[llvm] [InstCombine] Optimize sub(sext(add(x, y)), sext(add(x, z))). (PR #144174)
via llvm-commits
llvm-commits at lists.llvm.org
Fri Jun 13 17:41:52 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-transforms
Author: Slava Zakharin (vzakhari)
<details>
<summary>Changes</summary>
This pattern can be often met in Flang generated LLVM IR,
for example, for the counts of the loops generated for array
expressions like: `a(x:x+y)` or `a(x+z:x+z)` or their variations.
In order to compute the loop count, Flang needs to subtract
the lower bound of the array slice from the upper bound
of the array slice. To avoid the sign wraps, it sign extends
the original values (that may be of any user data type)
to `i64`.
This peephole is really helpful in CPU2017/548.exchange2,
where we have multiple following statements like this:
```
block(row+1:row+2, 7:9, i7) = block(row+1:row+2, 7:9, i7) - 10
```
While this is just a 2x3 iterations loop nest, LLVM cannot
figure it out, ending up vectorizing the inner loop really
hard (with a vector epilog and scalar remainder). This, in turn,
causes problems for LSR that ends up creating too many loop-carried
values in the loop containing the above statement, which are then
causing too many spills/reloads.
Alive2: https://alive2.llvm.org/ce/z/gLgfYX
Related to #<!-- -->143219.
---
Full diff: https://github.com/llvm/llvm-project/pull/144174.diff
2 Files Affected:
- (modified) llvm/lib/Transforms/InstCombine/InstCombineAddSub.cpp (+56)
- (added) llvm/test/Transforms/InstCombine/sub-sext-add.ll (+89)
``````````diff
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineAddSub.cpp b/llvm/lib/Transforms/InstCombine/InstCombineAddSub.cpp
index c1ce364eb1794..35de76d50672d 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineAddSub.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineAddSub.cpp
@@ -2807,6 +2807,62 @@ Instruction *InstCombinerImpl::visitSub(BinaryOperator &I) {
if (Instruction *Res = foldBinOpOfSelectAndCastOfSelectCondition(I))
return Res;
+ // (sub[ nsw][ nuw] (sext (add nsw (X, Y)), sext (X))) --> (sext (Y))
+ {
+ Value *Add0;
+ if (match(Op0, m_SExt(m_Value(Add0))) &&
+ match(Add0, m_Add(m_Value(X), m_Value(Y))) &&
+ match(Op1, m_SExt(m_Specific(X)))) {
+ auto *OBO0 = cast<OverflowingBinaryOperator>(Add0);
+ if (OBO0->hasNoSignedWrap()) {
+ // Non-constant Y requires new SExt.
+ unsigned numOfNewInstrs = !isa<Constant>(Y) ? 1 : 0;
+ // Check if we can trade some of the old instructions for the new ones.
+ unsigned numOfDeadInstrs = 0;
+ numOfDeadInstrs += Op0->hasOneUse() ? 1 : 0;
+ numOfDeadInstrs += Op1->hasOneUse() ? 1 : 0;
+ numOfDeadInstrs += Add0->hasOneUse() ? 1 : 0;
+ if (numOfDeadInstrs >= numOfNewInstrs) {
+ Value *SExtY = Builder.CreateSExt(Y, I.getType());
+ return replaceInstUsesWith(I, SExtY);
+ }
+ }
+ }
+ }
+
+ // (sub[ nsw] (sext (add nsw (X, Y)), sext (add nsw (X, Z)))) -->
+ // --> (sub[ nsw] (sext (Y), sext(Z)))
+ {
+ Value *Z, *Add0, *Add1;
+ if (match(Op0, m_SExt(m_Value(Add0))) &&
+ match(Add0, m_Add(m_Value(X), m_Value(Y))) &&
+ match(Op1, m_SExt(m_Value(Add1))) &&
+ match(Add1, m_Add(m_Specific(X), m_Value(Z)))) {
+ auto *OBO0 = cast<OverflowingBinaryOperator>(Add0);
+ auto *OBO1 = cast<OverflowingBinaryOperator>(Add1);
+ if (OBO0->hasNoSignedWrap() && OBO1->hasNoSignedWrap()) {
+ unsigned numOfNewInstrs = 0;
+ // Non-constant Y, Z require new SExt.
+ numOfNewInstrs += !isa<Constant>(Y) ? 1 : 0;
+ numOfNewInstrs += !isa<Constant>(Z) ? 1 : 0;
+ // Check if we can trade some of the old instructions for the new ones.
