[PowerPC] Modify the hasSideEffects of MTLR and MFLR from 1 to 0

Summary:
If we didn't set the value for hasSideEffects bit in our td file, `llvm-tblgen`
will set it as true for those instructions which has no match pattern.
The instructions `MTLR` and `MFLR` don't set the hasSideEffects flag and don't
have match pattern, so their hasSideEffects flag will be set true by
`llvm-tblgen`.
But in fact, we can use `[LR]` to model the two instructions, so they should not
have SideEffects.

This patch is to modify the hasSideEffects of MTLR and MFLR from 1 to 0.

Reviewed By: jsji

Differential Revision: https://reviews.llvm.org/D71390

15 files changed, 56 insertions, 52 deletions

diff --git a/llvm/lib/Target/PowerPC/PPCInstr64Bit.td b/llvm/lib/Target/PowerPC/PPCInstr64Bit.td
index 0f9ab56ce90..b8cb7b1fe7f 100644
--- a/llvm/lib/Target/PowerPC/PPCInstr64Bit.td
+++ b/llvm/lib/Target/PowerPC/PPCInstr64Bit.td
@@ -410,6 +410,7 @@ def DYNALLOC8 : PPCEmitTimePseudo<(outs g8rc:$result), (ins g8rc:$negsize, memri
 def DYNAREAOFFSET8 : PPCEmitTimePseudo<(outs i64imm:$result), (ins memri:$fpsi), "#DYNAREAOFFSET8",
                        [(set i64:$result, (PPCdynareaoffset iaddr:$fpsi))]>;
 
+let hasSideEffects = 0 in {
 let Defs = [LR8] in {
 def MTLR8  : XFXForm_7_ext<31, 467, 8, (outs), (ins g8rc:$rS),
                            "mtlr $rS", IIC_SprMTSPR>,
@@ -421,6 +422,7 @@ def MFLR8  : XFXForm_1_ext<31, 339, 8, (outs g8rc:$rT), (ins),
              PPC970_DGroup_First, PPC970_Unit_FXU;
 }
 } // Interpretation64Bit
+}
 
 //===----------------------------------------------------------------------===//
 // Fixed point instructions.
diff --git a/llvm/lib/Target/PowerPC/PPCInstrInfo.td b/llvm/lib/Target/PowerPC/PPCInstrInfo.td
index 99d8050170e..8f41bbfcda7 100644
--- a/llvm/lib/Target/PowerPC/PPCInstrInfo.td
+++ b/llvm/lib/Target/PowerPC/PPCInstrInfo.td
@@ -2698,6 +2698,7 @@ def MTCTRloop : XFXForm_7_ext<31, 467, 9, (outs), (ins gprc:$rS),
                 PPC970_DGroup_First, PPC970_Unit_FXU;
 }
 
+let hasSideEffects = 0 in {
 let Defs = [LR] in {
 def MTLR  : XFXForm_7_ext<31, 467, 8, (outs), (ins gprc:$rS),
                           "mtlr $rS", IIC_SprMTSPR>,
@@ -2708,6 +2709,7 @@ def MFLR  : XFXForm_1_ext<31, 339, 8, (outs gprc:$rT), (ins),
                           "mflr $rT", IIC_SprMFSPR>,
             PPC970_DGroup_First, PPC970_Unit_FXU;
 }
+}
 
 let isCodeGenOnly = 1 in {
   // Move to/from VRSAVE: despite being a SPR, the VRSAVE register is renamed
diff --git a/llvm/test/CodeGen/PowerPC/CSR-fit.ll b/llvm/test/CodeGen/PowerPC/CSR-fit.ll
index 49bfc79eb4c..ebaffdb0534 100644
--- a/llvm/test/CodeGen/PowerPC/CSR-fit.ll
+++ b/llvm/test/CodeGen/PowerPC/CSR-fit.ll
@@ -27,9 +27,9 @@ define dso_local signext i32 @caller1(i32 signext %a, i32 signext %b) local_unna
 ; CHECK-PWR8-NEXT:    nop
 ; CHECK-PWR8-NEXT:    addi r1, r1, 176
 ; CHECK-PWR8-NEXT:    ld r0, 16(r1)
-; CHECK-PWR8-NEXT:    mtlr r0
 ; CHECK-PWR8-NEXT:    ld r15, -136(r1) # 8-byte Folded Reload
 ; CHECK-PWR8-NEXT:    ld r14, -144(r1) # 8-byte Folded Reload
+; CHECK-PWR8-NEXT:    mtlr r0
 ; CHECK-PWR8-NEXT:    blr
 ;
 ; CHECK-PWR9-LABEL: caller1:
@@ -51,9 +51,9 @@ define dso_local signext i32 @caller1(i32 signext %a, i32 signext %b) local_unna
 ; CHECK-PWR9-NEXT:    nop
 ; CHECK-PWR9-NEXT:    addi r1, r1, 176
