diff options
Diffstat (limited to 'llvm/test/CodeGen/PowerPC')
| -rw-r--r-- | llvm/test/CodeGen/PowerPC/aix-cc-abi-mir.ll | 24 | ||||
| -rw-r--r-- | llvm/test/CodeGen/PowerPC/aix-nest-param.ll | 11 | ||||
| -rw-r--r-- | llvm/test/CodeGen/PowerPC/aix-trampoline.ll | 22 | ||||
| -rw-r--r-- | llvm/test/CodeGen/PowerPC/aix-vec_insert_elt.ll | 4 | ||||
| -rw-r--r-- | llvm/test/CodeGen/PowerPC/build-vector-tests.ll | 48 | ||||
| -rw-r--r-- | llvm/test/CodeGen/PowerPC/canonical-merge-shuffles.ll | 6 | ||||
| -rw-r--r-- | llvm/test/CodeGen/PowerPC/check-zero-vector.ll | 303 | ||||
| -rw-r--r-- | llvm/test/CodeGen/PowerPC/combine-fneg.ll | 1 | ||||
| -rw-r--r-- | llvm/test/CodeGen/PowerPC/fp-strict-round.ll | 6 | ||||
| -rw-r--r-- | llvm/test/CodeGen/PowerPC/frem.ll | 3 | ||||
| -rw-r--r-- | llvm/test/CodeGen/PowerPC/froundeven-legalization.ll | 8 | ||||
| -rw-r--r-- | llvm/test/CodeGen/PowerPC/handle-f16-storage-type.ll | 1 | ||||
| -rw-r--r-- | llvm/test/CodeGen/PowerPC/ldexp.ll | 2 | ||||
| -rw-r--r-- | llvm/test/CodeGen/PowerPC/llvm.modf.ll | 1 | ||||
| -rw-r--r-- | llvm/test/CodeGen/PowerPC/mtvsrbmi.ll | 87 | ||||
| -rw-r--r-- | llvm/test/CodeGen/PowerPC/vec_insert_elt.ll | 4 | ||||
| -rw-r--r-- | llvm/test/CodeGen/PowerPC/vector-constrained-fp-intrinsics.ll | 176 |
17 files changed, 191 insertions, 516 deletions
diff --git a/llvm/test/CodeGen/PowerPC/aix-cc-abi-mir.ll b/llvm/test/CodeGen/PowerPC/aix-cc-abi-mir.ll index 9ffb4fd..258ddf6 100644 --- a/llvm/test/CodeGen/PowerPC/aix-cc-abi-mir.ll +++ b/llvm/test/CodeGen/PowerPC/aix-cc-abi-mir.ll @@ -37,9 +37,9 @@ define signext i8 @test_chars(i8 signext %c1, i8 signext %c2, i8 signext %c3, i8 ; 32BIT: bb.0.entry: ; 32BIT-NEXT: liveins: $r3, $r4, $r5, $r6 ; 32BIT-NEXT: {{ $}} - ; 32BIT-NEXT: renamable $r3 = ADD4 killed renamable $r3, killed renamable $r4 - ; 32BIT-NEXT: renamable $r3 = ADD4 killed renamable $r3, killed renamable $r5 - ; 32BIT-NEXT: renamable $r3 = ADD4 killed renamable $r3, killed renamable $r6 + ; 32BIT-NEXT: renamable $r3 = nsw ADD4 killed renamable $r3, killed renamable $r4 + ; 32BIT-NEXT: renamable $r3 = nsw ADD4 killed renamable $r3, killed renamable $r5 + ; 32BIT-NEXT: renamable $r3 = nsw ADD4 killed renamable $r3, killed renamable $r6 ; 32BIT-NEXT: renamable $r3 = EXTSB killed renamable $r3 ; 32BIT-NEXT: BLR implicit $lr, implicit $rm, implicit $r3 ; @@ -47,9 +47,9 @@ define signext i8 @test_chars(i8 signext %c1, i8 signext %c2, i8 signext %c3, i8 ; 64BIT: bb.0.entry: ; 64BIT-NEXT: liveins: $x3, $x4, $x5, $x6 ; 64BIT-NEXT: {{ $}} - ; 64BIT-NEXT: renamable $r3 = ADD4 renamable $r3, renamable $r4, implicit killed $x4, implicit killed $x3 - ; 64BIT-NEXT: renamable $r3 = ADD4 killed renamable $r3, renamable $r5, implicit killed $x5 - ; 64BIT-NEXT: renamable $r3 = ADD4 killed renamable $r3, renamable $r6, implicit killed $x6, implicit-def $x3 + ; 64BIT-NEXT: renamable $r3 = nsw ADD4 renamable $r3, renamable $r4, implicit killed $x4, implicit killed $x3 + ; 64BIT-NEXT: renamable $r3 = nsw ADD4 killed renamable $r3, renamable $r5, implicit killed $x5 + ; 64BIT-NEXT: renamable $r3 = nsw ADD4 killed renamable $r3, renamable $r6, implicit killed $x6, implicit-def $x3 ; 64BIT-NEXT: renamable $x3 = EXTSB8 killed renamable $x3 ; 64BIT-NEXT: BLR8 implicit $lr8, implicit $rm, implicit $x3 entry: @@ -96,9 +96,9 @@ define signext i8 @test_chars_mix(i8 signext %c1, i8 zeroext %c2, i8 zeroext %c3 ; 32BIT: bb.0.entry: ; 32BIT-NEXT: liveins: $r3, $r4, $r5, $r6 ; 32BIT-NEXT: {{ $}} - ; 32BIT-NEXT: renamable $r3 = ADD4 killed renamable $r3, killed renamable $r4 - ; 32BIT-NEXT: renamable $r3 = ADD4 killed renamable $r3, killed renamable $r5 - ; 32BIT-NEXT: renamable $r3 = ADD4 killed renamable $r3, killed renamable $r6 + ; 32BIT-NEXT: renamable $r3 = nsw ADD4 killed renamable $r3, killed renamable $r4 + ; 32BIT-NEXT: renamable $r3 = nsw ADD4 killed renamable $r3, killed renamable $r5 + ; 32BIT-NEXT: renamable $r3 = nsw ADD4 killed renamable $r3, killed renamable $r6 ; 32BIT-NEXT: renamable $r3 = EXTSB killed renamable $r3 ; 32BIT-NEXT: BLR implicit $lr, implicit $rm, implicit $r3 ; @@ -106,9 +106,9 @@ define signext i8 @test_chars_mix(i8 signext %c1, i8 zeroext %c2, i8 zeroext %c3 ; 64BIT: bb.0.entry: ; 64BIT-NEXT: liveins: $x3, $x4, $x5, $x6 ; 64BIT-NEXT: {{ $}} - ; 64BIT-NEXT: renamable $r3 = ADD4 renamable $r3, renamable $r4, implicit killed $x4, implicit killed $x3 - ; 64BIT-NEXT: renamable $r3 = ADD4 killed renamable $r3, renamable $r5, implicit killed $x5 - ; 64BIT-NEXT: renamable $r3 = ADD4 killed renamable $r3, renamable $r6, implicit killed $x6, implicit-def $x3 + ; 64BIT-NEXT: renamable $r3 = nsw ADD4 renamable $r3, renamable $r4, implicit killed $x4, implicit killed $x3 + ; 64BIT-NEXT: renamable $r3 = nsw ADD4 killed renamable $r3, renamable $r5, implicit killed $x5 + ; 64BIT-NEXT: renamable $r3 = nsw ADD4 killed renamable $r3, renamable $r6, implicit killed $x6, implicit-def $x3 ; 64BIT-NEXT: renamable $x3 = EXTSB8 killed renamable $x3 ; 64BIT-NEXT: BLR8 implicit $lr8, implicit $rm, implicit $x3 entry: diff --git a/llvm/test/CodeGen/PowerPC/aix-nest-param.ll b/llvm/test/CodeGen/PowerPC/aix-nest-param.ll index 1863eaf..bfc7fbb 100644 --- a/llvm/test/CodeGen/PowerPC/aix-nest-param.ll +++ b/llvm/test/CodeGen/PowerPC/aix-nest-param.ll @@ -1,5 +1,5 @@ -; RUN: not --crash llc -mtriple powerpc-ibm-aix-xcoff < %s 2>&1 | FileCheck %s -; RUN: not --crash llc -mtriple powerpc64-ibm-aix-xcoff < %s 2>&1 | FileCheck %s +; RUN: llc -mtriple powerpc-ibm-aix-xcoff < %s 2>&1 | FileCheck %s +; RUN: llc -mtriple powerpc64-ibm-aix-xcoff < %s 2>&1 | FileCheck %s define ptr @nest_receiver(ptr nest %arg) nounwind { ret ptr %arg @@ -9,5 +9,10 @@ define ptr @nest_caller(ptr %arg) nounwind { %result = call ptr @nest_receiver(ptr nest %arg) ret ptr %result } +; CHECK-LABEL: .nest_receiver: +; CHECK: mr 3, 11 +; CHECK: blr -; CHECK: LLVM ERROR: Nest arguments are unimplemented. +; CHECK-LABEL: .nest_caller: +; CHECK: mr 11, 3 +; CHECK: bl .nest_receiver diff --git a/llvm/test/CodeGen/PowerPC/aix-trampoline.ll b/llvm/test/CodeGen/PowerPC/aix-trampoline.ll index b71f6b5..19df220 100644 --- a/llvm/test/CodeGen/PowerPC/aix-trampoline.ll +++ b/llvm/test/CodeGen/PowerPC/aix-trampoline.ll @@ -1,7 +1,7 @@ -; RUN: not --crash llc -mtriple powerpc-ibm-aix-xcoff < %s 2>&1 | FileCheck %s -; RUN: not --crash llc -mtriple powerpc64-ibm-aix-xcoff < %s 2>&1 | FileCheck %s - -; CHECK: LLVM ERROR: INIT_TRAMPOLINE operation is not supported on AIX. +; RUN: llc -mtriple powerpc-ibm-aix-xcoff < %s 2>&1 | \ +; RUN: FileCheck %s --check-prefix=32BIT +; RUN: llc -mtriple powerpc64-ibm-aix-xcoff < %s 2>&1 -mattr=-altivec | \ +; RUN: FileCheck %s --check-prefix=64BIT define void @create_trampoline(ptr %buffer, ptr %nval) nounwind { entry: @@ -12,3 +12,17 @@ entry: declare i32 @nested(i32); declare void @llvm.init.trampoline(ptr, ptr, ptr) nounwind + +; 32BIT: stw 4, 8(3) +; 32BIT: lwz [[FuncDesc:[0-9]+]], L..C0(2) +; 32BIT-DAG: lwz [[SCRATCH1:[0-9]+]], 0([[FuncDesc]]) +; 32BIT-DAG: lwz [[SCRATCH2:[0-9]+]], 4([[FuncDesc]]) +; 32BIT-DAG: stw [[SCRATCH1]], 0(3) +; 32BIT-DAG: stw [[SCRATCH2]], 4(3) + +; 64BIT: std 4, 16(3) +; 64BIT-DAG: ld [[FuncDesc:[0-9]+]], L..C0(2) +; 64BIT-DAG: ld [[SCRATCH1:[0-9]+]], 0([[FuncDesc]]) +; 64BIT-DAG: ld [[SCRATCH2:[0-9]+]], 8([[FuncDesc]]) +; 64BIT-DAG: std [[SCRATCH1]], 0(3) +; 64BIT-DAG: std [[SCRATCH2]], 8(3) diff --git a/llvm/test/CodeGen/PowerPC/aix-vec_insert_elt.ll b/llvm/test/CodeGen/PowerPC/aix-vec_insert_elt.ll index aae2326..afc7a39 100644 --- a/llvm/test/CodeGen/PowerPC/aix-vec_insert_elt.ll +++ b/llvm/test/CodeGen/PowerPC/aix-vec_insert_elt.ll @@ -750,25 +750,21 @@ entry: define <2 x double> @testDoubleImm1(<2 x double> %a, double %b) { ; CHECK-64-LABEL: testDoubleImm1: ; CHECK-64: # %bb.0: # %entry -; CHECK-64-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; CHECK-64-NEXT: xxpermdi 34, 1, 34, 1 ; CHECK-64-NEXT: blr ; ; CHECK-32-LABEL: testDoubleImm1: ; CHECK-32: # %bb.0: # %entry -; CHECK-32-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; CHECK-32-NEXT: xxpermdi 34, 1, 34, 1 ; CHECK-32-NEXT: blr ; ; CHECK-64-P10-LABEL: testDoubleImm1: ; CHECK-64-P10: # %bb.0: # %entry -; CHECK-64-P10-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; CHECK-64-P10-NEXT: xxpermdi 34, 1, 34, 1 ; CHECK-64-P10-NEXT: blr ; ; CHECK-32-P10-LABEL: testDoubleImm1: ; CHECK-32-P10: # %bb.0: # %entry -; CHECK-32-P10-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; CHECK-32-P10-NEXT: xxpermdi 34, 1, 34, 1 ; CHECK-32-P10-NEXT: blr entry: diff --git a/llvm/test/CodeGen/PowerPC/build-vector-tests.ll b/llvm/test/CodeGen/PowerPC/build-vector-tests.ll index 10fc308..9dd0fbe 100644 --- a/llvm/test/CodeGen/PowerPC/build-vector-tests.ll +++ b/llvm/test/CodeGen/PowerPC/build-vector-tests.ll @@ -1757,11 +1757,7 @@ entry: define <4 x i32> @fromRegsConvdtoi(double %a, double %b, double %c, double %d) { ; P9BE-LABEL: fromRegsConvdtoi: ; P9BE: # %bb.0: # %entry -; P9BE-NEXT: # kill: def $f4 killed $f4 def $vsl4 -; P9BE-NEXT: # kill: def $f2 killed $f2 def $vsl2 ; P9BE-NEXT: xxmrghd vs0, vs2, vs4 -; P9BE-NEXT: # kill: def $f3 killed $f3 def $vsl3 -; P9BE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; P9BE-NEXT: xvcvdpsxws v2, vs0 ; P9BE-NEXT: xxmrghd vs0, vs1, vs3 ; P9BE-NEXT: xvcvdpsxws v3, vs0 @@ -1770,11 +1766,7 @@ define <4 x i32> @fromRegsConvdtoi(double %a, double %b, double %c, double %d) { ; ; P9LE-LABEL: fromRegsConvdtoi: ; P9LE: # %bb.0: # %entry -; P9LE-NEXT: # kill: def $f3 killed $f3 def $vsl3 -; P9LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; P9LE-NEXT: xxmrghd vs0, vs3, vs1 -; P9LE-NEXT: # kill: def $f4 killed $f4 def $vsl4 -; P9LE-NEXT: # kill: def $f2 killed $f2 def $vsl2 ; P9LE-NEXT: xvcvdpsxws v2, vs0 ; P9LE-NEXT: xxmrghd vs0, vs4, vs2 ; P9LE-NEXT: xvcvdpsxws v3, vs0 @@ -1783,10 +1775,6 @@ define <4 x i32> @fromRegsConvdtoi(double %a, double %b, double %c, double %d) { ; ; P8BE-LABEL: fromRegsConvdtoi: ; P8BE: # %bb.0: # %entry -; P8BE-NEXT: # kill: def $f4 killed $f4 def $vsl4 -; P8BE-NEXT: # kill: def $f3 killed $f3 def $vsl3 -; P8BE-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; P8BE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; P8BE-NEXT: xxmrghd vs0, vs2, vs4 ; P8BE-NEXT: xxmrghd vs1, vs1, vs3 ; P8BE-NEXT: xvcvdpsxws v2, vs0 @@ -1796,10 +1784,6 @@ define <4 x i32> @fromRegsConvdtoi(double %a, double %b, double %c, double %d) { ; ; P8LE-LABEL: fromRegsConvdtoi: ; P8LE: # %bb.0: # %entry -; P8LE-NEXT: # kill: def $f4 killed $f4 def $vsl4 -; P8LE-NEXT: # kill: def $f3 killed $f3 def $vsl3 -; P8LE-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; P8LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; P8LE-NEXT: xxmrghd vs0, vs3, vs1 ; P8LE-NEXT: xxmrghd vs1, vs4, vs2 ; P8LE-NEXT: xvcvdpsxws v2, vs0 @@ -3262,11 +3246,7 @@ entry: define <4 x i32> @fromRegsConvdtoui(double %a, double %b, double %c, double %d) { ; P9BE-LABEL: fromRegsConvdtoui: ; P9BE: # %bb.0: # %entry -; P9BE-NEXT: # kill: def $f4 killed $f4 def $vsl4 -; P9BE-NEXT: # kill: def $f2 killed $f2 def $vsl2 ; P9BE-NEXT: xxmrghd vs0, vs2, vs4 -; P9BE-NEXT: # kill: def $f3 killed $f3 def $vsl3 -; P9BE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; P9BE-NEXT: xvcvdpuxws v2, vs0 ; P9BE-NEXT: xxmrghd vs0, vs1, vs3 ; P9BE-NEXT: xvcvdpuxws v3, vs0 @@ -3275,11 +3255,7 @@ define <4 x i32> @fromRegsConvdtoui(double %a, double %b, double %c, double %d) ; ; P9LE-LABEL: fromRegsConvdtoui: ; P9LE: # %bb.0: # %entry -; P9LE-NEXT: # kill: def $f3 killed $f3 def $vsl3 -; P9LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; P9LE-NEXT: xxmrghd vs0, vs3, vs1 -; P9LE-NEXT: # kill: def $f4 killed $f4 def $vsl4 -; P9LE-NEXT: # kill: def $f2 killed $f2 def $vsl2 ; P9LE-NEXT: xvcvdpuxws v2, vs0 ; P9LE-NEXT: xxmrghd vs0, vs4, vs2 ; P9LE-NEXT: xvcvdpuxws v3, vs0 @@ -3288,10 +3264,6 @@ define <4 x i32> @fromRegsConvdtoui(double %a, double %b, double %c, double %d) ; ; P8BE-LABEL: fromRegsConvdtoui: ; P8BE: # %bb.0: # %entry -; P8BE-NEXT: # kill: def $f4 killed $f4 def $vsl4 -; P8BE-NEXT: # kill: def $f3 killed $f3 def $vsl3 -; P8BE-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; P8BE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; P8BE-NEXT: xxmrghd vs0, vs2, vs4 ; P8BE-NEXT: xxmrghd vs1, vs1, vs3 ; P8BE-NEXT: xvcvdpuxws v2, vs0 @@ -3301,10 +3273,6 @@ define <4 x i32> @fromRegsConvdtoui(double %a, double %b, double %c, double %d) ; ; P8LE-LABEL: fromRegsConvdtoui: ; P8LE: # %bb.0: # %entry -; P8LE-NEXT: # kill: def $f4 killed $f4 def $vsl4 -; P8LE-NEXT: # kill: def $f3 killed $f3 def $vsl3 -; P8LE-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; P8LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; P8LE-NEXT: xxmrghd vs0, vs3, vs1 ; P8LE-NEXT: xxmrghd vs1, vs4, vs2 ; P8LE-NEXT: xvcvdpuxws v2, vs0 @@ -4578,32 +4546,24 @@ entry: define <2 x i64> @fromRegsConvdtoll(double %a, double %b) { ; P9BE-LABEL: fromRegsConvdtoll: ; P9BE: # %bb.0: # %entry -; P9BE-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; P9BE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; P9BE-NEXT: xxmrghd vs0, vs1, vs2 ; P9BE-NEXT: xvcvdpsxds v2, vs0 ; P9BE-NEXT: blr ; ; P9LE-LABEL: fromRegsConvdtoll: ; P9LE: # %bb.0: # %entry -; P9LE-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; P9LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; P9LE-NEXT: xxmrghd vs0, vs2, vs1 ; P9LE-NEXT: xvcvdpsxds v2, vs0 ; P9LE-NEXT: blr ; ; P8BE-LABEL: fromRegsConvdtoll: ; P8BE: # %bb.0: # %entry -; P8BE-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; P8BE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; P8BE-NEXT: xxmrghd vs0, vs1, vs2 ; P8BE-NEXT: xvcvdpsxds v2, vs0 ; P8BE-NEXT: blr ; ; P8LE-LABEL: fromRegsConvdtoll: ; P8LE: # %bb.0: # %entry -; P8LE-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; P8LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; P8LE-NEXT: xxmrghd vs0, vs2, vs1 ; P8LE-NEXT: xvcvdpsxds v2, vs0 ; P8LE-NEXT: blr @@ -5740,32 +5700,24 @@ entry: define <2 x i64> @fromRegsConvdtoull(double %a, double %b) { ; P9BE-LABEL: fromRegsConvdtoull: ; P9BE: # %bb.0: # %entry -; P9BE-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; P9BE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; P9BE-NEXT: xxmrghd vs0, vs1, vs2 ; P9BE-NEXT: xvcvdpuxds v2, vs0 ; P9BE-NEXT: blr ; ; P9LE-LABEL: fromRegsConvdtoull: ; P9LE: # %bb.0: # %entry -; P9LE-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; P9LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; P9LE-NEXT: xxmrghd vs0, vs2, vs1 ; P9LE-NEXT: xvcvdpuxds v2, vs0 ; P9LE-NEXT: blr ; ; P8BE-LABEL: fromRegsConvdtoull: ; P8BE: # %bb.0: # %entry -; P8BE-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; P8BE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; P8BE-NEXT: xxmrghd vs0, vs1, vs2 ; P8BE-NEXT: xvcvdpuxds v2, vs0 ; P8BE-NEXT: blr ; ; P8LE-LABEL: fromRegsConvdtoull: ; P8LE: # %bb.0: # %entry -; P8LE-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; P8LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; P8LE-NEXT: xxmrghd vs0, vs2, vs1 ; P8LE-NEXT: xvcvdpuxds v2, vs0 ; P8LE-NEXT: blr diff --git a/llvm/test/CodeGen/PowerPC/canonical-merge-shuffles.ll b/llvm/test/CodeGen/PowerPC/canonical-merge-shuffles.ll index b40fbc3..7f6fdc7 100644 --- a/llvm/test/CodeGen/PowerPC/canonical-merge-shuffles.ll +++ b/llvm/test/CodeGen/PowerPC/canonical-merge-shuffles.ll @@ -562,7 +562,6 @@ define dso_local void @no_crash_elt0_from_RHS(ptr noalias nocapture dereferencea ; CHECK-P8-NEXT: bl dummy ; CHECK-P8-NEXT: nop ; CHECK-P8-NEXT: xxlxor f0, f0, f0 -; CHECK-P8-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; CHECK-P8-NEXT: xxmrghd vs0, vs1, vs0 ; CHECK-P8-NEXT: xxswapd vs0, vs0 ; CHECK-P8-NEXT: stxvd2x vs0, 0, r30 @@ -577,7 +576,6 @@ define dso_local void @no_crash_elt0_from_RHS(ptr noalias nocapture dereferencea ; CHECK-P9-NEXT: bl dummy ; CHECK-P9-NEXT: nop ; CHECK-P9-NEXT: xxlxor f0, f0, f0 -; CHECK-P9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; CHECK-P9-NEXT: xxmrghd vs0, vs1, vs0 ; CHECK-P9-NEXT: stxv vs0, 0(r30) ; @@ -591,7 +589,6 @@ define dso_local void @no_crash_elt0_from_RHS(ptr noalias nocapture dereferencea ; CHECK-P9-BE-NEXT: bl dummy ; CHECK-P9-BE-NEXT: nop ; CHECK-P9-BE-NEXT: xxlxor f0, f0, f0 -; CHECK-P9-BE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; CHECK-P9-BE-NEXT: xxmrghd vs0, vs0, vs1 ; CHECK-P9-BE-NEXT: stxv vs0, 0(r30) ; @@ -618,7 +615,6 @@ define dso_local void @no_crash_elt0_from_RHS(ptr noalias nocapture dereferencea ; CHECK-P7-NEXT: bl dummy ; CHECK-P7-NEXT: nop ; CHECK-P7-NEXT: xxlxor f0, f0, f0 -; CHECK-P7-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; CHECK-P7-NEXT: xxmrghd vs0, vs1, vs0 ; CHECK-P7-NEXT: xxswapd vs0, vs0 ; CHECK-P7-NEXT: stxvd2x vs0, 0, r30 @@ -633,7 +629,6 @@ define dso_local void @no_crash_elt0_from_RHS(ptr noalias nocapture dereferencea ; P8-AIX-64-NEXT: bl .dummy[PR] ; P8-AIX-64-NEXT: nop ; P8-AIX-64-NEXT: xxlxor f0, f0, f0 -; P8-AIX-64-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; P8-AIX-64-NEXT: xxmrghd vs0, vs0, vs1 ; P8-AIX-64-NEXT: stxvd2x vs0, 0, r31 ; @@ -647,7 +642,6 @@ define dso_local void @no_crash_elt0_from_RHS(ptr noalias nocapture dereferencea ; P8-AIX-32-NEXT: bl .dummy[PR] ; P8-AIX-32-NEXT: nop ; P8-AIX-32-NEXT: xxlxor f0, f0, f0 -; P8-AIX-32-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; P8-AIX-32-NEXT: xxmrghd vs0, vs0, vs1 ; P8-AIX-32-NEXT: stxvd2x vs0, 0, r31 test_entry: diff --git a/llvm/test/CodeGen/PowerPC/check-zero-vector.ll b/llvm/test/CodeGen/PowerPC/check-zero-vector.ll index 59173e2..d8e66d6 100644 --- a/llvm/test/CodeGen/PowerPC/check-zero-vector.ll +++ b/llvm/test/CodeGen/PowerPC/check-zero-vector.ll @@ -1,3 +1,4 @@ +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5 ; RUN: llc -verify-machineinstrs -mcpu=pwr9 -mtriple=powerpc64le-unknown-linux-gnu \ ; RUN: < %s | FileCheck %s --check-prefix=POWERPC_64LE @@ -7,240 +8,90 @@ ; RUN: llc -verify-machineinstrs -mcpu=pwr9 -mtriple=powerpc-ibm-aix \ ; RUN: < %s | FileCheck %s --check-prefix=POWERPC_32 -define i32 @test_Greater_than(ptr %colauths, i32 signext %ncols) { -; This testcase is manually reduced to isolate the critical code blocks. -; It is designed to check for vector comparison specifically for zero vectors. -; In the vector.body section, we are expecting a comparison instruction (vcmpequh), -; merge instructions (vmrghh and vmrglh) which use exactly 2 vectors. -; The output of the merge instruction is being used by xxland and finally -; accumulated by vadduwm instruction. - +define i32 @test_Greater_than(ptr %colauths) { +; This testcase is for the special case of zero-vector comparisons. +; Currently the generated code does a comparison (vcmpequh) and then a negation (xxlnor). +; This pattern is expected to be optimized in a future patch. ; POWERPC_64LE-LABEL: test_Greater_than: -; POWERPC_64LE: .LBB0_6: # %vector.body -; POWERPC_64LE-NEXT: # -; POWERPC_64LE-NEXT: lxv [[R1:[0-9]+]], -64(4) -; POWERPC_64LE-NEXT: vcmpequh [[R2:[0-9]+]], [[R2]], [[R3:[0-9]+]] -; POWERPC_64LE-NEXT: xxlnor [[R1]], [[R1]], [[R1]] -; POWERPC_64LE-NEXT: vmrghh [[R4:[0-9]+]], [[R2]], [[R2]] -; POWERPC_64LE-NEXT: vmrglh [[R2]], [[R2]], [[R2]] -; POWERPC_64LE-NEXT: xxland [[R5:[0-9]+]], [[R5]], [[R6:[0-9]+]] -; POWERPC_64LE-NEXT: xxland [[R1]], [[R1]], [[R6]] -; POWERPC_64LE-NEXT: vadduwm [[R7:[0-9]+]], [[R7]], [[R4]] -; POWERPC_64LE: .LBB0_10: # %vec.epilog.vector.body -; POWERPC_64LE-NEXT: # -; POWERPC_64LE-NEXT: lxv [[R8:[0-9]+]], 0(4) -; POWERPC_64LE-NEXT: addi 4, 4, 16 -; POWERPC_64LE-NEXT: vcmpequh [[R9:[0-9]+]], [[R9]], [[R10:[0-9]+]] -; POWERPC_64LE-NEXT: xxlnor [[R8]], [[R8]], [[R8]] -; POWERPC_64LE-NEXT: vmrglh [[R11:[0-9]+]], [[R9]], [[R9]] -; POWERPC_64LE-NEXT: vmrghh [[R9]], [[R9]], [[R9]] -; POWERPC_64LE-NEXT: xxland [[R12:[0-9]+]], [[R12]], [[R6]] -; POWERPC_64LE-NEXT: xxland [[R8]], [[R8]], [[R6]] -; POWERPC_64LE-NEXT: vadduwm [[R7]], [[R7]], [[R9]] -; POWERPC_64LE-NEXT: vadduwm [[R3]], [[R3]], [[R11]] -; POWERPC_64LE-NEXT: bdnz .LBB0_10 -; POWERPC_64LE: blr +; POWERPC_64LE: # %bb.0: # %entry +; POWERPC_64LE-NEXT: lfd 0, 0(3) +; POWERPC_64LE-NEXT: xxlxor 35, 35, 35 +; POWERPC_64LE-NEXT: li 4, 0 +; POWERPC_64LE-NEXT: li 3, 4 +; POWERPC_64LE-NEXT: xxswapd 34, 0 +; POWERPC_64LE-NEXT: vcmpequh 2, 2, 3 +; POWERPC_64LE-NEXT: xxlnor 34, 34, 34 +; POWERPC_64LE-NEXT: vmrglh 3, 2, 2 +; POWERPC_64LE-NEXT: vextuwrx 4, 4, 2 +; POWERPC_64LE-NEXT: vextuwrx 3, 3, 3 +; POWERPC_64LE-NEXT: clrlwi 4, 4, 31 +; POWERPC_64LE-NEXT: rlwimi 4, 3, 1, 30, 30 +; POWERPC_64LE-NEXT: mfvsrwz 3, 35 +; POWERPC_64LE-NEXT: rlwimi 4, 3, 2, 29, 29 +; POWERPC_64LE-NEXT: li 3, 12 +; POWERPC_64LE-NEXT: vextuwrx 3, 3, 3 +; POWERPC_64LE-NEXT: rlwimi 4, 3, 3, 28, 28 +; POWERPC_64LE-NEXT: stb 4, -1(1) +; POWERPC_64LE-NEXT: lbz 3, -1(1) +; POWERPC_64LE-NEXT: popcntd 3, 3 +; POWERPC_64LE-NEXT: blr ; ; POWERPC_64-LABEL: test_Greater_than: -; POWERPC_64: L..BB0_6: # %vector.body -; POWERPC_64-NEXT: # -; POWERPC_64-NEXT: lxv [[R1:[0-9]+]], -64(4) -; POWERPC_64-NEXT: