[llvm] [NVPTX] Add support for "blocksareclusters" kernel attr (PR #152265)

Rajat Bajpai via llvm-commits llvm-commits at lists.llvm.org
Thu Aug 14 02:33:47 PDT 2025


================
@@ -0,0 +1,78 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_100 | FileCheck %s
+
+target triple = "nvptx64-nvidia-cuda"
+
+; Test "blocksareclusters" attribute with full "reqntid" and "cluster_dim"
+; attributes.
+define ptx_kernel void @kernel1(i32* %input, i32* %output) #0 #1 #2 {
+; CHECK-LABEL: kernel1(
+; CHECK:       .blocksareclusters
+; CHECK-NEXT:  .reqntid 1024, 1, 1
+; CHECK-NEXT:  .reqnctapercluster 2, 2, 2
+; CHECK-NEXT:  {
+; CHECK-EMPTY:
+; CHECK-EMPTY:
+; CHECK-NEXT:  // %bb.0:
+; CHECK-NEXT:    ret;
+  ret void
+}
+
+; Test "blocksareclusters" attribute with single dimension "reqntid" and
+; "cluster_dim" attributes.
+define ptx_kernel void @kernel2(i32* %input, i32* %output) #0 #3 #4 {
+; CHECK-LABEL: kernel2(
+; CHECK:       .blocksareclusters
+; CHECK-NEXT:  .reqntid 1024
+; CHECK-NEXT:  .reqnctapercluster 2 // @kernel2
+; CHECK-NEXT:  {
+; CHECK-EMPTY:
+; CHECK-EMPTY:
+; CHECK-NEXT:  // %bb.0:
+; CHECK-NEXT:    ret;
+  ret void
+}
+
+; Test "blocksareclusters" attribute with two dimensions(not z dimension)
+; "reqntid" and "cluster_dim" attributes.
+define ptx_kernel void @kernel3(i32* %input, i32* %output) #0 #5 #6 {
+; CHECK-LABEL: kernel3(
+; CHECK:       .blocksareclusters
+; CHECK-NEXT:  .reqntid 512, 2
+; CHECK-NEXT:  .reqnctapercluster 2, 2 // @kernel3
+; CHECK-NEXT:  {
+; CHECK-EMPTY:
+; CHECK-EMPTY:
+; CHECK-NEXT:  // %bb.0:
+; CHECK-NEXT:    ret;
+  ret void
+}
+
+; Test "blocksareclusters" attribute with full "reqntid" and "cluster_dim"
+; attributes where kernel attribute is provided through metadata.
----------------
rajatbajpai wrote:

Good to know, removed.

https://github.com/llvm/llvm-project/pull/152265


More information about the llvm-commits mailing list