (China Standard Time)

Anyone has a workaround to the error with flatbuffer? Have also that problem.

leonard951 · Answer 19 · Wed Jun 12 2019 00:06:03 GMT+0800 (China Standard Time)

I don't have the flatbuffer issue when applying the patch at #29515 and using gcc. Do you guys have to use llvm?

Koan-Sin Tan · Answer 20 · Fri Jun 14 2019 09:38:10 GMT+0800 (China Standard Time)

Haven't really checked what happened to cmake, bazel build works reliably for me with either gcc or clang :-)

renjie-liu · Answer 21 · Tue Jun 18 2019 14:14:28 GMT+0800 (China Standard Time)

we're working on that internally

Mohan Barathi · Answer 22 · Wed Jul 03 2019 17:52:32 GMT+0800 (China Standard Time)

Anyone has a workaround to the error with flatbuffer? Have also that problem.

Hi @vizero1 ...
I was able to solve the problem by following the workaround mentioned in issue 29806.

I have added those changes along with the above mentioned changes, and made a new Makefile (for aarch64 architecture).

Gist of the new makefile

renjie-liu · Answer 23 · Thu Jul 04 2019 13:52:16 GMT+0800 (China Standard Time)

Hi, can you sync to the head and try again? thanks!

Deleted user · Answer 24 · Thu Jul 04 2019 23:13:34 GMT+0800 (China Standard Time)

Hi, can you sync to the head and try again? thanks!

I successfully built head: https://github.com/tensorflow/tensorflow/tree/fc7bce9b4ada6ef123b899ed88889923c9fafae6
on aarch64 without needing the r1.14.0 build-fix (setting -flax-vector-conversions).

Thanks

renjie-liu · Answer 25 · Mon Jul 15 2019 10:52:26 GMT+0800 (China Standard Time)

mark this issue as fixed, plz reopen if any other issue occurs.