[PATCH] D100170: [NARY] Don't optimize min/max if there are side uses

[Phabricator via llvm-commits]

This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rG36b932d6a385: [NARY] Don't optimize min/max if there are side uses (authored by Evgeniy Brevnov <ybrevnov at azul.com>).

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D100170/new/

https://reviews.llvm.org/D100170

Files:
  llvm/lib/Transforms/Scalar/NaryReassociate.cpp
  llvm/test/Transforms/NaryReassociate/nary-req.ll


Index: llvm/test/Transforms/NaryReassociate/nary-req.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/NaryReassociate/nary-req.ll
@@ -0,0 +1,32 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -nary-reassociate -S | FileCheck %s
+; RUN: opt < %s -passes='nary-reassociate' -S | FileCheck %s
+
+declare i32 @llvm.smax.i32(i32 %a, i32 %b)
+
+; This is a negative test. We should not optimize if intermediate result
+; has a use outside of optimizaple pattern. In other words %smax2 has one
+; use from %smax3 and side use from %res2.
+define i32 @smax_test1(i32 %a, i32 %b, i32 %c) {
+; CHECK-LABEL: @smax_test1(
+; CHECK-NEXT:    [[C1:%.*]] = icmp sgt i32 [[A:%.*]], [[B:%.*]]
+; CHECK-NEXT:    [[SMAX1:%.*]] = select i1 [[C1]], i32 [[A]], i32 [[B]]
+; CHECK-NEXT:    [[C2:%.*]] = icmp sgt i32 [[B]], [[C:%.*]]
+; CHECK-NEXT:    [[SMAX2:%.*]] = select i1 [[C2]], i32 [[B]], i32 [[C]]
+; CHECK-NEXT:    [[C3:%.*]] = icmp sgt i32 [[SMAX2]], [[A]]
+; CHECK-NEXT:    [[SMAX3:%.*]] = select i1 [[C3]], i32 [[SMAX2]], i32 [[A]]
+; CHECK-NEXT:    [[RES:%.*]] = add i32 [[SMAX1]], [[SMAX3]]
+; CHECK-NEXT:    [[RES2:%.*]] = add i32 [[RES]], [[SMAX2]]
+; CHECK-NEXT:    ret i32 [[RES]]
+;
+  %c1 = icmp sgt i32 %a, %b
+  %smax1 = select i1 %c1, i32 %a, i32 %b
+  %c2 = icmp sgt i32 %b, %c
+  %smax2 = select i1 %c2, i32 %b, i32 %c
+  %c3 = icmp sgt i32 %smax2, %a
+  %smax3 = select i1 %c3, i32 %smax2, i32 %a
+  %res = add i32 %smax1, %smax3
+  %res2 = add i32 %res, %smax2
+  ret i32 %res
+}
+
Index: llvm/lib/Transforms/Scalar/NaryReassociate.cpp
===================================================================
--- llvm/lib/Transforms/Scalar/NaryReassociate.cpp
+++ llvm/lib/Transforms/Scalar/NaryReassociate.cpp
@@ -592,7 +592,7 @@
   Value *A = nullptr, *B = nullptr;
   MaxMinT m_MaxMin(m_Value(A), m_Value(B));
   for (unsigned int i = 0; i < 2; ++i) {
-    if (match(LHS, m_MaxMin)) {
+    if (LHS->getNumUses() <= 2 && match(LHS, m_MaxMin)) {
       const SCEV *AExpr = SE->getSCEV(A), *BExpr = SE->getSCEV(B);
       const SCEV *RHSExpr = SE->getSCEV(RHS);
       for (unsigned int j = 0; j < 2; ++j) {
@@ -610,6 +610,12 @@
           std::swap(AExpr, RHSExpr);
         }
 
+        // The optimization is profitable only if LHS can be removed in the end.
+        // In other words LHS should be used (directly or indirectly) by I only.
+        for (User *U : LHS->users())
+          if (U != I || !(U->hasOneUser() && *U->users().begin() == I))
+            continue;
+
         SCEVExpander Expander(*SE, *DL, "nary-reassociate");
         SmallVector<const SCEV *, 2> Ops1{ BExpr, AExpr };
         const SCEVTypes SCEVType = convertToSCEVype(m_MaxMin);


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D100170.336747.patch
Type: text/x-patch
Size: 2772 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210412/e5ace276/attachment.bin>