 ; CHECK-PWR9-NEXT:    ld r0, 16(r1)
-; CHECK-PWR9-NEXT:    mtlr r0
 ; CHECK-PWR9-NEXT:    ld r15, -136(r1) # 8-byte Folded Reload
 ; CHECK-PWR9-NEXT:    ld r14, -144(r1) # 8-byte Folded Reload
+; CHECK-PWR9-NEXT:    mtlr r0
 ; CHECK-PWR9-NEXT:    blr
 entry:
   %0 = tail call i32 asm "add $0, $1, $2", "=r,r,r,~{r14},~{r15}"(i32 %a, i32 %b)
@@ -81,9 +81,9 @@ define dso_local signext i32 @caller2(i32 signext %a, i32 signext %b) local_unna
 ; CHECK-PWR8-NEXT:    nop
 ; CHECK-PWR8-NEXT:    addi r1, r1, 176
 ; CHECK-PWR8-NEXT:    ld r0, 16(r1)
-; CHECK-PWR8-NEXT:    mtlr r0
 ; CHECK-PWR8-NEXT:    lfd f15, -136(r1) # 8-byte Folded Reload
 ; CHECK-PWR8-NEXT:    lfd f14, -144(r1) # 8-byte Folded Reload
+; CHECK-PWR8-NEXT:    mtlr r0
 ; CHECK-PWR8-NEXT:    blr
 ;
 ; CHECK-PWR9-LABEL: caller2:
@@ -105,9 +105,9 @@ define dso_local signext i32 @caller2(i32 signext %a, i32 signext %b) local_unna
 ; CHECK-PWR9-NEXT:    nop
 ; CHECK-PWR9-NEXT:    addi r1, r1, 176
 ; CHECK-PWR9-NEXT:    ld r0, 16(r1)
-; CHECK-PWR9-NEXT:    mtlr r0
 ; CHECK-PWR9-NEXT:    lfd f15, -136(r1) # 8-byte Folded Reload
 ; CHECK-PWR9-NEXT:    lfd f14, -144(r1) # 8-byte Folded Reload
+; CHECK-PWR9-NEXT:    mtlr r0
 ; CHECK-PWR9-NEXT:    blr
 entry:
   %0 = tail call i32 asm "add $0, $1, $2", "=r,r,r,~{f14},~{f15}"(i32 %a, i32 %b)
diff --git a/llvm/test/CodeGen/PowerPC/MCSE-caller-preserved-reg.ll b/llvm/test/CodeGen/PowerPC/MCSE-caller-preserved-reg.ll
index 717b568e046..c2a3d175271 100644
--- a/llvm/test/CodeGen/PowerPC/MCSE-caller-preserved-reg.ll
+++ b/llvm/test/CodeGen/PowerPC/MCSE-caller-preserved-reg.ll
@@ -42,8 +42,8 @@ define noalias i8* @_ZN2CC3funEv(%class.CC* %this) nounwind {
 ; CHECK-NEXT:    li 3, 0
 ; CHECK-NEXT:    addi 1, 1, 48
 ; CHECK-NEXT:    ld 0, 16(1)
-; CHECK-NEXT:    mtlr 0
 ; CHECK-NEXT:    ld 30, -16(1) # 8-byte Folded Reload
+; CHECK-NEXT:    mtlr 0
 ; CHECK-NEXT:    blr
 entry:
   %foo = getelementptr inbounds %class.CC, %class.CC* %this, i64 0, i32 0, i32 0
diff --git a/llvm/test/CodeGen/PowerPC/csr-split.ll b/llvm/test/CodeGen/PowerPC/csr-split.ll
index cd981a27d2e..0e2cf306e99 100644
--- a/llvm/test/CodeGen/PowerPC/csr-split.ll
+++ b/llvm/test/CodeGen/PowerPC/csr-split.ll
@@ -34,8 +34,8 @@ define dso_local signext i32 @test1(i32* %b) local_unnamed_addr  {
 ; CHECK-PWR9-NEXT:    extsw r3, r3
 ; CHECK-PWR9-NEXT:    addi r1, r1, 48
 ; CHECK-PWR9-NEXT:    ld r0, 16(r1)
-; CHECK-PWR9-NEXT:    mtlr r0
 ; CHECK-PWR9-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
+; CHECK-PWR9-NEXT:    mtlr r0
 ; CHECK-PWR9-NEXT:    blr
 ;
 ; CHECK-LABEL: test1:
@@ -116,8 +116,8 @@ define dso_local signext i32 @test2(i32* %p1) local_unnamed_addr  {
 ; CHECK-PWR9-NEXT:    extsw r3, r3
 ; CHECK-PWR9-NEXT:    addi r1, r1, 48
 ; CHECK-PWR9-NEXT:    ld r0, 16(r1)
-; CHECK-PWR9-NEXT:    mtlr r0
 ; CHECK-PWR9-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
+; CHECK-PWR9-NEXT:    mtlr r0
 ; CHECK-PWR9-NEXT:    blr
 ;
 ; CHECK-LABEL: test2:
@@ -199,9 +199,9 @@ define dso_local i8* @test3(i8** nocapture %p1, i8 zeroext %p2) local_unnamed_ad
 ; CHECK-PWR9-NEXT:    mr r3, r30
 ; CHECK-PWR9-NEXT:    addi r1, r1, 64
 ; CHECK-PWR9-NEXT:    ld r0, 16(r1)
-; CHECK-PWR9-NEXT:    mtlr r0
 ; CHECK-PWR9-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-PWR9-NEXT:    ld r29, -24(r1) # 8-byte Folded Reload
