RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-19 02:52:53 +02:00
Code Issues Projects Releases Wiki Activity

[ARM] Remove DLS lr, lr

Browse Source 
A DLS lr, lr instruction only moves lr to itself. It need not be emitted
on it's own to save a instruction in the loop preheader.

Differential Revision: https://reviews.llvm.org/D78916
This commit is contained in:
David Green 2021-02-02 11:09:31 +00:00
parent 306c653648
commit 505ef9e320
60 changed files with 29 additions and 232 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
lib/Target/ARM/ARMLowOverheadLoops.cpp
View File

@ -1452,17 +1452,26 @@ MachineInstr* ARMLowOverheadLoops::ExpandLoopStart(LowOverheadLoop &LoLoop) {
unsigned Opc = LoLoop.getStartOpcode();
MachineOperand &Count = LoLoop.getLoopStartOperand();
MachineInstrBuilder MIB =
BuildMI(*MBB, InsertPt, Start->getDebugLoc(), TII->get(Opc));
// A DLS lr, lr we needn't emit
MachineInstr* NewStart;
if (Opc == ARM::t2DLS && Count.isReg() && Count.getReg() == ARM::LR) {
LLVM_DEBUG(dbgs() << "ARM Loops: Didn't insert start: DLS lr, lr");
NewStart = nullptr;
} else {
MachineInstrBuilder MIB =
BuildMI(*MBB, InsertPt, Start->getDebugLoc(), TII->get(Opc));
MIB.addDef(ARM::LR);
MIB.add(Count);
if (!isDo(Start))
MIB.add(Start->getOperand(1));
MIB.addDef(ARM::LR);
MIB.add(Count);
if (!isDo(Start))
MIB.add(Start->getOperand(1));
LLVM_DEBUG(dbgs() << "ARM Loops: Inserted start: " << *MIB);
NewStart = &*MIB;
}
LoLoop.ToRemove.insert(Start);
LLVM_DEBUG(dbgs() << "ARM Loops: Inserted start: " << *MIB);
return &*MIB;
return NewStart;
}
void ARMLowOverheadLoops::ConvertVPTBlocks(LowOverheadLoop &LoLoop) {
@ -1644,7 +1653,8 @@ void ARMLowOverheadLoops::Expand(LowOverheadLoop &LoLoop) {
RevertLoopEnd(LoLoop.End, RevertLoopDec(LoLoop.Dec));
} else {
LoLoop.Start = ExpandLoopStart(LoLoop);
RemoveDeadBranch(LoLoop.Start);
if (LoLoop.Start)
RemoveDeadBranch(LoLoop.Start);
LoLoop.End = ExpandLoopEnd(LoLoop);
RemoveDeadBranch(LoLoop.End);
if (LoLoop.IsTailPredicationLegal())

4
test/CodeGen/Thumb2/LowOverheadLoops/cond-vector-reduce-mve-codegen.ll
View File

@ -17,7 +17,6 @@ define dso_local i32 @vpsel_mul_reduce_add(i32* noalias nocapture readonly %a, i
; CHECK-NEXT: sub.w r12, r12, #4
; CHECK-NEXT: add.w lr, lr, r12, lsr #2
; CHECK-NEXT: mov.w r12, #0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB0_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: and r4, r12, #15
@ -109,7 +108,6 @@ define dso_local i32 @vpsel_mul_reduce_add_2(i32* noalias nocapture readonly %a,
; CHECK-NEXT: movs r4, #1
; CHECK-NEXT: add.w lr, r4, lr, lsr #2
; CHECK-NEXT: movs r4, #0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB1_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: and r5, r4, #15
@ -212,7 +210,6 @@ define dso_local i32 @and_mul_reduce_add(i32* noalias nocapture readonly %a, i32
; CHECK-NEXT: movs r4, #1
; CHECK-NEXT: add.w lr, r4, lr, lsr #2
; CHECK-NEXT: movs r4, #0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB2_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.32 r12
@ -311,7 +308,6 @@ define dso_local i32 @or_mul_reduce_add(i32* noalias nocapture readonly %a, i32*
; CHECK-NEXT: movs r4, #1
; CHECK-NEXT: add.w lr, r4, lr, lsr #2
; CHECK-NEXT: movs r4, #0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB3_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.32 r12

1
test/CodeGen/Thumb2/LowOverheadLoops/constbound.ll
View File

@ -10,7 +10,6 @@ define dso_local i32 @test_500_504(i32* nocapture readonly %x) {
; CHECK-NEXT: adr r2, .LCPI0_0
; CHECK-NEXT: vldrw.u32 q0, [r2]
; CHECK-NEXT: mov.w r2, #500
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vdup.32 q1, r2
; CHECK-NEXT: movs r1, #0
; CHECK-NEXT: movs r2, #0

3
test/CodeGen/Thumb2/LowOverheadLoops/ctlz-non-zeros.mir
View File

@ -171,7 +171,6 @@ body: |
; CHECK: successors: %bb.2(0x80000000)
; CHECK: liveins: $r0, $r1, $r2, $r3
; CHECK: renamable $lr = t2LDRi12 $sp, 8, 14 /* CC::al */, $noreg :: (load 4 from %fixed-stack.0, align 8)
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: $r4 = tMOVr killed $lr, 14 /* CC::al */, $noreg
; CHECK: bb.2.loop.body:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)
@ -279,7 +278,6 @@ body: |
; CHECK: successors: %bb.2(0x80000000)
; CHECK: liveins: $r0, $r1, $r2, $r3, $r4
; CHECK: renamable $lr = t2LDRi12 $sp, 8, 14 /* CC::al */, $noreg :: (load 4 from %fixed-stack.0, align 8)
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: $r12 = tMOVr killed $lr, 14 /* CC::al */, $noreg
; CHECK: bb.2.loop.body:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)
@ -386,7 +384,6 @@ body: |
; CHECK: successors: %bb.2(0x80000000)
; CHECK: liveins: $r0, $r1, $r2, $r3, $r4
; CHECK: renamable $lr = t2LDRi12 $sp, 8, 14 /* CC::al */, $noreg :: (load 4 from %fixed-stack.0, align 8)
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: $r12 = tMOVr killed $lr, 14 /* CC::al */, $noreg
; CHECK: bb.2.loop.body:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)

1
test/CodeGen/Thumb2/LowOverheadLoops/disjoint-vcmp.mir
View File

@ -147,7 +147,6 @@ body: |
; CHECK: VSTR_P0_off killed renamable $vpr, $sp, 0, 14 /* CC::al */, $noreg :: (store 4 into %stack.0)
; CHECK: renamable $q0 = MVE_VDUP32 killed renamable $r5, 0, $noreg, undef renamable $q0
; CHECK: $r3 = tMOVr $r0, 14 /* CC::al */, $noreg
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: bb.2.bb9:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)
; CHECK: liveins: $lr, $q0, $r0, $r1, $r2, $r3, $r12

1
test/CodeGen/Thumb2/LowOverheadLoops/dont-remove-loop-update.mir
View File

@ -123,7 +123,6 @@ body: |
; CHECK: renamable $r12 = t2BICri killed renamable $r12, 3, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $r12 = t2SUBri killed renamable $r12, 4, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $lr, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: bb.2.vector.body:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)
; CHECK: liveins: $lr, $r0, $r1, $r2, $r3

1
test/CodeGen/Thumb2/LowOverheadLoops/fast-fp-loops.ll
View File

@ -226,7 +226,6 @@ define arm_aapcs_vfpcc float @fast_float_mac(float* nocapture readonly %b, float
; CHECK-NEXT: subs r3, #4
; CHECK-NEXT: add.w lr, r12, r3, lsr #2
; CHECK-NEXT: movs r3, #0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB1_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.32 r2

1
test/CodeGen/Thumb2/LowOverheadLoops/incorrect-sub-16.mir
View File

@ -113,7 +113,6 @@ body: |
; CHECK: renamable $r12 = t2BICri killed renamable $r12, 3, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $r12 = t2SUBri killed renamable $r12, 4, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $lr, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: bb.2.vector.body:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)
; CHECK: liveins: $lr, $r0, $r1, $r2, $r3

1
test/CodeGen/Thumb2/LowOverheadLoops/incorrect-sub-32.mir
View File

@ -121,7 +121,6 @@ body: |
; CHECK: renamable $r12 = t2BICri killed renamable $r12, 3, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $r12 = t2SUBri killed renamable $r12, 4, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $lr, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: bb.2.vector.body:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)
; CHECK: liveins: $lr, $r0, $r1, $r2, $r3

1
test/CodeGen/Thumb2/LowOverheadLoops/incorrect-sub-8.mir
View File

@ -114,7 +114,6 @@ body: |
; CHECK: renamable $r12 = t2BICri killed renamable $r12, 3, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $r12 = t2SUBri killed renamable $r12, 4, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $lr, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: bb.2.vector.body:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)
; CHECK: liveins: $lr, $r0, $r1, $r2, $r3

1
test/CodeGen/Thumb2/LowOverheadLoops/inloop-vpnot-1.mir
View File

@ -151,7 +151,6 @@ body: |
; CHECK: renamable $lr = t2SUBri killed renamable $lr, 4, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $q0 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q0
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $r4, killed renamable $lr, 19, 14 /* CC::al */, $noreg, $noreg
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: $r4 = tMOVr killed $lr, 14 /* CC::al */, $noreg
; CHECK: bb.2.vector.body:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)

1
test/CodeGen/Thumb2/LowOverheadLoops/inloop-vpnot-2.mir
View File

@ -151,7 +151,6 @@ body: |
; CHECK: renamable $lr = t2SUBri killed renamable $lr, 4, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $q0 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q0
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $r4, killed renamable $lr, 19, 14 /* CC::al */, $noreg, $noreg
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: $r4 = tMOVr killed $lr, 14 /* CC::al */, $noreg
; CHECK: bb.2.vector.body:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)

1
test/CodeGen/Thumb2/LowOverheadLoops/inloop-vpnot-3.mir
View File

@ -151,7 +151,6 @@ body: |
; CHECK: renamable $lr = t2SUBri killed renamable $lr, 4, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $q0 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q0
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $r4, killed renamable $lr, 19, 14 /* CC::al */, $noreg, $noreg
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: $r4 = tMOVr killed $lr, 14 /* CC::al */, $noreg
; CHECK: bb.2.vector.body:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)

2
test/CodeGen/Thumb2/LowOverheadLoops/it-block-chain-store.mir
View File

@ -143,7 +143,6 @@ body: |
; CHECK: renamable $r2, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $r2, killed renamable $lr, 19, 14 /* CC::al */, $noreg, $noreg
; CHECK: t2STRi12 renamable $lr, killed renamable $r3, 0, 14 /* CC::al */, $noreg :: (store 4 into %ir.iter.addr)
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: $r2 = tMOVr killed $lr, 14 /* CC::al */, $noreg
; CHECK: bb.1.do.body:
; CHECK: successors: %bb.1(0x7c000000), %bb.2(0x04000000)
@ -248,7 +247,6 @@ body: |
; CHECK: renamable $r2, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $r2, killed renamable $lr, 19, 14 /* CC::al */, $noreg, $noreg
; CHECK: t2STRi12 renamable $lr, killed renamable $r3, 0, 14 /* CC::al */, $noreg :: (store 4 into %ir.iter.addr)
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: $r2 = tMOVr killed $lr, 14 /* CC::al */, $noreg
; CHECK: bb.1.do.body:
; CHECK: successors: %bb.1(0x7c000000), %bb.2(0x04000000)