vcmpequh [[R2:[0-9]+]], [[R2]], [[R3:[0-9]+]] -; POWERPC_64-NEXT: xxlnor [[R1]], [[R1]], [[R1]] -; POWERPC_64-NEXT: vmrglh [[R4:[0-9]+]], [[R2]], [[R2]] -; POWERPC_64-NEXT: vmrghh [[R2]], [[R2]], [[R2]] -; POWERPC_64-NEXT: xxland [[R5:[0-9]+]], [[R5]], [[R6:[0-9]+]] -; POWERPC_64-NEXT: xxland [[R1]], [[R1]], [[R6]] -; POWERPC_64-NEXT: vadduwm [[R7:[0-9]+]], [[R7]], [[R4]] -; POWERPC_64: L..BB0_10: # %vec.epilog.vector.body -; POWERPC_64-NEXT: # -; POWERPC_64-NEXT: lxv [[R8:[0-9]+]], 0(4) -; POWERPC_64-NEXT: addi 4, 4, 16 -; POWERPC_64-NEXT: vcmpequh [[R9:[0-9]+]], [[R9]], [[R10:[0-9]+]] -; POWERPC_64-NEXT: xxlnor [[R8]], [[R8]], [[R8]] -; POWERPC_64-NEXT: vmrghh [[R11:[0-9]+]], [[R9]], [[R9]] -; POWERPC_64-NEXT: vmrglh [[R9]], [[R9]], [[R9]] -; POWERPC_64-NEXT: xxland [[R12:[0-9]+]], [[R12]], [[R6]] -; POWERPC_64-NEXT: xxland [[R8]], [[R8]], [[R6]] -; POWERPC_64-NEXT: vadduwm [[R7]], [[R7]], [[R9]] -; POWERPC_64-NEXT: vadduwm [[R3]], [[R3]], [[R11]] -; POWERPC_64-NEXT: bdnz L..BB0_10 -; POWERPC_64: blr +; POWERPC_64: # %bb.0: # %entry +; POWERPC_64-NEXT: lxsd 2, 0(3) +; POWERPC_64-NEXT: xxlxor 35, 35, 35 +; POWERPC_64-NEXT: li 4, 12 +; POWERPC_64-NEXT: li 3, 8 +; POWERPC_64-NEXT: vcmpequh 2, 2, 3 +; POWERPC_64-NEXT: xxlnor 34, 34, 34 +; POWERPC_64-NEXT: vmrghh 2, 2, 2 +; POWERPC_64-NEXT: vextuwlx 4, 4, 2 +; POWERPC_64-NEXT: vextuwlx 3, 3, 2 +; POWERPC_64-NEXT: clrlwi 4, 4, 31 +; POWERPC_64-NEXT: rlwimi 4, 3, 1, 30, 30 +; POWERPC_64-NEXT: mfvsrwz 3, 34 +; POWERPC_64-NEXT: rlwimi 4, 3, 2, 29, 29 +; POWERPC_64-NEXT: li 3, 0 +; POWERPC_64-NEXT: vextuwlx 3, 3, 2 +; POWERPC_64-NEXT: rlwimi 4, 3, 3, 28, 28 +; POWERPC_64-NEXT: stb 4, -1(1) +; POWERPC_64-NEXT: lbz 3, -1(1) +; POWERPC_64-NEXT: popcntd 3, 3 +; POWERPC_64-NEXT: blr ; ; POWERPC_32-LABEL: test_Greater_than: -; POWERPC_32: L..BB0_7: # %vector.body -; POWERPC_32-NEXT: # -; POWERPC_32-NEXT: lxv [[R1:[0-9]+]], 0(10) -; POWERPC_32-NEXT: addic [[R13:[0-9]+]], [[R13]], 64 -; POWERPC_32-NEXT: addze [[R14:[0-9]+]], [[R14]] -; POWERPC_32-NEXT: xor [[R15:[0-9]+]], [[R13]], [[R16:[0-9]+]] -; POWERPC_32-NEXT: or. [[R15]], [[R15]], [[R14]] -; POWERPC_32-NEXT: vcmpequh [[R2:[0-9]+]], [[R2]], [[R3:[0-9]+]] -; POWERPC_32-NEXT: xxlnor [[R1]], [[R1]], [[R1]] -; POWERPC_32-NEXT: vmrglh [[R4:[0-9]+]], [[R2]], [[R2]] -; POWERPC_32-NEXT: vmrghh [[R2]], [[R2]], [[R2]] -; POWERPC_32-NEXT: xxland [[R5:[0-9]+]], [[R5]], [[R6:[0-9]+]] -; POWERPC_32-NEXT: xxland [[R1]], [[R1]], [[R6]] -; POWERPC_32-NEXT: vadduwm [[R7:[0-9]+]], [[R7]], [[R4]] -; POWERPC_32: L..BB0_11: # %vec.epilog.vector.body -; POWERPC_32-NEXT: # -; POWERPC_32-NEXT: slwi [[R14]], [[R13]], 1 -; POWERPC_32-NEXT: addic [[R13]], [[R13]], 8 -; POWERPC_32-NEXT: addze [[R17:[0-9]+]], [[R17]] -; POWERPC_32-NEXT: lxvx [[R8:[0-9]+]], [[R18:[0-9]+]], [[R14]] -; POWERPC_32-NEXT: xor [[R14]], [[R13]], [[R16]] -; POWERPC_32-NEXT: or. [[R14]], [[R14]], [[R17]] -; POWERPC_32-NEXT: vcmpequh [[R9:[0-9]+]], [[R9]], [[R3]] -; POWERPC_32-NEXT: xxlnor [[R8]], [[R8]], [[R8]] -; POWERPC_32-NEXT: vmrghh [[R11:[0-9]+]], [[R9]], [[R9]] -; POWERPC_32-NEXT: vmrglh [[R9]], [[R9]], [[R9]] -; POWERPC_32-NEXT: xxland [[R12:[0-9]+]], [[R12]], [[R6]] -; POWERPC_32-NEXT: xxland [[R8]], [[R8]], [[R6]] -; POWERPC_32-NEXT: vadduwm [[R7]], [[R7]], [[R9]] -; POWERPC_32-NEXT: vadduwm [[R19:[0-9]+]], [[R19]], [[R11]] -; POWERPC_32-NEXT: bne 0, L..BB0_11 -; POWERPC_32: blr - entry: - %cmp5 = icmp sgt i32 %ncols, 0 - br i1 %cmp5, label %iter.check, label %for.cond.cleanup - -iter.check: ; preds = %entry - %wide.trip.count = zext nneg i32 %ncols to i64 - %min.iters.check = icmp ult i32 %ncols, 8 - br i1 %min.iters.check, label %for.body.preheader, label %vector.main.loop.iter.check - -for.body.preheader: ; preds = %vec.epilog.iter.check, %vec.epilog.middle.block, %iter.check - %indvars.iv.ph = phi i64 [ 0, %iter.check ], [ %n.vec, %vec.epilog.iter.check ], [ %n.vec31, %vec.epilog.middle.block ] - %num_cols_needed.06.ph = phi i32 [ 0, %iter.check ], [ %33, %vec.epilog.iter.check ], [ %40, %vec.epilog.middle.block ] - br label %for.body - -vector.main.loop.iter.check: ; preds = %iter.check - %min.iters.check9 = icmp ult i32 %ncols, 64 - br i1 %min.iters.check9, label %vec.epilog.ph, label %vector.ph - -vector.ph: ; preds = %vector.main.loop.iter.check - %n.vec = and i64 %wide.trip.count, 2147483584 - br label %vector.body - -vector.body: ; preds = %vector.body, %vector.ph - %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ] - %vec.phi = phi <8 x i32> [ zeroinitializer, %vector.ph ], [ %24, %vector.body ] - %vec.phi10 = phi <8 x i32> [ zeroinitializer, %vector.ph ], [ %25, %vector.body ] - %vec.phi11 = phi <8 x i32> [ zeroinitializer, %vector.ph ], [ %26, %vector.body ] - %vec.phi12 = phi <8 x i32> [ zeroinitializer, %vector.ph ], [ %27, %vector.body ] - %vec.phi13 = phi <8 x i32> [ zeroinitializer, %vector.ph ], [ %28, %vector.body ] - %vec.phi14 = phi <8 x i32> [ zeroinitializer, %vector.ph ], [ %29, %vector.body ] - %vec.phi15 = phi <8 x i32> [ zeroinitializer, %vector.ph ], [ %30, %vector.body ] - %vec.phi16 = phi <8 x i32> [ zeroinitializer, %vector.ph ], [ %31, %vector.body ] - %0 = getelementptr inbounds nuw i16, ptr %colauths, i64 %index - %1 = getelementptr inbounds nuw i8, ptr %0, i64 16 - %2 = getelementptr inbounds nuw i8, ptr %0, i64 32 - %3 = getelementptr inbounds nuw i8, ptr %0, i64 48 - %4 = getelementptr inbounds nuw i8, ptr %0, i64 64 - %5 = getelementptr inbounds nuw i8, ptr %0, i64 80 - %6 = getelementptr inbounds nuw i8, ptr %0, i64 96 - %7 = getelementptr inbounds nuw i8, ptr %0, i64 112 - %wide.load = load <8 x i16>, ptr %0, align 2, !tbaa !5 - %wide.load17 = load <8 x i16>, ptr %1, align 2, !tbaa !5 - %wide.load18 = load <8 x i16>, ptr %2, align 2, !tbaa !5 - %wide.load19 = load <8 x i16>, ptr %3, align 2, !tbaa !5 - %wide.load20 = load <8 x i16>, ptr %4, align 2, !tbaa !5 - %wide.load21 = load <8 x i16>, ptr %5, align 2, !tbaa !5 - %wide.load22 = load <8 x i16>, ptr %6, align 2, !tbaa !5 - %wide.load23 = load <8 x i16>, ptr %7, align 2, !tbaa !5 - %8 = icmp ne <8 x i16> %wide.load, zeroinitializer - %9 = icmp ne <8 x i16> %wide.load17, zeroinitializer - %10 = icmp ne <8 x i16> %wide.load18, zeroinitializer - %11 = icmp ne <8 x i16> %wide.load19, zeroinitializer - %12 = icmp ne <8 x i16> %wide.load20, zeroinitializer - %13 = icmp ne <8 x i16> %wide.load21, zeroinitializer - %14 = icmp ne <8 x i16> %wide.load22, zeroinitializer - %15 = icmp ne <8 x i16> %wide.load23, zeroinitializer - %16 = zext <8 x i1> %8 to <8 x i32> - %17 = zext <8 x i1> %9 to <8 x i32> - %18 = zext <8 x i1> %10 to <8 x i32> - %19 = zext <8 x i1> %11 to <8 x i32> - %20 = zext <8 x i1> %12 to <8 x i32> - %21 = zext <8 x i1> %13 to <8 x i32> - %22 = zext <8 x i1> %14 to <8 x i32> - %23 = zext <8 x i1> %15 to <8 x i32> - %24 = add <8 x i32> %vec.phi, %16 - %25 = add <8 x i32> %vec.phi10, %17 - %26 = add <8 x i32> %vec.phi11, %18 - %27 = add <8 x i32> %vec.phi12, %19 - %28 = add <8 x i32> %vec.phi13, %20 - %29 = add <8 x i32> %vec.phi14, %21 - %30 = add <8 x i32> %vec.phi15, %22 - %31 = add <8 x i32> %vec.phi16, %23 - %index.next = add nuw i64 %index, 64 - %32 = icmp eq i64 %index.next, %n.vec - br i1 %32, label %middle.block, label %vector.body, !llvm.loop !9 - -middle.block: ; preds = %vector.body - %bin.rdx = add <8 x i32> %25, %24 - %bin.rdx24 = add <8 x i32> %26, %bin.rdx - %bin.rdx25 = add <8 x i32> %27, %bin.rdx24 - %bin.rdx26 = add <8 x i32> %28, %bin.rdx25 - %bin.rdx27 = add <8 x i32> %29, %bin.rdx26 - %bin.rdx28 = add <8 x i32> %30, %bin.rdx27 - %bin.rdx29 = add <8 x i32> %31, %bin.rdx28 - %33 = tail call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> %bin.rdx29) - %cmp.n = icmp eq i64 %n.vec, %wide.trip.count - br i1 %cmp.n, label %for.cond.cleanup, label %vec.epilog.iter.check - -vec.epilog.iter.check: ; preds = %middle.block - %n.vec.remaining = and i64 %wide.trip.count, 56 - %min.epilog.iters.check = icmp eq i64 %n.vec.remaining, 0 - br i1 %min.epilog.iters.check, label %for.body.preheader, label %vec.epilog.ph - -vec.epilog.ph: ; preds = %vec.epilog.iter.check, %vector.main.loop.iter.check - %vec.epilog.resume.val = phi i64 [ %n.vec, %vec.epilog.iter.check ], [ 0, %vector.main.loop.iter.check ] - %bc.merge.rdx = phi i32 [ %33, %vec.epilog.iter.check ], [ 0, %vector.main.loop.iter.check ] - %n.vec31 = and i64 %wide.trip.count, 2147483640 - %34 = insertelement <8 x i32> <i32 poison, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>, i32 %bc.merge.rdx, i64 0 - br label %vec.epilog.vector.body - -vec.epilog.vector.body: ; preds = %vec.epilog.vector.body, %vec.epilog.ph - %index32 = phi i64 [ %vec.epilog.resume.val, %vec.epilog.ph ], [ %index.next35, %vec.epilog.vector.body ] - %vec.phi33 = phi <8 x i32> [ %34, %vec.epilog.ph ], [ %38, %vec.epilog.vector.body ] - %35 = getelementptr inbounds nuw i16, ptr %colauths, i64 %index32 - %wide.load34 = load <8 x i16>, ptr %35, align 2, !tbaa !5 - %36 = icmp ne <8 x i16> %wide.load34, zeroinitializer - %37 = zext <8 x i1> %36 to <8 x i32> - %38 = add <8 x i32> %vec.phi33, %37 - %index.next35 = add nuw i64 %index32, 8 - %39 = icmp eq i64 %index.next35, %n.vec31 - br i1 %39, label %vec.epilog.middle.block, label %vec.epilog.vector.body, !llvm.loop !13 - -vec.epilog.middle.block: ; preds = %vec.epilog.vector.body - %40 = tail call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> %38) - %cmp.n36 = icmp eq i64 %n.vec31, %wide.trip.count - br i1 %cmp.n36, label %for.cond.cleanup, label %for.body.preheader - -for.cond.cleanup: ; preds = %for.body, %middle.block, %vec.epilog.middle.block, %entry - %num_cols_needed.0.lcssa = phi i32 [ 0, %entry ], [ %33, %middle.block ], [ %40, %vec.epilog.middle.block ], [ %spec.select, %for.body ] - ret i32 %num_cols_needed.0.lcssa - -for.body: ; preds = %for.body.preheader, %for.body - %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ %indvars.iv.ph, %for.body.preheader ] - %num_cols_needed.06 = phi i32 [ %spec.select, %for.body ], [ %num_cols_needed.06.ph, %for.body.preheader ] - %arrayidx = getelementptr inbounds nuw i16, ptr %colauths, i64 %indvars.iv - %41 = load i16, ptr %arrayidx, align 2, !tbaa !5 - %tobool.not = icmp ne i16 %41, 0 - %inc = zext i1 %tobool.not to i32 - %spec.select = add nuw nsw i32 %num_cols_needed.06, %inc - %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 - %exitcond.not = icmp eq i64 %indvars.iv.next, %wide.trip.count - br i1 %exitcond.not, label %for.cond.cleanup, label %for.body, !llvm.loop !14 +; POWERPC_32: # %bb.0: # %entry +; POWERPC_32-NEXT: li 4, 4 +; POWERPC_32-NEXT: lxvwsx 1, 0, 3 +; POWERPC_32-NEXT: xxlxor 35, 35, 35 +; POWERPC_32-NEXT: lxvwsx 0, 3, 4 +; POWERPC_32-NEXT: xxmrghw 34, 1, 0 +; POWERPC_32-NEXT: vcmpequh 2, 2, 3 +; POWERPC_32-NEXT: xxlnor 34, 34, 34 +; POWERPC_32-NEXT: vmrghh 2, 2, 2 +; POWERPC_32-NEXT: stxv 34, -32(1) +; POWERPC_32-NEXT: lwz 3, -20(1) +; POWERPC_32-NEXT: lwz 4, -24(1) +; POWERPC_32-NEXT: clrlwi 3, 3, 31 +; POWERPC_32-NEXT: rlwimi 3, 4, 1, 30, 30 +; POWERPC_32-NEXT: lwz 4, -28(1) +; POWERPC_32-NEXT: rlwimi 3, 4, 2, 29, 29 +; POWERPC_32-NEXT: lwz 4, -32(1) +; POWERPC_32-NEXT: rlwimi 3, 4, 3, 28, 28 +; POWERPC_32-NEXT: popcntw 3, 3 +; POWERPC_32-NEXT: blr +entry: + %0 = load <4 x i16>, ptr %colauths, align 2, !tbaa !5 + %1 = icmp ne <4 x i16> %0, zeroinitializer + %2 = bitcast <4 x i1> %1 to i4 + %3 = tail call range(i4 0, 5) i4 @llvm.ctpop.i4(i4 %2) + %4 = zext nneg i4 %3 to i32 + ret i32 %4 } +declare i4 @llvm.ctpop.i4(i4) #1 + !5 = !