+; CHECK-PWR9-NEXT:    mtlr r0
 ; CHECK-PWR9-NEXT:    blr
 ;
 ; CHECK-LABEL: test3:
diff --git a/llvm/test/CodeGen/PowerPC/machine-pre.ll b/llvm/test/CodeGen/PowerPC/machine-pre.ll
index cc6d738bfc7..0a794972572 100644
--- a/llvm/test/CodeGen/PowerPC/machine-pre.ll
+++ b/llvm/test/CodeGen/PowerPC/machine-pre.ll
@@ -134,10 +134,10 @@ define dso_local signext i32 @foo(i32 signext %x, i32 signext %y) nounwind {
 ; CHECK-P9-NEXT:  .LBB1_10: # %cleanup20
 ; CHECK-P9-NEXT:    addi r1, r1, 80
 ; CHECK-P9-NEXT:    ld r0, 16(r1)
-; CHECK-P9-NEXT:    mtlr r0
 ; CHECK-P9-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-P9-NEXT:    ld r29, -24(r1) # 8-byte Folded Reload
 ; CHECK-P9-NEXT:    ld r28, -32(r1) # 8-byte Folded Reload
+; CHECK-P9-NEXT:    mtlr r0
 ; CHECK-P9-NEXT:    ld r27, -40(r1) # 8-byte Folded Reload
 ; CHECK-P9-NEXT:    blr
 entry:
diff --git a/llvm/test/CodeGen/PowerPC/not-fixed-frame-object.ll b/llvm/test/CodeGen/PowerPC/not-fixed-frame-object.ll
index b45b74fc5a1..ffb54edb68a 100644
--- a/llvm/test/CodeGen/PowerPC/not-fixed-frame-object.ll
+++ b/llvm/test/CodeGen/PowerPC/not-fixed-frame-object.ll
@@ -61,10 +61,10 @@ define dso_local signext i32 @caller(i32 signext %a, i32 signext %b, i32 signext
 ; CHECK-NEXT:    nop
 ; CHECK-NEXT:    addi r1, r1, 192
 ; CHECK-NEXT:    ld r0, 16(r1)
-; CHECK-NEXT:    mtlr r0
 ; CHECK-NEXT:    ld r31, -8(r1) # 8-byte Folded Reload
 ; CHECK-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-NEXT:    ld r29, -24(r1) # 8-byte Folded Reload
+; CHECK-NEXT:    mtlr r0
 ; CHECK-NEXT:    ld r28, -32(r1) # 8-byte Folded Reload
 ; CHECK-NEXT:    ld r27, -40(r1) # 8-byte Folded Reload
 ; CHECK-NEXT:    ld r26, -48(r1) # 8-byte Folded Reload
diff --git a/llvm/test/CodeGen/PowerPC/ppcf128-constrained-fp-intrinsics.ll b/llvm/test/CodeGen/PowerPC/ppcf128-constrained-fp-intrinsics.ll
index 497703e8c40..b5c81246ae6 100644
--- a/llvm/test/CodeGen/PowerPC/ppcf128-constrained-fp-intrinsics.ll
+++ b/llvm/test/CodeGen/PowerPC/ppcf128-constrained-fp-intrinsics.ll
@@ -1375,12 +1375,12 @@ define void @test_constrained_libcall_multichain(float* %firstptr, ppc_fp128* %r
 ; PC64LE-NEXT:    stfd 1, -16(30)
 ; PC64LE-NEXT:    addi 1, 1, 80
 ; PC64LE-NEXT:    ld 0, 16(1)
-; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
 ; PC64LE-NEXT:    ld 30, -40(1) # 8-byte Folded Reload
-; PC64LE-NEXT:    ld 29, -48(1) # 8-byte Folded Reload
 ; PC64LE-NEXT:    lfd 29, -24(1) # 8-byte Folded Reload
+; PC64LE-NEXT:    ld 29, -48(1) # 8-byte Folded Reload
+; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    blr
 ;
 ; PC64LE9-LABEL: test_constrained_libcall_multichain:
@@ -1426,12 +1426,12 @@ define void @test_constrained_libcall_multichain(float* %firstptr, ppc_fp128* %r
 ; PC64LE9-NEXT:    stfd 1, -16(30)
 ; PC64LE9-NEXT:    addi 1, 1, 80
 ; PC64LE9-NEXT:    ld 0, 16(1)
-; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE9-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
-; PC64LE9-NEXT:    lfd 29, -24(1) # 8-byte Folded Reload
 ; PC64LE9-NEXT:    ld 30, -40(1) # 8-byte Folded Reload
 ; PC64LE9-NEXT:    ld 29, -48(1) # 8-byte Folded Reload
+; PC64LE9-NEXT:    mtlr 0
+; PC64LE9-NEXT:    lfd 29, -24(1) # 8-byte Folded Reload
 ; PC64LE9-NEXT:    blr
 ;
 ; PC64-LABEL: test_constrained_libcall_multichain:
diff --git a/llvm/test/CodeGen/PowerPC/pr43527.ll b/llvm/test/CodeGen/PowerPC/pr43527.ll
