clang-hipify -> hipify-clang in documentation

Change-Id: I86ebc8112477db0d3e09f240beb3f9222d909ee6


[ROCm/clr commit: eb1fce0d77]
这个提交包含在:
Maneesh Gupta
2016-10-05 23:07:14 +05:30
父节点 5d19348868
当前提交 99d47a0850
修改 5 个文件,包含 6 行新增6 行删除
+1 -1
查看文件
@@ -33,7 +33,7 @@ HIP releases are typically of two types. The tag naming convention is different
- [HIP Porting Guide](docs/markdown/hip_porting_guide.md)
- [HIP Porting Driver Guide](docs/markdown/hip_porting_driver_api.md)
- [HIP Terminology](docs/markdown/hip_terms.md) (including Rosetta Stone of GPU computing terms across CUDA/HIP/HC/AMP/OpenL)
- [clang-hipify](clang-hipify/README.md)
- [hipify-clang](hipify-clang/README.md)
- [Developer/CONTRIBUTING Info](CONTRIBUTING.md)
- [Release Notes](RELEASE.md)
+2 -2
查看文件
@@ -114,7 +114,7 @@ These offer pointer-based memory interfaces (as opposed to opaque buffers) and c
- [hcsparse](https://bitbucket.org/multicoreware/hcsparse)
- [hcrng](https://bitbucket.org/multicoreware/hcrng)
Additionally, some of the cublas routines are automatically converted to hipblas equivalents by the clang-hipify tool. These APIs use cublas or hcblas depending on the platform, and replace the need
Additionally, some of the cublas routines are automatically converted to hipblas equivalents by the hipify-clang tool. These APIs use cublas or hcblas depending on the platform, and replace the need
to use conditional compilation.
### How does HIP compare with OpenCL?
@@ -148,7 +148,7 @@ The tools also struggle with more complex CUDA applications, in particular those
### Does Hipify automatically convert all source code?
Typically, Hipify can automatically convert almost all run-time code, and the coordinate indexing device code (i.e. threadIdx.x -> hipThreadIdx_x).
Most device code needs no additional conversion, since HIP and CUDA have similar names for math and built-in functions.
The clang-hipify tool will automatically modify the kernel signature as needed (automating a step that used to be done manually)
The hipify-clang tool will automatically modify the kernel signature as needed (automating a step that used to be done manually)
Additional porting may be required to deal with architecture feature queries or with CUDA capabilities that HIP doesn't support.
In general, developers should always expect to perform some platform-specific tuning and optimization.
@@ -95,6 +95,6 @@ Use hipcc to build the application, which is using hcc on AMD and nvcc on nvidia
- [HIP Runtime API (Doxygen)](http://gpuopen-professionalcompute-tools.github.io/HIP)
- [HIP Porting Guide](https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP/docs/markdown/hip_porting_guide.md)
- [HIP Terminology](https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP/docs/markdown/hip_terms.md) (including Rosetta Stone of GPU computing terms across CUDA/HIP/HC/AMP/OpenL)
- [clang-hipify](https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP/clang-hipify/README.md)
- [hipify-clang](https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP/hipify-clang/README.md)
- [Developer/CONTRIBUTING Info](https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP/CONTRIBUTING.md)
- [Release Notes](https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP/RELEASE.md)
@@ -69,6 +69,6 @@ Use hipcc to build the application, which is using hcc on AMD and nvcc on nvidia
- [HIP Runtime API (Doxygen)](http://gpuopen-professionalcompute-tools.github.io/HIP)
- [HIP Porting Guide](https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP/docs/markdown/hip_porting_guide.md)
- [HIP Terminology](https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP/docs/markdown/hip_terms.md) (including Rosetta Stone of GPU computing terms across CUDA/HIP/HC/AMP/OpenL)
- [clang-hipify](https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP/clang-hipify/README.md)
- [hipify-clang](https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP/hipify-clang/README.md)
- [Developer/CONTRIBUTING Info](https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP/CONTRIBUTING.md)
- [Release Notes](https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP/RELEASE.md)
@@ -46,6 +46,6 @@ Note this trace mode uses colors. "less -r" can handle raw control characters an
- [HIP Runtime API (Doxygen)](http://gpuopen-professionalcompute-tools.github.io/HIP)
- [HIP Porting Guide](https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP/docs/markdown/hip_porting_guide.md)
- [HIP Terminology](https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP/docs/markdown/hip_terms.md) (including Rosetta Stone of GPU computing terms across CUDA/HIP/HC/AMP/OpenL)
- [clang-hipify](https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP/clang-hipify/README.md)
- [hipify-clang](https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP/hipify-clang/README.md)
- [Developer/CONTRIBUTING Info](https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP/CONTRIBUTING.md)
- [Release Notes](https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP/RELEASE.md)