8
test/CodeGen/Thumb2/LowOverheadLoops/loop-guards.ll
View File

@ -18,7 +18,7 @@
; CHECK: t2CMPri renamable $lr, 0
; CHECK: tBcc %bb.4
; CHECK: bb.2.while.body.preheader:
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK-NOT: $lr = t2DLS killed renamable $lr
; CHECK: bb.3.while.body:
; CHECK: $lr = t2LEUpdate killed renamable $lr, %bb.3
define void @ne_and_guard(i1 zeroext %t1, i1 zeroext %t2, i32* nocapture %a, i32* nocapture readonly %b, i32 %N) {
@ -51,7 +51,7 @@ if.end: ; preds = %while.body, %entry
; CHECK: t2CMPri renamable $lr, 0
; CHECK: tBcc %bb.4
; CHECK: bb.2.while.body.preheader:
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK-NOT: $lr = t2DLS killed renamable $lr
; CHECK: bb.3.while.body:
; CHECK: $lr = t2LEUpdate killed renamable $lr, %bb.3
define void @ne_preheader(i1 zeroext %t1, i1 zeroext %t2, i32* nocapture %a, i32* nocapture readonly %b, i32 %N) {
@ -86,7 +86,7 @@ if.end: ; preds = %while.body, %while.
; CHECK: t2CMPri renamable $lr, 0
; CHECK: tBcc %bb.4
; CHECK: bb.2.while.body.preheader:
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK-NOT: $lr = t2DLS killed renamable $lr
; CHECK: bb.3.while.body:
; CHECK: $lr = t2LEUpdate killed renamable $lr, %bb.3
define void @eq_preheader(i1 zeroext %t1, i1 zeroext %t2, i32* nocapture %a, i32* nocapture readonly %b, i32 %N) {
@ -121,7 +121,7 @@ if.end: ; preds = %while.body, %while.
; CHECK: t2CMPri renamable $lr, 0
; CHECK: tBcc %bb.4
; CHECK: bb.2.while.body.preheader:
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK-NOT: $lr = t2DLS killed renamable $lr
; CHECK: bb.3.while.body:
; CHECK: $lr = t2LEUpdate killed renamable $lr, %bb.3
define void @ne_prepreheader(i1 zeroext %t1, i1 zeroext %t2, i32* nocapture %a, i32* nocapture readonly %b, i32 %N) {

2
test/CodeGen/Thumb2/LowOverheadLoops/lstp-insertion-position.mir
View File

@ -159,7 +159,6 @@ body: |
; CHECK: renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $r3 = tLDRpci %const.0, 14 /* CC::al */, $noreg :: (load 4 from constant-pool)
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: renamable $q1 = MVE_VDUP32 killed renamable $r3, 0, $noreg, undef renamable $q1
; CHECK: $s4 = VMOVS killed $s0, 14 /* CC::al */, $noreg, implicit killed $q1, implicit-def $q1
; CHECK: bb.2.vector.body:
@ -292,7 +291,6 @@ body: |
; CHECK: renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
; CHECK: renamable $lr = t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $r3 = tLDRpci %const.0, 14 /* CC::al */, $noreg :: (load 4 from constant-pool)
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: renamable $q1 = MVE_VDUP32 killed renamable $r3, 0, $noreg, undef renamable $q1
; CHECK: renamable $r2, dead $cpsr = tLSRri killed renamable $r2, 2, 14 /* CC::al */, $noreg
; CHECK: $s4 = VMOVS killed $s0, 14 /* CC::al */, $noreg, implicit killed $q1, implicit-def $q1

1
test/CodeGen/Thumb2/LowOverheadLoops/matrix.mir
View File

@ -321,7 +321,6 @@ body: |
; CHECK: liveins: $lr, $r4, $r12
; CHECK: renamable $r0, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
; CHECK: renamable $r1 = IMPLICIT_DEF
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: bb.10.for.body.i57:
; CHECK: successors: %bb.10(0x7c000000), %bb.11(0x04000000)
; CHECK: liveins: $lr, $r0, $r1, $r4, $r12

1
test/CodeGen/Thumb2/LowOverheadLoops/minloop.ll
View File

@ -26,7 +26,6 @@ define void @arm_min_q31(i32* nocapture readonly %pSrc, i32 %blockSize, i32* noc
; CHECK-NEXT: subs r7, #4
; CHECK-NEXT: add.w lr, r6, r7, lsr #2
; CHECK-NEXT: movs r6, #0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: movs r7, #4
; CHECK-NEXT: .LBB0_5: @ %while.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1

1
test/CodeGen/Thumb2/LowOverheadLoops/move-def-before-start.mir
View File

@ -124,7 +124,6 @@ body: |
; CHECK: renamable $r12 = t2SUBri killed renamable $r12, 4, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $lr, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
; CHECK: $r12 = t2MOVr killed $r3, 14 /* CC::al */, $noreg, $noreg
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: renamable $r3, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
; CHECK: renamable $r12 = t2LSRri killed renamable $r12, 1, 14 /* CC::al */, $noreg, $noreg
; CHECK: bb.2.vector.body:

1
test/CodeGen/Thumb2/LowOverheadLoops/move-start-after-def.mir
View File

@ -123,7 +123,6 @@ body: |
; CHECK: renamable $r12 = t2BICri killed renamable $r12, 3, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $r12 = t2SUBri killed renamable $r12, 4, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $lr, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: $r12 = t2MOVr killed $r3, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $r3, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
; CHECK: renamable $r12 = t2LSRri killed renamable $r12, 1, 14 /* CC::al */, $noreg, $noreg

1
test/CodeGen/Thumb2/LowOverheadLoops/multi-block-cond-iter-count.mir
View File

@ -263,7 +263,6 @@ body: |
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r2, 19, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $r2, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
; CHECK: renamable $r3, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: bb.8 (%ir-block.65):
; CHECK: successors: %bb.8(0x7c000000), %bb.9(0x04000000)
; CHECK: liveins: $lr, $r0, $r1, $r2, $r3, $r12

14
test/CodeGen/Thumb2/LowOverheadLoops/mve-float-loops.ll
View File

@ -94,7 +94,6 @@ define arm_aapcs_vfpcc void @float_float_mul(float* nocapture readonly %a, float
; CHECK-NEXT: mov r5, r1
; CHECK-NEXT: add.w lr, r6, r7, lsr #2
; CHECK-NEXT: mov r6, r2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB0_12: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q0, [r5], #16
@ -313,7 +312,6 @@ define arm_aapcs_vfpcc void @float_float_add(float* nocapture readonly %a, float
; CHECK-NEXT: mov r5, r1
; CHECK-NEXT: add.w lr, r6, r7, lsr #2
; CHECK-NEXT: mov r6, r2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB1_12: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q0, [r5], #16
@ -532,7 +530,6 @@ define arm_aapcs_vfpcc void @float_float_sub(float* nocapture readonly %a, float
; CHECK-NEXT: mov r5, r1
; CHECK-NEXT: add.w lr, r6, r7, lsr #2
; CHECK-NEXT: mov r6, r2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB2_12: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q0, [r5], #16
@ -682,7 +679,6 @@ define arm_aapcs_vfpcc void @float_int_mul(float* nocapture readonly %a, i32* no
; CHECK-NEXT: mov r5, r1
; CHECK-NEXT: add.w lr, r6, r7, lsr #2
; CHECK-NEXT: mov r6, r2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB3_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q0, [r5], #16
@ -890,7 +886,6 @@ define arm_aapcs_vfpcc void @float_int_int_mul(i32* nocapture readonly %a, i32*
; CHECK-NEXT: mov r4, r0
; CHECK-NEXT: add.w lr, r5, r6, lsr #2
; CHECK-NEXT: mov r5, r1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: mov r6, r2
; CHECK-NEXT: .LBB4_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -909,7 +904,6 @@ define arm_aapcs_vfpcc void @float_int_int_mul(i32* nocapture readonly %a, i32*
; CHECK-NEXT: add.w r0, r0, r12, lsl #2
; CHECK-NEXT: add.w r1, r1, r12, lsl #2
; CHECK-NEXT: add.w r2, r2, r12, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB4_7: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldr r3, [r0], #4
@ -995,7 +989,6 @@ define arm_aapcs_vfpcc void @half_half_mul(half* nocapture readonly %a, half* no
; CHECK-NEXT: mov r4, r0
; CHECK-NEXT: add.w lr, r5, r6, lsr #2
; CHECK-NEXT: mov r5, r1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: mov r6, r2
; CHECK-NEXT: .LBB5_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -1024,7 +1017,6 @@ define arm_aapcs_vfpcc void @half_half_mul(half* nocapture readonly %a, half* no
; CHECK-NEXT: add.w r0, r0, r12, lsl #1
; CHECK-NEXT: add.w r1, r1, r12, lsl #1
; CHECK-NEXT: add.w r2, r2, r12, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB5_7: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldr.16 s0, [r1]
@ -1112,7 +1104,6 @@ define arm_aapcs_vfpcc void @half_half_add(half* nocapture readonly %a, half* no
; CHECK-NEXT: mov r4, r0
; CHECK-NEXT: add.w lr, r5, r6, lsr #2
; CHECK-NEXT: mov r5, r1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: mov r6, r2
; CHECK-NEXT: .LBB6_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -1141,7 +1132,6 @@ define arm_aapcs_vfpcc void @half_half_add(half* nocapture readonly %a, half* no
; CHECK-NEXT: add.w r0, r0, r12, lsl #1
; CHECK-NEXT: add.w r1, r1, r12, lsl #1
; CHECK-NEXT: add.w r2, r2, r12, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB6_7: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldr.16 s0, [r1]
@ -1229,7 +1219,6 @@ define arm_aapcs_vfpcc void @half_half_sub(half* nocapture readonly %a, half* no
; CHECK-NEXT: mov r4, r0
; CHECK-NEXT: add.w lr, r5, r6, lsr #2
; CHECK-NEXT: mov r5, r1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: mov r6, r2
; CHECK-NEXT: .LBB7_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -1258,7 +1247,6 @@ define arm_aapcs_vfpcc void @half_half_sub(half* nocapture readonly %a, half* no
; CHECK-NEXT: add.w r0, r0, r12, lsl #1
; CHECK-NEXT: add.w r1, r1, r12, lsl #1
; CHECK-NEXT: add.w r2, r2, r12, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB7_7: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldr.16 s0, [r1]
@ -1346,7 +1334,6 @@ define arm_aapcs_vfpcc void @half_short_mul(half* nocapture readonly %a, i16* no
; CHECK-NEXT: mov r4, r0
; CHECK-NEXT: add.w lr, r5, r6, lsr #2
; CHECK-NEXT: mov r5, r1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: mov r6, r2
; CHECK-NEXT: .LBB8_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -1380,7 +1367,6 @@ define arm_aapcs_vfpcc void @half_short_mul(half* nocapture readonly %a, i16* no
; CHECK-NEXT: add.w r0, r0, r12, lsl #1
; CHECK-NEXT: add.w r1, r1, r12, lsl #1
; CHECK-NEXT: add.w r2, r2, r12, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB8_7: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldrsh r3, [r1], #2