{!6, !6, i64 0} !6 = !{!"short", !7, i64 0} !7 = !{!"omnipotent char", !8, i64 0} !8 = !{!"Simple C/C++ TBAA"} -!9 = distinct !{!9, !10, !11, !12} -!10 = !{!"llvm.loop.mustprogress"} -!11 = !{!"llvm.loop.isvectorized", i32 1} -!12 = !{!"llvm.loop.unroll.runtime.disable"} -!13 = distinct !{!13, !10, !11, !12} -!14 = distinct !{!14, !10, !12, !11} diff --git a/llvm/test/CodeGen/PowerPC/combine-fneg.ll b/llvm/test/CodeGen/PowerPC/combine-fneg.ll index a72abf7..04af094 100644 --- a/llvm/test/CodeGen/PowerPC/combine-fneg.ll +++ b/llvm/test/CodeGen/PowerPC/combine-fneg.ll @@ -6,7 +6,6 @@ define <4 x double> @fneg_fdiv_splat(double %a0, <4 x double> %a1) { ; CHECK-LABEL: fneg_fdiv_splat: ; CHECK: # %bb.0: # %entry ; CHECK-NEXT: addis 3, 2, .LCPI0_0@toc@ha -; CHECK-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; CHECK-NEXT: xxspltd 0, 1, 0 ; CHECK-NEXT: addi 3, 3, .LCPI0_0@toc@l ; CHECK-NEXT: xvredp 1, 0 diff --git a/llvm/test/CodeGen/PowerPC/fp-strict-round.ll b/llvm/test/CodeGen/PowerPC/fp-strict-round.ll index 4519cf4..eac4fb6 100644 --- a/llvm/test/CodeGen/PowerPC/fp-strict-round.ll +++ b/llvm/test/CodeGen/PowerPC/fp-strict-round.ll @@ -229,7 +229,6 @@ define <4 x float> @nearbyint_v4f32(<4 x float> %vf1, <4 x float> %vf2) strictfp ; P8-NEXT: xscvspdpn f1, vs0 ; P8-NEXT: bl nearbyintf ; P8-NEXT: nop -; P8-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; P8-NEXT: xxmrghd vs0, vs1, v30 ; P8-NEXT: xscvspdpn f1, v31 ; P8-NEXT: xvcvdpsp v29, vs0 @@ -240,7 +239,6 @@ define <4 x float> @nearbyint_v4f32(<4 x float> %vf1, <4 x float> %vf2) strictfp ; P8-NEXT: xscvspdpn f1, vs0 ; P8-NEXT: bl nearbyintf ; P8-NEXT: nop -; P8-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; P8-NEXT: xxmrghd vs0, v30, vs1 ; P8-NEXT: li r3, 160 ; P8-NEXT: xvcvdpsp v2, vs0 @@ -278,7 +276,6 @@ define <4 x float> @nearbyint_v4f32(<4 x float> %vf1, <4 x float> %vf2) strictfp ; P9-NEXT: xscvspdpn f1, vs0 ; P9-NEXT: bl nearbyintf ; P9-NEXT: nop -; P9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; P9-NEXT: xxmrghd vs0, vs1, v30 ; P9-NEXT: xscvspdpn f1, v31 ; P9-NEXT: xvcvdpsp v29, vs0 @@ -289,7 +286,6 @@ define <4 x float> @nearbyint_v4f32(<4 x float> %vf1, <4 x float> %vf2) strictfp ; P9-NEXT: xscvspdpn f1, vs0 ; P9-NEXT: bl nearbyintf ; P9-NEXT: nop -; P9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; P9-NEXT: xxmrghd vs0, v30, vs1 ; P9-NEXT: lxv v31, 64(r1) # 16-byte Folded Reload ; P9-NEXT: lxv v30, 48(r1) # 16-byte Folded Reload @@ -330,7 +326,6 @@ define <2 x double> @nearbyint_v2f64(<2 x double> %vf1, <2 x double> %vf2) stric ; P8-NEXT: bl nearbyint ; P8-NEXT: nop ; P8-NEXT: li r3, 144 -; P8-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; P8-NEXT: xxmrghd v2, v30, vs1 ; P8-NEXT: lxvd2x v31, r1, r3 # 16-byte Folded Reload ; P8-NEXT: li r3, 128 @@ -359,7 +354,6 @@ define <2 x double> @nearbyint_v2f64(<2 x double> %vf1, <2 x double> %vf2) stric ; P9-NEXT: xxswapd vs1, v31 ; P9-NEXT: bl nearbyint ; P9-NEXT: nop -; P9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; P9-NEXT: xxmrghd v2, v30, vs1 ; P9-NEXT: lxv v31, 48(r1) # 16-byte Folded Reload ; P9-NEXT: lxv v30, 32(r1) # 16-byte Folded Reload diff --git a/llvm/test/CodeGen/PowerPC/frem.ll b/llvm/test/CodeGen/PowerPC/frem.ll index 21cb206..19b4b1c 100644 --- a/llvm/test/CodeGen/PowerPC/frem.ll +++ b/llvm/test/CodeGen/PowerPC/frem.ll @@ -70,7 +70,6 @@ define <4 x float> @frem4x32(<4 x float> %a, <4 x float> %b) { ; CHECK-NEXT: xscvspdpn 2, 0 ; CHECK-NEXT: bl fmodf ; CHECK-NEXT: nop -; CHECK-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; CHECK-NEXT: xxmrghd 0, 1, 61 ; CHECK-NEXT: xscvspdpn 1, 62 ; CHECK-NEXT: xscvspdpn 2, 63 @@ -84,7 +83,6 @@ define <4 x float> @frem4x32(<4 x float> %a, <4 x float> %b) { ; CHECK-NEXT: xscvspdpn 2, 0 ; CHECK-NEXT: bl fmodf ; CHECK-NEXT: nop -; CHECK-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; CHECK-NEXT: xxmrghd 0, 61, 1 ; CHECK-NEXT: lxv 63, 80(1) # 16-byte Folded Reload ; CHECK-NEXT: lxv 62, 64(1) # 16-byte Folded Reload @@ -126,7 +124,6 @@ define <2 x double> @frem2x64(<2 x double> %a, <2 x double> %b) { ; CHECK-NEXT: xxswapd 2, 63 ; CHECK-NEXT: bl fmod ; CHECK-NEXT: nop -; CHECK-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; CHECK-NEXT: xxmrghd 34, 61, 1 ; CHECK-NEXT: lxv 63, 64(1) # 16-byte Folded Reload ; CHECK-NEXT: lxv 62, 48(1) # 16-byte Folded Reload diff --git a/llvm/test/CodeGen/PowerPC/froundeven-legalization.ll b/llvm/test/CodeGen/PowerPC/froundeven-legalization.ll index 3ae0b02..238e200 100644 --- a/llvm/test/CodeGen/PowerPC/froundeven-legalization.ll +++ b/llvm/test/CodeGen/PowerPC/froundeven-legalization.ll @@ -41,47 +41,39 @@ define void @test(ptr %p1, ptr %p2) nounwind { ; CHECK-NEXT: xxswapd 61, 63 ; CHECK-NEXT: bl roundeven ; CHECK-NEXT: nop -; CHECK-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; CHECK-NEXT: xxswapd 56, 1 ; CHECK-NEXT: xxlor 1, 59, 59 ; CHECK-NEXT: bl roundeven ; CHECK-NEXT: nop -; CHECK-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; CHECK-NEXT: xxswapd 0, 1 ; CHECK-NEXT: xxlor 1, 60, 60 ; CHECK-NEXT: xxmrgld 59, 0, 56 ; CHECK-NEXT: bl roundeven ; CHECK-NEXT: nop -; CHECK-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; CHECK-NEXT: xxswapd 60, 1 ; CHECK-NEXT: xxlor 1, 62, 62 ; CHECK-NEXT: bl roundeven ; CHECK-NEXT: nop -; CHECK-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; CHECK-NEXT: xxswapd 0, 1 ; CHECK-NEXT: xxlor 1, 61, 61 ; CHECK-NEXT: xxmrgld 62, 0, 60 ; CHECK-NEXT: bl roundeven ; CHECK-NEXT: nop -; CHECK-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; CHECK-NEXT: xxswapd 61, 1 ; CHECK-NEXT: xxlor 1, 63, 63 ; CHECK-NEXT: bl roundeven ; CHECK-NEXT: nop -; CHECK-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; CHECK-NEXT: xxswapd 0, 1 ; CHECK-NEXT: xxlor 1, 57, 57 ; CHECK-NEXT: xxmrgld 63, 0, 61 ; CHECK-NEXT: bl roundeven ; CHECK-NEXT: nop -; CHECK-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; CHECK-NEXT: xxswapd 61, 1 ; CHECK-NEXT: xxlor 1, 58, 58 ; CHECK-NEXT: bl roundeven ; CHECK-NEXT: nop ; CHECK-NEXT: li 3, 160 ; CHECK-NEXT: stxvd2x 63, 30, 29 -; CHECK-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; CHECK-NEXT: xxswapd 0, 1 ; CHECK-NEXT: stxvd2x 62, 30, 28 ; CHECK-NEXT: stxvd2x 59, 30, 27 diff --git a/llvm/test/CodeGen/PowerPC/handle-f16-storage-type.ll b/llvm/test/CodeGen/PowerPC/handle-f16-storage-type.ll index b83ac4a..50f05cc 100644 --- a/llvm/test/CodeGen/PowerPC/handle-f16-storage-type.ll +++ b/llvm/test/CodeGen/PowerPC/handle-f16-storage-type.ll @@ -666,7 +666,6 @@ define <4 x float> @test_extend32_vec4(ptr %p) #0 { ; P8-NEXT: bl __extendhfsf2 ; P8-NEXT: nop ; P8-NEXT: li r3, 80 -; P8-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; P8-NEXT: xxmrghd vs0, vs61, vs1 ; P8-NEXT: xxmrghd vs1, vs63, vs62 ; P8-NEXT: ld r30, 96(r1) # 8-byte Folded Reload diff --git a/llvm/test/CodeGen/PowerPC/ldexp.ll b/llvm/test/CodeGen/PowerPC/ldexp.ll index 23748bc..8d7253b 100644 --- a/llvm/test/CodeGen/PowerPC/ldexp.ll +++ b/llvm/test/CodeGen/PowerPC/ldexp.ll @@ -107,7 +107,6 @@ define <4 x float> @ldexp_v4f32(<4 x float> %val, <4 x i32> %exp) nounwind { ; CHECK-NEXT: extsw r4, r3 ; CHECK-NEXT: bl ldexpf ; CHECK-NEXT: nop -; CHECK-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; CHECK-NEXT: xxmrghd vs0, vs1, v29 ; CHECK-NEXT: li r3, 0 ; CHECK-NEXT: vextuwrx r3, r3, v31 @@ -124,7 +123,6 @@ define <4 x float> @ldexp_v4f32(<4 x float> %val, <4 x i32> %exp) nounwind { ; CHECK-NEXT: xscvspdpn f1, vs0 ; CHECK-NEXT: bl ldexpf ; CHECK-NEXT: nop -; CHECK-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; CHECK-NEXT: xxmrghd vs0, vs1, v29 ; CHECK-NEXT: lxv v31, 80(r1) # 16-byte Folded Reload ; CHECK-NEXT: lxv v30, 64(r1) # 16-byte Folded Reload diff --git a/llvm/test/CodeGen/PowerPC/llvm.modf.ll b/llvm/test/CodeGen/PowerPC/llvm.modf.ll index 203b3bd..1b137c7 100644 --- a/llvm/test/CodeGen/PowerPC/llvm.modf.ll +++ b/llvm/test/CodeGen/PowerPC/llvm.modf.ll @@ -294,7 +294,6 @@ define { <2 x double>, <2 x double> } @test_modf_v2f64(<2 x double> %a) { ; CHECK-NEXT: addi r4, r1, 40 ; CHECK-NEXT: bl modf ; CHECK-NEXT: nop -; CHECK-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; CHECK-NEXT: xxmrghd v2, v30, vs1 ; CHECK-NEXT: lfd f0, 32(r1) ; CHECK-NEXT: lfd f1, 40(r1) diff --git a/llvm/test/CodeGen/PowerPC/mtvsrbmi.ll b/llvm/test/CodeGen/PowerPC/mtvsrbmi.ll index 232014d..a9503f7 100644 --- a/llvm/test/CodeGen/PowerPC/mtvsrbmi.ll +++ b/llvm/test/CodeGen/PowerPC/mtvsrbmi.ll @@ -2,22 +2,87 @@ ; Verify whether the generated assembly for the following function includes the mtvsrbmi instruction. ; vector unsigned char v00FF() ; { -; vector unsigned char x = { 0xFF, 0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0 }; -; return x; +; vector unsigned char x = { 0xFF, 0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0 }; +; return x; +; } +; vector unsigned short short00FF() +; { +; vector unsigned short x = { 0xFF, 0,0,0, 0,0,0,0}; +; return x; +; } +; vector unsigned int int00FF() +; { +; vector unsigned int x = { 0xFF, 0,0,0}; +; return x; +; } +; vector unsigned long long longlong00FF() +; { +; vector unsigned long long x = { 0xFF, 0}; +; return x; ; } ; RUN: llc < %s -ppc-asm-full-reg-names -mtriple=powerpc-ibm-aix -mcpu=pwr10 -verify-machineinstrs \ -; RUN: | FileCheck %s --check-prefix=CHECK +; RUN: | FileCheck %s --check-prefixes=CHECK,CHECK-BE + +; RUN: llc < %s -ppc-asm-full-reg-names -mtriple=powerpc64le-unknown-gnu-linux -mcpu=pwr10 -verify-machineinstrs \ +; RUN: | FileCheck %s --check-prefixes=CHECK,CHECK-LE + +; CHECK-NOT: .byte 255 +; CHECK-NOT: .byte 0 define dso_local noundef range(i8 -1, 1) <16 x i8> @_Z5v00FFv() { -; CHECK-NOT: L..CPI0_0: -; CHECK-NOT: .byte 255 # 0xff -; CHECK-NOT: .byte 0 # 0x0 - -; CHECK-LABEL: _Z5v00FFv: -; CHECK: # %bb.0: # %entry -; CHECK-NEXT: mtvsrbmi v2, 1 -; CHECK-NEXT: blr +; CHECK-BE-LABEL: _Z5v00FFv: +; CHECK-BE: # %bb.0: # %entry +; CHECK-BE-NEXT: mtvsrbmi v2, 32768 +; CHECK-BE-NEXT: blr +; +; CHECK-LE-LABEL: _Z5v00FFv: +; CHECK-LE: # %bb.0: # %entry +; CHECK-LE-NEXT: mtvsrbmi v2, 1 +; CHECK-LE-NEXT: blr + entry: ret <16 x i8> <i8 -1, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0> } + +define dso_local noundef range(i16 0, 256) <8 x i16> @_Z9short00FFv() { +; CHECK-BE-LABEL: _Z9short00FFv: +; CHECK-BE: # %bb.0: # %entry +; CHECK-BE-NEXT: mtvsrbmi v2, 16384 +; CHECK-BE-NEXT: blr +; +; CHECK-LE-LABEL: _Z9short00FFv: +; CHECK-LE: # %bb.0: # %entry +; CHECK-LE-NEXT: mtvsrbmi v2, 1 +; CHECK-LE-NEXT: blr +entry: + ret <8 x i16> <i16 255, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0> +} + +define dso_local noundef range(i32 0, 256) <4 x i32> @_Z7int00FFv() { +; CHECK-BE-LABEL: _Z7int00FFv: +; CHECK-BE: # %bb.0: # %entry +; CHECK-BE-NEXT: mtvsrbmi v2, 4096 +; CHECK-BE-NEXT: blr +; +; CHECK-LE-LABEL: _Z7int00FFv: +; CHECK-LE: # %bb.0: # %entry +; CHECK-LE-NEXT: mtvsrbmi v2, 1 +; CHECK-LE-NEXT: blr +entry: + ret <4 x i32> <i32 255, i32 0, i32 0, i32 0> +} + +define dso_local noundef range(i64 0, 256) <2 x i64> @_Z12longlong00FFv() { +; CHECK-BE-LABEL: _Z12longlong00FFv: +; CHECK-BE: # %bb.0: # %entry +; CHECK-BE-NEXT: mtvsrbmi v2, 256 +; CHECK-BE-NEXT: blr +; +; CHECK-LE-LABEL: _Z12longlong00FFv: +; CHECK-LE: # %bb.0: # %entry +; CHECK-LE-NEXT: mtvsrbmi v2, 1 +; CHECK-LE-NEXT: blr +entry: + ret <2 x i64> <i64 255, i64 0> +} diff --git a/llvm/test/CodeGen/PowerPC/vec_insert_elt.ll b/llvm/test/CodeGen/PowerPC/vec_insert_elt.ll index b98aed8..291a9c1 100644 --- a/llvm/test/CodeGen/PowerPC/vec_insert_elt.ll +++ b/llvm/test/CodeGen/PowerPC/vec_insert_elt.ll @@ -940,25 +940,21 @@ entry: define <2 x double> @testDoubleImm1(<2 x double> %a, double %b) { ; CHECK-LABEL: testDoubleImm1: ; CHECK: # %bb.0: # %entry -; CHECK-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; CHECK-NEXT: xxmrghd v2, v2, vs1 ; CHECK-NEXT: blr ; ; CHECK-BE-LABEL: testDoubleImm1: ; CHECK-BE: # %bb.0: # %entry -; CHECK-BE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; CHECK-BE-NEXT: xxpermdi v2, vs1, v2, 1 ; CHECK-BE-NEXT: blr ; ; CHECK-P9-LABEL: testDoubleImm1: ; CHECK-P9: # %bb.0: # %entry -; CHECK-P9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; CHECK-P9-NEXT: xxpermdi v2, vs1, v2, 1 ; CHECK-P9-NEXT: blr ; ; AIX-P8-LABEL: testDoubleImm1: ; AIX-P8: # %bb.0: # %entry -; AIX-P8-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; AIX-P8-NEXT: xxpermdi v2, vs1, v2, 1 ; AIX-P8-NEXT: blr entry: diff --git a/llvm/test/CodeGen/PowerPC/vector-constrained-fp-intrinsics.ll b/llvm/test/CodeGen/PowerPC/vector-constrained-fp-intrinsics.ll index 5dac21b..71c3069 100644 --- a/llvm/test/CodeGen/PowerPC/vector-constrained-fp-intrinsics.ll +++ b/llvm/test/CodeGen/PowerPC/vector-constrained-fp-intrinsics.ll @@ -107,10 +107,6 @@ entry: define <3 x double> @constrained_vector_fdiv_v3f64(<3 x double> %x, <3 x double> %y) #0 { ; PC64LE-LABEL: constrained_vector_fdiv_v3f64: ; PC64LE: # %bb.0: # %entry -; PC64LE-NEXT: # kill: def $f5 killed $f5 def $vsl5 -; PC64LE-NEXT: # kill: def $f4 killed $f4 def $vsl4 -; PC64LE-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 0, 5, 4 ; PC64LE-NEXT: xxmrghd 1, 2, 1 ; PC64LE-NEXT: xsdivdp 3, 3, 6 @@ -120,10 +116,6 @@ define <3 x double> @constrained_vector_fdiv_v3f64(<3 x double> %x, <3 x double> ; ; PC64LE9-LABEL: constrained_vector_fdiv_v3f64: ; PC64LE9: # %bb.0: # %entry -; PC64LE9-NEXT: # kill: def $f5 killed $f5 def $vsl5 -; PC64LE9-NEXT: # kill: def $f4 killed $f4 def $vsl4 -; PC64LE9-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 0, 5, 4 ; PC64LE9-NEXT: xxmrghd 1, 2, 1 ; PC64LE9-NEXT: xsdivdp 3, 3, 6 @@ -217,7 +209,6 @@ define <2 x double> @constrained_vector_frem_v2f64(<2 x double> %x, <2 x double> ; PC64LE-NEXT: bl fmod ; PC64LE-NEXT: nop ; PC64LE-NEXT: li 3, 80 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 34, 61, 1 ; PC64LE-NEXT: lxvd2x 63, 1, 3 # 16-byte Folded Reload ; PC64LE-NEXT: li 3, 64 @@ -248,7 +239,6 @@ define <2 x double> @constrained_vector_frem_v2f64(<2 x double> %x, <2 x double> ; PC64LE9-NEXT: xxswapd 2, 63 ; PC64LE9-NEXT: bl fmod ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 34, 61, 1 ; PC64LE9-NEXT: lxv 63, 64(1) # 16-byte Folded Reload ; PC64LE9-NEXT: lxv 62, 48(1) # 16-byte Folded Reload @@ -400,7 +390,6 @@ define <3 x double> @constrained_vector_frem_v3f64(<3 x double> %x, <3 x double> ; PC64LE-NEXT: fmr 2, 30 ; PC64LE-NEXT: bl fmod ; PC64LE-NEXT: nop -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 63, 1, 63 ; PC64LE-NEXT: fmr 1, 29 ; PC64LE-NEXT: fmr 2, 31 @@ -442,7 +431,6 @@ define <3 x double> @constrained_vector_frem_v3f64(<3 x double> %x, <3 x double> ; PC64LE9-NEXT: fmr 2, 30 ; PC64LE9-NEXT: bl fmod ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 63, 1, 63 ; PC64LE9-NEXT: fmr 1, 29 ; PC64LE9-NEXT: fmr 2, 31 @@ -498,7 +486,6 @@ define <4 x double> @constrained_vector_frem_v4f64(<4 x double> %x, <4 x double> ; PC64LE-NEXT: xxswapd 2, 62 ; PC64LE-NEXT: bl fmod ; PC64LE-NEXT: nop -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 62, 59, 1 ; PC64LE-NEXT: xxlor 1, 61, 61 ; PC64LE-NEXT: xxlor 2, 63, 63 @@ -511,7 +498,6 @@ define <4 x double> @constrained_vector_frem_v4f64(<4 x double> %x, <4 x double> ; PC64LE-NEXT: nop ; PC64LE-NEXT: li 3, 112 ; PC64LE-NEXT: vmr 2, 30 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 35, 60, 1 ; PC64LE-NEXT: lxvd2x 63, 1, 3 # 16-byte Folded Reload ; PC64LE-NEXT: li 3, 96 @@ -550,7 +536,6 @@ define <4 x double> @constrained_vector_frem_v4f64(<4 x double> %x, <4 x double> ; PC64LE9-NEXT: xxswapd 2, 62 ; PC64LE9-NEXT: bl fmod ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 62, 59, 1 ; PC64LE9-NEXT: xscpsgndp 1, 61, 61 ; PC64LE9-NEXT: xscpsgndp 2, 63, 63 @@ -561,7 +546,6 @@ define <4 x double> @constrained_vector_frem_v4f64(<4 x double> %x, <4 x double> ; PC64LE9-NEXT: xxswapd 2, 63 ; PC64LE9-NEXT: bl fmod ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 35, 60, 1 ; PC64LE9-NEXT: vmr 2, 30 ; PC64LE9-NEXT: lxv 63, 96(1) # 16-byte Folded Reload @@ -686,10 +670,6 @@ entry: define <3 x double> @constrained_vector_fmul_v3f64(<3 x double> %x, <3 x double> %y) #0 { ; PC64LE-LABEL: constrained_vector_fmul_v3f64: ; PC64LE: # %bb.0: # %entry -; PC64LE-NEXT: # kill: def $f5 killed $f5 def $vsl5 -; PC64LE-NEXT: # kill: def $f4 killed $f4 def $vsl4 -; PC64LE-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 0, 5, 4 ; PC64LE-NEXT: xxmrghd 1, 2, 1 ; PC64LE-NEXT: xsmuldp 3, 3, 6 @@ -699,10 +679,6 @@ define <3 x double> @constrained_vector_fmul_v3f64(<3 x double> %x, <3 x double> ; ; PC64LE9-LABEL: constrained_vector_fmul_v3f64: ; PC64LE9: # %bb.0: # %entry -; PC64LE9-NEXT: # kill: def $f5 killed $f5 def $vsl5 -; PC64LE9-NEXT: # kill: def $f4 killed $f4 def $vsl4 -; PC64LE9-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 0, 5, 4 ; PC64LE9-NEXT: xxmrghd 1, 2, 1 ; PC64LE9-NEXT: xsmuldp 3, 3, 6 @@ -844,10 +820,6 @@ entry: define <3 x double> @constrained_vector_fadd_v3f64(<3 x double> %x, <3 x double> %y) #0 { ; PC64LE-LABEL: constrained_vector_fadd_v3f64: ; PC64LE: # %bb.0: # %entry -; PC64LE-NEXT: # kill: def $f5 killed $f5 def $vsl5 -; PC64LE-NEXT: # kill: def $f4 killed $f4 def $vsl4 -; PC64LE-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 0, 5, 4 ; PC64LE-NEXT: xxmrghd 1, 2, 1 ; PC64LE-NEXT: xsadddp 3, 3, 6 @@ -857,10 +829,6 @@ define <3 x double> @constrained_vector_fadd_v3f64(<3 x double> %x, <3 x double> ; ; PC64LE9-LABEL: constrained_vector_fadd_v3f64: ; PC64LE9: # %bb.0: # %entry -; PC64LE9-NEXT: # kill: def $f5 killed $f5 def $vsl5 -; PC64LE9-NEXT: # kill: def $f4 killed $f4 def $vsl4 -; PC64LE9-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 0, 5, 4 ; PC64LE9-NEXT: xxmrghd 1, 2, 1 ; PC64LE9-NEXT: xsadddp 3, 3, 6 @@ -1002,10 +970,6 @@ entry: define <3 x double> @constrained_vector_fsub_v3f64(<3 x double> %x, <3 x double> %y) #0 { ; PC64LE-LABEL: constrained_vector_fsub_v3f64: ; PC64LE: # %bb.0: # %entry -; PC64LE-NEXT: # kill: def $f5 killed $f5 def $vsl5 -; PC64LE-NEXT: # kill: def $f4 killed $f4 def $vsl4 -; PC64LE-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 0, 5, 4 ; PC64LE-NEXT: xxmrghd 1, 2, 1 ; PC64LE-NEXT: xssubdp 3, 3, 6 @@ -1015,10 +979,6 @@ define <3 x double> @constrained_vector_fsub_v3f64(<3 x double> %x, <3 x double> ; ; PC64LE9-LABEL: constrained_vector_fsub_v3f64: ; PC64LE9: # %bb.0: # %entry -; PC64LE9-NEXT: # kill: def $f5 killed $f5 def $vsl5 -; PC64LE9-NEXT: # kill: def $f4 killed $f4 def $vsl4 -; PC64LE9-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 0, 5, 4 ; PC64LE9-NEXT: xxmrghd 1, 2, 1 ; PC64LE9-NEXT: xssubdp 3, 3, 6 @@ -1145,8 +1105,6 @@ entry: define <3 x double> @constrained_vector_sqrt_v3f64(<3 x double> %x) #0 { ; PC64LE-LABEL: constrained_vector_sqrt_v3f64: ; PC64LE: # %bb.0: # %entry -; PC64LE-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 0, 2, 1 ; PC64LE-NEXT: xssqrtdp 3, 3 ; PC64LE-NEXT: xvsqrtdp 2, 0 @@ -1155,8 +1113,6 @@ define <3 x double> @constrained_vector_sqrt_v3f64(<3 x double> %x) #0 { ; ; PC64LE9-LABEL: constrained_vector_sqrt_v3f64: ; PC64LE9: # %bb.0: # %entry -; PC64LE9-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 0, 2, 1 ; PC64LE9-NEXT: xssqrtdp 3, 3 ; PC64LE9-NEXT: xvsqrtdp 2, 0 @@ -1247,7 +1203,6 @@ define <2 x double> @constrained_vector_pow_v2f64(<2 x double> %x, <2 x double> ; PC64LE-NEXT: bl pow ; PC64LE-NEXT: nop ; PC64LE-NEXT: li 3, 80 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 34, 61, 1 ; PC64LE-NEXT: lxvd2x 63, 1, 3 # 16-byte Folded Reload ; PC64LE-NEXT: li 3, 64 @@ -1278,7 +1233,6 @@ define <2 x double> @constrained_vector_pow_v2f64(<2 x double> %x, <2 x double> ; PC64LE9-NEXT: xxswapd 2, 63 ; PC64LE9-NEXT: bl pow ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 34, 61, 1 ; PC64LE9-NEXT: lxv 63, 64(1) # 16-byte Folded Reload ; PC64LE9-NEXT: lxv 62, 48(1) # 16-byte Folded Reload @@ -1430,7 +1384,6 @@ define <3 x double> @constrained_vector_pow_v3f64(<3 x double> %x, <3 x double> ; PC64LE-NEXT: fmr 2, 30 ; PC64LE-NEXT: bl pow ; PC64LE-NEXT: nop -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 63, 1, 63 ; PC64LE-NEXT: fmr 1, 29 ; PC64LE-NEXT: fmr 2, 31 @@ -1472,7 +1425,6 @@ define <3 x double> @constrained_vector_pow_v3f64(<3 x double> %x, <3 x double> ; PC64LE9-NEXT: fmr 2, 30 ; PC64LE9-NEXT: bl pow ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 63, 1, 63 ; PC64LE9-NEXT: fmr 1, 29 ; PC64LE9-NEXT: fmr 2, 31 @@ -1528,7 +1480,6 @@ define <4 x double> @constrained_vector_pow_v4f64(<4 x double> %x, <4 x double> ; PC64LE-NEXT: xxswapd 2, 62 ; PC64LE-NEXT: bl pow ; PC64LE-NEXT: nop -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 62, 59, 1 ; PC64LE-NEXT: xxlor 1, 61, 61 ; PC64LE-NEXT: xxlor 2, 63, 63 @@ -1541,7 +1492,6 @@ define <4 x double> @constrained_vector_pow_v4f64(<4 x double> %x, <4 x double> ; PC64LE-NEXT: nop ; PC64LE-NEXT: li 3, 112 ; PC64LE-NEXT: vmr 2, 30 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 35, 60, 1 ; PC64LE-NEXT: lxvd2x 63, 1, 3 # 16-byte Folded Reload ; PC64LE-NEXT: li 3, 96 @@ -1580,7 +1530,6 @@ define <4 x double> @constrained_vector_pow_v4f64(<4 x double> %x, <4 x double> ; PC64LE9-NEXT: xxswapd 2, 62 ; PC64LE9-NEXT: bl pow ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 62, 59, 1 ; PC64LE9-NEXT: xscpsgndp 1, 61, 61 ; PC64LE9-NEXT: xscpsgndp 2, 63, 63 @@ -1591,7 +1540,6 @@ define <4 x double> @constrained_vector_pow_v4f64(<4 x double> %x, <4 x double> ; PC64LE9-NEXT: xxswapd 2, 63 ; PC64LE9-NEXT: bl pow ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 35, 60, 1 ; PC64LE9-NEXT: vmr 2, 30 ; PC64LE9-NEXT: lxv 63, 96(1) # 16-byte Folded Reload @@ -1670,7 +1618,6 @@ define <2 x double> @constrained_vector_powi_v2f64(<2 x double> %x, i32 %y) #0 { ; PC64LE-NEXT: bl __powidf2 ; PC64LE-NEXT: nop ; PC64LE-NEXT: li 3, 64 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 34, 62, 1 ; PC64LE-NEXT: ld 30, 80(1) # 8-byte Folded Reload ; PC64LE-NEXT: lxvd2x 63, 1, 3 # 16-byte Folded Reload @@ -1700,7 +1647,6 @@ define <2 x double> @constrained_vector_powi_v2f64(<2 x double> %x, i32 %y) #0 { ; PC64LE9-NEXT: mr 4, 30 ; PC64LE9-NEXT: bl __powidf2 ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 34, 62, 1 ; PC64LE9-NEXT: lxv 63, 48(1) # 16-byte Folded Reload ; PC64LE9-NEXT: lxv 62, 32(1) # 16-byte Folded Reload @@ -1844,7 +1790,6 @@ define <3 x double> @constrained_vector_powi_v3f64(<3 x double> %x, i32 %y) #0 { ; PC64LE-NEXT: mr 4, 30 ; PC64LE-NEXT: bl __powidf2 ; PC64LE-NEXT: nop -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 63, 1, 63 ; PC64LE-NEXT: fmr 1, 31 ; PC64LE-NEXT: mr 4, 30 @@ -1883,7 +1828,6 @@ define <3 x double> @constrained_vector_powi_v3f64(<3 x double> %x, i32 %y) #0 { ; PC64LE9-NEXT: mr 4, 30 ; PC64LE9-NEXT: bl __powidf2 ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 63, 1, 63 ; PC64LE9-NEXT: fmr 1, 31 ; PC64LE9-NEXT: mr 4, 30 @@ -1934,7 +1878,6 @@ define <4 x double> @constrained_vector_powi_v4f64(<4 x double> %x, i32 %y) #0 { ; PC64LE-NEXT: mr 4, 30 ; PC64LE-NEXT: bl __powidf2 ; PC64LE-NEXT: nop -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 62, 61, 1 ; PC64LE-NEXT: xxlor 1, 63, 63 ; PC64LE-NEXT: mr 4, 30 @@ -1947,7 +1890,6 @@ define <4 x double> @constrained_vector_powi_v4f64(<4 x double> %x, i32 %y) #0 { ; PC64LE-NEXT: nop ; PC64LE-NEXT: li 3, 80 ; PC64LE-NEXT: vmr 2, 30 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 35, 61, 1 ; PC64LE-NEXT: ld 30, 96(1) # 8-byte Folded Reload ; PC64LE-NEXT: lxvd2x 63, 1, 3 # 16-byte Folded Reload @@ -1981,7 +1923,6 @@ define <4 x double> @constrained_vector_powi_v4f64(<4 x double> %x, i32 %y) #0 { ; PC64LE9-NEXT: mr 4, 30 ; PC64LE9-NEXT: bl __powidf2 ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 62, 61, 1 ; PC64LE9-NEXT: xscpsgndp 1, 63, 63 ; PC64LE9-NEXT: mr 4, 30 @@ -1992,7 +1933,6 @@ define <4 x double> @constrained_vector_powi_v4f64(<4 x double> %x, i32 %y) #0 { ; PC64LE9-NEXT: mr 4, 30 ; PC64LE9-NEXT: bl __powidf2 ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 35, 61, 1 ; PC64LE9-NEXT: vmr 2, 30 ; PC64LE9-NEXT: lxv 63, 64(1) # 16-byte Folded Reload @@ -2063,7 +2003,6 @@ define <2 x double> @constrained_vector_sin_v2f64(<2 x double> %x) #0 { ; PC64LE-NEXT: bl sin ; PC64LE-NEXT: nop ; PC64LE-NEXT: li 3, 64 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 34, 62, 1 ; PC64LE-NEXT: lxvd2x 63, 1, 3 # 16-byte Folded Reload ; PC64LE-NEXT: li 3, 48 @@ -2088,7 +2027,6 @@ define <2 x double> @constrained_vector_sin_v2f64(<2 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 63 ; PC64LE9-NEXT: bl sin ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 34, 62, 1 ; PC64LE9-NEXT: lxv 63, 48(1) # 16-byte Folded Reload ; PC64LE9-NEXT: lxv 62, 32(1) # 16-byte Folded Reload @@ -2211,7 +2149,6 @@ define <3 x double> @constrained_vector_sin_v3f64(<3 x double> %x) #0 { ; PC64LE-NEXT: fmr 1, 30 ; PC64LE-NEXT: bl sin ; PC64LE-NEXT: nop -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 63, 1, 63 ; PC64LE-NEXT: fmr 1, 31 ; PC64LE-NEXT: bl sin @@ -2244,7 +2181,6 @@ define <3 x double> @constrained_vector_sin_v3f64(<3 x double> %x) #0 { ; PC64LE9-NEXT: fmr 1, 30 ; PC64LE9-NEXT: bl sin ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 63, 1, 63 ; PC64LE9-NEXT: fmr 1, 31 ; PC64LE9-NEXT: bl sin @@ -2288,7 +2224,6 @@ define <4 x double> @constrained_vector_sin_v4f64(<4 x double> %x) #0 { ; PC64LE-NEXT: xxswapd 1, 62 ; PC64LE-NEXT: bl sin ; PC64LE-NEXT: nop -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 62, 61, 1 ; PC64LE-NEXT: xxlor 1, 63, 63 ; PC64LE-NEXT: bl sin @@ -2299,7 +2234,6 @@ define <4 x double> @constrained_vector_sin_v4f64(<4 x double> %x) #0 { ; PC64LE-NEXT: nop ; PC64LE-NEXT: li 3, 80 ; PC64LE-NEXT: vmr 2, 30 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 35, 61, 1 ; PC64LE-NEXT: lxvd2x 63, 1, 3 # 16-byte Folded Reload ; PC64LE-NEXT: li 3, 64 @@ -2328,7 +2262,6 @@ define <4 x double> @constrained_vector_sin_v4f64(<4 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 62 ; PC64LE9-NEXT: bl sin ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 62, 61, 1 ; PC64LE9-NEXT: xscpsgndp 1, 63, 63 ; PC64LE9-NEXT: bl sin @@ -2337,7 +2270,6 @@ define <4 x double> @constrained_vector_sin_v4f64(<4 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 63 ; PC64LE9-NEXT: bl sin ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 35, 61, 1 ; PC64LE9-NEXT: vmr 2, 30 ; PC64LE9-NEXT: lxv 63, 64(1) # 16-byte Folded Reload @@ -2406,7 +2338,6 @@ define <2 x double> @constrained_vector_cos_v2f64(<2 x double> %x) #0 { ; PC64LE-NEXT: bl cos ; PC64LE-NEXT: nop ; PC64LE-NEXT: li 3, 64 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 34, 62, 1 ; PC64LE-NEXT: lxvd2x 63, 1, 3 # 16-byte Folded Reload ; PC64LE-NEXT: li 3, 48 @@ -2431,7 +2362,6 @@ define <2 x double> @constrained_vector_cos_v2f64(<2 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 63 ; PC64LE9-NEXT: bl cos ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 34, 62, 1 ; PC64LE9-NEXT: lxv 63, 48(1) # 16-byte Folded Reload ; PC64LE9-NEXT: lxv 62, 32(1) # 16-byte Folded Reload @@ -2554,7 +2484,6 @@ define <3 x double> @constrained_vector_cos_v3f64(<3 x double> %x) #0 { ; PC64LE-NEXT: fmr 1, 30 ; PC64LE-NEXT: bl cos ; PC64LE-NEXT: nop -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 63, 1, 63 ; PC64LE-NEXT: fmr 1, 31 ; PC64LE-NEXT: bl cos @@ -2587,7 +2516,6 @@ define <3 x double> @constrained_vector_cos_v3f64(<3 x double> %x) #0 { ; PC64LE9-NEXT: fmr 1, 30 ; PC64LE9-NEXT: bl cos ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 63, 1, 63 ; PC64LE9-NEXT: fmr 1, 31 ; PC64LE9-NEXT: bl cos @@ -2631,7 +2559,6 @@ define <4 x double> @constrained_vector_cos_v4f64(<4 x double> %x) #0 { ; PC64LE-NEXT: xxswapd 1, 62 ; PC64LE-NEXT: bl cos ; PC64LE-NEXT: nop -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 62, 61, 1 ; PC64LE-NEXT: xxlor 1, 63, 63 ; PC64LE-NEXT: bl cos @@ -2642,7 +2569,6 @@ define <4 x double> @constrained_vector_cos_v4f64(<4 x double> %x) #0 { ; PC64LE-NEXT: nop ; PC64LE-NEXT: li 3, 80 ; PC64LE-NEXT: vmr 2, 30 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 35, 61, 1 ; PC64LE-NEXT: lxvd2x 63, 1, 3 # 16-byte Folded Reload ; PC64LE-NEXT: li 3, 64 @@ -2671,7 +2597,6 @@ define <4 x double> @constrained_vector_cos_v4f64(<4 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 62 ; PC64LE9-NEXT: bl cos ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 62, 61, 1 ; PC64LE9-NEXT: xscpsgndp 1, 63, 63 ; PC64LE9-NEXT: bl cos @@ -2680,7 +2605,6 @@ define <4 x double> @constrained_vector_cos_v4f64(<4 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 63 ; PC64LE9-NEXT: bl cos ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 35, 61, 1 ; PC64LE9-NEXT: vmr 2, 30 ; PC64LE9-NEXT: lxv 63, 64(1) # 16-byte Folded Reload @@ -2749,7 +2673,6 @@ define <2 x double> @constrained_vector_exp_v2f64(<2 x double> %x) #0 { ; PC64LE-NEXT: bl exp ; PC64LE-NEXT: nop ; PC64LE-NEXT: li 3, 64 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 34, 62, 1 ; PC64LE-NEXT: lxvd2x 63, 1, 3 # 16-byte Folded Reload ; PC64LE-NEXT: li 3, 48 @@ -2774,7 +2697,6 @@ define <2 x double> @constrained_vector_exp_v2f64(<2 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 63 ; PC64LE9-NEXT: bl exp ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 34, 62, 1 ; PC64LE9-NEXT: lxv 63, 48(1) # 16-byte Folded Reload ; PC64LE9-NEXT: lxv 62, 32(1) # 16-byte Folded Reload @@ -2897,7 +2819,6 @@ define <3 x double> @constrained_vector_exp_v3f64(<3 x double> %x) #0 { ; PC64LE-NEXT: fmr 1, 30 ; PC64LE-NEXT: bl exp ; PC64LE-NEXT: nop -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 63, 1, 63 ; PC64LE-NEXT: fmr 1, 31 ; PC64LE-NEXT: bl exp @@ -2930,7 +2851,6 @@ define <3 x double> @constrained_vector_exp_v3f64(<3 x double> %x) #0 { ; PC64LE9-NEXT: fmr 1, 30 ; PC64LE9-NEXT: bl exp ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 63, 1, 63 ; PC64LE9-NEXT: fmr 1, 31 ; PC64LE9-NEXT: bl exp @@ -2974,7 +2894,6 @@ define <4 x double> @constrained_vector_exp_v4f64(<4 x double> %x) #0 { ; PC64LE-NEXT: xxswapd 1, 62 ; PC64LE-NEXT: bl exp ; PC64LE-NEXT: nop -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 62, 61, 1 ; PC64LE-NEXT: xxlor 1, 63, 63 ; PC64LE-NEXT: bl exp @@ -2985,7 +2904,6 @@ define <4 x double> @constrained_vector_exp_v4f64(<4 x double> %x) #0 { ; PC64LE-NEXT: nop ; PC64LE-NEXT: li 3, 80 ; PC64LE-NEXT: vmr 2, 30 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 35, 61, 1 ; PC64LE-NEXT: lxvd2x 63, 1, 3 # 16-byte Folded Reload ; PC64LE-NEXT: li 3, 64 @@ -3014,7 +2932,6 @@ define <4 x double> @constrained_vector_exp_v4f64(<4 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 62 ; PC64LE9-NEXT: bl exp ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 62, 61, 1 ; PC64LE9-NEXT: xscpsgndp 1, 63, 63 ; PC64LE9-NEXT: bl exp @@ -3023,7 +2940,6 @@ define <4 x double> @constrained_vector_exp_v4f64(<4 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 63 ; PC64LE9-NEXT: bl exp ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 35, 61, 1 ; PC64LE9-NEXT: vmr 2, 30 ; PC64LE9-NEXT: lxv 63, 64(1) # 16-byte Folded Reload @@ -3092,7 +3008,6 @@ define <2 x double> @constrained_vector_exp2_v2f64(<2 x double> %x) #0 { ; PC64LE-NEXT: bl exp2 ; PC64LE-NEXT: nop ; PC64LE-NEXT: li 3, 64 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 34, 62, 1 ; PC64LE-NEXT: lxvd2x 63, 1, 3 # 16-byte Folded Reload ; PC64LE-NEXT: li 3, 48 @@ -3117,7 +3032,6 @@ define <2 x double> @constrained_vector_exp2_v2f64(<2 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 63 ; PC64LE9-NEXT: bl exp2 ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 34, 62, 1 ; PC64LE9-NEXT: lxv 63, 48(1) # 16-byte Folded Reload ; PC64LE9-NEXT: lxv 62, 32(1) # 16-byte Folded Reload @@ -3240,7 +3154,6 @@ define <3 x double> @constrained_vector_exp2_v3f64(<3 x double> %x) #0 { ; PC64LE-NEXT: fmr 1, 30 ; PC64LE-NEXT: bl exp2 ; PC64LE-NEXT: nop -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 63, 1, 63 ; PC64LE-NEXT: fmr 1, 31 ; PC64LE-NEXT: bl exp2 @@ -3273,7 +3186,6 @@ define <3 x double> @constrained_vector_exp2_v3f64(<3 x double> %x) #0 { ; PC64LE9-NEXT: fmr 1, 30 ; PC64LE9-NEXT: bl exp2 ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 63, 1, 63 ; PC64LE9-NEXT: fmr 1, 31 ; PC64LE9-NEXT: bl exp2 @@ -3317,7 +3229,6 @@ define <4 x double> @constrained_vector_exp2_v4f64(<4 x double> %x) #0 { ; PC64LE-NEXT: xxswapd 1, 62 ; PC64LE-NEXT: bl exp2 ; PC64LE-NEXT: nop -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 62, 61, 1 ; PC64LE-NEXT: xxlor 1, 63, 63 ; PC64LE-NEXT: bl exp2 @@ -3328,7 +3239,6 @@ define <4 x double> @constrained_vector_exp2_v4f64(<4 x double> %x) #0 { ; PC64LE-NEXT: nop ; PC64LE-NEXT: li 3, 80 ; PC64LE-NEXT: vmr 2, 30 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 35, 61, 1 ; PC64LE-NEXT: lxvd2x 63, 1, 3 # 16-byte Folded Reload ; PC64LE-NEXT: li 3, 64 @@ -3357,7 +3267,6 @@ define <4 x double> @constrained_vector_exp2_v4f64(<4 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 62 ; PC64LE9-NEXT: bl exp2 ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 62, 61, 1 ; PC64LE9-NEXT: xscpsgndp 1, 63, 63 ; PC64LE9-NEXT: bl exp2 @@ -3366,7 +3275,6 @@ define <4 x double> @constrained_vector_exp2_v4f64(<4 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 63 ; PC64LE9-NEXT: bl exp2 ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 35, 61, 1 ; PC64LE9-NEXT: vmr 2, 30 ; PC64LE9-NEXT: lxv 63, 64(1) # 16-byte Folded Reload @@ -3435,7 +3343,6 @@ define <2 x double> @constrained_vector_log_v2f64(<2 x double> %x) #0 { ; PC64LE-NEXT: bl log ; PC64LE-NEXT: nop ; PC64LE-NEXT: li 3, 64 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 34, 62, 1 ; PC64LE-NEXT: lxvd2x 63, 1, 3 # 16-byte Folded Reload ; PC64LE-NEXT: li 3, 48 @@ -3460,7 +3367,6 @@ define <2 x double> @constrained_vector_log_v2f64(<2 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 63 ; PC64LE9-NEXT: bl log ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 34, 62, 1 ; PC64LE9-NEXT: lxv 63, 48(1) # 16-byte Folded Reload ; PC64LE9-NEXT: lxv 62, 32(1) # 16-byte Folded Reload @@ -3583,7 +3489,6 @@ define <3 x double> @constrained_vector_log_v3f64(<3 x double> %x) #0 { ; PC64LE-NEXT: fmr 1, 30 ; PC64LE-NEXT: bl log ; PC64LE-NEXT: nop -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 63, 1, 63 ; PC64LE-NEXT: fmr 1, 31 ; PC64LE-NEXT: bl log @@ -3616,7 +3521,6 @@ define <3 x double> @constrained_vector_log_v3f64(<3 x double> %x) #0 { ; PC64LE9-NEXT: fmr 1, 30 ; PC64LE9-NEXT: bl log ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 63, 1, 63 ; PC64LE9-NEXT: fmr 1, 31 ; PC64LE9-NEXT: bl log @@ -3660,7 +3564,6 @@ define <4 x double> @constrained_vector_log_v4f64(<4 x double> %x) #0 { ; PC64LE-NEXT: xxswapd 1, 62 ; PC64LE-NEXT: bl log ; PC64LE-NEXT: nop -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 62, 61, 1 ; PC64LE-NEXT: xxlor 1, 63, 63 ; PC64LE-NEXT: bl log @@ -3671,7 +3574,6 @@ define <4 x double> @constrained_vector_log_v4f64(<4 x double> %x) #0 { ; PC64LE-NEXT: nop ; PC64LE-NEXT: li 3, 80 ; PC64LE-NEXT: vmr 2, 30 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 35, 61, 1 ; PC64LE-NEXT: lxvd2x 63, 1, 3 # 16-byte Folded Reload ; PC64LE-NEXT: li 3, 64 @@ -3700,7 +3602,6 @@ define <4 x double> @constrained_vector_log_v4f64(<4 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 62 ; PC64LE9-NEXT: bl log ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 62, 61, 1 ; PC64LE9-NEXT: xscpsgndp 1, 63, 63 ; PC64LE9-NEXT: bl log @@ -3709,7 +3610,6 @@ define <4 x double> @constrained_vector_log_v4f64(<4 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 63 ; PC64LE9-NEXT: bl log ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 35, 61, 1 ; PC64LE9-NEXT: vmr 2, 30 ; PC64LE9-NEXT: lxv 63, 64(1) # 16-byte Folded Reload @@ -3778,7 +3678,6 @@ define <2 x double> @constrained_vector_log10_v2f64(<2 x double> %x) #0 { ; PC64LE-NEXT: bl log10 ; PC64LE-NEXT: nop ; PC64LE-NEXT: li 3, 64 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 34, 62, 1 ; PC64LE-NEXT: lxvd2x 63, 1, 3 # 16-byte Folded Reload ; PC64LE-NEXT: li 3, 48 @@ -3803,7 +3702,6 @@ define <2 x double> @constrained_vector_log10_v2f64(<2 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 63 ; PC64LE9-NEXT: bl log10 ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 34, 62, 1 ; PC64LE9-NEXT: lxv 63, 48(1) # 16-byte Folded Reload ; PC64LE9-NEXT: lxv 62, 32(1) # 16-byte Folded Reload @@ -3926,7 +3824,6 @@ define <3 x double> @constrained_vector_log10_v3f64(<3 x double> %x) #0 { ; PC64LE-NEXT: fmr 1, 30 ; PC64LE-NEXT: bl log10 ; PC64LE-NEXT: nop -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 63, 1, 63 ; PC64LE-NEXT: fmr 1, 31 ; PC64LE-NEXT: bl log10 @@ -3959,7 +3856,6 @@ define <3 x double> @constrained_vector_log10_v3f64(<3 x double> %x) #0 { ; PC64LE9-NEXT: fmr 1, 30 ; PC64LE9-NEXT: bl log10 ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 63, 1, 63 ; PC64LE9-NEXT: fmr 1, 31 ; PC64LE9-NEXT: bl log10 @@ -4003,7 +3899,6 @@ define <4 x double> @constrained_vector_log10_v4f64(<4 x double> %x) #0 { ; PC64LE-NEXT: xxswapd 1, 62 ; PC64LE-NEXT: bl log10 ; PC64LE-NEXT: nop -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 62, 61, 1 ; PC64LE-NEXT: xxlor 1, 63, 63 ; PC64LE-NEXT: bl log10 @@ -4014,7 +3909,6 @@ define <4 x double> @constrained_vector_log10_v4f64(<4 x double> %x) #0 { ; PC64LE-NEXT: nop ; PC64LE-NEXT: li 3, 80 ; PC64LE-NEXT: vmr 2, 30 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 35, 61, 1 ; PC64LE-NEXT: lxvd2x 63, 1, 3 # 16-byte Folded Reload ; PC64LE-NEXT: li 3, 64 @@ -4043,7 +3937,6 @@ define <4 x double> @constrained_vector_log10_v4f64(<4 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 62 ; PC64LE9-NEXT: bl log10 ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 62, 61, 1 ; PC64LE9-NEXT: xscpsgndp 1, 63, 63 ; PC64LE9-NEXT: bl log10 @@ -4052,7 +3945,6 @@ define <4 x double> @constrained_vector_log10_v4f64(<4 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 63 ; PC64LE9-NEXT: bl log10 ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 35, 61, 1 ; PC64LE9-NEXT: vmr 2, 30 ; PC64LE9-NEXT: lxv 63, 64(1) # 16-byte Folded Reload @@ -4121,7 +4013,6 @@ define <2 x double> @constrained_vector_log2_v2f64(<2 x double> %x) #0 { ; PC64LE-NEXT: bl log2 ; PC64LE-NEXT: nop ; PC64LE-NEXT: li 3, 64 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 34, 62, 1 ; PC64LE-NEXT: lxvd2x 63, 1, 3 # 16-byte Folded Reload ; PC64LE-NEXT: li 3, 48 @@ -4146,7 +4037,6 @@ define <2 x double> @constrained_vector_log2_v2f64(<2 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 63 ; PC64LE9-NEXT: bl log2 ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 34, 62, 1 ; PC64LE9-NEXT: lxv 63, 48(1) # 16-byte Folded Reload ; PC64LE9-NEXT: lxv 62, 32(1) # 16-byte Folded Reload @@ -4269,7 +4159,6 @@ define <3 x double> @constrained_vector_log2_v3f64(<3 x double> %x) #0 { ; PC64LE-NEXT: fmr 1, 30 ; PC64LE-NEXT: bl log2 ; PC64LE-NEXT: nop -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 63, 1, 63 ; PC64LE-NEXT: fmr 1, 31 ; PC64LE-NEXT: bl log2 @@ -4302,7 +4191,6 @@ define <3 x double> @constrained_vector_log2_v3f64(<3 x double> %x) #0 { ; PC64LE9-NEXT: fmr 1, 30 ; PC64LE9-NEXT: bl log2 ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 63, 1, 63 ; PC64LE9-NEXT: fmr 1, 31 ; PC64LE9-NEXT: bl log2 @@ -4346,7 +4234,6 @@ define <4 x double> @constrained_vector_log2_v4f64(<4 x double> %x) #0 { ; PC64LE-NEXT: xxswapd 1, 62 ; PC64LE-NEXT: bl log2 ; PC64LE-NEXT: nop -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 62, 61, 1 ; PC64LE-NEXT: xxlor 1, 63, 63 ; PC64LE-NEXT: bl log2 @@ -4357,7 +4244,6 @@ define <4 x double> @constrained_vector_log2_v4f64(<4 x double> %x) #0 { ; PC64LE-NEXT: nop ; PC64LE-NEXT: li 3, 80 ; PC64LE-NEXT: vmr 2, 30 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 35, 61, 1 ; PC64LE-NEXT: lxvd2x 63, 1, 3 # 16-byte Folded Reload ; PC64LE-NEXT: li 3, 64 @@ -4386,7 +4272,6 @@ define <4 x double> @constrained_vector_log2_v4f64(<4 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 62 ; PC64LE9-NEXT: bl log2 ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 62, 61, 1 ; PC64LE9-NEXT: xscpsgndp 1, 63, 63 ; PC64LE9-NEXT: bl log2 @@ -4395,7 +4280,6 @@ define <4 x double> @constrained_vector_log2_v4f64(<4 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 63 ; PC64LE9-NEXT: bl log2 ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 35, 61, 1 ; PC64LE9-NEXT: vmr 2, 30 ; PC64LE9-NEXT: lxv 63, 64(1) # 16-byte Folded Reload @@ -4503,8 +4387,6 @@ define <3 x float> @constrained_vector_rint_v3f32(<3 x float> %x) #0 { define <3 x double> @constrained_vector_rint_v3f64(<3 x double> %x) #0 { ; PC64LE-LABEL: constrained_vector_rint_v3f64: ; PC64LE: # %bb.0: # %entry -; PC64LE-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 0, 2, 1 ; PC64LE-NEXT: xsrdpic 3, 3 ; PC64LE-NEXT: xvrdpic 2, 0 @@ -4513,8 +4395,6 @@ define <3 x double> @constrained_vector_rint_v3f64(<3 x double> %x) #0 { ; ; PC64LE9-LABEL: constrained_vector_rint_v3f64: ; PC64LE9: # %bb.0: # %entry -; PC64LE9-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 0, 2, 1 ; PC64LE9-NEXT: xsrdpic 3, 3 ; PC64LE9-NEXT: xvrdpic 2, 0 @@ -4599,7 +4479,6 @@ define <2 x double> @constrained_vector_nearbyint_v2f64(<2 