index 7c3e438a26c..023898a46cc 100644
--- a/llvm/test/CodeGen/PowerPC/pr43527.ll
+++ b/llvm/test/CodeGen/PowerPC/pr43527.ll
@@ -34,9 +34,9 @@ define dso_local void @test(i64 %arg, i64 %arg1) {
 ; CHECK-NEXT:    stb r3, 0(r3)
 ; CHECK-NEXT:    addi r1, r1, 64
 ; CHECK-NEXT:    ld r0, 16(r1)
-; CHECK-NEXT:    mtlr r0
 ; CHECK-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-NEXT:    ld r29, -24(r1) # 8-byte Folded Reload
+; CHECK-NEXT:    mtlr r0
 ; CHECK-NEXT:    blr
 ; CHECK-NEXT:  .LBB0_5: # %bb2
 ; CHECK-NEXT:  .LBB0_6: # %bb14
diff --git a/llvm/test/CodeGen/PowerPC/pr44183.ll b/llvm/test/CodeGen/PowerPC/pr44183.ll
index 1a6f932bc6d..483f84c884b 100644
--- a/llvm/test/CodeGen/PowerPC/pr44183.ll
+++ b/llvm/test/CodeGen/PowerPC/pr44183.ll
@@ -31,8 +31,8 @@ define void @_ZN1m1nEv(%struct.m.2.5.8.11* %this) local_unnamed_addr nounwind al
 ; CHECK-NEXT:    nop
 ; CHECK-NEXT:    addi r1, r1, 48
 ; CHECK-NEXT:    ld r0, 16(r1)
-; CHECK-NEXT:    mtlr r0
 ; CHECK-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
+; CHECK-NEXT:    mtlr r0
 ; CHECK-NEXT:    blr
 entry:
   %bc = getelementptr inbounds %struct.m.2.5.8.11, %struct.m.2.5.8.11* %this, i64 0, i32 2
diff --git a/llvm/test/CodeGen/PowerPC/sjlj.ll b/llvm/test/CodeGen/PowerPC/sjlj.ll
index 3c1eee7fb39..7c8f83e6ec8 100644
--- a/llvm/test/CodeGen/PowerPC/sjlj.ll
+++ b/llvm/test/CodeGen/PowerPC/sjlj.ll
@@ -81,8 +81,8 @@ return:                                           ; preds = %if.end, %if.then
 ; CHECK: # %bb.1:
 
 ; CHECK: .LBB1_3:
-; CHECK: mflr [[REGL:[0-9]+]]
 ; CHECK: ld [[REG2:[0-9]+]], [[OFF]](31)                   # 8-byte Folded Reload
+; CHECK: mflr [[REGL:[0-9]+]]
 ; CHECK: std [[REGL]], 8([[REG2]])
 ; CHECK: li 3, 0
 
diff --git a/llvm/test/CodeGen/PowerPC/sms-phi-1.ll b/llvm/test/CodeGen/PowerPC/sms-phi-1.ll
index 436c3b41325..5cb685e9830 100644
--- a/llvm/test/CodeGen/PowerPC/sms-phi-1.ll
+++ b/llvm/test/CodeGen/PowerPC/sms-phi-1.ll
@@ -36,8 +36,8 @@ define void @main() nounwind #0 {
 ; CHECK-NEXT:    stwu 4, 4(3)
 ; CHECK-NEXT:    addi 1, 1, 48
 ; CHECK-NEXT:    ld 0, 16(1)
-; CHECK-NEXT:    mtlr 0
 ; CHECK-NEXT:    ld 30, -16(1) # 8-byte Folded Reload
+; CHECK-NEXT:    mtlr 0
 ; CHECK-NEXT:    blr
   %1 = tail call i64 @strtol()
   %2 = trunc i64 %1 to i32
diff --git a/llvm/test/CodeGen/PowerPC/sms-phi-3.ll b/llvm/test/CodeGen/PowerPC/sms-phi-3.ll
index 12a44f92266..cdb5100b290 100644
--- a/llvm/test/CodeGen/PowerPC/sms-phi-3.ll
+++ b/llvm/test/CodeGen/PowerPC/sms-phi-3.ll
@@ -54,9 +54,9 @@ define void @phi3(i32*) nounwind {
 ; CHECK-NEXT:    stdu 3, 8(4)
 ; CHECK-NEXT:    addi 1, 1, 64
 ; CHECK-NEXT:    ld 0, 16(1)
-; CHECK-NEXT:    mtlr 0
 ; CHECK-NEXT:    ld 30, -16(1) # 8-byte Folded Reload
 ; CHECK-NEXT:    ld 29, -24(1) # 8-byte Folded Reload
+; CHECK-NEXT:    mtlr 0
 ; CHECK-NEXT:    blr
   %2 = tail call noalias i8* @malloc()
   %3 = bitcast i8* %2 to %0**
diff --git a/llvm/test/CodeGen/PowerPC/tocSaveInPrologue.ll b/llvm/test/CodeGen/PowerPC/tocSaveInPrologue.ll
index 79f57eb05d1..5235f3359a8 100644
--- a/llvm/test/CodeGen/PowerPC/tocSaveInPrologue.ll
+++ b/llvm/test/CodeGen/PowerPC/tocSaveInPrologue.ll
@@ -43,10 +43,10 @@ define dso_local void @test(void (i32)* nocapture %fp, i32 signext %Arg, i32 sig
 ; CHECK-NEXT:    ld 2, 24(r1)
 ; CHECK-NEXT:    addi r1, r1, 64
