[llvm] [NVPTX] Fixed few other failing ptxas tests (PR #125963)

via llvm-commits llvm-commits at lists.llvm.org
Wed Feb 5 16:01:04 PST 2025


llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-backend-nvptx

Author: Artem Belevich (Artem-B)

<details>
<summary>Changes</summary>



---
Full diff: https://github.com/llvm/llvm-project/pull/125963.diff


3 Files Affected:

- (modified) llvm/test/CodeGen/NVPTX/inline-asm-b128-test1.ll (+1-1) 
- (modified) llvm/test/CodeGen/NVPTX/inline-asm-b128-test2.ll (+1-1) 
- (modified) llvm/test/CodeGen/NVPTX/inline-asm-b128-test3.ll (+1-1) 


``````````diff
diff --git a/llvm/test/CodeGen/NVPTX/inline-asm-b128-test1.ll b/llvm/test/CodeGen/NVPTX/inline-asm-b128-test1.ll
index 4ebeba06032c6c..eaf6cf59dd0662 100644
--- a/llvm/test/CodeGen/NVPTX/inline-asm-b128-test1.ll
+++ b/llvm/test/CodeGen/NVPTX/inline-asm-b128-test1.ll
@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --extra_scrub --version 5
 ; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_70 -mattr=+ptx83 | FileCheck %s
-; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_70 -mattr=+ptx83 | %ptxas-verify -arch=sm_70 %}
+; RUN: %if ptxas-12.3 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_70 -mattr=+ptx83 | %ptxas-verify -arch=sm_70 %}
 
 target triple = "nvptx64-nvidia-cuda"
 
diff --git a/llvm/test/CodeGen/NVPTX/inline-asm-b128-test2.ll b/llvm/test/CodeGen/NVPTX/inline-asm-b128-test2.ll
index d5f3d83573e294..8441c30e4c4d46 100644
--- a/llvm/test/CodeGen/NVPTX/inline-asm-b128-test2.ll
+++ b/llvm/test/CodeGen/NVPTX/inline-asm-b128-test2.ll
@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
 ; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_70 -mattr=+ptx83 | FileCheck %s
-; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_70 -mattr=+ptx83 | %ptxas-verify -arch=sm_70 %}
+; RUN: %if ptxas-12.3 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_70 -mattr=+ptx83 | %ptxas-verify -arch=sm_70 %}
 
 target triple = "nvptx64-nvidia-cuda"
 
diff --git a/llvm/test/CodeGen/NVPTX/inline-asm-b128-test3.ll b/llvm/test/CodeGen/NVPTX/inline-asm-b128-test3.ll
index a3d40169c46958..39b8bf87e9fc55 100644
--- a/llvm/test/CodeGen/NVPTX/inline-asm-b128-test3.ll
+++ b/llvm/test/CodeGen/NVPTX/inline-asm-b128-test3.ll
@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --extra_scrub --version 5
 ; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_70 -mattr=+ptx83 | FileCheck %s
-; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_70 -mattr=+ptx83 | %ptxas-verify -arch=sm_70 %}
+; RUN: %if ptxas-12.3 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_70 -mattr=+ptx83 | %ptxas-verify -arch=sm_70 %}
 
 target triple = "nvptx64-nvidia-cuda"
 

``````````

</details>


https://github.com/llvm/llvm-project/pull/125963


More information about the llvm-commits mailing list