[llvm] 93c8235 - [AArch64TTI] Compute imm materialization cost for AArch64 intrinsics
Florian Hahn via llvm-commits
llvm-commits at lists.llvm.org
Wed Dec 4 03:09:34 PST 2019
Author: Florian Hahn
Date: 2019-12-04T11:09:03Z
New Revision: 93c8235702cb47d078d6e585a4f6446cba72c6fa
URL: https://github.com/llvm/llvm-project/commit/93c8235702cb47d078d6e585a4f6446cba72c6fa
DIFF: https://github.com/llvm/llvm-project/commit/93c8235702cb47d078d6e585a4f6446cba72c6fa.diff
LOG: [AArch64TTI] Compute imm materialization cost for AArch64 intrinsics
Currently, getIntImmCost returns TCC_Free for almost all intrinsics.
For most AArch64 specific intrinsics however, it looks like integer
constants cannot be folded into most of them (at least the ones I checked).
Unless we know that we can fold integer operands with the intrinsic, we
handle more cases correctly by returning the cost to materialize the
immediate than return TCC_Free.
Reviewers: SjoerdMeijer, dmgreen, t.p.northover, ributzka
Reviewed By: SjoerdMeijer
Differential Revision: https://reviews.llvm.org/D70669
Added:
llvm/test/Transforms/ConstantHoisting/AArch64/const-hoist-intrinsics.ll
Modified:
llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
Removed:
################################################################################
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index 908d72dbfc3e..ddbddb9607d7 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -156,6 +156,12 @@ int AArch64TTIImpl::getIntImmCost(Intrinsic::ID IID, unsigned Idx,
if (BitSize == 0)
return TTI::TCC_Free;
+ // Most (all?) AArch64 intrinsics do not support folding immediates into the
+ // selected instruction, so we compute the materialization cost for the
+ // immediate directly.
+ if (IID >= Intrinsic::aarch64_addg && IID <= Intrinsic::aarch64_udiv)
+ return AArch64TTIImpl::getIntImmCost(Imm, Ty);
+
switch (IID) {
default:
return TTI::TCC_Free;
diff --git a/llvm/test/Transforms/ConstantHoisting/AArch64/const-hoist-intrinsics.ll b/llvm/test/Transforms/ConstantHoisting/AArch64/const-hoist-intrinsics.ll
new file mode 100644
index 000000000000..92007ef42413
--- /dev/null
+++ b/llvm/test/Transforms/ConstantHoisting/AArch64/const-hoist-intrinsics.ll
@@ -0,0 +1,89 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -mtriple=arm64-darwin-unknown -S -consthoist < %s | FileCheck %s
+
+; Make sure we hoist constants out of intrinsics.
+
+define void @test_stxr(i64* %ptr) {
+; CHECK-LABEL: @test_stxr(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: [[CONST:%.*]] = bitcast i64 -9223372036317904832 to i64
+; CHECK-NEXT: [[PTR_0:%.*]] = getelementptr i64, i64* [[PTR:%.*]], i64 0
+; CHECK-NEXT: [[CONST_MAT:%.*]] = add i64 [[CONST]], -64
+; CHECK-NEXT: [[BAR_0:%.*]] = call i32 @llvm.aarch64.stxr.p0i64(i64 [[CONST_MAT]], i64* [[PTR_0]])
+; CHECK-NEXT: [[PTR_1:%.*]] = getelementptr i64, i64* [[PTR]], i64 1
+; CHECK-NEXT: [[BAR_1:%.*]] = call i32 @llvm.aarch64.stxr.p0i64(i64 [[CONST]], i64* [[PTR_1]])
+; CHECK-NEXT: [[PTR_2:%.*]] = getelementptr i64, i64* [[PTR]], i64 2
+; CHECK-NEXT: [[CONST_MAT1:%.*]] = add i64 [[CONST]], 64
+; CHECK-NEXT: [[BAR_2:%.*]] = call i32 @llvm.aarch64.stxr.p0i64(i64 [[CONST_MAT1]], i64* [[PTR_2]])
+; CHECK-NEXT: [[PTR_3:%.*]] = getelementptr i64, i64* [[PTR]], i64 3
+; CHECK-NEXT: [[CONST_MAT2:%.*]] = add i64 [[CONST]], 128
+; CHECK-NEXT: [[BAR_3:%.*]] = call i32 @llvm.aarch64.stxr.p0i64(i64 [[CONST_MAT2]], i64* [[PTR_3]])
+; CHECK-NEXT: ret void
+;
+entry:
+ %ptr.0 = getelementptr i64, i64* %ptr, i64 0
+ %bar.0 = call i32 @llvm.aarch64.stxr.p0i64(i64 -9223372036317904896, i64* %ptr.0)
+ %ptr.1 = getelementptr i64, i64* %ptr, i64 1
+ %bar.1 = call i32 @llvm.aarch64.stxr.p0i64(i64 -9223372036317904832, i64* %ptr.1)
+ %ptr.2 = getelementptr i64, i64* %ptr, i64 2
+ %bar.2 = call i32 @llvm.aarch64.stxr.p0i64(i64 -9223372036317904768, i64* %ptr.2)
+ %ptr.3 = getelementptr i64, i64* %ptr, i64 3
+ %bar.3 = call i32 @llvm.aarch64.stxr.p0i64(i64 -9223372036317904704, i64* %ptr.3)
+ ret void
+}
+
+declare i32 @llvm.aarch64.stxr.p0i64(i64 , i64*)
+
+define i64 @test_udiv(i64 %x) {
+; CHECK-LABEL: @test_udiv(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: [[CONST:%.*]] = bitcast i64 -9223372036317904832 to i64
+; CHECK-NEXT: [[CONST_MAT:%.*]] = add i64 [[CONST]], -64
+; CHECK-NEXT: [[BAR_0:%.*]] = call i64 @llvm.aarch64.udiv.i64(i64 [[CONST_MAT]], i64 [[X:%.*]])
+; CHECK-NEXT: [[BAR_1:%.*]] = call i64 @llvm.aarch64.udiv.i64(i64 [[CONST]], i64 [[X]])
+; CHECK-NEXT: [[CONST_MAT1:%.*]] = add i64 [[CONST]], 64
+; CHECK-NEXT: [[BAR_2:%.*]] = call i64 @llvm.aarch64.udiv.i64(i64 [[CONST_MAT1]], i64 [[X]])
+; CHECK-NEXT: [[CONST_MAT2:%.*]] = add i64 [[CONST]], 128
+; CHECK-NEXT: [[BAR_3:%.*]] = call i64 @llvm.aarch64.udiv.i64(i64 [[CONST_MAT2]], i64 [[X]])
+; CHECK-NEXT: [[RES_1:%.*]] = add i64 [[BAR_0]], [[BAR_1]]
+; CHECK-NEXT: [[RES_2:%.*]] = add i64 [[RES_1]], [[BAR_2]]
+; CHECK-NEXT: [[RES_3:%.*]] = add i64 [[RES_2]], [[BAR_3]]
+; CHECK-NEXT: ret i64 [[RES_3]]
+;
+entry:
+ %bar.0 = call i64 @llvm.aarch64.udiv.i64.i64(i64 -9223372036317904896, i64 %x)
+ %bar.1 = call i64 @llvm.aarch64.udiv.i64.i64(i64 -9223372036317904832, i64 %x)
+ %bar.2 = call i64 @llvm.aarch64.udiv.i64.i64(i64 -9223372036317904768, i64 %x)
+ %bar.3 = call i64 @llvm.aarch64.udiv.i64.i64(i64 -9223372036317904704, i64 %x)
+ %res.1 = add i64 %bar.0, %bar.1
+ %res.2 = add i64 %res.1, %bar.2
+ %res.3 = add i64 %res.2, %bar.3
+ ret i64 %res.3
+}
+
+declare i64 @llvm.aarch64.udiv.i64.i64(i64, i64)
+
+define void @test_free_intrinsics(i64 %x, i8* %ptr) {
+; CHECK-LABEL: @test_free_intrinsics(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: call void @llvm.lifetime.start.p0i8(i64 100000000032, i8* [[PTR:%.*]])
+; CHECK-NEXT: call void @llvm.lifetime.start.p0i8(i64 100000000064, i8* [[PTR]])
+; CHECK-NEXT: call void @llvm.lifetime.end.p0i8(i64 100000000128, i8* [[PTR]])
+; CHECK-NEXT: [[I:%.*]] = call {}* @llvm.invariant.start.p0i8(i64 100000000256, i8* [[PTR]])
+; CHECK-NEXT: call void @llvm.invariant.end.p0i8({}* [[I]], i64 100000000256, i8* [[PTR]])
+; CHECK-NEXT: ret void
+;
+entry:
+ call void @llvm.lifetime.start.p0i8(i64 100000000032, i8* %ptr)
+ call void @llvm.lifetime.start.p0i8(i64 100000000064, i8* %ptr)
+ call void @llvm.lifetime.end.p0i8(i64 100000000128, i8* %ptr)
+ %i = call {}* @llvm.invariant.start.p0i8(i64 100000000256, i8* %ptr)
+ call void @llvm.invariant.end.p0i8({}* %i, i64 100000000256, i8* %ptr)
+ ret void
+}
+
+declare void @llvm.lifetime.start.p0i8(i64, i8*)
+declare void @llvm.lifetime.end.p0i8(i64, i8*)
+
+declare {}* @llvm.invariant.start.p0i8(i64, i8* nocapture)
+declare void @llvm.invariant.end.p0i8({}*, i64, i8* nocapture)
More information about the llvm-commits
mailing list