 ; CHECK-NEXT:    ld r0, 16(r1)
-; CHECK-NEXT:    mtlr r0
 ; CHECK-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-NEXT:    ld r29, -24(r1) # 8-byte Folded Reload
 ; CHECK-NEXT:    ld r28, -32(r1) # 8-byte Folded Reload
+; CHECK-NEXT:    mtlr r0
 ; CHECK-NEXT:    blr
 entry:
   %cmp7 = icmp sgt i32 %Len, 0
diff --git a/llvm/test/CodeGen/PowerPC/vector-constrained-fp-intrinsics.ll b/llvm/test/CodeGen/PowerPC/vector-constrained-fp-intrinsics.ll
index 41eb3903dff..3fb77420d3a 100644
--- a/llvm/test/CodeGen/PowerPC/vector-constrained-fp-intrinsics.ll
+++ b/llvm/test/CodeGen/PowerPC/vector-constrained-fp-intrinsics.ll
@@ -293,8 +293,8 @@ define <2 x double> @constrained_vector_frem_v2f64() #0 {
 ; PC64LE-NEXT:    xxmrghd 34, 1, 0
 ; PC64LE-NEXT:    addi 1, 1, 80
 ; PC64LE-NEXT:    ld 0, 16(1)
-; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
+; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    blr
 ;
 ; PC64LE9-LABEL: constrained_vector_frem_v2f64:
@@ -322,8 +322,8 @@ define <2 x double> @constrained_vector_frem_v2f64() #0 {
 ; PC64LE9-NEXT:    xxmrghd 34, 1, 0
 ; PC64LE9-NEXT:    addi 1, 1, 64
 ; PC64LE9-NEXT:    ld 0, 16(1)
-; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
+; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    blr
 entry:
   %rem = call <2 x double> @llvm.experimental.constrained.frem.v2f64(
@@ -375,10 +375,10 @@ define <3 x float> @constrained_vector_frem_v3f32() #0 {
 ; PC64LE-NEXT:    vperm 2, 3, 2, 4
 ; PC64LE-NEXT:    addi 1, 1, 64
 ; PC64LE-NEXT:    ld 0, 16(1)
-; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
 ; PC64LE-NEXT:    lfd 29, -24(1) # 8-byte Folded Reload
+; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    blr
 ;
 ; PC64LE9-LABEL: constrained_vector_frem_v3f32:
@@ -421,9 +421,9 @@ define <3 x float> @constrained_vector_frem_v3f32() #0 {
 ; PC64LE9-NEXT:    vperm 2, 3, 2, 4
 ; PC64LE9-NEXT:    addi 1, 1, 64
 ; PC64LE9-NEXT:    ld 0, 16(1)
-; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE9-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
+; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    lfd 29, -24(1) # 8-byte Folded Reload
 ; PC64LE9-NEXT:    blr
 entry:
@@ -1542,8 +1542,8 @@ define <2 x double> @constrained_vector_pow_v2f64() #0 {
 ; PC64LE-NEXT:    xxmrghd 34, 1, 0
 ; PC64LE-NEXT:    addi 1, 1, 80
 ; PC64LE-NEXT:    ld 0, 16(1)
-; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
+; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    blr
 ;
 ; PC64LE9-LABEL: constrained_vector_pow_v2f64:
@@ -1571,8 +1571,8 @@ define <2 x double> @constrained_vector_pow_v2f64() #0 {
 ; PC64LE9-NEXT:    xxmrghd 34, 1, 0
 ; PC64LE9-NEXT:    addi 1, 1, 64
 ; PC64LE9-NEXT:    ld 0, 16(1)
-; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
+; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    blr
 entry:
   %pow = call <2 x double> @llvm.experimental.constrained.pow.v2f64(
@@ -1624,10 +1624,10 @@ define <3 x float> @constrained_vector_pow_v3f32() #0 {
 ; PC64LE-NEXT:    vperm 2, 3, 2, 4
 ; PC64LE-NEXT:    addi 1, 1, 64
 ; PC64LE-NEXT:    ld 0, 16(1)
-; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
 ; PC64LE-NEXT:    lfd 29, -24(1) # 8-byte Folded Reload
+; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    blr
 ;
 ; PC64LE9-LABEL: constrained_vector_pow_v3f32:
