forked from OSchip/llvm-project
87 lines
2.9 KiB
YAML
87 lines
2.9 KiB
YAML
# RUN: llc -o /dev/null %s -mtriple=arm-eabi -mcpu=cortex-r52 -run-pass machine-scheduler -enable-misched -debug-only=machine-scheduler -misched-topdown 2>&1 | FileCheck %s --check-prefix=CHECK --check-prefix=TOPDOWN
|
|
# RUN: llc -o /dev/null %s -mtriple=arm-eabi -mcpu=cortex-r52 -run-pass machine-scheduler -enable-misched -debug-only=machine-scheduler -misched-bottomup 2>&1 | FileCheck %s --check-prefix=CHECK --check-prefix=BOTTOMUP
|
|
# REQUIRES: asserts
|
|
--- |
|
|
; ModuleID = 'foo.ll'
|
|
source_filename = "foo.ll"
|
|
target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-a:0:32-n32-S64"
|
|
target triple = "arm---eabi"
|
|
|
|
%struct.__neon_int8x8x4_t = type { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> }
|
|
; Function Attrs: nounwind
|
|
define <8 x i8> @foo(i8* %A) {
|
|
%tmp1 = call %struct.__neon_int8x8x4_t @llvm.arm.neon.vld4.v8i8.p0i8(i8* %A, i32 8)
|
|
%tmp2 = extractvalue %struct.__neon_int8x8x4_t %tmp1, 0
|
|
%tmp3 = extractvalue %struct.__neon_int8x8x4_t %tmp1, 1
|
|
%tmp4 = add <8 x i8> %tmp2, %tmp3
|
|
ret <8 x i8> %tmp4
|
|
}
|
|
declare %struct.__neon_int8x8x4_t @llvm.arm.neon.vld4.v8i8.p0i8(i8*, i32)
|
|
|
|
# CHECK: ********** MI Scheduling **********
|
|
# CHECK: ScheduleDAGMILive::schedule starting
|
|
# CHECK: SU(1): %1:qqpr = VLD4d8Pseudo %0:gpr, 8, 14, $noreg :: (load (s256) from %ir.A, align 8)
|
|
# CHECK: Latency : 8
|
|
# CHECK: Single Issue : true;
|
|
# CHECK: SU(2): %4:dpr = VADDv8i8 %1.dsub_0:qqpr, %1.dsub_1:qqpr, 14, $noreg
|
|
# CHECK: Latency : 5
|
|
# CHECK: Single Issue : false;
|
|
# CHECK: SU(3): %5:gpr, %6:gpr = VMOVRRD %4:dpr, 14, $noreg
|
|
# CHECK: Latency : 4
|
|
# CHECK: Single Issue : false;
|
|
|
|
# TOPDOWN: Scheduling SU(1) %1:qqpr = VLD4d8Pseudo
|
|
# TOPDOWN: Bump cycle to end group
|
|
# TOPDOWN: Scheduling SU(2) %4:dpr = VADDv8i8
|
|
|
|
# BOTTOMUP: Scheduling SU(2) %4:dpr = VADDv8i8
|
|
# BOTTOMUP: Scheduling SU(1) %1:qqpr = VLD4d8Pseudo
|
|
# BOTTOMUP: Bump cycle to begin group
|
|
|
|
...
|
|
---
|
|
name: foo
|
|
alignment: 4
|
|
exposesReturnsTwice: false
|
|
legalized: false
|
|
regBankSelected: false
|
|
selected: false
|
|
tracksRegLiveness: true
|
|
registers:
|
|
- { id: 0, class: gpr }
|
|
- { id: 1, class: qqpr }
|
|
- { id: 2, class: dpr }
|
|
- { id: 3, class: dpr }
|
|
- { id: 4, class: dpr }
|
|
- { id: 5, class: gpr }
|
|
- { id: 6, class: gpr }
|
|
liveins:
|
|
- { reg: '$r0', virtual-reg: '%0' }
|
|
frameInfo:
|
|
isFrameAddressTaken: false
|
|
isReturnAddressTaken: false
|
|
hasStackMap: false
|
|
hasPatchPoint: false
|
|
stackSize: 0
|
|
offsetAdjustment: 0
|
|
maxAlignment: 0
|
|
adjustsStack: false
|
|
hasCalls: false
|
|
maxCallFrameSize: 0
|
|
hasOpaqueSPAdjustment: false
|
|
hasVAStart: false
|
|
hasMustTailInVarArgFunc: false
|
|
body: |
|
|
bb.0 (%ir-block.0):
|
|
liveins: $r0
|
|
|
|
%0 = COPY $r0
|
|
%1 = VLD4d8Pseudo %0, 8, 14, $noreg :: (load (s256) from %ir.A, align 8)
|
|
%4 = VADDv8i8 %1.dsub_0, %1.dsub_1, 14, $noreg
|
|
%5, %6 = VMOVRRD %4, 14, $noreg
|
|
$r0 = COPY %5
|
|
$r1 = COPY %6
|
|
BX_RET 14, $noreg, implicit $r0, implicit killed $r1
|
|
|
|
...
|