[NVPTX][test] fixup version for ptxas on trunc-tofp.ll

[AlexMaclean]

No description provided.

[llvmbot]

@llvm/pr-subscribers-backend-nvptx

Author: Alex MacLean (AlexMaclean)

Changes

---

Full diff: https://github.com/llvm/llvm-project/pull/149558.diff

1 Files Affected:

• (modified) llvm/test/CodeGen/NVPTX/trunc-tofp.ll (+2-2)

diff --git a/llvm/test/CodeGen/NVPTX/trunc-tofp.ll b/llvm/test/CodeGen/NVPTX/trunc-tofp.ll
index 404c423cc026a..12502b6f29899 100644
--- a/llvm/test/CodeGen/NVPTX/trunc-tofp.ll
+++ b/llvm/test/CodeGen/NVPTX/trunc-tofp.ll
@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
-; RUN: llc < %s -mcpu=sm_80 | FileCheck %s
-; RUN: %if ptxas %{ llc < %s -mcpu=sm_80 | %ptxas-verify %}
+; RUN: llc < %s -mcpu=sm_50 | FileCheck %s
+; RUN: %if ptxas %{ llc < %s -mcpu=sm_50 | %ptxas-verify -arch=sm_50 %}
 
 target triple = "nvptx64-nvidia-cuda"