5
test/CodeGen/Thumb2/LowOverheadLoops/mve-tail-data-types.ll
View File

@ -17,7 +17,6 @@ define arm_aapcs_vfpcc i32 @test_acc_scalar_char(i8 zeroext %a, i8* nocapture re
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r12, lsr #2
; CHECK-NEXT: movs r3, #0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB0_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.32 r2
@ -93,7 +92,6 @@ define arm_aapcs_vfpcc i32 @test_acc_scalar_short(i16 signext %a, i16* nocapture
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r12, lsr #2
; CHECK-NEXT: movs r3, #0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB1_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.32 r2
@ -169,7 +167,6 @@ define arm_aapcs_vfpcc i32 @test_acc_scalar_uchar(i8 zeroext %a, i8* nocapture r
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r12, lsr #2
; CHECK-NEXT: movs r3, #0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB2_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.32 r2
@ -245,7 +242,6 @@ define arm_aapcs_vfpcc i32 @test_acc_scalar_ushort(i16 signext %a, i16* nocaptur
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r12, lsr #2
; CHECK-NEXT: movs r3, #0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB3_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.32 r2
@ -321,7 +317,6 @@ define arm_aapcs_vfpcc i32 @test_acc_scalar_int(i32 %a, i32* nocapture readonly
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r12, lsr #2
; CHECK-NEXT: movs r3, #0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB4_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.32 r2

1
test/CodeGen/Thumb2/LowOverheadLoops/non-masked-load.mir
View File

@ -131,7 +131,6 @@ body: |
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $r3, renamable $r12, 35, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $r3 = t2LSRri killed renamable $r12, 4, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $r3 = t2SUBrs renamable $r2, killed renamable $r3, 34, 14 /* CC::al */, $noreg, $noreg
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: bb.2.vector.body:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)
; CHECK: liveins: $lr, $q0, $r0, $r1, $r2, $r3

1
test/CodeGen/Thumb2/LowOverheadLoops/non-masked-store.mir
View File

@ -118,7 +118,6 @@ body: |
; CHECK: renamable $r12 = t2BICri killed renamable $r12, 15, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $r12 = t2SUBri killed renamable $r12, 16, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $lr, killed renamable $r12, 35, 14 /* CC::al */, $noreg, $noreg
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: bb.2.vector.body:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)
; CHECK: liveins: $lr, $r0, $r1, $r2, $r3

9
test/CodeGen/Thumb2/LowOverheadLoops/reductions.ll
View File

@ -74,7 +74,6 @@ define dso_local arm_aapcs_vfpcc signext i16 @one_loop_add_add_v8i16(i8* nocaptu
; CHECK-NEXT: sub.w r12, r3, #8
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r12, lsr #3
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB1_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.16 r2
@ -147,7 +146,6 @@ define dso_local arm_aapcs_vfpcc zeroext i8 @one_loop_sub_add_v16i8(i8* nocaptur
; CHECK-NEXT: sub.w r12, r3, #16
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r12, lsr #4
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB2_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.8 r2
@ -217,7 +215,6 @@ define dso_local arm_aapcs_vfpcc signext i16 @one_loop_sub_add_v8i16(i8* nocaptu
; CHECK-NEXT: sub.w r12, r3, #8
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r12, lsr #3
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB3_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.16 r2
@ -289,7 +286,6 @@ define dso_local arm_aapcs_vfpcc zeroext i8 @one_loop_mul_add_v16i8(i8* nocaptur
; CHECK-NEXT: sub.w r12, r3, #16
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r12, lsr #4
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB4_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.8 r2
@ -359,7 +355,6 @@ define dso_local arm_aapcs_vfpcc signext i16 @one_loop_mul_add_v8i16(i8* nocaptu
; CHECK-NEXT: sub.w r12, r3, #8
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r12, lsr #3
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB5_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.16 r2
@ -431,7 +426,6 @@ define dso_local arm_aapcs_vfpcc i32 @two_loops_mul_add_v4i32(i8* nocapture read
; CHECK-NEXT: mov r5, r1
; CHECK-NEXT: add.w lr, r3, r6, lsr #2
; CHECK-NEXT: mov r3, r2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB6_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.32 r3
@ -453,7 +447,6 @@ define dso_local arm_aapcs_vfpcc i32 @two_loops_mul_add_v4i32(i8* nocapture read
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r6, lsr #2
; CHECK-NEXT: vmov.32 q0[0], r12
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB6_5: @ %vector.body46
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.32 r2
@ -558,7 +551,6 @@ define dso_local arm_aapcs_vfpcc void @two_reductions_mul_add_v8i16(i8* nocaptur
; CHECK-NEXT: add.w lr, r4, r3, lsr #3
; CHECK-NEXT: mov r3, r0
; CHECK-NEXT: mov r4, r1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB7_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.16 r2
@ -677,7 +669,6 @@ define i32 @wrongop(%struct.date* nocapture readonly %pd) {
; CHECK-NEXT: bic r0, r0, #3
; CHECK-NEXT: subs r0, #4
; CHECK-NEXT: add.w lr, r12, r0, lsr #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB8_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.32 r2

1
test/CodeGen/Thumb2/LowOverheadLoops/remat-vctp.ll
View File

@ -106,7 +106,6 @@ define void @dont_remat_predicated_vctp(i32* %arg, i32* %arg1, i32* %arg2, i32*
; CHECK-NEXT: add.w lr, r5, #3
; CHECK-NEXT: movs r5, #1
; CHECK-NEXT: add.w lr, r5, lr, lsr #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB1_1: @ %bb6
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.32 r12

1
test/CodeGen/Thumb2/LowOverheadLoops/remove-elem-moves.mir
View File

@ -210,7 +210,6 @@ body: |
; CHECK: liveins: $lr, $r3, $r12
; CHECK: renamable $r0, dead $cpsr = tSUBi3 killed renamable $r3, 4, 14 /* CC::al */, $noreg
; CHECK: renamable $r1 = t2SUBri killed renamable $r12, 4, 14 /* CC::al */, $noreg, $noreg
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: bb.8.while.body:
; CHECK: successors: %bb.8(0x7c000000), %bb.9(0x04000000)
; CHECK: liveins: $lr, $r0, $r1

1
test/CodeGen/Thumb2/LowOverheadLoops/skip-debug.mir
View File

@ -200,7 +200,6 @@ body: |
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $lr, renamable $r3, 19, 14 /* CC::al */, $noreg, $noreg, debug-location !28
; CHECK: renamable $r3, dead $cpsr = tLSRri killed renamable $r3, 2, 14 /* CC::al */, $noreg, debug-location !28
; CHECK: renamable $r3 = t2SUBrs renamable $r2, killed renamable $r3, 18, 14 /* CC::al */, $noreg, $noreg, debug-location !28
; CHECK: $lr = t2DLS killed renamable $lr, debug-location !28
; CHECK: bb.2.vector.body:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)
; CHECK: liveins: $lr, $q0, $r0, $r1, $r2, $r3

1
test/CodeGen/Thumb2/LowOverheadLoops/unpredload.ll
View File

@ -59,7 +59,6 @@ define i32 @bad(i32* readonly %x, i32* nocapture readonly %y, i32 %n) {
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r12, lsr #2
; CHECK-NEXT: mov.w r12, #0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB1_1: @ %do.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.32 r2

1
test/CodeGen/Thumb2/LowOverheadLoops/unrolled-and-vector.mir
View File

@ -301,7 +301,6 @@ body: |
; CHECK: renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 4, 14 /* CC::al */, $noreg
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $lr, killed renamable $r3, 19, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $r3, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: bb.7.for.body:
; CHECK: successors: %bb.7(0x7c000000), %bb.8(0x04000000)
; CHECK: liveins: $lr, $r0, $r1, $r2, $r3, $r12

1
test/CodeGen/Thumb2/LowOverheadLoops/vaddv.mir
View File

@ -2980,7 +2980,6 @@ body: |
; CHECK: renamable $r2, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $r2, killed renamable $r12, 27, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $r2, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: bb.2.while.body:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)
; CHECK: liveins: $lr, $r0, $r1, $r2, $r3

3
test/CodeGen/Thumb2/LowOverheadLoops/vctp-in-vpt.mir
View File

@ -291,7 +291,6 @@ body: |
; CHECK: VSTR_P0_off killed renamable $vpr, $sp, 0, 14 /* CC::al */, $noreg :: (store 4 into %stack.0)
; CHECK: $r3 = tMOVr $r0, 14 /* CC::al */, $noreg
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $lr, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: bb.2.bb9:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)
; CHECK: liveins: $lr, $r0, $r1, $r2, $r3
@ -434,7 +433,6 @@ body: |
; CHECK: VSTR_P0_off killed renamable $vpr, $sp, 0, 14 /* CC::al */, $noreg :: (store 4 into %stack.0)
; CHECK: $r3 = tMOVr $r0, 14 /* CC::al */, $noreg
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $lr, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: bb.2.bb9:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)
; CHECK: liveins: $lr, $r0, $r1, $r2, $r3
@ -577,7 +575,6 @@ body: |
; CHECK: VSTR_P0_off killed renamable $vpr, $sp, 0, 14 /* CC::al */, $noreg :: (store 4 into %stack.0)
; CHECK: $r3 = tMOVr $r0, 14 /* CC::al */, $noreg
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $lr, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: bb.2.bb9:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)
; CHECK: liveins: $lr, $r0, $r1, $r2, $r3

1
test/CodeGen/Thumb2/LowOverheadLoops/vctp16-reduce.mir
View File

@ -137,7 +137,6 @@ body: |
; CHECK: renamable $r12 = t2LSRri killed renamable $r12, 3, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $q0 = MVE_VLDRWU32 killed renamable $r3, 0, 0, $noreg :: (load 16 from constant-pool)
; CHECK: renamable $r3 = t2SUBrs renamable $r2, killed renamable $r12, 26, 14 /* CC::al */, $noreg, $noreg
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: bb.2.vector.body:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)
; CHECK: liveins: $lr, $q0, $r0, $r1, $r2, $r3

3
test/CodeGen/Thumb2/LowOverheadLoops/vector-arith-codegen.ll
View File

@ -17,7 +17,6 @@ define dso_local i32 @mul_reduce_add(i32* noalias nocapture readonly %a, i32* no
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r12, lsr #2
; CHECK-NEXT: movs r3, #0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB0_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.32 r2
@ -94,7 +93,6 @@ define dso_local i32 @mul_reduce_add_const(i32* noalias nocapture readonly %a, i
; CHECK-NEXT: subs r1, #4
; CHECK-NEXT: add.w lr, r3, r1, lsr #2
; CHECK-NEXT: movs r1, #0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB1_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.32 r2
@ -165,7 +163,6 @@ define dso_local i32 @add_reduce_add_const(i32* noalias nocapture readonly %a, i
; CHECK-NEXT: subs r1, #4
; CHECK-NEXT: add.w lr, r3, r1, lsr #2
; CHECK-NEXT: movs r1, #0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB2_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.32 r2