@@ -1670,9 +1670,9 @@ define <3 x float> @constrained_vector_pow_v3f32() #0 {
 ; PC64LE9-NEXT:    vperm 2, 3, 2, 4
 ; PC64LE9-NEXT:    addi 1, 1, 64
 ; PC64LE9-NEXT:    ld 0, 16(1)
-; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE9-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
+; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    lfd 29, -24(1) # 8-byte Folded Reload
 ; PC64LE9-NEXT:    blr
 entry:
@@ -2032,9 +2032,9 @@ define <3 x float> @constrained_vector_powi_v3f32() #0 {
 ; PC64LE-NEXT:    vperm 2, 3, 2, 4
 ; PC64LE-NEXT:    addi 1, 1, 48
 ; PC64LE-NEXT:    ld 0, 16(1)
-; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
+; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    blr
 ;
 ; PC64LE9-LABEL: constrained_vector_powi_v3f32:
@@ -2074,9 +2074,9 @@ define <3 x float> @constrained_vector_powi_v3f32() #0 {
 ; PC64LE9-NEXT:    vperm 2, 3, 2, 4
 ; PC64LE9-NEXT:    addi 1, 1, 48
 ; PC64LE9-NEXT:    ld 0, 16(1)
-; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE9-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
+; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    blr
 entry:
   %powi = call <3 x float> @llvm.experimental.constrained.powi.v3f32(
@@ -2405,9 +2405,9 @@ define <3 x float> @constrained_vector_sin_v3f32() #0 {
 ; PC64LE-NEXT:    vperm 2, 4, 2, 3
 ; PC64LE-NEXT:    addi 1, 1, 48
 ; PC64LE-NEXT:    ld 0, 16(1)
-; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
+; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    blr
 ;
 ; PC64LE9-LABEL: constrained_vector_sin_v3f32:
@@ -2444,9 +2444,9 @@ define <3 x float> @constrained_vector_sin_v3f32() #0 {
 ; PC64LE9-NEXT:    vperm 2, 4, 2, 3
 ; PC64LE9-NEXT:    addi 1, 1, 48
 ; PC64LE9-NEXT:    ld 0, 16(1)
-; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE9-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
+; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    blr
 entry:
   %sin = call <3 x float> @llvm.experimental.constrained.sin.v3f32(
@@ -2758,9 +2758,9 @@ define <3 x float> @constrained_vector_cos_v3f32() #0 {
 ; PC64LE-NEXT:    vperm 2, 4, 2, 3
 ; PC64LE-NEXT:    addi 1, 1, 48
 ; PC64LE-NEXT:    ld 0, 16(1)
-; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
+; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    blr
 ;
 ; PC64LE9-LABEL: constrained_vector_cos_v3f32:
@@ -2797,9 +2797,9 @@ define <3 x float> @constrained_vector_cos_v3f32() #0 {
 ; PC64LE9-NEXT:    vperm 2, 4, 2, 3
 ; PC64LE9-NEXT:    addi 1, 1, 48
 ; PC64LE9-NEXT:    ld 0, 16(1)
-; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE9-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
+; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    blr
 entry:
   %cos = call <3 x float> @llvm.experimental.constrained.cos.v3f32(
@@ -3111,9 +3111,9 @@ define <3 x float> @constrained_vector_exp_v3f32() #0 {
 ; PC64LE-NEXT:    vperm 2, 4, 2, 3
 ; PC64LE-NEXT:    addi 1, 1, 48
 ; PC64LE-NEXT:    ld 0, 16(1)
-; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
+; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    blr
 ;
 ; PC64LE9-LABEL: constrained_vector_exp_v3f32:
@@ -3150,9 +3150,9 @@ define <3 x float> @constrained_vector_exp_v3f32() #0 {
 ; PC64LE9-NEXT:    vperm 2, 4, 2, 3
 ; PC64LE9-NEXT:    addi 1, 1, 48
 ; PC64LE9-NEXT:    ld 0, 16(1)
-; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE9-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
+; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    blr
 entry:
   %exp = call <3 x float> @llvm.experimental.constrained.exp.v3f32(
@@ -3464,9 +3464,9 @@ define <3 x float> @constrained_vector_exp2_v3f32() #0 {
 ; PC64LE-NEXT:    vperm 2, 4, 2, 3
 ; PC64LE-NEXT:    addi 1, 1, 48
 ; PC64LE-NEXT:    ld 0, 16(1)
-; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
+; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    blr
 ;
 ; PC64LE9-LABEL: constrained_vector_exp2_v3f32:
@@ -3503,9 +3503,9 @@ define <3 x float> @constrained_vector_exp2_v3f32() #0 {
 ; PC64LE9-NEXT:    vperm 2, 4, 2, 3
 ; PC64LE9-NEXT:    addi 1, 1, 48
 ; PC64LE9-NEXT:    ld 0, 16(1)
-; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE9-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
+; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    blr
 entry:
   %exp2 = call <3 x float> @llvm.experimental.constrained.exp2.v3f32(
@@ -3817,9 +3817,9 @@ define <3 x float> @constrained_vector_log_v3f32() #0 {
 ; PC64LE-NEXT:    vperm 2, 4, 2, 3
 ; PC64LE-NEXT:    addi 1, 1, 48
 ; PC64LE-NEXT:    ld 0, 16(1)
-; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
+; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    blr
 ;
 ; PC64LE9-LABEL: constrained_vector_log_v3f32:
@@ -3856,9 +3856,9 @@ define <3 x float> @constrained_vector_log_v3f32() #0 {
 ; PC64LE9-NEXT:    vperm 2, 4, 2, 3
 ; PC64LE9-NEXT:    addi 1, 1, 48
 ; PC64LE9-NEXT:    ld 0, 16(1)
-; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE9-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
+; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    blr
 entry:
   %log = call <3 x float> @llvm.experimental.constrained.log.v3f32(
@@ -4170,9 +4170,9 @@ define <3 x float> @constrained_vector_log10_v3f32() #0 {
 ; PC64LE-NEXT:    vperm 2, 4, 2, 3
 ; PC64LE-NEXT:    addi 1, 1, 48
 ; PC64LE-NEXT:    ld 0, 16(1)
-; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
+; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    blr
 ;
 ; PC64LE9-LABEL: constrained_vector_log10_v3f32:
@@ -4209,9 +4209,9 @@ define <3 x float> @constrained_vector_log10_v3f32() #0 {
 ; PC64LE9-NEXT:    vperm 2, 4, 2, 3
 ; PC64LE9-NEXT:    addi 1, 1, 48
 ; PC64LE9-NEXT:    ld 0, 16(1)
-; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE9-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
+; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    blr
 entry:
   %log10 = call <3 x float> @llvm.experimental.constrained.log10.v3f32(
@@ -4523,9 +4523,9 @@ define <3 x float> @constrained_vector_log2_v3f32() #0 {
 ; PC64LE-NEXT:    vperm 2, 4, 2, 3
 ; PC64LE-NEXT:    addi 1, 1, 48
 ; PC64LE-NEXT:    ld 0, 16(1)
-; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
+; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    blr
 ;
 ; PC64LE9-LABEL: constrained_vector_log2_v3f32:
@@ -4562,9 +4562,9 @@ define <3 x float> @constrained_vector_log2_v3f32() #0 {
 ; PC64LE9-NEXT:    vperm 2, 4, 2, 3
 ; PC64LE9-NEXT:    addi 1, 1, 48
 ; PC64LE9-NEXT:    ld 0, 16(1)
-; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE9-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
+; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    blr
 entry:
