Comments (7)
e7176cf causes such error. inline code cant work properly in some CPU.
from ppl.nn.
You can append -DPPL_USE_X86_AVX512=OFF
to the cmake command-line to separate the AVX512 codes.
But in this case, the error is not about the CPU but the compiler.
Can you tell us about your environment?
Including OS, compiler and the command-line?
from ppl.nn.
You can append
-DPPL_USE_X86_AVX512=OFF
to the cmake command-line to separate the AVX512 codes.
PPL_USE_X86_AVX512 work for me.
But in this case, the error is not about the CPU but the compiler.
Can you tell us about your environment?
Including OS, compiler and the command-line?
os : ubuntu20.04
gcc: 9.3.0
cmd: ./build.sh -DHPCC_USE_X86_64=ON
from ppl.nn.
os : ubuntu20.04
gcc: 9.3.0
cmd: ./build.sh -DHPCC_USE_X86_64=ON
I cannot reproduce the compile error with a similar environment.
I have built the lastest master successfully with:
CPU: i7-10700K
OS: ubuntu 20.04.2
gcc: 9.3.0
cmd: ./build.sh -DHPCC_USE_X86_64=ON
Can you show the entire error message by GCC?
from ppl.nn.
os : ubuntu20.04
gcc: 9.3.0
cmd: ./build.sh -DHPCC_USE_X86_64=ONI cannot reproduce the compile error with a similar environment.
I have built the lastest master successfully with:
CPU: i7-10700K
OS: ubuntu 20.04.2
gcc: 9.3.0
cmd: ./build.sh -DHPCC_USE_X86_64=ONCan you show the entire error message by GCC?
Hope it is not late to say sorry. I think my description above may guides wrong direction.
In brief, try to replace 'Release' with 'Debug' in build.sh and then rebuild your master.
/home/workspace/ppl.nn/src/ppl/nn/engines/x86/impls/src/ppl/kernel/x86/fp32/gemm/fma/gemm_kernel_fp32_fma.cpp: In function ‘void ppl::kernel::x86::gemm_fp32_fma_kernel_core(int64_t*) [with long int u_m = 1; long int u_n = 8]’:
/home/workspace/ppl.nn/src/ppl/nn/engines/x86/impls/src/ppl/kernel/x86/fp32/gemm/fma/gemm_kernel_fp32_fma.cpp:321:6: warning: asm operand 4 probably doesn’t match constraints
321 | );
| ^
/home/workspace/ppl.nn/src/ppl/nn/engines/x86/impls/src/ppl/kernel/x86/fp32/gemm/fma/gemm_kernel_fp32_fma.cpp:321:6: error: impossible constraint in ‘asm’
/home/workspace/ppl.nn/src/ppl/nn/engines/x86/impls/src/ppl/kernel/x86/fp32/gemm/fma/gemm_kernel_fp32_fma.cpp: In function ‘void ppl::kernel::x86::gemm_fp32_fma_kernel_core(int64_t*) [with long int u_m = 2; long int u_n = 8]’:
/home/workspace/ppl.nn/src/ppl/nn/engines/x86/impls/src/ppl/kernel/x86/fp32/gemm/fma/gemm_kernel_fp32_fma.cpp:321:6: warning: asm operand 4 probably doesn’t match constraints
321 | );
from ppl.nn.
os : ubuntu20.04
gcc: 9.3.0
cmd: ./build.sh -DHPCC_USE_X86_64=ONI cannot reproduce the compile error with a similar environment.
I have built the lastest master successfully with:
CPU: i7-10700K
OS: ubuntu 20.04.2
gcc: 9.3.0
cmd: ./build.sh -DHPCC_USE_X86_64=ON
Can you show the entire error message by GCC?Hope it is not late to say sorry. I think my description above may guides wrong direction.
In brief, try to replace 'Release' with 'Debug' in build.sh and then rebuild your master./home/workspace/ppl.nn/src/ppl/nn/engines/x86/impls/src/ppl/kernel/x86/fp32/gemm/fma/gemm_kernel_fp32_fma.cpp: In function ‘void ppl::kernel::x86::gemm_fp32_fma_kernel_core(int64_t*) [with long int u_m = 1; long int u_n = 8]’: /home/workspace/ppl.nn/src/ppl/nn/engines/x86/impls/src/ppl/kernel/x86/fp32/gemm/fma/gemm_kernel_fp32_fma.cpp:321:6: warning: asm operand 4 probably doesn’t match constraints 321 | ); | ^ /home/workspace/ppl.nn/src/ppl/nn/engines/x86/impls/src/ppl/kernel/x86/fp32/gemm/fma/gemm_kernel_fp32_fma.cpp:321:6: error: impossible constraint in ‘asm’ /home/workspace/ppl.nn/src/ppl/nn/engines/x86/impls/src/ppl/kernel/x86/fp32/gemm/fma/gemm_kernel_fp32_fma.cpp: In function ‘void ppl::kernel::x86::gemm_fp32_fma_kernel_core(int64_t*) [with long int u_m = 2; long int u_n = 8]’: /home/workspace/ppl.nn/src/ppl/nn/engines/x86/impls/src/ppl/kernel/x86/fp32/gemm/fma/gemm_kernel_fp32_fma.cpp:321:6: warning: asm operand 4 probably doesn’t match constraints 321 | );
Hello, I fix the compile issue with bulid type Debug
in #109 .
You can try my forked repo first or wait for the manager to accept the merge request.
from ppl.nn.
LGTM
from ppl.nn.
Related Issues (20)
- Onnx run error HOT 2
- 请问支持int8在高通芯片上cDSP进行推理吗?
- Slice op question HOT 1
- pplnn run mobilenet v2 model failed. (use cuda) HOT 7
- linux compile error protobuf static assertion failed HOT 3
- malloc_consolidate(): invalid chunk size HOT 2
- pplnn save-input 得到的NDARRAY的 shape不正确 HOT 1
- 如何使用cmake的将ppl.nn和依赖ppl.nn的代码一同编译? HOT 3
- Segmentation fault at ppl::nn::x86::X86Kernel::DumpOutputTensors HOT 5
- 获取模型推理结果(GetOutputs)耗时长 HOT 2
- Install Error HOT 1
- The compilation passed, but an error was reported in test phase HOT 2
- Floating point exception (core dumped) ? HOT 4
- 使用x86 engine运行resnet50 fp16 onnx模型 core dump
- (Ask) why InferInheritedType handle int8 to fp16 out? HOT 3
- Got wrong output shape when run a Gemm op(transB=0) use cuda HOT 4
- Crash with ONNX Split operator
- 关于全局engine,其他线程引用导致的性能下降问题 HOT 4
- 推理误差排查
- 多模型pipeline的示例
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ppl.nn.