4
test/CodeGen/Thumb2/LowOverheadLoops/vpt-blocks.mir
View File

@ -349,7 +349,6 @@ body: |
; CHECK: renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $r3, dead $cpsr = nsw tRSB renamable $r2, 14 /* CC::al */, $noreg
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: bb.2.vector.body:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)
; CHECK: liveins: $lr, $q0, $r0, $r1, $r2, $r3
@ -481,7 +480,6 @@ body: |
; CHECK: renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $r3, dead $cpsr = nsw tRSB renamable $r2, 14 /* CC::al */, $noreg
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: bb.2.vector.body:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)
; CHECK: liveins: $lr, $q0, $r0, $r1, $r2, $r3
@ -956,7 +954,6 @@ body: |
; CHECK: renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
; CHECK: dead renamable $r3, dead $cpsr = nsw tRSB renamable $r2, 14 /* CC::al */, $noreg
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: bb.2.vector.body:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)
; CHECK: liveins: $lr, $q0, $r0, $r1, $r2
@ -1254,7 +1251,6 @@ body: |
; CHECK: renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
; CHECK: renamable $lr = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $q2 = MVE_VMOVimmi32 4, 0, $noreg, undef renamable $q2
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: bb.2 (align 4):
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)
; CHECK: liveins: $lr, $q0, $q1, $q2, $r0, $r1, $r2

1
test/CodeGen/Thumb2/LowOverheadLoops/wrong-liveout-lsr-shift.mir
View File

@ -137,7 +137,6 @@ body: |
; CHECK: renamable $r12 = t2LSRri killed renamable $r12, 2, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $q0 = MVE_VLDRWU32 killed renamable $r3, 0, 0, $noreg :: (load 16 from constant-pool)
; CHECK: renamable $r3 = t2SUBrs renamable $r2, killed renamable $r12, 26, 14 /* CC::al */, $noreg, $noreg
; CHECK: $lr = t2DLS killed renamable $lr
; CHECK: bb.2.vector.body:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)
; CHECK: liveins: $lr, $q0, $r0, $r1, $r2, $r3

1
test/CodeGen/Thumb2/active_lane_mask.ll
View File

@ -424,7 +424,6 @@ define void @test_width2(i32* nocapture readnone %x, i32* nocapture %y, i8 zeroe
; CHECK-NEXT: vldrw.u32 q2, [r2]
; CHECK-NEXT: add.w lr, r3, r0, lsr #1
; CHECK-NEXT: mov.w r8, #0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vand q1, q1, q0
; CHECK-NEXT: .LBB4_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1

1
test/CodeGen/Thumb2/aligned-nonfallthrough.ll
View File

@ -7,7 +7,6 @@ define i32 @loop(i32* nocapture readonly %x) {
; CHECK-NEXT: .save {r7, lr}
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: mov.w lr, #500
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: movs r1, #0
; CHECK-NEXT: .p2align 2
; CHECK-NEXT: .LBB0_1: @ %for.body

1
test/CodeGen/Thumb2/mve-float16regloops.ll
View File

@ -703,7 +703,6 @@ define dso_local void @test_nested(half* noalias nocapture %pInT1, half* noalias
; CHECK-NEXT: push {r4, r5, r6, lr}
; CHECK-NEXT: ldrd lr, r12, [sp, #16]
; CHECK-NEXT: lsl.w r3, r12, #1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB14_1: @ %for.body.us
; CHECK-NEXT: @ =>This Loop Header: Depth=1
; CHECK-NEXT: @ Child Loop BB14_2 Depth 2

1
test/CodeGen/Thumb2/mve-float32regloops.ll
View File

@ -703,7 +703,6 @@ define dso_local void @test_nested(float* noalias nocapture %pInT1, float* noali
; CHECK-NEXT: push {r4, r5, r6, lr}
; CHECK-NEXT: ldrd lr, r12, [sp, #16]
; CHECK-NEXT: lsl.w r3, r12, #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB14_1: @ %for.body.us
; CHECK-NEXT: @ =>This Loop Header: Depth=1
; CHECK-NEXT: @ Child Loop BB14_2 Depth 2

11
test/CodeGen/Thumb2/mve-fp16convertloops.ll
View File

@ -8,7 +8,6 @@ define void @to_4(float* nocapture readonly %x, half* noalias nocapture %y) {
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: mov.w lr, #256
; CHECK-NEXT: adr r2, .LCPI0_0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q0, [r2]
; CHECK-NEXT: .LBB0_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -54,7 +53,6 @@ define void @to_8(float* nocapture readonly %x, half* noalias nocapture %y) {
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: mov.w lr, #128
; CHECK-NEXT: adr r2, .LCPI1_0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q0, [r2]
; CHECK-NEXT: .LBB1_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -104,7 +102,6 @@ define void @to_16(float* nocapture readonly %x, half* noalias nocapture %y) {
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: mov.w lr, #64
; CHECK-NEXT: adr r2, .LCPI2_0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q0, [r2]
; CHECK-NEXT: .LBB2_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -162,7 +159,6 @@ define void @from_4(half* nocapture readonly %x, float* noalias nocapture %y) {
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: mov.w lr, #256
; CHECK-NEXT: adr r2, .LCPI3_0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q0, [r2]
; CHECK-NEXT: .LBB3_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -208,7 +204,6 @@ define void @from_8(half* nocapture readonly %x, float* noalias nocapture %y) {
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: mov.w lr, #128
; CHECK-NEXT: adr r2, .LCPI4_0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q0, [r2]
; CHECK-NEXT: .LBB4_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -258,7 +253,6 @@ define void @from_16(half* nocapture readonly %x, float* noalias nocapture %y) {
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: mov.w lr, #64
; CHECK-NEXT: adr r2, .LCPI5_0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q0, [r2]
; CHECK-NEXT: .LBB5_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -316,7 +310,6 @@ define void @both_4(half* nocapture readonly %x, half* noalias nocapture %y) {
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: mov.w lr, #256
; CHECK-NEXT: adr r2, .LCPI6_0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q0, [r2]
; CHECK-NEXT: .LBB6_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -364,7 +357,6 @@ define void @both_8(half* nocapture readonly %x, half* noalias nocapture %y) {
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: mov.w lr, #128
; CHECK-NEXT: adr r2, .LCPI7_0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q0, [r2]
; CHECK-NEXT: .LBB7_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -417,7 +409,6 @@ define void @both_16(half* nocapture readonly %x, half* noalias nocapture %y) {
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: mov.w lr, #64
; CHECK-NEXT: adr r2, .LCPI8_0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q0, [r2]
; CHECK-NEXT: .LBB8_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -480,7 +471,6 @@ define void @both_8_I(half* nocapture readonly %x, half* noalias nocapture %y) {
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: mov.w lr, #128
; CHECK-NEXT: adr r2, .LCPI9_0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q0, [r2]
; CHECK-NEXT: .LBB9_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -536,7 +526,6 @@ define void @both_16_I(half* nocapture readonly %x, half* noalias nocapture %y)
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: mov.w lr, #128
; CHECK-NEXT: adr r2, .LCPI10_0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q0, [r2]
; CHECK-NEXT: .LBB10_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1

2
test/CodeGen/Thumb2/mve-gather-ptrs.ll
View File

@ -701,7 +701,6 @@ define void @foo_ptr_p_int32_t(i32* %dest, i32** %src, i32 %n) {
; CHECK-NEXT: subs r2, #4
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r2, lsr #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB22_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q0, [r1], #16
@ -747,7 +746,6 @@ define void @foo_ptr_p_float(float* %dest, float** %src, i32 %n) {
; CHECK-NEXT: subs r2, #4
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r2, lsr #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB23_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q0, [r1], #16

1
test/CodeGen/Thumb2/mve-gather-scatter-optimisation.ll
View File

@ -713,7 +713,6 @@ define dso_local void @arm_mat_mult_q15(i16* noalias nocapture readonly %A, i16*
; CHECK-NEXT: sub.w lr, r9, r7
; CHECK-NEXT: mla r3, r0, r7, r1
; CHECK-NEXT: ldr r0, [sp, #20] @ 4-byte Reload
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: add.w r5, r0, r5, lsl #1
; CHECK-NEXT: add.w r3, r6, r3, lsl #1
; CHECK-NEXT: .LBB10_14: @ %for.body8.us.us

10
test/CodeGen/Thumb2/mve-gather-scatter-ptr-address.ll
View File

@ -9,7 +9,6 @@ define void @ptr_iv_v4i32(i32* noalias nocapture readonly %A, i32* noalias nocap
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: mov.w lr, #249
; CHECK-NEXT: adr r3, .LCPI0_0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q0, [r3]
; CHECK-NEXT: .LBB0_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -60,7 +59,6 @@ define void @ptr_iv_v4i32_mult(i32* noalias nocapture readonly %A, i32* noalias
; CHECK-NEXT: mov.w lr, #249
; CHECK-NEXT: adr r1, .LCPI1_0
; CHECK-NEXT: adr r3, .LCPI1_1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q0, [r3]
; CHECK-NEXT: vldrw.u32 q1, [r1]
; CHECK-NEXT: .LBB1_1: @ %vector.body
@ -117,7 +115,6 @@ define void @ptr_iv_v8i16(i16* noalias nocapture readonly %A, i16* noalias nocap
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: mov.w lr, #249
; CHECK-NEXT: adr r3, .LCPI2_0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q0, [r3]
; CHECK-NEXT: .LBB2_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -173,7 +170,6 @@ define void @ptr_iv_v8i16_mult(i16* noalias nocapture readonly %A, i16* noalias
; CHECK-NEXT: mov.w lr, #249
; CHECK-NEXT: adr.w r12, .LCPI3_0
; CHECK-NEXT: adr r3, .LCPI3_1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q0, [r3]
; CHECK-NEXT: vldrw.u32 q1, [r12]
; CHECK-NEXT: .LBB3_1: @ %vector.body
@ -239,7 +235,6 @@ define void @ptr_iv_v16i8(i8* noalias nocapture readonly %A, i8* noalias nocaptu
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: mov.w lr, #249
; CHECK-NEXT: adr r3, .LCPI4_0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q0, [r3]
; CHECK-NEXT: .LBB4_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -303,7 +298,6 @@ define void @ptr_iv_v16i8_mult(i8* noalias nocapture readonly %A, i8* noalias no
; CHECK-NEXT: mov.w lr, #249
; CHECK-NEXT: adr.w r12, .LCPI5_0
; CHECK-NEXT: adr r3, .LCPI5_1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q0, [r3]
; CHECK-NEXT: vldrw.u32 q1, [r12]
; CHECK-NEXT: .LBB5_1: @ %vector.body
@ -385,7 +379,6 @@ define void @ptr_iv_v4f32(float* noalias nocapture readonly %A, float* noalias n
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: mov.w lr, #249
; CHECK-NEXT: adr r3, .LCPI6_0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q0, [r3]
; CHECK-NEXT: .LBB6_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -436,7 +429,6 @@ define void @ptr_iv_v4f32_mult(float* noalias nocapture readonly %A, float* noal
; CHECK-NEXT: mov.w lr, #249
; CHECK-NEXT: adr r1, .LCPI7_0
; CHECK-NEXT: adr r3, .LCPI7_1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q0, [r3]
; CHECK-NEXT: vldrw.u32 q1, [r1]
; CHECK-NEXT: .LBB7_1: @ %vector.body
@ -496,7 +488,6 @@ define void @ptr_iv_v8f16(half* noalias nocapture readonly %A, half* noalias noc
; CHECK-NEXT: vcvtb.f16.f32 s0, s0
; CHECK-NEXT: adr r3, .LCPI8_0
; CHECK-NEXT: vmov.f16 r2, s0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q0, [r3]
; CHECK-NEXT: .LBB8_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -556,7 +547,6 @@ define void @ptr_iv_v8f16_mult(half* noalias nocapture readonly %A, half* noalia
; CHECK-NEXT: vmov.f16 r1, s0
; CHECK-NEXT: vldrw.u32 q0, [r2]
; CHECK-NEXT: adr r2, .LCPI9_1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q1, [r2]
; CHECK-NEXT: .LBB9_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1

