maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[PowerPC] Do not attempt to reuse load for 64-bit FP_TO_UINT without FPCVT 

We call the function that attempts to reuse the conversion without checking
whether the target matches the constraints that the callee expects. This patch
adds the check prior to the call.

Fixes: https://bugs.llvm.org/show_bug.cgi?id=43976

Differential revision: https://reviews.llvm.org/D77564
This commit is contained in:
Nemanja Ivanovic 2020-04-20 12:59:47 -05:00
parent 1cac82cf38
commit 64b31d96df
2 changed files with 62 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
llvm/lib/Target/PowerPC/PPCISelLowering.cpp
View File

@ -8210,9 +8210,10 @@ bool PPCTargetLowering::canReuseLoadAddress(SDValue Op, EVT MemVT,
SelectionDAG &DAG,
ISD::LoadExtType ET) const {
SDLoc dl(Op);
bool ValidFPToUint = Op.getOpcode() == ISD::FP_TO_UINT &&
(Subtarget.hasFPCVT() || Op.getValueType() == MVT::i32);
if (ET == ISD::NON_EXTLOAD &&
(Op.getOpcode() == ISD::FP_TO_UINT ||
Op.getOpcode() == ISD::FP_TO_SINT) &&
(ValidFPToUint || Op.getOpcode() == ISD::FP_TO_SINT) &&
isOperationLegalOrCustom(Op.getOpcode(),
Op.getOperand(0).getValueType())) {

59
llvm/test/CodeGen/PowerPC/pr43976.ll Normal file
View File

@ -0,0 +1,59 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=powerpc64-unknown-unknown -verify-machineinstrs \
; RUN: -ppc-asm-full-reg-names < %s | FileCheck %s
@a = dso_local local_unnamed_addr global double 0.000000e+00, align 8
define dso_local signext i32 @b() local_unnamed_addr #0 {
; CHECK-LABEL: b:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: mflr r0
; CHECK-NEXT: std r0, 16(r1)
; CHECK-NEXT: stdu r1, -144(r1)
; CHECK-NEXT: addis r3, r2, a@toc@ha
; CHECK-NEXT: addis r4, r2, .LCPI0_0@toc@ha
; CHECK-NEXT: lfd f0, a@toc@l(r3)
; CHECK-NEXT: lfs f1, .LCPI0_0@toc@l(r4)
; CHECK-NEXT: li r4, 1
; CHECK-NEXT: sldi r4, r4, 63
; CHECK-NEXT: fsub f2, f0, f1
; CHECK-NEXT: fctidz f2, f2
; CHECK-NEXT: stfd f2, 128(r1)
; CHECK-NEXT: fctidz f2, f0
; CHECK-NEXT: stfd f2, 120(r1)
; CHECK-NEXT: ld r3, 128(r1)
; CHECK-NEXT: ld r5, 120(r1)
; CHECK-NEXT: fcmpu cr0, f0, f1
; CHECK-NEXT: xor r3, r3, r4
; CHECK-NEXT: bc 12, lt, .LBB0_1
; CHECK-NEXT: b .LBB0_2
; CHECK-NEXT: .LBB0_1: # %entry
; CHECK-NEXT: addi r3, r5, 0
; CHECK-NEXT: .LBB0_2: # %entry
; CHECK-NEXT: std r3, 112(r1)
; CHECK-NEXT: addis r3, r2, .LCPI0_1@toc@ha
; CHECK-NEXT: lfd f0, 112(r1)
; CHECK-NEXT: lfs f1, .LCPI0_1@toc@l(r3)
; CHECK-NEXT: fcfid f0, f0
; CHECK-NEXT: fmul f0, f0, f1
; CHECK-NEXT: fctiwz f0, f0
; CHECK-NEXT: stfd f0, 136(r1)
; CHECK-NEXT: lwa r3, 140(r1)
; CHECK-NEXT: bl g
; CHECK-NEXT: nop
; CHECK-NEXT: addi r1, r1, 144
; CHECK-NEXT: ld r0, 16(r1)
; CHECK-NEXT: mtlr r0
; CHECK-NEXT: blr
entry:
%0 = load double, double* @a, align 8
%conv = fptoui double %0 to i64
%conv1 = sitofp i64 %conv to double
%mul = fmul double %conv1, 1.000000e+06
%conv2 = fptosi double %mul to i32
%call = tail call signext i32 @g(i32 signext %conv2) #0
ret i32 %call
}
declare signext i32 @g(i32 signext) local_unnamed_addr
attributes #0 = { nounwind }