[llvm] 0985202 - [InstCombine] optimize powi(X,Y) * X with Ofast

via llvm-commits llvm-commits at lists.llvm.org
Thu Mar 14 07:06:43 PDT 2024


Author: zhongyunde 00443407
Date: 2024-03-14T22:05:20+08:00
New Revision: 098520244f90e9330d3ae78bd1061aee2e3688c0

URL: https://github.com/llvm/llvm-project/commit/098520244f90e9330d3ae78bd1061aee2e3688c0
DIFF: https://github.com/llvm/llvm-project/commit/098520244f90e9330d3ae78bd1061aee2e3688c0.diff

LOG: [InstCombine] optimize powi(X,Y) * X with Ofast

Try to transform the powi(X, Y) * X into powi(X, Y+1) with Ofast

For this case, when the Y is 3, then powi(X, 4) is replaced by
X2 = X * X; X2 * X2 in the further step.
Similar to D109954, who requires reassoc.

Fixes https://github.com/llvm/llvm-project/issues/69862.

Added: 
    

Modified: 
    llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
    llvm/test/Transforms/InstCombine/powi.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp b/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
index 278be6233f4b8a..55d89c6108f033 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
@@ -683,6 +683,18 @@ Instruction *InstCombinerImpl::foldFMulReassoc(BinaryOperator &I) {
     return replaceInstUsesWith(I, Pow);
   }
 
+  // powi(X, Y) * X --> powi(X, Y+1)
+  // X * powi(X, Y) --> powi(X, Y+1)
+  if (match(&I, m_c_FMul(m_OneUse(m_Intrinsic<Intrinsic::powi>(m_Value(X),
+                                                               m_Value(Y))),
+                         m_Deferred(X))) &&
+      willNotOverflowSignedAdd(Y, ConstantInt::get(Y->getType(), 1), I)) {
+    auto *Y1 = Builder.CreateAdd(Y, ConstantInt::get(Y->getType(), 1));
+    auto *NewPow = Builder.CreateIntrinsic(
+        Intrinsic::powi, {X->getType(), Y1->getType()}, {X, Y1}, &I);
+    return replaceInstUsesWith(I, NewPow);
+  }
+
   if (I.isOnlyUserOfAnyOperand()) {
     // pow(X, Y) * pow(X, Z) -> pow(X, Y + Z)
     if (match(Op0, m_Intrinsic<Intrinsic::pow>(m_Value(X), m_Value(Y))) &&

diff  --git a/llvm/test/Transforms/InstCombine/powi.ll b/llvm/test/Transforms/InstCombine/powi.ll
index 89efbb6f453611..95722d09a17ad3 100644
--- a/llvm/test/Transforms/InstCombine/powi.ll
+++ b/llvm/test/Transforms/InstCombine/powi.ll
@@ -341,3 +341,52 @@ define double @fdiv_pow_powi_negative_variable(double %x, i32 %y) {
   %div = fdiv reassoc nnan double %p1, %x
   ret double %div
 }
+
+; powi(X, Y) * X --> powi(X, Y+1)
+define double @powi_fmul_powi_x(double noundef %x) {
+; CHECK-LABEL: @powi_fmul_powi_x(
+; CHECK-NEXT:    [[MUL:%.*]] = call reassoc double @llvm.powi.f64.i32(double [[X:%.*]], i32 4)
+; CHECK-NEXT:    ret double [[MUL]]
+;
+  %p1 = tail call double @llvm.powi.f64.i32(double %x, i32 3)
+  %mul = fmul reassoc double %p1, %x
+  ret double %mul
+}
+
+; Negative test: Multi-use
+define double @powi_fmul_powi_x_multi_use(double noundef %x) {
+; CHECK-LABEL: @powi_fmul_powi_x_multi_use(
+; CHECK-NEXT:    [[P1:%.*]] = tail call double @llvm.powi.f64.i32(double [[X:%.*]], i32 3)
+; CHECK-NEXT:    tail call void @use(double [[P1]])
+; CHECK-NEXT:    [[MUL:%.*]] = fmul reassoc double [[P1]], [[X]]
+; CHECK-NEXT:    ret double [[MUL]]
+;
+  %p1 = tail call double @llvm.powi.f64.i32(double %x, i32 3)
+  tail call void @use(double %p1)
+  %mul = fmul reassoc double %p1, %x
+  ret double %mul
+}
+
+; Negative test: Miss fmf flag
+define double @powi_fmul_powi_x_missing_reassoc(double noundef %x) {
+; CHECK-LABEL: @powi_fmul_powi_x_missing_reassoc(
+; CHECK-NEXT:    [[P1:%.*]] = tail call double @llvm.powi.f64.i32(double [[X:%.*]], i32 3)
+; CHECK-NEXT:    [[MUL:%.*]] = fmul double [[P1]], [[X]]
+; CHECK-NEXT:    ret double [[MUL]]
+;
+  %p1 = tail call double @llvm.powi.f64.i32(double %x, i32 3)
+  %mul = fmul double %p1, %x
+  ret double %mul
+}
+
+; Negative test: overflow
+define double @powi_fmul_powi_x_overflow(double noundef %x) {
+; CHECK-LABEL: @powi_fmul_powi_x_overflow(
+; CHECK-NEXT:    [[P1:%.*]] = tail call double @llvm.powi.f64.i32(double [[X:%.*]], i32 2147483647)
+; CHECK-NEXT:    [[MUL:%.*]] = fmul reassoc double [[P1]], [[X]]
+; CHECK-NEXT:    ret double [[MUL]]
+;
+  %p1 = tail call double @llvm.powi.f64.i32(double %x, i32 2147483647) ; INT_MAX
+  %mul = fmul reassoc double %p1, %x
+  ret double %mul
+}


        


More information about the llvm-commits mailing list