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

[Sander de Smalen via Phabricator via llvm-commits]

sdesmalen updated this revision to Diff 493862.
sdesmalen added a comment.

- Added a test without vscale_range, to show it results in explicit anding of upper bits.
- Replaced LLVM_FALLTHROUGH with explicit 'llvm_unreachable' and added a switch-statement for the intrinsic ID.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D143016/new/

https://reviews.llvm.org/D143016

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


Index: llvm/test/Transforms/InstCombine/vscale.ll
===================================================================
--- llvm/test/Transforms/InstCombine/vscale.ll
+++ llvm/test/Transforms/InstCombine/vscale.ll
@@ -4,8 +4,8 @@
 
 define i64 @promote_vscale_i32_to_i64() {
 ; CHECK-LABEL: @promote_vscale_i32_to_i64(
-; CHECK-NEXT:    [[VSCALE:%.*]] = call i32 @llvm.vscale.i32()
-; CHECK-NEXT:    [[EXT:%.*]] = zext i32 [[VSCALE]] to i64
+; CHECK-NEXT:    [[VSCALE:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[EXT:%.*]] = and i64 [[VSCALE]], 4294967295
 ; CHECK-NEXT:    ret i64 [[EXT]]
 ;
   %vscale = call i32 @llvm.vscale.i32()
@@ -15,9 +15,9 @@
 
 define i64 @pomote_zext_shl_vscale_i32_to_i64() {
 ; CHECK-LABEL: @pomote_zext_shl_vscale_i32_to_i64(
-; CHECK-NEXT:    [[VSCALE:%.*]] = call i32 @llvm.vscale.i32()
-; CHECK-NEXT:    [[SHL:%.*]] = shl i32 [[VSCALE]], 3
-; CHECK-NEXT:    [[EXT:%.*]] = zext i32 [[SHL]] to i64
+; CHECK-NEXT:    [[VSCALE:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[SHL:%.*]] = shl i64 [[VSCALE]], 3
+; CHECK-NEXT:    [[EXT:%.*]] = and i64 [[SHL]], 4294967288
 ; CHECK-NEXT:    ret i64 [[EXT]]
 ;
   %vscale = call i32 @llvm.vscale.i32()
@@ -30,10 +30,9 @@
 ; vscale_range attribute so that the 'and' is folded away.
 define i64 @free_zext_vscale_shl_i32_to_i64() #0 {
 ; CHECK-LABEL: @free_zext_vscale_shl_i32_to_i64(
-; CHECK-NEXT:    [[VSCALE:%.*]] = call i32 @llvm.vscale.i32()
-; CHECK-NEXT:    [[SHL:%.*]] = shl nuw nsw i32 [[VSCALE]], 3
-; CHECK-NEXT:    [[EXT:%.*]] = zext i32 [[SHL]] to i64
-; CHECK-NEXT:    ret i64 [[EXT]]
+; 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
Index: llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
===================================================================
--- llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
+++ llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
@@ -252,6 +252,20 @@
     Res = CastInst::Create(
       static_cast<Instruction::CastOps>(Opc), I->getOperand(0), Ty);
     break;
+  case Instruction::Call:
+    if (const IntrinsicInst *II = dyn_cast<IntrinsicInst>(I)) {
+      switch (II->getIntrinsicID()) {
+      default:
+        llvm_unreachable("Unsupported call!");
+      case Intrinsic::vscale: {
+        Function *Fn =
+            Intrinsic::getDeclaration(I->getModule(), Intrinsic::vscale, {Ty});
+        Res = CallInst::Create(Fn->getFunctionType(), Fn);
+        break;
+      }
+      }
+    }
+    break;
   default:
     // TODO: Can handle more cases here.
     llvm_unreachable("Unreachable!");
@@ -1217,6 +1231,13 @@
         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: D143016.493862.patch
Type: text/x-patch
Size: 3181 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230201/19882e4a/attachment.bin>