maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/X86/pr30284.ll

23 lines
1.2 KiB
LLVM
Raw Normal View History

[ExecutionDepsFix] Don't make copies of LiveReg objects when collecting operands for soft instructions Summary: While collecting operands we make copies of the LiveReg objects which are stored in the LiveRegs array. If the instruction uses the same register multiple times we end up with multiple copies. Later we iterate through the collected list of LiveReg objects and merge DomainValues. In the process of doing this the merge function can change the contents of the original LiveReg object in the LiveRegs array, but not the copies that have been made. So when we get to the second usage of the register we end up seeing a stale copy of the LiveReg object. To fix this I've stopped copying and now just store a pointer to the original LiveReg object. Another option might be to avoid adding the same register to the Regs array twice, but this approach seemed simpler. The included test case exposes this bug due to an AVX-512 masked OR instruction using the same register for the passthru operand and one of the inputs to the OR operation. Fixes PR30284. Reviewers: RKSimon, stoklund, MatzeB, spatel, myatsina Reviewed By: RKSimon Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D30242 llvm-svn: 296260
2017-02-26 02:12:25 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i386-unknown-linux-gnu -mattr=avx512dq | FileCheck %s
define void @f_f___un_3C_unf_3E_un_3C_unf_3E_() {
; CHECK-LABEL: f_f___un_3C_unf_3E_un_3C_unf_3E_:
; CHECK: # BB#0:
; CHECK-NEXT: vmovapd 0, %zmm0
; CHECK-NEXT: vmovapd 64, %zmm1
; CHECK-NEXT: vmovapd {{.*#+}} zmm2 = [0,16,0,16,0,16,0,16,0,16,0,16,0,16,0,16]
; CHECK-NEXT: vorpd %zmm2, %zmm0, %zmm0 {%k1}
; CHECK-NEXT: vorpd %zmm2, %zmm1, %zmm1 {%k1}
; CHECK-NEXT: vmovapd %zmm1, 64
; CHECK-NEXT: vmovapd %zmm0, 0
[X86] Generate VZEROUPPER for Skylake-avx512. VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be. Differential Revision: https://reviews.llvm.org/D29874 llvm-svn: 296859
2017-03-03 17:03:24 +08:00
; CHECK-NEXT: vzeroupper
[ExecutionDepsFix] Don't make copies of LiveReg objects when collecting operands for soft instructions Summary: While collecting operands we make copies of the LiveReg objects which are stored in the LiveRegs array. If the instruction uses the same register multiple times we end up with multiple copies. Later we iterate through the collected list of LiveReg objects and merge DomainValues. In the process of doing this the merge function can change the contents of the original LiveReg object in the LiveRegs array, but not the copies that have been made. So when we get to the second usage of the register we end up seeing a stale copy of the LiveReg object. To fix this I've stopped copying and now just store a pointer to the original LiveReg object. Another option might be to avoid adding the same register to the Regs array twice, but this approach seemed simpler. The included test case exposes this bug due to an AVX-512 masked OR instruction using the same register for the passthru operand and one of the inputs to the OR operation. Fixes PR30284. Reviewers: RKSimon, stoklund, MatzeB, spatel, myatsina Reviewed By: RKSimon Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D30242 llvm-svn: 296260
2017-02-26 02:12:25 +08:00
; CHECK-NEXT: retl
%a_load22 = load <16 x i64>, <16 x i64>* null, align 1
%bitop = or <16 x i64> %a_load22, <i64 68719476736, i64 68719476736, i64 68719476736, i64 68719476736, i64 68719476736, i64 68719476736, i64 68719476736, i64 68719476736, i64 68719476736, i64 68719476736, i64 68719476736, i64 68719476736, i64 68719476736, i64 68719476736, i64 68719476736, i64 68719476736>
%v.i = load <16 x i64>, <16 x i64>* null
%v1.i41 = select <16 x i1> undef, <16 x i64> %bitop, <16 x i64> %v.i
store <16 x i64> %v1.i41, <16 x i64>* null
ret void
}