[llvm] b396921 - [SCCP] Handle llvm.vscale intrinsic calls (#114033)

[via llvm-commits]

Author: Hari Limaye
Date: 2024-10-31T12:22:15Z
New Revision: b396921d0c7d9ad396a1ee6ac85d0dbda965699f

URL: https://github.com/llvm/llvm-project/commit/b396921d0c7d9ad396a1ee6ac85d0dbda965699f
DIFF: https://github.com/llvm/llvm-project/commit/b396921d0c7d9ad396a1ee6ac85d0dbda965699f.diff

LOG: [SCCP] Handle llvm.vscale intrinsic calls (#114033)

Teach SCCP to compute a constant range for calls to llvm.vscale
intrinsics.

Added: 
    llvm/test/Transforms/SCCP/vscale-intrinsic.ll

Modified: 
    llvm/lib/Transforms/Utils/SCCPSolver.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Transforms/Utils/SCCPSolver.cpp b/llvm/lib/Transforms/Utils/SCCPSolver.cpp
index c65710ea7551ac..4225e7e80fda6f 100644
--- a/llvm/lib/Transforms/Utils/SCCPSolver.cpp
+++ b/llvm/lib/Transforms/Utils/SCCPSolver.cpp
@@ -1923,6 +1923,12 @@ void SCCPInstVisitor::handleCallResult(CallBase &CB) {
       return (void)mergeInValue(IV, &CB, CopyOfVal);
     }
 
+    if (II->getIntrinsicID() == Intrinsic::vscale) {
+      unsigned BitWidth = CB.getType()->getScalarSizeInBits();
+      const ConstantRange Result = getVScaleRange(II->getFunction(), BitWidth);
+      return (void)mergeInValue(II, ValueLatticeElement::getRange(Result));
+    }
+
     if (ConstantRange::isIntrinsicSupported(II->getIntrinsicID())) {
       // Compute result range for intrinsics supported by ConstantRange.
       // Do this even if we don't know a range for all operands, as we may

diff  --git a/llvm/test/Transforms/SCCP/vscale-intrinsic.ll b/llvm/test/Transforms/SCCP/vscale-intrinsic.ll
new file mode 100644
index 00000000000000..7dc7ea9b991912
--- /dev/null
+++ b/llvm/test/Transforms/SCCP/vscale-intrinsic.ll
@@ -0,0 +1,81 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt < %s -passes=sccp -S | FileCheck %s
+
+define i1 @vscale_i32_noattr() {
+; CHECK-LABEL: define i1 @vscale_i32_noattr() {
+; CHECK-NEXT:    [[SCALE:%.*]] = call i32 @llvm.vscale.i32()
+; CHECK-NEXT:    [[CMP2:%.*]] = icmp ule i32 [[SCALE]], 16
+; CHECK-NEXT:    [[RES:%.*]] = and i1 true, [[CMP2]]
+; CHECK-NEXT:    ret i1 [[RES]]
+;
+  %scale = call i32 @llvm.vscale.i32()
+  %cmp1 = icmp uge i32 %scale, 1
+  %cmp2 = icmp ule i32 %scale, 16
+  %res = and i1 %cmp1, %cmp2
+  ret i1 %res
+}
+
+define i1 @vscale_i32_attr() vscale_range(1, 16) {
+; CHECK-LABEL: define i1 @vscale_i32_attr(
+; CHECK-SAME: ) #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT:    [[SCALE:%.*]] = call i32 @llvm.vscale.i32()
+; CHECK-NEXT:    ret i1 true
+;
+  %scale = call i32 @llvm.vscale.i32()
+  %cmp1 = icmp uge i32 %scale, 1
+  %cmp2 = icmp ule i32 %scale, 16
+  %res = and i1 %cmp1, %cmp2
+  ret i1 %res
+}
+
+define i1 @vscale_i64_noattr() {
+; CHECK-LABEL: define i1 @vscale_i64_noattr() {
+; CHECK-NEXT:    [[SCALE:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[CMP2:%.*]] = icmp ule i64 [[SCALE]], 16
+; CHECK-NEXT:    [[RES:%.*]] = and i1 true, [[CMP2]]
+; CHECK-NEXT:    ret i1 [[RES]]
+;
+  %scale = call i64 @llvm.vscale.i64()
+  %cmp1 = icmp uge i64 %scale, 1
+  %cmp2 = icmp ule i64 %scale, 16
+  %res = and i1 %cmp1, %cmp2
+  ret i1 %res
+}
+
+define i1 @vscale_i64_attr() vscale_range(1, 16) {
+; CHECK-LABEL: define i1 @vscale_i64_attr(
+; CHECK-SAME: ) #[[ATTR0]] {
+; CHECK-NEXT:    [[SCALE:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    ret i1 true
+;
+  %scale = call i64 @llvm.vscale.i64()
+  %cmp1 = icmp uge i64 %scale, 1
+  %cmp2 = icmp ule i64 %scale, 16
+  %res = and i1 %cmp1, %cmp2
+  ret i1 %res
+}
+
+define i32 @vscale_branch_elim(i32 %x) vscale_range(1, 16) {
+; CHECK-LABEL: define i32 @vscale_branch_elim(
+; CHECK-SAME: i32 [[X:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT:  [[ENTRY:.*:]]
+; CHECK-NEXT:    [[SCALE:%.*]] = call i32 @llvm.vscale.i32()
+; CHECK-NEXT:    [[BOUND:%.*]] = shl nuw nsw i32 [[SCALE]], 3
+; CHECK-NEXT:    br label %[[IF_END:.*]]
+; CHECK:       [[IF_END]]:
+; CHECK-NEXT:    ret i32 [[X]]
+;
+entry:
+  %scale = call i32 @llvm.vscale.i32()
+  %bound = shl nsw nuw i32 %scale, 3
+  %cmp = icmp uge i32 1, %bound
+  br i1 %cmp, label %if.then, label %if.end
+
+if.then:
+  %double = mul i32 %x, 2
+  br label %if.end
+
+if.end:
+  %res = phi i32 [ %x, %entry ], [ %double, %if.then]
+  ret i32 %res
+}