SWDEV-444835 - Merge changes in hip made in 6.1- to staging

Change-Id: I2ebebc7655f804a2192153ad1e07069ec2394c98


[ROCm/hip commit: 9eb37e9947]
This commit is contained in:
jujiang
2024-02-28 14:38:33 -05:00
förälder 5f6ae77a1e
incheckning 5495cd7892
7 ändrade filer med 15 tillägg och 15 borttagningar
+1 -1
Visa fil
@@ -43,7 +43,7 @@ Similiar format for future branches.
### Get HIP source code
A new repository 'hipother' is added in the ROCm 6.1 release, which is branched out from HIP.
The 'hipother'provides files required to support the HIP back-end implementation on some non-AMD platforms, like NVIDIA.
The 'hipother' provides files required to support the HIP back-end implementation on some non-AMD platforms, like NVIDIA.
```shell
git clone -b "$ROCM_BRANCH" https://github.com/ROCm/clr.git
@@ -57,16 +57,12 @@ Should use roctracer/rocTX instead
## HIP Texture Management APIs
### hipGetTextureReference
### hipGetTextureAlignmentOffset
### hipTexRefSetAddressMode
### hipTexRefSetArray
### hipTexRefSetFilterMode
### hipTexRefSetFlags
### hipTexRefSetFormat
### hipBindTexture
### hipBindTexture2D
### hipBindTextureToArray
### hipGetTextureAlignmentOffset
### hipUnbindTexture
### hipTexRefGetAddress
### hipTexRefGetAddressMode
### hipTexRefGetFilterMode
@@ -85,6 +81,10 @@ Should use roctracer/rocTX instead
### hipTexRefSetMipmapLevelBias
### hipTexRefSetMipmapLevelClamp
### hipTexRefSetMipmappedArray
### hipBindTextureToMipmappedArray
### hipTexRefGetBorderColor
### hipTexRefGetArray
### hipBindTexture
### hipBindTexture2D
### hipBindTextureToArray
### hipUnbindTexture
### hipBindTextureToMipmappedArray
@@ -681,7 +681,7 @@ Users need to include assert.h to use assert. For assert to work in both device
HIP provides the function abort() which can be used to terminate the application when terminal failures are detected. It is implemented using the `__builtin_trap()` function.
This function produces the effects of using `asm("trap")` in the CUDA code.
This function produces a similar effect of using `asm("trap")` in the CUDA code.
Note, in HIP, the function terminates the entire application, while in CUDA, `asm("trap")`only terminates the dispatch and the application continues to run.
+2 -2
Visa fil
@@ -2,12 +2,12 @@
## HIP RTC lib
HIP allows you to compile kernels at runtime with its ```hiprtc*``` APIs.
Kernels can be store as a text string and can be passed on to HIPRTC APIs alongside options to guide the compilation.
Kernels can be stored as a text string and can be passed on to HIPRTC APIs alongside options to guide the compilation.
NOTE:
- This library can be used on systems without HIP install nor AMD GPU driver installed at all (offline compilation). Therefore it does not depend on any HIP runtime library.
- But it does depend on COMGr. We may try to statically link COMGr into HIPRTC to avoid any ambiguity.
- But it does depend on COMGr. You may try to statically link COMGr into HIPRTC to avoid any ambiguity.
- Developers can decide to bundle this library with their application.
## Compile APIs
@@ -129,7 +129,7 @@ HIPRTC APIs accept HIP source files in character string format as input paramete
For more details on HIPRTC APIs, refer to [HIP Runtime API Reference](https://rocm.docs.amd.com/projects/HIP/en/latest/doxygen/html/index.html).
For Linux developers, the link here (https://github.com/ROCm/hip-tests/blob/develop/samples/2_Cookbook/23_cmake_hiprtc/saxpy.cpp) shows an example how to program HIP application using runtime compilation mechanism, and detail HIPRTC programming guide is also available in Github (https://github.com/ROCm/HIP/blob/develop/docs/user_guide/hip_rtc.md).
For Linux developers, the link [here](https://github.com/ROCm/hip-tests/blob/develop/samples/2_Cookbook/23_cmake_hiprtc/saxpy.cpp) shows an example how to program HIP application using runtime compilation mechanism, and detail HIPRTC programming guide is also available in Github (https://github.com/ROCm/HIP/blob/develop/docs/user_guide/hip_rtc.md).
## HIP Graph
HIP graph is supported. For more details, refer to the HIP API Guide.
@@ -146,7 +146,7 @@ The per-thread default stream is a blocking stream and will synchronize with the
The per-thread default stream can be enabled via adding a compilation option,
"-fgpu-default-stream=per-thread".
And users can explicitly use "hipStreamPerThread" as per-thread default stream handle as input in API commands. There are test codes as examples in the link (https://github.com/ROCm/hip-tests/tree/develop/catch/unit/streamperthread).
And users can explicitly use "hipStreamPerThread" as per-thread default stream handle as input in API commands. There are test codes as examples in the [link](https://github.com/ROCm/hip-tests/tree/develop/catch/unit/streamperthread).
## Use of Long Double Type