AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

SWDEV-422771 - Update some documents

Browse Source 
Change-Id: I7a4032af44b66b6936e845ecce59e189f5c03664
This commit is contained in:
Julia Jiang
2023-09-22 14:37:33 -04:00
committed by Julia Jiang
parent 2e8e205552
commit a4066ec239
8 changed files with 26 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/user_guide/faq.md
+1 -1
View File
@@ -280,7 +280,7 @@ The per-thread default stream is an implicit stream local to both the thread and
The per-thread default stream is a blocking stream and will synchronize with the default null stream if both are used in a program.
In ROCm, a compilation option should be added in order to compile the translation unit with per-thread default stream enabled.
“-fgpu-default-stream=per-thread”.
"-fgpu-default-stream=per-thread".
Once source is compiled with per-thread default stream enabled, all APIs will be executed on per thread default stream, hence there will not be any implicit synchronization with other streams.
Besides, per-thread default stream be enabled per translation unit, users can compile some files with feature enabled and some with feature disabled. Feature enabled translation unit will have default stream as per thread and there will not be any implicit synchronization done but other modules will have legacy default stream which will do implicit synchronization.
docs/user_guide/hip_porting_guide.md
+3 -3
View File
@@ -89,7 +89,7 @@ directory names.
| CUB | rocPRIM | Low Level Optimized Parallel Primitives
| cuDNN | MIOpen | Deep learning Solver Library
| cuRAND | rocRAND | Random Number Generator Library
| EIGEN | EIGEN – HIP port | C++ template library for linear algebra: matrices, vectors, numerical solvers,
| EIGEN | EIGEN - HIP port | C++ template library for linear algebra: matrices, vectors, numerical solvers,
| NCCL | RCCL | Communications Primitives Library based on the MPI equivalents
@@ -333,7 +333,7 @@ CPPFLAGS += $(shell $(HIP_PATH)/bin/hipconfig --cpp_config)
nvcc includes some headers by default. However, HIP does not include default headers, and instead all required files must be explicitly included.
Specifically, files that call HIP run-time APIs or define HIP kernels must explicitly include the appropriate HIP headers.
If the compilation process reports that it cannot find necessary APIs (for example, "error: identifier ‘hipSetDevice’ is undefined"),
If the compilation process reports that it cannot find necessary APIs (for example, "error: identifier hipSetDevice is undefined"),
ensure that the file includes hip_runtime.h (or hip_runtime_api.h, if appropriate).
The hipify-perl script automatically converts "cuda_runtime.h" to "hip_runtime.h," and it converts "cuda_runtime_api.h" to "hip_runtime_api.h", but it may miss nested headers or macros.
@@ -465,7 +465,7 @@ As an example, please see the code from the [link](github.com/ROCm-Developer-Too
With the #ifdef condition, HIP APIs work as expected on both AMD and NVIDIA platforms.
Note, cudaMemoryType enum value cudaMemoryTypeUnregstered is not supported currently in hipMemoryType, due to HIP functionality backward compatibility.
Note, cudaMemoryTypeUnregstered is currently not supported in hipMemoryType enum, due to HIP functionality backward compatibility.
## threadfence_system
Threadfence_system makes all device memory writes, all writes to mapped host memory, and all writes to peer memory visible to CPU and other GPU devices.
docs/user_guide/programming_manual.md
+6 -6
View File
@@ -29,10 +29,10 @@ Note, Numa policy is so far implemented on Linux, and under development on Windo
### Coherency Controls
ROCm defines two coherency options for host memory:
- Coherent memory : Supports fine-grain synchronization while the kernel is running.  For example, a kernel can perform atomic operations that are visible to the host CPU or to other (peer) GPUs.  Synchronization instructions include threadfence_system and C++11-style atomic operations.
- Coherent memory : Supports fine-grain synchronization while the kernel is running. For example, a kernel can perform atomic operations that are visible to the host CPU or to other (peer) GPUs. Synchronization instructions include threadfence_system and C++11-style atomic operations.
In order to achieve this fine-grained coherence, many AMD GPUs use a limited cache policy, such as leaving these allocations uncached by the GPU, or making them read-only.
- Non-coherent memory : Can be cached by GPU, but cannot support synchronization while the kernel is running.  Non-coherent memory can be optionally synchronized only at command (end-of-kernel or copy command) boundaries.  This memory is appropriate for high-performance access when fine-grain synchronization is not required.
- Non-coherent memory : Can be cached by GPU, but cannot support synchronization while the kernel is running. Non-coherent memory can be optionally synchronized only at command (end-of-kernel or copy command) boundaries. This memory is appropriate for high-performance access when fine-grain synchronization is not required.
HIP provides the developer with controls to select which type of memory is used via allocation flags passed to hipHostMalloc and the HIP_HOST_COHERENT environment variable. By default, the environment variable HIP_HOST_COHERENT is set to 0 in HIP.
The control logic in the current version of HIP is as follows:
@@ -59,10 +59,10 @@ Non-coherent
### hipEventSynchronize
Developers can control the release scope for hipEvents:
- By default, the GPU performs a device-scope acquire and release operation with each recorded event.  This will make host and device memory visible to other commands executing on the same device.
- By default, the GPU performs a device-scope acquire and release operation with each recorded event. This will make host and device memory visible to other commands executing on the same device.
A stronger system-level fence can be specified when the event is created with hipEventCreateWithFlags:
- hipEventReleaseToSystem : Perform a system-scope release operation when the event is recorded.  This will make both Coherent and Non-Coherent host memory visible to other agents in the system, but may involve heavyweight operations such as cache flushing.  Coherent memory will typically use lighter-weight in-kernel synchronization mechanisms such as an atomic operation and thus does not need to use hipEventReleaseToSystem.
- hipEventReleaseToSystem : Perform a system-scope release operation when the event is recorded. This will make both Coherent and Non-Coherent host memory visible to other agents in the system, but may involve heavyweight operations such as cache flushing. Coherent memory will typically use lighter-weight in-kernel synchronization mechanisms such as an atomic operation and thus does not need to use hipEventReleaseToSystem.
- hipEventDisableTiming: Events created with this flag would not record profiling data and provide best performance if used for synchronization.
### Summary and Recommendations:
@@ -146,7 +146,7 @@ The test codes in the link (https://github.com/ROCm-Developer-Tools/HIP/blob/dev
The per-thread default stream is supported in HIP. It is an implicit stream local to both the thread and the current device. This means that the command issued to the per-thread default stream by the thread does not implicitly synchronize with other streams (like explicitly created streams), or default per-thread stream on other threads.
The per-thread default stream is a blocking stream and will synchronize with the default null stream if both are used in a program.
The per-thread default stream can be enabled via adding a compilation option,
“-fgpu-default-stream=per-thread”.
"-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-Developer-Tools/hip-tests/tree/develop/catch/unit/streamperthread).
@@ -193,4 +193,4 @@ Here is an example to create and use static libraries:
hipcc libHipDevice.a test.cpp -fgpu-rdc -o test.out
```
For more information, please see samples/2_Cookbook/15_static_library/host_functions and samples/2_Cookbook/15_static_library/device_functions.
For more information, please see [HIP samples](https://github.com/ROCm-Developer-Tools/hip-tests/tree/rocm-5.5.x/samples/2_Cookbook/15_static_library/host_functions) and [samples](https://github.com/ROCm-Developer-Tools/hip-tests/tree/rocm-5.5.x/samples/2_Cookbook/15_static_library/device_functions).