[llvm] 3f8af4f - [NFC][AMDGPU] Pre-commit srl preserve flag test (#146747)

[via llvm-commits]

Author: LU-JOHN
Date: 2025-07-07T14:40:29+09:00
New Revision: 3f8af4f55129b818752e2e95e319474ee239a894

URL: https://github.com/llvm/llvm-project/commit/3f8af4f55129b818752e2e95e319474ee239a894
DIFF: https://github.com/llvm/llvm-project/commit/3f8af4f55129b818752e2e95e319474ee239a894.diff

LOG: [NFC][AMDGPU] Pre-commit srl preserve flag test (#146747)

Pre-commit test for exact flag preservation when converting from 64-bit
srl to 32-bit.

Signed-off-by: John Lu <John.Lu at amd.com>

Added: 
    llvm/test/CodeGen/AMDGPU/srl64_reduce_flags.ll

Modified: 
    

Removed: 
    


################################################################################
diff  --git a/llvm/test/CodeGen/AMDGPU/srl64_reduce_flags.ll b/llvm/test/CodeGen/AMDGPU/srl64_reduce_flags.ll
new file mode 100644
index 0000000000000..c79a94b837a31
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/srl64_reduce_flags.ll
@@ -0,0 +1,41 @@
+; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -stop-after=finalize-isel -o - %s | FileCheck %s
+
+;; Test that reduction of:
+;;
+;;   DST = lshr i64 X, Y
+;;
+;; where Y is in the range [63-32] to:
+;;
+;;   DST = [srl i32 X, (Y & 0x1F), 0]
+;;
+;; preserves flags
+
+define i64 @srl_exact(i64 %arg0, i64 %shift_amt) {
+  ; CHECK-LABEL: name: srl_exact
+  ; CHECK: bb.0 (%ir-block.0):
+  ; CHECK-NEXT:   liveins: $vgpr1, $vgpr2
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr2
+  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
+  ; CHECK-NEXT:   [[DEF:%[0-9]+]]:sreg_32 = IMPLICIT_DEF
+  ; CHECK-NEXT:   [[DEF1:%[0-9]+]]:sreg_32 = IMPLICIT_DEF
+  ; CHECK-NEXT:   [[DEF2:%[0-9]+]]:sgpr_32 = IMPLICIT_DEF
+  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[DEF]]
+  ; CHECK-NEXT:   [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE killed [[COPY2]], %subreg.sub0, [[COPY1]], %subreg.sub1
+  ; CHECK-NEXT:   [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
+  ; CHECK-NEXT:   [[DEF3:%[0-9]+]]:sreg_32 = IMPLICIT_DEF
+  ; CHECK-NEXT:   [[DEF4:%[0-9]+]]:sreg_32 = IMPLICIT_DEF
+  ; CHECK-NEXT:   [[DEF5:%[0-9]+]]:sgpr_32 = IMPLICIT_DEF
+  ; CHECK-NEXT:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[DEF3]]
+  ; CHECK-NEXT:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, killed [[COPY4]], %subreg.sub1
+  ; CHECK-NEXT:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE1]].sub0
+  ; CHECK-NEXT:   [[V_LSHRREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 killed [[COPY5]], killed [[COPY3]], implicit $exec
+  ; CHECK-NEXT:   [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
+  ; CHECK-NEXT:   $vgpr0 = COPY [[V_LSHRREV_B32_e64_]]
+  ; CHECK-NEXT:   $vgpr1 = COPY [[V_MOV_B32_e32_]]
+  ; CHECK-NEXT:   SI_RETURN implicit $vgpr0, implicit $vgpr1
+  %or = or i64 %shift_amt, 32
+  %srl = lshr exact i64 %arg0, %or
+  ret i64 %srl
+}