+ unsigned numOfDeadInstrs = 0;
+ numOfDeadInstrs += Op0->hasOneUse() ? 1 : 0;
+ numOfDeadInstrs += Op1->hasOneUse() ? 1 : 0;
+ numOfDeadInstrs += Add0->hasOneUse() ? 1 : 0;
+ numOfDeadInstrs += Add1->hasOneUse() ? 1 : 0;
+ if (numOfDeadInstrs >= numOfNewInstrs) {
+ Value *SExtY = Builder.CreateSExt(Y, I.getType());
+ Value *SExtZ = Builder.CreateSExt(Z, I.getType());
+ Value *Sub = Builder.CreateSub(SExtY, SExtZ, "",
+ /* HasNUW */ false,
+ /* HasNSW */ I.hasNoSignedWrap());
+ return replaceInstUsesWith(I, Sub);
+ }
+ }
+ }
+ }
+
return TryToNarrowDeduceFlags();
}
diff --git a/llvm/test/Transforms/InstCombine/sub-sext-add.ll b/llvm/test/Transforms/InstCombine/sub-sext-add.ll
new file mode 100644
index 0000000000000..8b12acdf95ba5
--- /dev/null
+++ b/llvm/test/Transforms/InstCombine/sub-sext-add.ll
@@ -0,0 +1,89 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -passes=instcombine -S | FileCheck %s
+
+define i64 @src_2add_2sext_sub(i32 %x, i32 %y, i32 %z) {
+; CHECK-LABEL: define i64 @src_2add_2sext_sub(
+; CHECK-SAME: i32 [[X:%.*]], i32 [[Y:%.*]], i32 [[Z:%.*]]) {
+; CHECK-NEXT: [[SEXT1:%.*]] = sext i32 [[Y]] to i64
+; CHECK-NEXT: [[SEXT2:%.*]] = sext i32 [[Z]] to i64
+; CHECK-NEXT: [[SUB:%.*]] = sub nsw i64 [[SEXT1]], [[SEXT2]]
+; CHECK-NEXT: ret i64 [[SUB]]
+;
+ %add1 = add nsw i32 %x, %y
+ %add2 = add nsw i32 %x, %z
+ %sext1 = sext i32 %add1 to i64
+ %sext2 = sext i32 %add2 to i64
+ %sub = sub i64 %sext1, %sext2
+ ret i64 %sub
+}
+
+define i64 @src_2add_2sext_sub_nsw(i32 %x, i32 %y, i32 %z) {
+; CHECK-LABEL: define i64 @src_2add_2sext_sub_nsw(
+; CHECK-SAME: i32 [[X:%.*]], i32 [[Y:%.*]], i32 [[Z:%.*]]) {
+; CHECK-NEXT: [[SEXT1:%.*]] = sext i32 [[Y]] to i64
+; CHECK-NEXT: [[SEXT2:%.*]] = sext i32 [[Z]] to i64
+; CHECK-NEXT: [[SUB:%.*]] = sub nsw i64 [[SEXT1]], [[SEXT2]]
+; CHECK-NEXT: ret i64 [[SUB]]
+;
+ %add1 = add nsw i32 %x, %y
+ %add2 = add nsw i32 %x, %z
+ %sext1 = sext i32 %add1 to i64
+ %sext2 = sext i32 %add2 to i64
+ %sub = sub nsw i64 %sext1, %sext2
+ ret i64 %sub
+}
+
+define i64 @src_2add_2sext_sub_nuw(i32 %x, i32 %y, i32 %z) {
+; CHECK-LABEL: define i64 @src_2add_2sext_sub_nuw(
+; CHECK-SAME: i32 [[X:%.*]], i32 [[Y:%.*]], i32 [[Z:%.*]]) {
+; CHECK-NEXT: [[TMP1:%.*]] = sext i32 [[Y]] to i64
+; CHECK-NEXT: [[TMP2:%.*]] = sext i32 [[Z]] to i64
+; CHECK-NEXT: [[SUB:%.*]] = sub nsw i64 [[TMP1]], [[TMP2]]
+; CHECK-NEXT: ret i64 [[SUB]]
+;
+ %add1 = add nsw i32 %x, %y
+ %add2 = add nsw i32 %x, %z
+ %sext1 = sext i32 %add1 to i64
+ %sext2 = sext i32 %add2 to i64
+ %sub = sub nuw i64 %sext1, %sext2
+ ret i64 %sub
+}
+
+define i64 @src_x_add_2sext_sub(i32 %x, i32 %y) {
+; CHECK-LABEL: define i64 @src_x_add_2sext_sub(
+; CHECK-SAME: i32 [[X:%.*]], i32 [[Y:%.*]]) {
+; CHECK-NEXT: [[SUB:%.*]] = sext i32 [[Y]] to i64
+; CHECK-NEXT: ret i64 [[SUB]]
+;
+ %add1 = add nsw i32 %x, %y
+ %sext1 = sext i32 %add1 to i64
+ %sext2 = sext i32 %x to i64
+ %sub = sub i64 %sext1, %sext2
+ ret i64 %sub
+}
+
+define i64 @src_x_add_2sext_sub_nsw(i32 %x, i32 %y) {
+; CHECK-LABEL: define i64 @src_x_add_2sext_sub_nsw(
+; CHECK-SAME: i32 [[X:%.*]], i32 [[Y:%.*]]) {
+; CHECK-NEXT: [[SUB:%.*]] = sext i32 [[Y]] to i64
+; CHECK-NEXT: ret i64 [[SUB]]
+;
+ %add1 = add nsw i32 %x, %y
+ %sext1 = sext i32 %add1 to i64
+ %sext2 = sext i32 %x to i64
+ %sub = sub nsw i64 %sext1, %sext2
+ ret i64 %sub
+}
+
+define i64 @src_x_add_2sext_sub_nuw(i32 %x, i32 %y) {
+; CHECK-LABEL: define i64 @src_x_add_2sext_sub_nuw(
+; CHECK-SAME: i32 [[X:%.*]], i32 [[Y:%.*]]) {
+; CHECK-NEXT: [[SUB:%.*]] = sext i32 [[Y]] to i64
+; CHECK-NEXT: ret i64 [[SUB]]
+;
+ %add1 = add nsw i32 %x, %y
+ %sext1 = sext i32 %add1 to i64
+ %sext2 = sext i32 %x to i64
+ %sub = sub nuw i64 %sext1, %sext2
+ ret i64 %sub
+}
``````````
</details>
https://github.com/llvm/llvm-project/pull/144174
More information about the llvm-commits
mailing list