1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 20:51:52 +01:00
llvm-mirror/test/CodeGen/AArch64/wineh_shrinkwrap.mir
Martin Storsjö ba79f9fef9 [AArch64] Match the windows canonical callee saved register order
On windows, the callee saved registers in a canonical prologue are
ordered starting from a lower register number at a lower stack
address (with the possible gap for aligning the stack at the top);
this is the opposite order that llvm normally produces.

To achieve this, reverse the order of the registers in the
assignCalleeSavedSpillSlots callback, to get the stack objects
laid out by PrologEpilogInserter in the right order, and adjust
computeCalleeSaveRegisterPairs to lay them out from the bottom up.

This allows generated prologs more often to match the format that
allows the unwind info to be written as packed info.

Differential Revision: https://reviews.llvm.org/D88677
2020-10-03 21:37:22 +03:00

147 lines
5.3 KiB
YAML

# RUN: llc -O2 -o - %s -mtriple=aarch64-windows -start-before=shrink-wrap \
# RUN: -stop-after=prologepilog | FileCheck %s --check-prefix=WIN64
# RUN: llc -O2 -o - %s -mtriple=aarch64-linux -start-before=shrink-wrap \
# RUN: -stop-after=prologepilog | FileCheck %s --check-prefix=LINUX
# This tests checks that shrink wrapping bails out on Windows AMR64 due to the
# use of Windows CFI. We don't currently support fragments for WIndows EH on
# ARM64.
# The same test gets shrink wrapped on Linux ARM64.
# WIN64-LABEL: bb.0.entry:
# WIN64: early-clobber $sp = frame-setup STRXpre killed $x19, $sp, -32
# WIN64-LABEL: bb.1:
# WIN64-LABEL: bb.2.if.then:
# LINUX-LABEL: bb.0.entry:
# LINUX-LABEL: bb.1:
# LINUX-LABEL: bb.2.if.then:
# LINUX: early-clobber $sp = frame-setup STRXpre killed $fp, $sp, -32
--- |
; ModuleID = 'shrink.cpp'
target datalayout = "e-m:w-p:64:64-i32:32-i64:64-i128:128-n32:64-S128"
target triple = "aarch64-unknown-windows-msvc19.11.0"
define dso_local i32 @"?func@@YAHHH@Z"(i32 %a, i32 %b) local_unnamed_addr #0 {
entry:
%A = alloca [1000 x i32], align 4
%cmp = icmp sgt i32 %a, 1
br i1 %cmp, label %if.then, label %return
if.then: ; preds = %entry
%0 = bitcast [1000 x i32]* %A to i8*
call void @llvm.lifetime.start.p0i8(i64 4000, i8* nonnull %0) #3
%arraydecay2 = bitcast [1000 x i32]* %A to i32*
call void @"?init@@YAXPEAH@Z"(i32* nonnull %arraydecay2)
%arrayidx = getelementptr inbounds [1000 x i32], [1000 x i32]* %A, i64 0, i64 100
%1 = load i32, i32* %arrayidx, align 4, !tbaa !2
%add = add i32 %b, 1
%add1 = add i32 %add, %1
call void @llvm.lifetime.end.p0i8(i64 4000, i8* nonnull %0) #3
br label %return
return: ; preds = %entry, %if.then
%retval.0 = phi i32 [ %add1, %if.then ], [ 0, %entry ]
ret i32 %retval.0
}
; Function Attrs: argmemonly nounwind
declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture) #1
declare dso_local void @"?init@@YAXPEAH@Z"(i32*) local_unnamed_addr #2
; Function Attrs: argmemonly nounwind
declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture) #1
; Function Attrs: nounwind
declare void @llvm.stackprotector(i8*, i8**) #3
attributes #0 = { "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "frame-pointer"="none" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="generic" "target-features"="+neon" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #1 = { argmemonly nounwind }
attributes #2 = { "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "frame-pointer"="none" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="generic" "target-features"="+neon" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #3 = { nounwind }
!llvm.module.flags = !{!0}
!llvm.ident = !{!1}
!0 = !{i32 1, !"wchar_size", i32 2}
!1 = !{!"clang version 8.0.0"}
!2 = !{!3, !3, i64 0}
!3 = !{!"int", !4, i64 0}
!4 = !{!"omnipotent char", !5, i64 0}
!5 = !{!"Simple C++ TBAA"}
...
---
name: '?func@@YAHHH@Z'
alignment: 4
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
failedISel: false
tracksRegLiveness: true
registers:
liveins:
- { reg: '$w0', virtual-reg: '' }
- { reg: '$w1', virtual-reg: '' }
frameInfo:
isFrameAddressTaken: false
isReturnAddressTaken: false
hasStackMap: false
hasPatchPoint: false
stackSize: 0
offsetAdjustment: 0
maxAlignment: 4
adjustsStack: true
hasCalls: true
stackProtector: ''
maxCallFrameSize: 0
cvBytesOfCalleeSavedRegisters: 0
hasOpaqueSPAdjustment: false
hasVAStart: false
hasMustTailInVarArgFunc: false
localFrameSize: 4000
savePoint: ''
restorePoint: ''
fixedStack:
stack:
- { id: 0, name: A, type: default, offset: 0, size: 4000, alignment: 4,
stack-id: default, callee-saved-register: '', callee-saved-restored: true,
local-offset: -4000, debug-info-variable: '', debug-info-expression: '',
debug-info-location: '' }
constants:
body: |
bb.0.entry:
successors: %bb.2(0x40000000), %bb.1(0x40000000)
liveins: $w0, $w1
dead $wzr = SUBSWri killed renamable $w0, 2, 0, implicit-def $nzcv
Bcc 10, %bb.2, implicit killed $nzcv
bb.1:
successors: %bb.3(0x80000000)
renamable $w0 = COPY $wzr
B %bb.3
bb.2.if.then:
successors: %bb.3(0x80000000)
liveins: $w1
renamable $w19 = COPY $w1
ADJCALLSTACKDOWN 0, 0, implicit-def dead $sp, implicit $sp
$x0 = ADDXri %stack.0.A, 0, 0
BL @"?init@@YAXPEAH@Z", csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit-def $sp
ADJCALLSTACKUP 0, 0, implicit-def dead $sp, implicit $sp
renamable $w8 = LDRWui %stack.0.A, 100 :: (dereferenceable load 4 from %ir.arrayidx, !tbaa !2)
renamable $w8 = ADDWrr killed renamable $w19, killed renamable $w8
renamable $w0 = ADDWri killed renamable $w8, 1, 0
bb.3.return:
liveins: $w0
RET_ReallyLR implicit $w0
...