3
test/CodeGen/Thumb2/mve-gather-scatter-tailpred.ll
View File

@ -13,7 +13,6 @@ define dso_local void @mve_gather_qi_wb(i32* noalias nocapture readonly %A, i32*
; CHECK-NEXT: movw lr, #1250
; CHECK-NEXT: vadd.i32 q0, q0, r1
; CHECK-NEXT: adds r1, r3, #4
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB0_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.32 r3
@ -85,7 +84,6 @@ define dso_local void @mve_gatherscatter_offset(i32* noalias nocapture readonly
; CHECK-NEXT: vmov.i32 q2, #0x0
; CHECK-NEXT: vmov.i32 q0, #0x14
; CHECK-NEXT: movw lr, #1250
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB1_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.32 r3
@ -160,7 +158,6 @@ define dso_local void @mve_scatter_qi(i32* noalias nocapture readonly %A, i32* n
; CHECK-NEXT: vmov.i32 q2, #0x3
; CHECK-NEXT: vadd.i32 q0, q0, r1
; CHECK-NEXT: adds r1, r3, #4
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB2_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.32 r3

1
test/CodeGen/Thumb2/mve-nounrolledremainder.ll
View File

@ -163,7 +163,6 @@ define void @notailpred(half* nocapture readonly %pSrcA, half* nocapture readonl
; CHECK-NEXT: add.w r12, r0, r6, lsl #1
; CHECK-NEXT: add.w lr, r5, r7, lsr #3
; CHECK-NEXT: add.w r7, r2, r6, lsl #1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: and r5, r3, #7
; CHECK-NEXT: .LBB1_8: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1

3
test/CodeGen/Thumb2/mve-postinc-distribute.ll
View File

@ -12,7 +12,6 @@ define i32 @vaddv(i32* nocapture readonly %data, i32 %N) {
; CHECK-NEXT: cmp r1, #1
; CHECK-NEXT: blt .LBB0_4
; CHECK-NEXT: @ %bb.1: @ %for.body.preheader
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: mov r1, r0
; CHECK-NEXT: movs r0, #0
; CHECK-NEXT: .LBB0_2: @ %for.body
@ -285,7 +284,6 @@ define void @fma8(float* noalias nocapture readonly %A, float* noalias nocapture
; CHECK-NEXT: mov r4, r0
; CHECK-NEXT: add.w lr, r5, r6, lsr #3
; CHECK-NEXT: mov r5, r1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: mov r6, r2
; CHECK-NEXT: .LBB2_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -309,7 +307,6 @@ define void @fma8(float* noalias nocapture readonly %A, float* noalias nocapture
; CHECK-NEXT: add.w r0, r0, r12, lsl #2
; CHECK-NEXT: add.w r1, r1, r12, lsl #2
; CHECK-NEXT: add.w r2, r2, r12, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB2_7: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldr s0, [r0]

3
test/CodeGen/Thumb2/mve-postinc-lsr.ll
View File

@ -24,7 +24,6 @@ define void @fma(float* noalias nocapture readonly %A, float* noalias nocapture
; CHECK-NEXT: mov r4, r0
; CHECK-NEXT: add.w lr, r5, r6, lsr #2
; CHECK-NEXT: mov r5, r1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: mov r6, r2
; CHECK-NEXT: .LBB0_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -43,7 +42,6 @@ define void @fma(float* noalias nocapture readonly %A, float* noalias nocapture
; CHECK-NEXT: add.w r0, r0, r12, lsl #2
; CHECK-NEXT: add.w r1, r1, r12, lsl #2
; CHECK-NEXT: add.w r2, r2, r12, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB0_7: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldr s0, [r0]
@ -136,7 +134,6 @@ define void @fma_tailpred(float* noalias nocapture readonly %A, float* noalias n
; CHECK-NEXT: vldrw.u32 q0, [r4]
; CHECK-NEXT: add.w lr, lr, r12, lsr #2
; CHECK-NEXT: sub.w r12, r3, #1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: movs r3, #0
; CHECK-NEXT: vdup.32 q1, r12
; CHECK-NEXT: .LBB1_2: @ %vector.body

10
test/CodeGen/Thumb2/mve-pred-threshold.ll
View File

@ -16,7 +16,6 @@ define arm_aapcs_vfpcc void @thres_i32(i32* %data, i16 zeroext %N, i32 %T) {
; CHECK-NEXT: vmov.i32 q0, #0x0
; CHECK-NEXT: add.w lr, r3, r1, lsr #2
; CHECK-NEXT: rsbs r1, r2, #0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB0_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q1, [r0]
@ -73,7 +72,6 @@ define arm_aapcs_vfpcc void @thresh_i16(i16* %data, i16 zeroext %N, i16 signext
; CHECK-NEXT: vmov.i32 q0, #0x0
; CHECK-NEXT: add.w lr, r3, r1, lsr #3
; CHECK-NEXT: rsbs r1, r2, #0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB1_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrh.u16 q1, [r0]
@ -130,7 +128,6 @@ define arm_aapcs_vfpcc void @thresh_i8(i8* %data, i16 zeroext %N, i8 signext %T)
; CHECK-NEXT: vmov.i32 q0, #0x0
; CHECK-NEXT: add.w lr, r3, r1, lsr #4
; CHECK-NEXT: rsbs r1, r2, #0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB2_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrb.u8 q1, [r0]
@ -186,7 +183,6 @@ define arm_aapcs_vfpcc void @thresh_f32(float* %data, i16 zeroext %N, float %T)
; CHECK-NEXT: movs r2, #1
; CHECK-NEXT: add.w lr, r2, r1, lsr #2
; CHECK-NEXT: vmov r1, s0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vmov.i32 q0, #0x0
; CHECK-NEXT: eor r2, r1, #-2147483648
; CHECK-NEXT: .LBB3_2: @ %vector.body
@ -246,7 +242,6 @@ define arm_aapcs_vfpcc void @thresh_f16(half* %data, i16 zeroext %N, float %T.co
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r1, lsr #3
; CHECK-NEXT: vmov.f16 r1, s0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vmov.i32 q0, #0x0
; CHECK-NEXT: .LBB4_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -309,7 +304,6 @@ define arm_aapcs_vfpcc void @thres_rev_i32(i32* %data, i16 zeroext %N, i32 %T) {
; CHECK-NEXT: vmov.i32 q0, #0x0
; CHECK-NEXT: add.w lr, r3, r1, lsr #2
; CHECK-NEXT: rsbs r1, r2, #0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB5_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q1, [r0]
@ -366,7 +360,6 @@ define arm_aapcs_vfpcc void @thresh_rev_i16(i16* %data, i16 zeroext %N, i16 sign
; CHECK-NEXT: vmov.i32 q0, #0x0
; CHECK-NEXT: add.w lr, r3, r1, lsr #3
; CHECK-NEXT: rsbs r1, r2, #0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB6_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrh.u16 q1, [r0]
@ -423,7 +416,6 @@ define arm_aapcs_vfpcc void @thresh_rev_i8(i8* %data, i16 zeroext %N, i8 signext
; CHECK-NEXT: vmov.i32 q0, #0x0
; CHECK-NEXT: add.w lr, r3, r1, lsr #4
; CHECK-NEXT: rsbs r1, r2, #0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB7_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrb.u8 q1, [r0]
@ -479,7 +471,6 @@ define arm_aapcs_vfpcc void @thresh_rev_f32(float* %data, i16 zeroext %N, float
; CHECK-NEXT: movs r2, #1
; CHECK-NEXT: add.w lr, r2, r1, lsr #2
; CHECK-NEXT: vmov r1, s0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vmov.i32 q0, #0x0
; CHECK-NEXT: eor r2, r1, #-2147483648
; CHECK-NEXT: .LBB8_2: @ %vector.body
@ -539,7 +530,6 @@ define arm_aapcs_vfpcc void @thresh_rev_f16(half* %data, i16 zeroext %N, float %
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r1, lsr #3
; CHECK-NEXT: vmov.f16 r1, s0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vmov.i32 q0, #0x0
; CHECK-NEXT: .LBB9_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1

