[PATCH] D143016: [InstCombine] Promote expression tree with @llvm.vscale when zero-extending result.

Sander de Smalen via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Tue Jan 31 14:05:03 PST 2023


sdesmalen created this revision.
sdesmalen added reviewers: goldstein.w.n, nikic, MattDevereau.
Herald added subscribers: StephenFan, hiraditya.
Herald added a project: All.
sdesmalen requested review of this revision.
Herald added subscribers: llvm-commits, alextsao1999.
Herald added a project: LLVM.

The LoopVectorizer emits the (scaled) element count as i32, which for
scalable VFs results in calls to @llvm.vscale.i32(). This value is scaled
and further zero-extended to i64.

The zero-extend can be folded away by executing the whole expression in i64
type using @llvm.vscale.i64(). Any logical `and` that would needed to mask
the result can be further folded away by KnownBits analysis when
vscale_range is set.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D143016

Files:
  llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
  llvm/test/Transforms/InstCombine/AArch64/vscale.ll


Index: llvm/test/Transforms/InstCombine/AArch64/vscale.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/InstCombine/AArch64/vscale.ll
@@ -0,0 +1,30 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -passes='instcombine' -S < %s | FileCheck %s
+target triple = "aarch64"
+target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
+
+define i64 @free_zext_vscale_i32_to_i64() #0 {
+; CHECK-LABEL: @free_zext_vscale_i32_to_i64(
+; CHECK-NEXT:    [[VSCALE:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    ret i64 [[VSCALE]]
+;
+  %vscale = call i32 @llvm.vscale.i32()
+  %ext = zext i32 %vscale to i64
+  ret i64 %ext
+}
+
+define i64 @free_zext_vscale_shl_i32_to_i64() #0 {
+; CHECK-LABEL: @free_zext_vscale_shl_i32_to_i64(
+; CHECK-NEXT:    [[VSCALE:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[SHL:%.*]] = shl nuw nsw i64 [[VSCALE]], 3
+; CHECK-NEXT:    ret i64 [[SHL]]
+;
+  %vscale = call i32 @llvm.vscale.i32()
+  %shl = shl i32 %vscale, 3
+  %ext = zext i32 %shl to i64
+  ret i64 %ext
+}
+
+declare i32 @llvm.vscale.i32()
+
+attributes #0 = { vscale_range(1,16) "target-features"="+sve" }
Index: llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
===================================================================
--- llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
+++ llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
@@ -252,6 +252,16 @@
     Res = CastInst::Create(
       static_cast<Instruction::CastOps>(Opc), I->getOperand(0), Ty);
     break;
+  case Instruction::Call:
+    if (const IntrinsicInst *II = dyn_cast<IntrinsicInst>(I)) {
+      if (II->getIntrinsicID() == Intrinsic::vscale) {
+        Function *Fn =
+            Intrinsic::getDeclaration(I->getModule(), Intrinsic::vscale, {Ty});
+        Res = CallInst::Create(Fn->getFunctionType(), Fn);
+        break;
+      }
+    }
+    LLVM_FALLTHROUGH;
   default:
     // TODO: Can handle more cases here.
     llvm_unreachable("Unreachable!");
@@ -1217,6 +1227,13 @@
         return false;
     return true;
   }
+  case Instruction::Call:
+    // llvm.vscale() can always be executed in larger type, because the
+    // value is automatically zero-extended.
+    if (const IntrinsicInst *II = dyn_cast<IntrinsicInst>(I))
+      if (II->getIntrinsicID() == Intrinsic::vscale)
+        return true;
+    return false;
   default:
     // TODO: Can handle more cases here.
     return false;


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D143016.493729.patch
Type: text/x-patch
Size: 2507 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230131/02191a87/attachment.bin>


More information about the llvm-commits mailing list