[llvm] [NVPTX] Add proper precondition in tensormap_replace_sm_103a test (PR #174144)

[via llvm-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-backend-nvptx

Author: Walter Lee (googlewalt)

<details>
<summary>Changes</summary>

Fixes 14b1d770db7f9ee49693063ad851215dede0766e.

---
Full diff: https://github.com/llvm/llvm-project/pull/174144.diff


1 Files Affected:

- (modified) llvm/test/CodeGen/NVPTX/tensormap_replace_sm_103a.ll (+1-1) 


``````````diff
diff --git a/llvm/test/CodeGen/NVPTX/tensormap_replace_sm_103a.ll b/llvm/test/CodeGen/NVPTX/tensormap_replace_sm_103a.ll
index 197bbdee692c2..931fe70a60182 100644
--- a/llvm/test/CodeGen/NVPTX/tensormap_replace_sm_103a.ll
+++ b/llvm/test/CodeGen/NVPTX/tensormap_replace_sm_103a.ll
@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
 ; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_103a -mattr=+ptx88 | FileCheck %s
-; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_103a -mattr=+ptx88 | %ptxas-verify -arch=sm_103a %}
+; RUN: %if ptxas-sm_103a && ptxas-isa-8.8 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_103a -mattr=+ptx88 | %ptxas-verify -arch=sm_103a %}
 
 define void @tensormap_replace_swizzle_mode(ptr addrspace(1) %global_addr, ptr addrspace(3) %shared_addr) {
 ; CHECK-LABEL: tensormap_replace_swizzle_mode(

``````````

</details>


https://github.com/llvm/llvm-project/pull/174144