37
test/CodeGen/Thumb2/mve-satmul-loops.ll
View File

@ -34,7 +34,6 @@ define arm_aapcs_vfpcc void @ssatmul_s_q31(i32* nocapture readonly %pSrcA, i32*
; CHECK-NEXT: add.w r11, r2, r3, lsl #2
; CHECK-NEXT: add.w r10, r1, r3, lsl #2
; CHECK-NEXT: add.w r12, r0, r3, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q0, [r4]
; CHECK-NEXT: vmvn.i32 q1, #0x80000000
; CHECK-NEXT: .LBB0_4: @ %vector.body
@ -106,7 +105,6 @@ define arm_aapcs_vfpcc void @ssatmul_s_q31(i32* nocapture readonly %pSrcA, i32*
; CHECK-NEXT: .LBB0_6: @ %for.body.preheader
; CHECK-NEXT: sub.w lr, r3, r7
; CHECK-NEXT: mov.w r0, #-1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: mov.w r1, #-2147483648
; CHECK-NEXT: mvn r2, #-2147483648
; CHECK-NEXT: .LBB0_7: @ %for.body
@ -251,7 +249,6 @@ define arm_aapcs_vfpcc void @ssatmul_4_q31(i32* nocapture readonly %pSrcA, i32*
; CHECK-NEXT: add.w r11, r2, r3, lsl #2
; CHECK-NEXT: add.w r9, r1, r3, lsl #2
; CHECK-NEXT: add.w r12, r0, r3, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q1, [r4]
; CHECK-NEXT: .LBB1_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -383,7 +380,6 @@ define arm_aapcs_vfpcc void @ssatmul_4_q31(i32* nocapture readonly %pSrcA, i32*
; CHECK-NEXT: .LBB1_6: @ %for.body.preheader21
; CHECK-NEXT: sub.w lr, r3, r7
; CHECK-NEXT: mov.w r0, #-1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: mov.w r3, #-2147483648
; CHECK-NEXT: mvn r2, #-2147483648
; CHECK-NEXT: .LBB1_7: @ %for.body
@ -523,7 +519,6 @@ define arm_aapcs_vfpcc void @ssatmul_4t_q31(i32* nocapture readonly %pSrcA, i32*
; CHECK-NEXT: add.w lr, r6, r7, lsr #2
; CHECK-NEXT: adr r6, .LCPI2_0
; CHECK-NEXT: subs r7, r3, #1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q0, [r6]
; CHECK-NEXT: mov.w r9, #0
; CHECK-NEXT: vdup.32 q1, r7
@ -747,7 +742,6 @@ define arm_aapcs_vfpcc void @usatmul_2_q31(i32* nocapture readonly %pSrcA, i32*
; CHECK-NEXT: add.w r11, r1, r5, lsl #2
; CHECK-NEXT: add.w lr, r6, r7, lsr #1
; CHECK-NEXT: add.w r12, r0, r5, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB3_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldrd r4, r7, [r0]
@ -788,7 +782,6 @@ define arm_aapcs_vfpcc void @usatmul_2_q31(i32* nocapture readonly %pSrcA, i32*
; CHECK-NEXT: beq .LBB3_8
; CHECK-NEXT: .LBB3_6: @ %for.body.preheader
; CHECK-NEXT: sub.w lr, r3, r7
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB3_7: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldr r0, [r12], #4
@ -904,7 +897,6 @@ define arm_aapcs_vfpcc void @usatmul_4_q31(i32* nocapture readonly %pSrcA, i32*
; CHECK-NEXT: add.w r9, r1, r8, lsl #2
; CHECK-NEXT: add.w lr, r6, r7, lsr #2
; CHECK-NEXT: add.w r12, r0, r8, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB4_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q0, [r0], #16
@ -977,7 +969,6 @@ define arm_aapcs_vfpcc void @usatmul_4_q31(i32* nocapture readonly %pSrcA, i32*
; CHECK-NEXT: beq .LBB4_8
; CHECK-NEXT: .LBB4_6: @ %for.body.preheader21
; CHECK-NEXT: sub.w lr, r3, r8
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB4_7: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldr r0, [r12], #4
@ -1094,7 +1085,6 @@ define arm_aapcs_vfpcc void @ssatmul_4_q15(i16* nocapture readonly %pSrcA, i16*
; CHECK-NEXT: add.w lr, r4, r6, lsr #2
; CHECK-NEXT: add.w r4, r2, r5, lsl #1
; CHECK-NEXT: add.w r6, r1, r5, lsl #1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB5_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrh.s32 q0, [r0], #8
@ -1109,7 +1099,6 @@ define arm_aapcs_vfpcc void @ssatmul_4_q15(i16* nocapture readonly %pSrcA, i16*
; CHECK-NEXT: popeq {r4, r5, r6, pc}
; CHECK-NEXT: .LBB5_6: @ %for.body.preheader21
; CHECK-NEXT: sub.w lr, r3, r5
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB5_7: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldrsh r0, [r12], #2
@ -1222,7 +1211,6 @@ define arm_aapcs_vfpcc void @ssatmul_8_q15(i16* nocapture readonly %pSrcA, i16*
; CHECK-NEXT: add.w lr, r4, r6, lsr #3
; CHECK-NEXT: add.w r4, r2, r5, lsl #1
; CHECK-NEXT: add.w r6, r1, r5, lsl #1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB6_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrh.s32 q0, [r0, #8]
@ -1242,7 +1230,6 @@ define arm_aapcs_vfpcc void @ssatmul_8_q15(i16* nocapture readonly %pSrcA, i16*
; CHECK-NEXT: popeq {r4, r5, r6, pc}
; CHECK-NEXT: .LBB6_6: @ %for.body.preheader21
; CHECK-NEXT: sub.w lr, r3, r5
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB6_7: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldrsh r0, [r12], #2
@ -1354,7 +1341,6 @@ define arm_aapcs_vfpcc void @ssatmul_8i_q15(i16* nocapture readonly %pSrcA, i16*
; CHECK-NEXT: add.w lr, r4, r6, lsr #3
; CHECK-NEXT: add.w r4, r2, r5, lsl #1
; CHECK-NEXT: add.w r6, r1, r5, lsl #1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB7_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrh.u16 q0, [r0], #16
@ -1371,7 +1357,6 @@ define arm_aapcs_vfpcc void @ssatmul_8i_q15(i16* nocapture readonly %pSrcA, i16*
; CHECK-NEXT: popeq {r4, r5, r6, pc}
; CHECK-NEXT: .LBB7_6: @ %for.body.preheader21
; CHECK-NEXT: sub.w lr, r3, r5
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB7_7: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldrsh r0, [r12], #2
@ -1490,7 +1475,6 @@ define arm_aapcs_vfpcc void @ssatmul_s4t_q15(i16* nocapture readonly %pSrcA, i16
; CHECK-NEXT: vldrw.u32 q0, [r4]
; CHECK-NEXT: add.w lr, lr, r12, lsr #2
; CHECK-NEXT: sub.w r12, r3, #1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: movs r3, #0
; CHECK-NEXT: vdup.32 q1, r12
; CHECK-NEXT: .LBB8_2: @ %vector.body
@ -1581,7 +1565,6 @@ define arm_aapcs_vfpcc void @ssatmul_8t_q15(i16* nocapture readonly %pSrcA, i16*
; CHECK-NEXT: movs r5, #0
; CHECK-NEXT: add.w lr, lr, r12, lsr #3
; CHECK-NEXT: sub.w r12, r3, #1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q4, [r4]
; CHECK-NEXT: vdup.32 q1, r12
; CHECK-NEXT: vmov.i8 q2, #0x0
@ -1747,7 +1730,6 @@ define arm_aapcs_vfpcc void @ssatmul_8ti_q15(i16* nocapture readonly %pSrcA, i16
; CHECK-NEXT: vmov.i8 q2, #0x0
; CHECK-NEXT: add.w lr, lr, r12, lsr #3
; CHECK-NEXT: sub.w r12, r3, #1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q4, [r4]
; CHECK-NEXT: movs r3, #0
; CHECK-NEXT: vdup.32 q1, r12
@ -1884,7 +1866,6 @@ define arm_aapcs_vfpcc void @usatmul_4_q15(i16* nocapture readonly %pSrcA, i16*
; CHECK-NEXT: add.w lr, r4, r6, lsr #2
; CHECK-NEXT: add.w r4, r2, r5, lsl #1
; CHECK-NEXT: add.w r6, r1, r5, lsl #1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB11_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrh.u32 q0, [r0], #8
@ -1900,7 +1881,6 @@ define arm_aapcs_vfpcc void @usatmul_4_q15(i16* nocapture readonly %pSrcA, i16*
; CHECK-NEXT: .LBB11_6: @ %for.body.preheader21
; CHECK-NEXT: sub.w lr, r3, r5
; CHECK-NEXT: movw r0, #65535
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB11_7: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldrh r1, [r12], #2
@ -2013,7 +1993,6 @@ define arm_aapcs_vfpcc void @usatmul_8_q15(i16* nocapture readonly %pSrcA, i16*
; CHECK-NEXT: add.w lr, r4, r6, lsr #3
; CHECK-NEXT: add.w r4, r2, r5, lsl #1
; CHECK-NEXT: add.w r6, r1, r5, lsl #1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB12_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrh.u32 q0, [r0, #8]
@ -2034,7 +2013,6 @@ define arm_aapcs_vfpcc void @usatmul_8_q15(i16* nocapture readonly %pSrcA, i16*
; CHECK-NEXT: .LBB12_6: @ %for.body.preheader21
; CHECK-NEXT: sub.w lr, r3, r5
; CHECK-NEXT: movw r0, #65535
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB12_7: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldrh r1, [r12], #2
@ -2152,7 +2130,6 @@ define arm_aapcs_vfpcc void @ssatmul_4_q7(i8* nocapture readonly %pSrcA, i8* noc
; CHECK-NEXT: add.w lr, r4, r6, lsr #2
; CHECK-NEXT: adds r4, r2, r5
; CHECK-NEXT: adds r6, r1, r5
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB13_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrb.s32 q2, [r0], #4
@ -2169,7 +2146,6 @@ define arm_aapcs_vfpcc void @ssatmul_4_q7(i8* nocapture readonly %pSrcA, i8* noc
; CHECK-NEXT: popeq {r4, r5, r6, pc}
; CHECK-NEXT: .LBB13_6: @ %for.body.preheader21
; CHECK-NEXT: sub.w lr, r3, r5
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB13_7: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldrsb r0, [r12], #1
@ -2281,7 +2257,6 @@ define arm_aapcs_vfpcc void @ssatmul_8_q7(i8* nocapture readonly %pSrcA, i8* noc
; CHECK-NEXT: add.w lr, r4, r6, lsr #3
; CHECK-NEXT: adds r4, r2, r5
; CHECK-NEXT: adds r6, r1, r5
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB14_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrb.s16 q0, [r0], #8
@ -2296,7 +2271,6 @@ define arm_aapcs_vfpcc void @ssatmul_8_q7(i8* nocapture readonly %pSrcA, i8* noc
; CHECK-NEXT: popeq {r4, r5, r6, pc}
; CHECK-NEXT: .LBB14_6: @ %for.body.preheader23
; CHECK-NEXT: sub.w lr, r3, r5
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB14_7: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldrsb r0, [r12], #1
@ -2409,7 +2383,6 @@ define arm_aapcs_vfpcc void @ssatmul_16_q7(i8* nocapture readonly %pSrcA, i8* no
; CHECK-NEXT: add.w lr, r4, r6, lsr #4
; CHECK-NEXT: adds r4, r2, r5
; CHECK-NEXT: adds r6, r1, r5
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB15_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrb.s16 q0, [r0, #8]
@ -2429,7 +2402,6 @@ define arm_aapcs_vfpcc void @ssatmul_16_q7(i8* nocapture readonly %pSrcA, i8* no
; CHECK-NEXT: popeq {r4, r5, r6, pc}
; CHECK-NEXT: .LBB15_6: @ %for.body.preheader23
; CHECK-NEXT: sub.w lr, r3, r5
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB15_7: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldrsb r0, [r12], #1
@ -2541,7 +2513,6 @@ define arm_aapcs_vfpcc void @ssatmul_16i_q7(i8* nocapture readonly %pSrcA, i8* n
; CHECK-NEXT: add.w lr, r4, r6, lsr #4
; CHECK-NEXT: adds r4, r2, r5
; CHECK-NEXT: adds r6, r1, r5
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB16_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrb.u8 q0, [r0], #16
@ -2558,7 +2529,6 @@ define arm_aapcs_vfpcc void @ssatmul_16i_q7(i8* nocapture readonly %pSrcA, i8* n
; CHECK-NEXT: popeq {r4, r5, r6, pc}
; CHECK-NEXT: .LBB16_6: @ %for.body.preheader23
; CHECK-NEXT: sub.w lr, r3, r5
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB16_7: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldrsb r0, [r12], #1
@ -2680,7 +2650,6 @@ define arm_aapcs_vfpcc void @ssatmul_8t_q7(i8* nocapture readonly %pSrcA, i8* no
; CHECK-NEXT: vmov.i8 q2, #0x0
; CHECK-NEXT: add.w lr, lr, r12, lsr #3
; CHECK-NEXT: sub.w r12, r3, #1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vldrw.u32 q4, [r4]
; CHECK-NEXT: movs r3, #0
; CHECK-NEXT: vdup.32 q1, r12
@ -2800,7 +2769,6 @@ define arm_aapcs_vfpcc void @ssatmul_16t_q7(i8* nocapture readonly %pSrcA, i8* n
; CHECK-NEXT: vmov.i8 q2, #0x0
; CHECK-NEXT: add.w lr, lr, r12, lsr #4
; CHECK-NEXT: sub.w r12, r3, #1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vstrw.32 q0, [sp, #32] @ 16-byte Spill
; CHECK-NEXT: vldrw.u32 q0, [r4]
; CHECK-NEXT: adr r4, .LCPI18_2
@ -3100,7 +3068,6 @@ define arm_aapcs_vfpcc void @ssatmul_16ti_q7(i8* nocapture readonly %pSrcA, i8*
; CHECK-NEXT: vmov.i8 q2, #0x0
; CHECK-NEXT: add.w lr, lr, r12, lsr #4
; CHECK-NEXT: sub.w r12, r3, #1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vstrw.32 q0, [sp, #32] @ 16-byte Spill
; CHECK-NEXT: vldrw.u32 q0, [r4]
; CHECK-NEXT: adr r4, .LCPI19_2
@ -3315,7 +3282,6 @@ define arm_aapcs_vfpcc void @usatmul_8_q7(i8* nocapture readonly %pSrcA, i8* noc
; CHECK-NEXT: add.w lr, r4, r6, lsr #3
; CHECK-NEXT: adds r4, r2, r5
; CHECK-NEXT: adds r6, r1, r5
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB20_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrb.u16 q0, [r0], #8
@ -3330,7 +3296,6 @@ define arm_aapcs_vfpcc void @usatmul_8_q7(i8* nocapture readonly %pSrcA, i8* noc
; CHECK-NEXT: popeq {r4, r5, r6, pc}
; CHECK-NEXT: .LBB20_6: @ %for.body.preheader23
; CHECK-NEXT: sub.w lr, r3, r5
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB20_7: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldrb r0, [r12], #1
@ -3443,7 +3408,6 @@ define arm_aapcs_vfpcc void @usatmul_16_q7(i8* nocapture readonly %pSrcA, i8* no
; CHECK-NEXT: add.w lr, r4, r6, lsr #4
; CHECK-NEXT: adds r4, r2, r5
; CHECK-NEXT: adds r6, r1, r5
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB21_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrb.u16 q0, [r0, #8]
@ -3465,7 +3429,6 @@ define arm_aapcs_vfpcc void @usatmul_16_q7(i8* nocapture readonly %pSrcA, i8* no
; CHECK-NEXT: popeq {r4, r5, r6, pc}
; CHECK-NEXT: .LBB21_6: @ %for.body.preheader23
; CHECK-NEXT: sub.w lr, r3, r5
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB21_7: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldrb r0, [r12], #1

