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/domain-reassignment-test.ll

38 lines
1.1 KiB
LLVM
Raw Normal View History

[X86DomainReassignment] Don't compare stack-allocated values by address Summary: The Closure allocated in the main loop is allocated on the stack. However, later in the code its address is taken (and used for comparisons). This obviously doesn't work. In fact, the Closure will get the same stack address during every loop iteration, rendering the check that intended to identify Closure conflicts entirely ineffective. Fix this bug by giving every Closure a unique ID and using that for comparison. Alternatively, we could heap allocate the closure object. Fixes PR37396 Fixes JuliaLang/julia#27032 Reviewers: craig.topper, guyblank Reviewed By: craig.topper Subscribers: vchuravy, llvm-commits Differential Revision: https://reviews.llvm.org/D46800 llvm-svn: 332682
2018-05-18 09:03:01 +08:00
; RUN: llc -mcpu=skylake-avx512 -mtriple=x86_64-unknown-linux-gnu %s -o - | FileCheck %s
[X86DomainReassignment] Hopefully fix buildbot failure The Darwin build bot failed with: ``` llc -mcpu=skylake-avx512 -mtriple=x86_64-unknown-linux-gnu domain-reassignment-test.ll -o - | llvm-mc -- Exit Code: 134 Command Output (stderr): -- Assertion failed: (MAI->hasSingleParameterDotFile()), function EmitFileDirective, file lib/MC/MCAsmStreamer.cpp, line 1087. ``` Looks like this is because the `llvm-mc` command was missing a triple directive and defaulting to MachO. Add the triple option. llvm-svn: 332694
2018-05-18 12:36:38 +08:00
; RUN: llc -mcpu=skylake-avx512 -mtriple=x86_64-unknown-linux-gnu %s -o - | llvm-mc -triple=x86_64-unknown-linux-gnu
[X86DomainReassignment] Don't compare stack-allocated values by address Summary: The Closure allocated in the main loop is allocated on the stack. However, later in the code its address is taken (and used for comparisons). This obviously doesn't work. In fact, the Closure will get the same stack address during every loop iteration, rendering the check that intended to identify Closure conflicts entirely ineffective. Fix this bug by giving every Closure a unique ID and using that for comparison. Alternatively, we could heap allocate the closure object. Fixes PR37396 Fixes JuliaLang/julia#27032 Reviewers: craig.topper, guyblank Reviewed By: craig.topper Subscribers: vchuravy, llvm-commits Differential Revision: https://reviews.llvm.org/D46800 llvm-svn: 332682
2018-05-18 09:03:01 +08:00
; Check that the X86 domain reassignment pass doesn't introduce an illegal
; test instruction. See PR37396
define void @japi1_foo2_34617() {
pass2:
br label %if5
L174:
%tmp = icmp sgt <2 x i64> undef, zeroinitializer
%tmp1 = icmp sle <2 x i64> undef, undef
%tmp2 = and <2 x i1> %tmp, %tmp1
%tmp3 = extractelement <2 x i1> %tmp2, i32 0
%tmp4 = extractelement <2 x i1> %tmp2, i32 1
%tmp106 = and i1 %tmp4, %tmp3
%tmp107 = zext i1 %tmp106 to i8
%tmp108 = and i8 %tmp122, %tmp107
%tmp109 = icmp eq i8 %tmp108, 0
; CHECK-NOT: testb {{%k[0-7]}}
br i1 %tmp109, label %L188, label %L190
if5:
%b.055 = phi i8 [ 1, %pass2 ], [ %tmp122, %if5 ]
%tmp118 = icmp sgt i64 undef, 0
%tmp119 = icmp sle i64 undef, undef
%tmp120 = and i1 %tmp118, %tmp119
%tmp121 = zext i1 %tmp120 to i8
%tmp122 = and i8 %b.055, %tmp121
br i1 undef, label %L174, label %if5
L188:
unreachable
L190:
ret void
}