[PATCH] D149918: [InstCombine] Add oneuse checks to shr + cmp constant folds.

[Amara Emerson via Phabricator via llvm-commits]

This revision was automatically updated to reflect the committed changes.
Closed by commit rGa66051c68a43: [InstCombine] Add oneuse checks to shr + cmp constant folds. (authored by aemerson).

Changed prior to commit:
  https://reviews.llvm.org/D149918?vs=557818&id=557902#toc

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D149918/new/

https://reviews.llvm.org/D149918

Files:
  llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
  llvm/test/Transforms/InstCombine/ashr-icmp-minmax-idiom-break.ll
  llvm/test/Transforms/InstCombine/icmp-shr-lt-gt.ll
  llvm/test/Transforms/PhaseOrdering/icmp-ashr-breaking-select-idiom.ll


Index: llvm/test/Transforms/PhaseOrdering/icmp-ashr-breaking-select-idiom.ll
===================================================================
--- llvm/test/Transforms/PhaseOrdering/icmp-ashr-breaking-select-idiom.ll
+++ llvm/test/Transforms/PhaseOrdering/icmp-ashr-breaking-select-idiom.ll
@@ -5,8 +5,7 @@
 ; CHECK-LABEL: define i32 @testa(
 ; CHECK-SAME: i32 [[MUL:%.*]]) local_unnamed_addr #[[ATTR0:[0-9]+]] {
 ; CHECK-NEXT:    [[SHR:%.*]] = ashr i32 [[MUL]], 15
-; CHECK-NEXT:    [[CMP4_I:%.*]] = icmp slt i32 [[MUL]], 1073741824
-; CHECK-NEXT:    [[SPEC_SELECT_I:%.*]] = select i1 [[CMP4_I]], i32 [[SHR]], i32 32767
+; CHECK-NEXT:    [[SPEC_SELECT_I:%.*]] = tail call i32 @llvm.smin.i32(i32 [[SHR]], i32 32767)
 ; CHECK-NEXT:    ret i32 [[SPEC_SELECT_I]]
 ;
   %shr = ashr i32 %mul, 15
@@ -20,11 +19,8 @@
 ; CHECK-LABEL: define i32 @testb(
 ; CHECK-SAME: i32 [[MUL:%.*]]) local_unnamed_addr #[[ATTR0]] {
 ; CHECK-NEXT:    [[SHR102:%.*]] = ashr i32 [[MUL]], 7
-; CHECK-NEXT:    [[CMP4_I:%.*]] = icmp sgt i32 [[MUL]], 16383
-; CHECK-NEXT:    [[RETVAL_0_I:%.*]] = select i1 [[CMP4_I]], i32 127, i32 -128
-; CHECK-NEXT:    [[TMP1:%.*]] = add i32 [[MUL]], 16384
-; CHECK-NEXT:    [[CLEANUP_DEST_SLOT_0_I:%.*]] = icmp ult i32 [[TMP1]], 32768
-; CHECK-NEXT:    [[SPEC_SELECT_I:%.*]] = select i1 [[CLEANUP_DEST_SLOT_0_I]], i32 [[SHR102]], i32 [[RETVAL_0_I]]
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call i32 @llvm.smax.i32(i32 [[SHR102]], i32 -128)
+; CHECK-NEXT:    [[SPEC_SELECT_I:%.*]] = tail call i32 @llvm.smin.i32(i32 [[TMP1]], i32 127)
 ; CHECK-NEXT:    ret i32 [[SPEC_SELECT_I]]
 ;
   %shr102 = ashr i32 %mul, 7
Index: llvm/test/Transforms/InstCombine/icmp-shr-lt-gt.ll
===================================================================
--- llvm/test/Transforms/InstCombine/icmp-shr-lt-gt.ll
+++ llvm/test/Transforms/InstCombine/icmp-shr-lt-gt.ll
@@ -900,7 +900,7 @@
 define i1 @ashrsgt_01_00_multiuse(i4 %x, ptr %p) {
 ; CHECK-LABEL: @ashrsgt_01_00_multiuse(
 ; CHECK-NEXT:    [[S:%.*]] = ashr i4 [[X:%.*]], 1
-; CHECK-NEXT:    [[C:%.*]] = icmp sgt i4 [[X]], 1
+; CHECK-NEXT:    [[C:%.*]] = icmp sgt i4 [[S]], 0
 ; CHECK-NEXT:    store i4 [[S]], ptr [[P:%.*]], align 1
 ; CHECK-NEXT:    ret i1 [[C]]
 ;
Index: llvm/test/Transforms/InstCombine/ashr-icmp-minmax-idiom-break.ll
===================================================================
--- llvm/test/Transforms/InstCombine/ashr-icmp-minmax-idiom-break.ll
+++ llvm/test/Transforms/InstCombine/ashr-icmp-minmax-idiom-break.ll
@@ -1,8 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2
 ; RUN: opt < %s -passes=instcombine -S | FileCheck %s
 
-; This test is pre-committed to show sub-optimal codegen due to
-; min/max idiom breakage. On AArch64, these constants are also expensive to materialize,
+; Check we don't have sub-optimal codegen due to min/max idiom breakage.
+; On AArch64, these constants are also expensive to materialize,
 ; and therefore generate poor code vs maintaining the min/max idiom.
 
 define i64 @dont_break_minmax_i64(i64 %conv, i64 %conv2) {
@@ -10,8 +10,7 @@
 ; CHECK-SAME: (i64 [[CONV:%.*]], i64 [[CONV2:%.*]]) {
 ; CHECK-NEXT:    [[MUL:%.*]] = mul nsw i64 [[CONV]], [[CONV2]]
 ; CHECK-NEXT:    [[SHR:%.*]] = ashr i64 [[MUL]], 4
-; CHECK-NEXT:    [[CMP4_I:%.*]] = icmp slt i64 [[MUL]], 5579712
-; CHECK-NEXT:    [[SPEC_SELECT_I:%.*]] = select i1 [[CMP4_I]], i64 [[SHR]], i64 348731
+; CHECK-NEXT:    [[SPEC_SELECT_I:%.*]] = call i64 @llvm.smin.i64(i64 [[SHR]], i64 348731)
 ; CHECK-NEXT:    ret i64 [[SPEC_SELECT_I]]
 ;
   %mul = mul nsw i64 %conv, %conv2
Index: llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
===================================================================
--- llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
+++ llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
@@ -2451,7 +2451,7 @@
   // constant-value-based preconditions in the folds below, then we could assert
   // those conditions rather than checking them. This is difficult because of
   // undef/poison (PR34838).
-  if (IsAShr) {
+  if (IsAShr && Shr->hasOneUse()) {
     if (IsExact || Pred == CmpInst::ICMP_SLT || Pred == CmpInst::ICMP_ULT) {
       // When ShAmtC can be shifted losslessly:
       // icmp PRED (ashr exact X, ShAmtC), C --> icmp PRED X, (C << ShAmtC)


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D149918.557902.patch
Type: text/x-patch
Size: 4322 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20231026/719880dc/attachment.bin>