9
test/CodeGen/Thumb2/mve-shifts-scalar.ll
View File

@ -10,7 +10,6 @@ define dso_local arm_aapcs_vfpcc void @sink_shl_i32(i32* nocapture readonly %in,
; CHECK-NEXT: sub.w r12, r3, #4
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r12, lsr #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB0_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q0, [r0], #16
@ -54,7 +53,6 @@ define dso_local arm_aapcs_vfpcc void @sink_shl_i16(i16* nocapture readonly %in,
; CHECK-NEXT: sub.w r12, r3, #4
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r12, lsr #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB1_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q0, [r0], #8
@ -98,7 +96,6 @@ define dso_local arm_aapcs_vfpcc void @sink_shl_i8(i8* nocapture readonly %in, i
; CHECK-NEXT: sub.w r12, r3, #4
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r12, lsr #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB2_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q0, [r0], #4
@ -143,7 +140,6 @@ define dso_local arm_aapcs_vfpcc void @sink_lshr_i32(i32* nocapture readonly %in
; CHECK-NEXT: sub.w r12, r3, #4
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r12, lsr #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB3_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q0, [r0], #16
@ -188,7 +184,6 @@ define dso_local arm_aapcs_vfpcc void @sink_lshr_i16(i16* nocapture readonly %in
; CHECK-NEXT: sub.w r12, r3, #4
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r12, lsr #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB4_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q0, [r0], #8
@ -233,7 +228,6 @@ define dso_local arm_aapcs_vfpcc void @sink_lshr_i8(i8* nocapture readonly %in,
; CHECK-NEXT: sub.w r12, r3, #4
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r12, lsr #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB5_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q0, [r0], #4
@ -278,7 +272,6 @@ define dso_local arm_aapcs_vfpcc void @sink_ashr_i32(i32* nocapture readonly %in
; CHECK-NEXT: sub.w r12, r3, #4
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r12, lsr #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB6_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q0, [r0], #16
@ -323,7 +316,6 @@ define dso_local arm_aapcs_vfpcc void @sink_ashr_i16(i16* nocapture readonly %in
; CHECK-NEXT: sub.w r12, r3, #4
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r12, lsr #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB7_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q0, [r0], #8
@ -368,7 +360,6 @@ define dso_local arm_aapcs_vfpcc void @sink_ashr_i8(i8* nocapture readonly %in,
; CHECK-NEXT: sub.w r12, r3, #4
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r12, lsr #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB8_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q0, [r0], #4

6
test/CodeGen/Thumb2/mve-vabdus.ll
View File

@ -487,7 +487,6 @@ define void @vabd_loop_s8(i8* nocapture readonly %x, i8* nocapture readonly %y,
; CHECK-NEXT: .save {r7, lr}
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: mov.w lr, #64
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB6_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrb.s32 q0, [r1, #12]
@ -548,7 +547,6 @@ define void @vabd_loop_s16(i16* nocapture readonly %x, i16* nocapture readonly %
; CHECK-NEXT: .save {r7, lr}
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: mov.w lr, #128
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB7_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrh.s32 q0, [r1, #8]
@ -604,7 +602,6 @@ define void @vabd_loop_s32(i32* nocapture readonly %x, i32* nocapture readonly %
; CHECK-NEXT: vpush {d8, d9}
; CHECK-NEXT: mov.w lr, #256
; CHECK-NEXT: mov.w r12, #1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vmov.i32 q0, #0x0
; CHECK-NEXT: .LBB8_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -700,7 +697,6 @@ define void @vabd_loop_u8(i8* nocapture readonly %x, i8* nocapture readonly %y,
; CHECK-NEXT: .save {r7, lr}
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: mov.w lr, #64
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB9_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrb.u32 q0, [r1, #12]
@ -761,7 +757,6 @@ define void @vabd_loop_u16(i16* nocapture readonly %x, i16* nocapture readonly %
; CHECK-NEXT: .save {r7, lr}
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: mov.w lr, #128
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB10_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrh.u32 q0, [r1, #8]
@ -817,7 +812,6 @@ define void @vabd_loop_u32(i32* nocapture readonly %x, i32* nocapture readonly %
; CHECK-NEXT: vpush {d8, d9, d10, d11}
; CHECK-NEXT: mov.w lr, #256
; CHECK-NEXT: vmov.i64 q0, #0xffffffff
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: vmov.i32 q1, #0x0
; CHECK-NEXT: .LBB11_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1

