forked from OSchip/llvm-project
91 lines
3.7 KiB
YAML
91 lines
3.7 KiB
YAML
# RUN: llc %s -mtriple=s390x-linux-gnu -mcpu=z13 -start-before=postmisched \
|
|
# RUN: -debug-only=machine-scheduler -o - 2>&1 | FileCheck %s
|
|
# REQUIRES: asserts
|
|
|
|
# Test that the cycle index is the same before and after scheduling an
|
|
# instruction with 6 decoder slots.
|
|
|
|
# CHECK: ++ | Current cycle index: 3
|
|
# CHECK-NEXT: ++ | Resource counters: Z13_FXaUnit:2
|
|
# CHECK-NEXT: ** ScheduleDAGMI::schedule picking next node
|
|
# CHECK-NEXT: ** Available: {SU(3):DL/FXa(4cyc)/LSU/6uops/GroupsAlone, SU(6):LARL/FXa}
|
|
# CHECK-NEXT: ** Best so far: SU(3):DL/FXa(4cyc)/LSU/6uops/GroupsAlone Grouping cost:-1 Height:43
|
|
# CHECK-NEXT: ** Tried : SU(6):LARL/FXa Height:14
|
|
# CHECK-NEXT: ** Scheduling SU(3) Grouping cost:-1
|
|
# CHECK-NEXT: ++ HazardRecognizer emitting SU(3):DL/FXa(4cyc)/LSU/6uops/GroupsAlone
|
|
# CHECK-NEXT: ++ Decode group before emission: <empty>
|
|
# CHECK-NEXT: ++ Completed decode group: { SU(3):DL/FXa(4cyc)/LSU/6uops/GroupsAlone } (6 decoder slots)
|
|
# CHECK-NEXT: ++ | Current decoder group: <empty>
|
|
# CHECK-NEXT: ++ | Current cycle index: 3
|
|
|
|
|
|
--- |
|
|
; ModuleID = '<stdin>'
|
|
source_filename = "<stdin>"
|
|
target datalayout = "E-m:e-i1:8:16-i8:8:16-i64:64-f128:64-v128:64-a:8:16-n32:64"
|
|
target triple = "s390x--linux-gnu"
|
|
|
|
%0 = type { i8, i8, i8, i8, i16, i32, i32, i32 }
|
|
|
|
@TTSize = external dso_local local_unnamed_addr global i32, align 4
|
|
@AS_TTable = external dso_local local_unnamed_addr global %0*, align 8
|
|
@Variant = external dso_local local_unnamed_addr global i32, align 4
|
|
|
|
define dso_local void @LearnStoreTT(i32 signext %arg, i32 zeroext %arg1, i32 signext %arg2) #0 {
|
|
bb:
|
|
%tmp = load i32, i32* @TTSize, align 4
|
|
%tmp3 = urem i32 %arg1, %tmp
|
|
%tmp4 = load %0*, %0** @AS_TTable, align 8
|
|
%tmp5 = zext i32 %tmp3 to i64
|
|
%tmp6 = load i32, i32* @Variant, align 4
|
|
%tmp7 = add i32 %tmp6, -3
|
|
%tmp8 = icmp ugt i32 %tmp7, 1
|
|
%tmp9 = select i1 %tmp8, i8 3, i8 1
|
|
store i8 %tmp9, i8* undef, align 1
|
|
store i32 %arg, i32* undef, align 4
|
|
%tmp10 = trunc i32 %arg2 to i8
|
|
store i8 %tmp10, i8* null, align 1
|
|
%tmp11 = getelementptr inbounds %0, %0* %tmp4, i64 %tmp5, i32 2
|
|
store i8 0, i8* %tmp11, align 2
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { "target-cpu"="z13" }
|
|
|
|
...
|
|
---
|
|
name: LearnStoreTT
|
|
alignment: 4
|
|
tracksRegLiveness: true
|
|
liveins:
|
|
- { reg: '$r2d' }
|
|
- { reg: '$r3d' }
|
|
- { reg: '$r4d' }
|
|
frameInfo:
|
|
maxCallFrameSize: 0
|
|
body: |
|
|
bb.0.bb:
|
|
liveins: $r2d, $r3d, $r4d
|
|
|
|
$r1d = LGR $r3d, implicit-def $r0q
|
|
renamable $r3d = LARL @TTSize
|
|
renamable $r0d = LLILL 0, implicit killed $r0q, implicit-def $r0q
|
|
renamable $r0q = DL killed renamable $r0q, killed renamable $r3d, 0, $noreg :: (dereferenceable load 4 from @TTSize)
|
|
renamable $r3d = LGRL @AS_TTable :: (dereferenceable load 8 from @AS_TTable)
|
|
renamable $r1d = LLGFR renamable $r0l, implicit killed $r0q
|
|
renamable $r5d = LARL @Variant
|
|
renamable $r0l = LHI -3
|
|
renamable $r0l = A killed renamable $r0l, killed renamable $r5d, 0, $noreg, implicit-def dead $cc :: (dereferenceable load 4 from @Variant)
|
|
CLFI killed renamable $r0l, 1, implicit-def $cc
|
|
renamable $r0l = LHI 1
|
|
renamable $r0l = LOCHI killed renamable $r0l, 3, 14, 2, implicit killed $cc
|
|
STC killed renamable $r0l, undef renamable $r1d, 0, $noreg :: (store 1 into `i8* undef`)
|
|
ST renamable $r2l, undef renamable $r1d, 0, $noreg, implicit killed $r2d :: (store 4 into `i32* undef`)
|
|
STC renamable $r4l, $noreg, 0, $noreg, implicit killed $r4d :: (store 1 into `i8* null`)
|
|
renamable $r1d = MGHI killed renamable $r1d, 20
|
|
renamable $r0l = LHI 0
|
|
STC killed renamable $r0l, killed renamable $r3d, 2, killed renamable $r1d :: (store 1 into %ir.tmp11, align 2)
|
|
Return
|
|
|
|
...
|