[AArch64][SVE] Add instcombine for PTEST_ANY(X=OP(PG,...), X) -> PTES…

…T_ANY(PG, X)) Given this is an OR reduction the two are equivalent and later optimizations (AArch64InstrInfo::optimizePTestInstr) may rewrite the sequence to use the flag-setting variant of instruction X, to remove the PTEST altogether. Reviewed By: paulwalker-arm, bsmith Differential Revision: https://reviews.llvm.org/D134946
intel · Oct 12, 2022 · 388cacb · 388cacb
1 parent 5b5756e
commit 388cacb
Show file tree

Hide file tree

Showing 2 changed files with 49 additions and 6 deletions.
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -966,14 +966,15 @@ static Optional<Instruction *> instCombineSVEPTest(InstCombiner &IC,
   IntrinsicInst *Op1 = dyn_cast<IntrinsicInst>(II.getArgOperand(0));
   IntrinsicInst *Op2 = dyn_cast<IntrinsicInst>(II.getArgOperand(1));
 
-  if (Op1 && Op2 &&
-      Op1->getIntrinsicID() == Intrinsic::aarch64_sve_convert_to_svbool &&
-      Op2->getIntrinsicID() == Intrinsic::aarch64_sve_convert_to_svbool &&
-      Op1->getArgOperand(0)->getType() == Op2->getArgOperand(0)->getType()) {
+  if (!Op1 || !Op2)
+    return None;
 
-    IRBuilder<> Builder(II.getContext());
-    Builder.SetInsertPoint(&II);
+  IRBuilder<> Builder(II.getContext());
+  Builder.SetInsertPoint(&II);
 
+  if (Op1->getIntrinsicID() == Intrinsic::aarch64_sve_convert_to_svbool &&
+      Op2->getIntrinsicID() == Intrinsic::aarch64_sve_convert_to_svbool &&
+      Op1->getArgOperand(0)->getType() == Op2->getArgOperand(0)->getType()) {
     Value *Ops[] = {Op1->getArgOperand(0), Op2->getArgOperand(0)};
     Type *Tys[] = {Op1->getArgOperand(0)->getType()};
 
@@ -983,6 +984,22 @@ static Optional<Instruction *> instCombineSVEPTest(InstCombiner &IC,
     return IC.replaceInstUsesWith(II, PTest);
   }
 
+  // Transform PTEST_ANY(X=OP(PG,...), X) -> PTEST_ANY(PG, X)).
+  // Later optimizations may rewrite sequence to use the flag-setting variant
+  // of instruction X to remove PTEST.
+  if ((Op1 == Op2) &&
+      (II.getIntrinsicID() == Intrinsic::aarch64_sve_ptest_any) &&
+      ((Op1->getIntrinsicID() == Intrinsic::aarch64_sve_brkb_z) ||
+       (Op1->getIntrinsicID() == Intrinsic::aarch64_sve_rdffr_z))) {
+    Value *Ops[] = {Op1->getArgOperand(0), Op1};
+    Type *Tys[] = {Op1->getType()};
+
+    auto *PTest = Builder.CreateIntrinsic(II.getIntrinsicID(), Tys, Ops);
+    PTest->takeName(&II);
+
+    return IC.replaceInstUsesWith(II, PTest);
+  }
+
   return None;
 }
 

diff --git a/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsics-ptest.ll b/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsics-ptest.ll
@@ -32,6 +32,29 @@ define i1 @ptest_any2(<vscale x 4 x i1> %a) #0 {
   ret i1 %out
 }
 
+; Rewrite PTEST_ANY(X=OP(PG,...), X) -> PTEST_ANY(PG, X)).
+define i1 @ptest_any_brkb_z(<vscale x 16 x i1> %pg, <vscale x 16 x i1> %a) {
+; CHECK-LABEL: @ptest_any_brkb_z(
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.brkb.z.nxv16i1(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i1> [[A:%.*]])
+; CHECK-NEXT:    [[OUT:%.*]] = call i1 @llvm.aarch64.sve.ptest.any.nxv16i1(<vscale x 16 x i1> [[PG]], <vscale x 16 x i1> [[TMP1]])
+; CHECK-NEXT:    ret i1 [[OUT]]
+;
+  %1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.brkb.z.nxv16i1(<vscale x 16 x i1> %pg, <vscale x 16 x i1> %a)
+  %out = call i1 @llvm.aarch64.sve.ptest.any.nxv16i1(<vscale x 16 x i1> %1, <vscale x 16 x i1> %1)
+  ret i1 %out
+}
+
+define i1 @ptest_any_rdffr_z(<vscale x 16 x i1> %pg) {
+; CHECK-LABEL: @ptest_any_rdffr_z(
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.rdffr.z(<vscale x 16 x i1> [[PG:%.*]])
+; CHECK-NEXT:    [[OUT:%.*]] = call i1 @llvm.aarch64.sve.ptest.any.nxv16i1(<vscale x 16 x i1> [[PG]], <vscale x 16 x i1> [[TMP1]])
+; CHECK-NEXT:    ret i1 [[OUT]]
+;
+  %1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.rdffr.z(<vscale x 16 x i1> %pg)
+  %out = call i1 @llvm.aarch64.sve.ptest.any.nxv16i1(<vscale x 16 x i1> %1, <vscale x 16 x i1> %1)
+  ret i1 %out
+}
+
 define i1 @ptest_first(<vscale x 4 x i1> %a) #0 {
 ; CHECK-LABEL: @ptest_first(
 ; CHECK-NEXT:    [[MASK:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 0)
@@ -81,4 +104,7 @@ declare <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x
 declare <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1>)
 declare <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1>)
 
+declare <vscale x 16 x i1> @llvm.aarch64.sve.brkb.z.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>)
+declare <vscale x 16 x i1> @llvm.aarch64.sve.rdffr.z(<vscale x 16 x i1>)
+
 attributes #0 = { "target-features"="+sve" }