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

Added sample with __gfx*__ macro used

Browse Source 
Change-Id: I80a474947ea1b755082dad5329d1aff3ee78840c


[ROCm/hip commit: a45f6f7ff3]
This commit is contained in:
Sarbojit Sarkar
2020-10-12 02:44:58 -04:00
committed by Sarbojit Sarkar
parent e2f6d2f26c
commit 665440e499
4 changed files with 141 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
projects/hip/docs/markdown/hip_kernel_language.md
+3 -1
View File
@@ -52,7 +52,7 @@
- [In-Line Assembly](#in-line-assembly)
- [C++ Support](#c-support)
- [Kernel Compilation](#kernel-compilation)
- [GFX Arch specific kernel](#gfx-arch-specific-kernel)
<!-- tocstop -->
## Introduction
@@ -803,3 +803,5 @@ The file format for binary is `.co` which means Code Object. The following comma
Note that one important fact to remember when using binary code objects is that the number of arguments to the kernel are different on HCC and NVCC path. Refer to the sample in samples/0_Intro/module_api for differences in the arguments to be passed to the kernel.
## gfx-arch-specific-kernel
Clang defined '__gfx*__' macros can be used to execute gfx arch specific codes inside the kernel. Refer to the sample 14_gpu_arch in samples/2_Cookbook.