   %log2 = call <3 x float> @llvm.experimental.constrained.log2.v3f32(
@@ -4876,9 +4876,9 @@ define <3 x float> @constrained_vector_rint_v3f32() #0 {
 ; PC64LE-NEXT:    vperm 2, 4, 2, 3
 ; PC64LE-NEXT:    addi 1, 1, 48
 ; PC64LE-NEXT:    ld 0, 16(1)
-; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
+; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    blr
 ;
 ; PC64LE9-LABEL: constrained_vector_rint_v3f32:
@@ -4915,9 +4915,9 @@ define <3 x float> @constrained_vector_rint_v3f32() #0 {
 ; PC64LE9-NEXT:    vperm 2, 4, 2, 3
 ; PC64LE9-NEXT:    addi 1, 1, 48
 ; PC64LE9-NEXT:    ld 0, 16(1)
-; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE9-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
+; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    blr
  entry:
   %rint = call <3 x float> @llvm.experimental.constrained.rint.v3f32(
@@ -5229,9 +5229,9 @@ define <3 x float> @constrained_vector_nearbyint_v3f32() #0 {
 ; PC64LE-NEXT:    vperm 2, 4, 2, 3
 ; PC64LE-NEXT:    addi 1, 1, 48
 ; PC64LE-NEXT:    ld 0, 16(1)
-; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
+; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    blr
 ;
 ; PC64LE9-LABEL: constrained_vector_nearbyint_v3f32:
@@ -5268,9 +5268,9 @@ define <3 x float> @constrained_vector_nearbyint_v3f32() #0 {
 ; PC64LE9-NEXT:    vperm 2, 4, 2, 3
 ; PC64LE9-NEXT:    addi 1, 1, 48
 ; PC64LE9-NEXT:    ld 0, 16(1)
-; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE9-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
+; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    blr
 entry:
   %nearby = call <3 x float> @llvm.experimental.constrained.nearbyint.v3f32(
@@ -5600,10 +5600,10 @@ define <3 x float> @constrained_vector_maxnum_v3f32() #0 {
 ; PC64LE-NEXT:    vperm 2, 3, 2, 4
 ; PC64LE-NEXT:    addi 1, 1, 64
 ; PC64LE-NEXT:    ld 0, 16(1)
-; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
 ; PC64LE-NEXT:    lfd 29, -24(1) # 8-byte Folded Reload
+; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    blr
 ;
 ; PC64LE9-LABEL: constrained_vector_maxnum_v3f32:
@@ -5647,9 +5647,9 @@ define <3 x float> @constrained_vector_maxnum_v3f32() #0 {
 ; PC64LE9-NEXT:    vperm 2, 3, 2, 4
 ; PC64LE9-NEXT:    addi 1, 1, 64
 ; PC64LE9-NEXT:    ld 0, 16(1)
-; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE9-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
+; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    lfd 29, -24(1) # 8-byte Folded Reload
 ; PC64LE9-NEXT:    blr
 entry:
@@ -6009,10 +6009,10 @@ define <3 x float> @constrained_vector_minnum_v3f32() #0 {
 ; PC64LE-NEXT:    vperm 2, 3, 2, 4
 ; PC64LE-NEXT:    addi 1, 1, 64
 ; PC64LE-NEXT:    ld 0, 16(1)
-; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
 ; PC64LE-NEXT:    lfd 29, -24(1) # 8-byte Folded Reload
+; PC64LE-NEXT:    mtlr 0
 ; PC64LE-NEXT:    blr
 ;
 ; PC64LE9-LABEL: constrained_vector_minnum_v3f32:
@@ -6056,9 +6056,9 @@ define <3 x float> @constrained_vector_minnum_v3f32() #0 {
 ; PC64LE9-NEXT:    vperm 2, 3, 2, 4
 ; PC64LE9-NEXT:    addi 1, 1, 64
 ; PC64LE9-NEXT:    ld 0, 16(1)
-; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    lfd 31, -8(1) # 8-byte Folded Reload
 ; PC64LE9-NEXT:    lfd 30, -16(1) # 8-byte Folded Reload
+; PC64LE9-NEXT:    mtlr 0
 ; PC64LE9-NEXT:    lfd 29, -24(1) # 8-byte Folded Reload
 ; PC64LE9-NEXT:    blr
 entry: