[PATCH] D70669: [AArch64TTI] Do not return TCC_Free for all unknown intrinsics.

[Florian Hahn via Phabricator via llvm-commits]

fhahn created this revision.
fhahn added reviewers: SjoerdMeijer, dmgreen, t.p.northover, ributzka.
Herald added subscribers: dexonsmith, hiraditya, kristof.beyls.
Herald added a project: LLVM.

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.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D70669

Files:
  llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
  llvm/test/Transforms/ConstantHoisting/AArch64/const-hoist-intrinsics.ll


Index: llvm/test/Transforms/ConstantHoisting/AArch64/const-hoist-intrinsics.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/ConstantHoisting/AArch64/const-hoist-intrinsics.ll
@@ -0,0 +1,65 @@
+; 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)
Index: llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
===================================================================
--- llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -157,8 +157,10 @@
     return TTI::TCC_Free;
 
   switch (IID) {
+  // Unless we know that we can fold the immediate operand into a specific
+  // intrinsic, compute the materialization cost for the immediate.
   default:
-    return TTI::TCC_Free;
+    break;
   case Intrinsic::sadd_with_overflow:
   case Intrinsic::uadd_with_overflow:
   case Intrinsic::ssub_with_overflow:


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D70669.230884.patch
Type: text/x-patch
Size: 4256 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20191125/72e94cbc/attachment.bin>