Add common CHECK prefix

Author: justinfargnoli

llvm/test/CodeGen/NVPTX/cp-async-bulk.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_90 -mattr=+ptx80| FileCheck --check-prefixes=CHECK-PTX64 %s
-; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx80 --nvptx-short-ptr| FileCheck --check-prefixes=CHECK-PTX-SHARED32 %s
+; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx80| FileCheck --check-prefixes=CHECK,CHECK-PTX64 %s
+; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx80 --nvptx-short-ptr| FileCheck --check-prefixes=CHECK,CHECK-PTX-SHARED32 %s
 ; RUN: %if ptxas-12.3 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx80| %ptxas-verify -arch=sm_90 %}
 ; RUN: %if ptxas-12.3 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx80 --nvptx-short-ptr| %ptxas-verify -arch=sm_90 %}
 
@@ -119,31 +119,18 @@ define void @cp_async_bulk_cta_to_cluster(ptr addrspace(3) %src, ptr addrspace(3
 }
 
 define void @cp_async_bulk_prefetch(ptr addrspace(1) %src, i32 %size, i64 %ch) {
-; CHECK-PTX64-LABEL: cp_async_bulk_prefetch(
-; CHECK-PTX64:       {
-; CHECK-PTX64-NEXT:    .reg .b32 %r<2>;
-; CHECK-PTX64-NEXT:    .reg .b64 %rd<3>;
-; CHECK-PTX64-EMPTY:
-; CHECK-PTX64-NEXT:  // %bb.0:
-; CHECK-PTX64-NEXT:    ld.param.u64 %rd1, [cp_async_bulk_prefetch_param_0];
-; CHECK-PTX64-NEXT:    ld.param.u32 %r1, [cp_async_bulk_prefetch_param_1];
-; CHECK-PTX64-NEXT:    ld.param.u64 %rd2, [cp_async_bulk_prefetch_param_2];
-; CHECK-PTX64-NEXT:    cp.async.bulk.prefetch.L2.global.L2::cache_hint [%rd1], %r1, %rd2;
-; CHECK-PTX64-NEXT:    cp.async.bulk.prefetch.L2.global [%rd1], %r1;
-; CHECK-PTX64-NEXT:    ret;
-;
-; CHECK-PTX-SHARED32-LABEL: cp_async_bulk_prefetch(
-; CHECK-PTX-SHARED32:       {
-; CHECK-PTX-SHARED32-NEXT:    .reg .b32 %r<2>;
-; CHECK-PTX-SHARED32-NEXT:    .reg .b64 %rd<3>;
-; CHECK-PTX-SHARED32-EMPTY:
-; CHECK-PTX-SHARED32-NEXT:  // %bb.0:
-; CHECK-PTX-SHARED32-NEXT:    ld.param.u64 %rd1, [cp_async_bulk_prefetch_param_0];
-; CHECK-PTX-SHARED32-NEXT:    ld.param.u32 %r1, [cp_async_bulk_prefetch_param_1];
-; CHECK-PTX-SHARED32-NEXT:    ld.param.u64 %rd2, [cp_async_bulk_prefetch_param_2];
-; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.prefetch.L2.global.L2::cache_hint [%rd1], %r1, %rd2;
-; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.prefetch.L2.global [%rd1], %r1;
-; CHECK-PTX-SHARED32-NEXT:    ret;
+; CHECK-LABEL: cp_async_bulk_prefetch(
+; CHECK:       {
+; CHECK-NEXT:    .reg .b32 %r<2>;
+; CHECK-NEXT:    .reg .b64 %rd<3>;
+; CHECK-EMPTY:
+; CHECK-NEXT:  // %bb.0:
+; CHECK-NEXT:    ld.param.u64 %rd1, [cp_async_bulk_prefetch_param_0];
+; CHECK-NEXT:    ld.param.u32 %r1, [cp_async_bulk_prefetch_param_1];
+; CHECK-NEXT:    ld.param.u64 %rd2, [cp_async_bulk_prefetch_param_2];
+; CHECK-NEXT:    cp.async.bulk.prefetch.L2.global.L2::cache_hint [%rd1], %r1, %rd2;
+; CHECK-NEXT:    cp.async.bulk.prefetch.L2.global [%rd1], %r1;
+; CHECK-NEXT:    ret;
   tail call void @llvm.nvvm.cp.async.bulk.prefetch.L2(ptr addrspace(1) %src, i32 %size, i64 %ch, i1 1)
   tail call void @llvm.nvvm.cp.async.bulk.prefetch.L2(ptr addrspace(1) %src, i32 %size, i64 0, i1 0)
   ret void