34
test/CodeGen/Thumb2/mve-vecreduce-loops.ll
View File

@ -25,7 +25,6 @@ define i32 @add_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: subs r0, r3, #4
; CHECK-NEXT: add.w lr, r2, r0, lsr #2
; CHECK-NEXT: movs r0, #0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: mov r2, r12
; CHECK-NEXT: .LBB0_5: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -39,7 +38,6 @@ define i32 @add_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: .LBB0_7: @ %for.body.preheader1
; CHECK-NEXT: sub.w lr, r1, r3
; CHECK-NEXT: add.w r2, r12, r3, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB0_8: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldr r1, [r2], #4
@ -115,7 +113,6 @@ define i32 @mul_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: sub.w r3, r12, #4
; CHECK-NEXT: add.w lr, r2, r3, lsr #2
; CHECK-NEXT: mov r2, r0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB1_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q1, [r2], #16
@ -134,7 +131,6 @@ define i32 @mul_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: .LBB1_6: @ %for.body.preheader1
; CHECK-NEXT: sub.w lr, r1, r12
; CHECK-NEXT: add.w r0, r0, r12, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB1_7: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldr r1, [r0], #4
@ -215,7 +211,6 @@ define i32 @and_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: vmov.i8 q0, #0xff
; CHECK-NEXT: add.w lr, r2, r12, lsr #2
; CHECK-NEXT: mov r2, r0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB2_5: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q1, [r2], #16
@ -234,7 +229,6 @@ define i32 @and_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: .LBB2_7: @ %for.body.preheader1
; CHECK-NEXT: sub.w lr, r1, r3
; CHECK-NEXT: add.w r0, r0, r3, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB2_8: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldr r1, [r0], #4
@ -315,7 +309,6 @@ define i32 @or_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: vmov.i32 q0, #0x0
; CHECK-NEXT: add.w lr, r2, r12, lsr #2
; CHECK-NEXT: mov r2, r0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB3_5: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q1, [r2], #16
@ -334,7 +327,6 @@ define i32 @or_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: .LBB3_7: @ %for.body.preheader1
; CHECK-NEXT: sub.w lr, r1, r3
; CHECK-NEXT: add.w r0, r0, r3, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB3_8: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldr r1, [r0], #4
@ -415,7 +407,6 @@ define i32 @xor_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: vmov.i32 q0, #0x0
; CHECK-NEXT: add.w lr, r2, r12, lsr #2
; CHECK-NEXT: mov r2, r0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB4_5: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q1, [r2], #16
@ -434,7 +425,6 @@ define i32 @xor_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: .LBB4_7: @ %for.body.preheader1
; CHECK-NEXT: sub.w lr, r1, r3
; CHECK-NEXT: add.w r0, r0, r3, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB4_8: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldr r1, [r0], #4
@ -515,7 +505,6 @@ define float @fadd_f32(float* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: vmov.i32 q0, #0x0
; CHECK-NEXT: add.w lr, r3, r12, lsr #2
; CHECK-NEXT: mov r3, r0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB5_5: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q1, [r3], #16
@ -530,7 +519,6 @@ define float @fadd_f32(float* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: .LBB5_7: @ %for.body.preheader1
; CHECK-NEXT: sub.w lr, r1, r2
; CHECK-NEXT: add.w r0, r0, r2, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB5_8: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldr s2, [r0]
@ -616,7 +604,6 @@ define float @fmul_f32(float* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: vmov.f32 q0, #1.000000e+00
; CHECK-NEXT: add.w lr, r3, r12, lsr #2
; CHECK-NEXT: mov r3, r0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB6_5: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q1, [r3], #16
@ -631,7 +618,6 @@ define float @fmul_f32(float* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: .LBB6_7: @ %for.body.preheader1
; CHECK-NEXT: sub.w lr, r1, r2
; CHECK-NEXT: add.w r0, r0, r2, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB6_8: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldr s2, [r0]
@ -713,7 +699,6 @@ define i32 @smin_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: vmvn.i32 q0, #0x80000000
; CHECK-NEXT: add.w lr, r2, r12, lsr #2
; CHECK-NEXT: mov r2, r0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB7_5: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q1, [r2], #16
@ -727,7 +712,6 @@ define i32 @smin_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: .LBB7_7: @ %for.body.preheader1
; CHECK-NEXT: sub.w lr, r1, r3
; CHECK-NEXT: add.w r0, r0, r3, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB7_8: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldr r1, [r0], #4
@ -811,7 +795,6 @@ define i32 @smin_i32_inloop(i32* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: subs r0, r3, #4
; CHECK-NEXT: add.w lr, r2, r0, lsr #2
; CHECK-NEXT: mvn r0, #-2147483648
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: mov r2, r12
; CHECK-NEXT: .LBB8_5: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -825,7 +808,6 @@ define i32 @smin_i32_inloop(i32* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: .LBB8_7: @ %for.body.preheader1
; CHECK-NEXT: sub.w lr, r1, r3
; CHECK-NEXT: add.w r2, r12, r3, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB8_8: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldr r1, [r2], #4
@ -909,7 +891,6 @@ define i32 @smax_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: vmov.i32 q0, #0x80000000
; CHECK-NEXT: add.w lr, r2, r12, lsr #2
; CHECK-NEXT: mov r2, r0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB9_5: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q1, [r2], #16
@ -923,7 +904,6 @@ define i32 @smax_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: .LBB9_7: @ %for.body.preheader1
; CHECK-NEXT: sub.w lr, r1, r3
; CHECK-NEXT: add.w r0, r0, r3, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB9_8: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldr r1, [r0], #4
@ -1007,7 +987,6 @@ define i32 @smax_i32_inloop(i32* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: subs r0, r3, #4
; CHECK-NEXT: add.w lr, r2, r0, lsr #2
; CHECK-NEXT: mov.w r0, #-2147483648
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: mov r2, r12
; CHECK-NEXT: .LBB10_5: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -1021,7 +1000,6 @@ define i32 @smax_i32_inloop(i32* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: .LBB10_7: @ %for.body.preheader1
; CHECK-NEXT: sub.w lr, r1, r3
; CHECK-NEXT: add.w r2, r12, r3, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB10_8: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldr r1, [r2], #4
@ -1105,7 +1083,6 @@ define i32 @umin_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: vmov.i8 q0, #0xff
; CHECK-NEXT: add.w lr, r2, r12, lsr #2
; CHECK-NEXT: mov r2, r0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB11_5: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q1, [r2], #16
@ -1119,7 +1096,6 @@ define i32 @umin_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: .LBB11_7: @ %for.body.preheader1
; CHECK-NEXT: sub.w lr, r1, r3
; CHECK-NEXT: add.w r0, r0, r3, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB11_8: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldr r1, [r0], #4
@ -1203,7 +1179,6 @@ define i32 @umin_i32_inloop(i32* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: subs r0, r3, #4
; CHECK-NEXT: add.w lr, r2, r0, lsr #2
; CHECK-NEXT: mov.w r0, #-1
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: mov r2, r12
; CHECK-NEXT: .LBB12_5: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -1217,7 +1192,6 @@ define i32 @umin_i32_inloop(i32* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: .LBB12_7: @ %for.body.preheader1
; CHECK-NEXT: sub.w lr, r1, r3
; CHECK-NEXT: add.w r2, r12, r3, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB12_8: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldr r1, [r2], #4
@ -1301,7 +1275,6 @@ define i32 @umax_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: vmov.i32 q0, #0x0
; CHECK-NEXT: add.w lr, r2, r12, lsr #2
; CHECK-NEXT: mov r2, r0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB13_5: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q1, [r2], #16
@ -1315,7 +1288,6 @@ define i32 @umax_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: .LBB13_7: @ %for.body.preheader1
; CHECK-NEXT: sub.w lr, r1, r3
; CHECK-NEXT: add.w r0, r0, r3, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB13_8: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldr r1, [r0], #4
@ -1399,7 +1371,6 @@ define i32 @umax_i32_inloop(i32* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: subs r0, r3, #4
; CHECK-NEXT: add.w lr, r2, r0, lsr #2
; CHECK-NEXT: movs r0, #0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: mov r2, r12
; CHECK-NEXT: .LBB14_5: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -1413,7 +1384,6 @@ define i32 @umax_i32_inloop(i32* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: .LBB14_7: @ %for.body.preheader1
; CHECK-NEXT: sub.w lr, r1, r3
; CHECK-NEXT: add.w r2, r12, r3, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB14_8: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldr r1, [r2], #4
@ -1497,7 +1467,6 @@ define float @fmin_f32(float* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: vmov.i32 q0, #0x0
; CHECK-NEXT: add.w lr, r3, r12, lsr #2
; CHECK-NEXT: mov r3, r0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB15_5: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q1, [r3], #16
@ -1513,7 +1482,6 @@ define float @fmin_f32(float* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: .LBB15_7: @ %for.body.preheader1
; CHECK-NEXT: sub.w lr, r1, r2
; CHECK-NEXT: add.w r0, r0, r2, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB15_8: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldmia r0!, {s2}
@ -1602,7 +1570,6 @@ define float @fmax_f32(float* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: vmov.i32 q0, #0x0
; CHECK-NEXT: add.w lr, r3, r12, lsr #2
; CHECK-NEXT: mov r3, r0
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB16_5: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q1, [r3], #16
@ -1618,7 +1585,6 @@ define float @fmax_f32(float* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: .LBB16_7: @ %for.body.preheader1
; CHECK-NEXT: sub.w lr, r1, r2
; CHECK-NEXT: add.w r0, r0, r2, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB16_8: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldmia r0!, {s2}

2
test/CodeGen/Thumb2/mve-vldshuffle.ll
View File

@ -25,7 +25,6 @@ define void @arm_cmplx_mag_squared_f16(half* nocapture readonly %pSrc, half* noc
; CHECK-NEXT: add.w r12, r1, r4, lsl #1
; CHECK-NEXT: add.w lr, r5, r3, lsr #3
; CHECK-NEXT: add.w r3, r0, r4, lsl #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: and r5, r2, #7
; CHECK-NEXT: .LBB0_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
@ -155,7 +154,6 @@ define void @arm_cmplx_mag_squared_f32(float* nocapture readonly %pSrc, float* n
; CHECK-NEXT: add.w r12, r1, r4, lsl #2
; CHECK-NEXT: add.w lr, r5, r3, lsr #2
; CHECK-NEXT: add.w r3, r0, r4, lsl #3
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: and r5, r2, #3
; CHECK-NEXT: .LBB1_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1

1
test/CodeGen/Thumb2/mve-vldst4.ll
View File

@ -21,7 +21,6 @@ define void @vldst4(half* nocapture readonly %pIn, half* nocapture %pOut, i32 %n
; CHECK-NEXT: sub.w r12, r3, #8
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r12, lsr #3
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB0_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrh.u16 q5, [r0, #32]

3
test/CodeGen/Thumb2/mve-vqdmulh.ll
View File

@ -200,7 +200,6 @@ define void @vqdmulh_loop_i8(i8* nocapture readonly %x, i8* nocapture readonly %
; CHECK-NEXT: .save {r7, lr}
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: mov.w lr, #64
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB8_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrb.u8 q0, [r0], #16
@ -245,7 +244,6 @@ define void @vqdmulh_loop_i16(i16* nocapture readonly %x, i16* nocapture readonl
; CHECK-NEXT: .save {r7, lr}
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: mov.w lr, #128
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB9_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrh.u16 q0, [r0], #16
@ -290,7 +288,6 @@ define void @vqdmulh_loop_i32(i32* nocapture readonly %x, i32* nocapture readonl
; CHECK-NEXT: .save {r7, lr}
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: mov.w lr, #256
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB10_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q0, [r0], #16

4
test/Transforms/HardwareLoops/ARM/calls-codegen.ll
View File

@ -5,7 +5,7 @@
; CHECK-LABEL: test_target_specific:
; CHECK: mov.w lr, #50
; CHECK: dls lr, lr
; CHECK-NOT: dls lr, lr
; CHECK-NOT: mov lr,
; CHECK: [[LOOP_HEADER:\.LBB[0-9_]+]]:
; CHECK: le lr, [[LOOP_HEADER]]
@ -32,7 +32,7 @@ exit:
; CHECK-LABEL: test_fabs:
; CHECK: mov.w lr, #100
; CHECK: dls lr, lr
; CHECK-NOT: dls lr, lr
; CHECK-NOT: mov lr,
; CHECK: [[LOOP_HEADER:\.LBB[0-9_]+]]:
; CHECK-NOT: bl

6
test/Transforms/HardwareLoops/ARM/simple-do.ll
View File

@ -109,7 +109,8 @@ while.end:
; CHECK-LLC: do_inc2:
; CHECK-LLC-NOT: mov lr,
; CHECK-LLC: dls lr, {{.*}}
; CHECK-LLC: add.w lr,
; CHECK-LLC-NOT: dls lr,
; CHECK-LLC-NOT: mov lr,
; CHECK-LLC: [[LOOP_HEADER:\.LBB[0-9._]+]]:
; CHECK-LLC: le lr, [[LOOP_HEADER]]
@ -162,7 +163,8 @@ while.end:
; CHECK-LLC: do_dec2
; CHECK-LLC-NOT: mov lr,
; CHECK-LLC: dls lr, {{.*}}
; CHECK-LLC: add.w lr,
; CHECK-LLC-NOT: dls lr,
; CHECK-LLC-NOT: mov lr,
; CHECK-LLC: [[LOOP_HEADER:\.LBB[0-9_]+]]:
; CHECK-LLC: le lr, [[LOOP_HEADER]]

1
test/Transforms/HardwareLoops/ARM/structure.ll
View File

@ -395,7 +395,6 @@ for.body:
; CHECK-UNROLL-NEXT: [[PROLOGUE:.LBB[0-9_]+]]:
; CHECK-UNROLL: le lr, [[PROLOGUE]]
; CHECK-UNROLL-NEXT: [[PROLOGUE_EXIT:.LBB[0-9_]+]]:
; CHECK-UNROLL: dls lr, lr
; CHECK-UNROLL: [[BODY:.LBB[0-9_]+]]:
; CHECK-UNROLL: le lr, [[BODY]]
; CHECK-UNROLL-NOT: b