x double> %x) #0 { ; PC64LE-NEXT: bl nearbyint ; PC64LE-NEXT: nop ; PC64LE-NEXT: li 3, 64 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 34, 62, 1 ; PC64LE-NEXT: lxvd2x 63, 1, 3 # 16-byte Folded Reload ; PC64LE-NEXT: li 3, 48 @@ -4624,7 +4503,6 @@ define <2 x double> @constrained_vector_nearbyint_v2f64(<2 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 63 ; PC64LE9-NEXT: bl nearbyint ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 34, 62, 1 ; PC64LE9-NEXT: lxv 63, 48(1) # 16-byte Folded Reload ; PC64LE9-NEXT: lxv 62, 32(1) # 16-byte Folded Reload @@ -4747,7 +4625,6 @@ define <3 x double> @constrained_vector_nearby_v3f64(<3 x double> %x) #0 { ; PC64LE-NEXT: fmr 1, 30 ; PC64LE-NEXT: bl nearbyint ; PC64LE-NEXT: nop -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 63, 1, 63 ; PC64LE-NEXT: fmr 1, 31 ; PC64LE-NEXT: bl nearbyint @@ -4780,7 +4657,6 @@ define <3 x double> @constrained_vector_nearby_v3f64(<3 x double> %x) #0 { ; PC64LE9-NEXT: fmr 1, 30 ; PC64LE9-NEXT: bl nearbyint ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 63, 1, 63 ; PC64LE9-NEXT: fmr 1, 31 ; PC64LE9-NEXT: bl nearbyint @@ -4824,7 +4700,6 @@ define <4 x double> @constrained_vector_nearbyint_v4f64(<4 x double> %x) #0 { ; PC64LE-NEXT: xxswapd 1, 62 ; PC64LE-NEXT: bl nearbyint ; PC64LE-NEXT: nop -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 62, 61, 1 ; PC64LE-NEXT: xxlor 1, 63, 63 ; PC64LE-NEXT: bl nearbyint @@ -4835,7 +4710,6 @@ define <4 x double> @constrained_vector_nearbyint_v4f64(<4 x double> %x) #0 { ; PC64LE-NEXT: nop ; PC64LE-NEXT: li 3, 80 ; PC64LE-NEXT: vmr 2, 30 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 35, 61, 1 ; PC64LE-NEXT: lxvd2x 63, 1, 3 # 16-byte Folded Reload ; PC64LE-NEXT: li 3, 64 @@ -4864,7 +4738,6 @@ define <4 x double> @constrained_vector_nearbyint_v4f64(<4 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 62 ; PC64LE9-NEXT: bl nearbyint ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 62, 61, 1 ; PC64LE9-NEXT: xscpsgndp 1, 63, 63 ; PC64LE9-NEXT: bl nearbyint @@ -4873,7 +4746,6 @@ define <4 x double> @constrained_vector_nearbyint_v4f64(<4 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 63 ; PC64LE9-NEXT: bl nearbyint ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 35, 61, 1 ; PC64LE9-NEXT: vmr 2, 30 ; PC64LE9-NEXT: lxv 63, 64(1) # 16-byte Folded Reload @@ -5055,10 +4927,6 @@ define <3 x double> @constrained_vector_max_v3f64(<3 x double> %x, <3 x double> ; PC64LE-NEXT: mflr 0 ; PC64LE-NEXT: stdu 1, -64(1) ; PC64LE-NEXT: li 3, 48 -; PC64LE-NEXT: # kill: def $f5 killed $f5 def $vsl5 -; PC64LE-NEXT: # kill: def $f4 killed $f4 def $vsl4 -; PC64LE-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 0, 5, 4 ; PC64LE-NEXT: xxmrghd 1, 2, 1 ; PC64LE-NEXT: std 0, 80(1) @@ -5082,10 +4950,6 @@ define <3 x double> @constrained_vector_max_v3f64(<3 x double> %x, <3 x double> ; PC64LE9: # %bb.0: # %entry ; PC64LE9-NEXT: mflr 0 ; PC64LE9-NEXT: stdu 1, -48(1) -; PC64LE9-NEXT: # kill: def $f5 killed $f5 def $vsl5 -; PC64LE9-NEXT: # kill: def $f4 killed $f4 def $vsl4 -; PC64LE9-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 0, 5, 4 ; PC64LE9-NEXT: xxmrghd 1, 2, 1 ; PC64LE9-NEXT: std 0, 64(1) @@ -5295,10 +5159,6 @@ define <3 x double> @constrained_vector_min_v3f64(<3 x double> %x, <3 x double> ; PC64LE-NEXT: mflr 0 ; PC64LE-NEXT: stdu 1, -64(1) ; PC64LE-NEXT: li 3, 48 -; PC64LE-NEXT: # kill: def $f5 killed $f5 def $vsl5 -; PC64LE-NEXT: # kill: def $f4 killed $f4 def $vsl4 -; PC64LE-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 0, 5, 4 ; PC64LE-NEXT: xxmrghd 1, 2, 1 ; PC64LE-NEXT: std 0, 80(1) @@ -5322,10 +5182,6 @@ define <3 x double> @constrained_vector_min_v3f64(<3 x double> %x, <3 x double> ; PC64LE9: # %bb.0: # %entry ; PC64LE9-NEXT: mflr 0 ; PC64LE9-NEXT: stdu 1, -48(1) -; PC64LE9-NEXT: # kill: def $f5 killed $f5 def $vsl5 -; PC64LE9-NEXT: # kill: def $f4 killed $f4 def $vsl4 -; PC64LE9-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 0, 5, 4 ; PC64LE9-NEXT: xxmrghd 1, 2, 1 ; PC64LE9-NEXT: std 0, 64(1) @@ -6664,8 +6520,6 @@ entry: define <3 x double> @constrained_vector_ceil_v3f64(<3 x double> %x) #0 { ; PC64LE-LABEL: constrained_vector_ceil_v3f64: ; PC64LE: # %bb.0: # %entry -; PC64LE-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 0, 2, 1 ; PC64LE-NEXT: xsrdpip 3, 3 ; PC64LE-NEXT: xvrdpip 2, 0 @@ -6674,8 +6528,6 @@ define <3 x double> @constrained_vector_ceil_v3f64(<3 x double> %x) #0 { ; ; PC64LE9-LABEL: constrained_vector_ceil_v3f64: ; PC64LE9: # %bb.0: # %entry -; PC64LE9-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 0, 2, 1 ; PC64LE9-NEXT: xsrdpip 3, 3 ; PC64LE9-NEXT: xvrdpip 2, 0 @@ -6776,8 +6628,6 @@ entry: define <3 x double> @constrained_vector_floor_v3f64(<3 x double> %x) #0 { ; PC64LE-LABEL: constrained_vector_floor_v3f64: ; PC64LE: # %bb.0: # %entry -; PC64LE-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 0, 2, 1 ; PC64LE-NEXT: xsrdpim 3, 3 ; PC64LE-NEXT: xvrdpim 2, 0 @@ -6786,8 +6636,6 @@ define <3 x double> @constrained_vector_floor_v3f64(<3 x double> %x) #0 { ; ; PC64LE9-LABEL: constrained_vector_floor_v3f64: ; PC64LE9: # %bb.0: # %entry -; PC64LE9-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 0, 2, 1 ; PC64LE9-NEXT: xsrdpim 3, 3 ; PC64LE9-NEXT: xvrdpim 2, 0 @@ -6888,8 +6736,6 @@ entry: define <3 x double> @constrained_vector_round_v3f64(<3 x double> %x) #0 { ; PC64LE-LABEL: constrained_vector_round_v3f64: ; PC64LE: # %bb.0: # %entry -; PC64LE-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 0, 2, 1 ; PC64LE-NEXT: xsrdpi 3, 3 ; PC64LE-NEXT: xvrdpi 2, 0 @@ -6898,8 +6744,6 @@ define <3 x double> @constrained_vector_round_v3f64(<3 x double> %x) #0 { ; ; PC64LE9-LABEL: constrained_vector_round_v3f64: ; PC64LE9: # %bb.0: # %entry -; PC64LE9-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 0, 2, 1 ; PC64LE9-NEXT: xsrdpi 3, 3 ; PC64LE9-NEXT: xvrdpi 2, 0 @@ -6999,8 +6843,6 @@ entry: define <3 x double> @constrained_vector_trunc_v3f64(<3 x double> %x) #0 { ; PC64LE-LABEL: constrained_vector_trunc_v3f64: ; PC64LE: # %bb.0: # %entry -; PC64LE-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 0, 2, 1 ; PC64LE-NEXT: xsrdpiz 3, 3 ; PC64LE-NEXT: xvrdpiz 2, 0 @@ -7009,8 +6851,6 @@ define <3 x double> @constrained_vector_trunc_v3f64(<3 x double> %x) #0 { ; ; PC64LE9-LABEL: constrained_vector_trunc_v3f64: ; PC64LE9: # %bb.0: # %entry -; PC64LE9-NEXT: # kill: def $f2 killed $f2 def $vsl2 -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 0, 2, 1 ; PC64LE9-NEXT: xsrdpiz 3, 3 ; PC64LE9-NEXT: xvrdpiz 2, 0 @@ -8209,7 +8049,6 @@ define <2 x double> @constrained_vector_tan_v2f64(<2 x double> %x) #0 { ; PC64LE-NEXT: bl tan ; PC64LE-NEXT: nop ; PC64LE-NEXT: li 3, 64 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 34, 62, 1 ; PC64LE-NEXT: lxvd2x 63, 1, 3 # 16-byte Folded Reload ; PC64LE-NEXT: li 3, 48 @@ -8234,7 +8073,6 @@ define <2 x double> @constrained_vector_tan_v2f64(<2 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 63 ; PC64LE9-NEXT: bl tan ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 34, 62, 1 ; PC64LE9-NEXT: lxv 63, 48(1) # 16-byte Folded Reload ; PC64LE9-NEXT: lxv 62, 32(1) # 16-byte Folded Reload @@ -8357,7 +8195,6 @@ define <3 x double> @constrained_vector_tan_v3f64(<3 x double> %x) #0 { ; PC64LE-NEXT: fmr 1, 30 ; PC64LE-NEXT: bl tan ; PC64LE-NEXT: nop -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 63, 1, 63 ; PC64LE-NEXT: fmr 1, 31 ; PC64LE-NEXT: bl tan @@ -8390,7 +8227,6 @@ define <3 x double> @constrained_vector_tan_v3f64(<3 x double> %x) #0 { ; PC64LE9-NEXT: fmr 1, 30 ; PC64LE9-NEXT: bl tan ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 63, 1, 63 ; PC64LE9-NEXT: fmr 1, 31 ; PC64LE9-NEXT: bl tan @@ -8434,7 +8270,6 @@ define <4 x double> @constrained_vector_tan_v4f64(<4 x double> %x) #0 { ; PC64LE-NEXT: xxswapd 1, 62 ; PC64LE-NEXT: bl tan ; PC64LE-NEXT: nop -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 62, 61, 1 ; PC64LE-NEXT: xxlor 1, 63, 63 ; PC64LE-NEXT: bl tan @@ -8445,7 +8280,6 @@ define <4 x double> @constrained_vector_tan_v4f64(<4 x double> %x) #0 { ; PC64LE-NEXT: nop ; PC64LE-NEXT: li 3, 80 ; PC64LE-NEXT: vmr 2, 30 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 35, 61, 1 ; PC64LE-NEXT: lxvd2x 63, 1, 3 # 16-byte Folded Reload ; PC64LE-NEXT: li 3, 64 @@ -8474,7 +8308,6 @@ define <4 x double> @constrained_vector_tan_v4f64(<4 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 62 ; PC64LE9-NEXT: bl tan ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 62, 61, 1 ; PC64LE9-NEXT: xscpsgndp 1, 63, 63 ; PC64LE9-NEXT: bl tan @@ -8483,7 +8316,6 @@ define <4 x double> @constrained_vector_tan_v4f64(<4 x double> %x) #0 { ; PC64LE9-NEXT: xxswapd 1, 63 ; PC64LE9-NEXT: bl tan ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 35, 61, 1 ; PC64LE9-NEXT: vmr 2, 30 ; PC64LE9-NEXT: lxv 63, 64(1) # 16-byte Folded Reload @@ -8558,7 +8390,6 @@ define <2 x double> @constrained_vector_atan2_v2f64(<2 x double> %x, <2 x double ; PC64LE-NEXT: bl atan2 ; PC64LE-NEXT: nop ; PC64LE-NEXT: li 3, 80 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 34, 61, 1 ; PC64LE-NEXT: lxvd2x 63, 1, 3 # 16-byte Folded Reload ; PC64LE-NEXT: li 3, 64 @@ -8589,7 +8420,6 @@ define <2 x double> @constrained_vector_atan2_v2f64(<2 x double> %x, <2 x double ; PC64LE9-NEXT: xxswapd 2, 63 ; PC64LE9-NEXT: bl atan2 ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 34, 61, 1 ; PC64LE9-NEXT: lxv 63, 64(1) # 16-byte Folded Reload ; PC64LE9-NEXT: lxv 62, 48(1) # 16-byte Folded Reload @@ -8741,7 +8571,6 @@ define <3 x double> @constrained_vector_atan2_v3f64(<3 x double> %x, <3 x double ; PC64LE-NEXT: fmr 2, 30 ; PC64LE-NEXT: bl atan2 ; PC64LE-NEXT: nop -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 63, 1, 63 ; PC64LE-NEXT: fmr 1, 29 ; PC64LE-NEXT: fmr 2, 31 @@ -8783,7 +8612,6 @@ define <3 x double> @constrained_vector_atan2_v3f64(<3 x double> %x, <3 x double ; PC64LE9-NEXT: fmr 2, 30 ; PC64LE9-NEXT: bl atan2 ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 63, 1, 63 ; PC64LE9-NEXT: fmr 1, 29 ; PC64LE9-NEXT: fmr 2, 31 @@ -8839,7 +8667,6 @@ define <4 x double> @constrained_vector_atan2_v4f64(<4 x double> %x, <4 x double ; PC64LE-NEXT: xxswapd 2, 62 ; PC64LE-NEXT: bl atan2 ; PC64LE-NEXT: nop -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 62, 59, 1 ; PC64LE-NEXT: xxlor 1, 61, 61 ; PC64LE-NEXT: xxlor 2, 63, 63 @@ -8852,7 +8679,6 @@ define <4 x double> @constrained_vector_atan2_v4f64(<4 x double> %x, <4 x double ; PC64LE-NEXT: nop ; PC64LE-NEXT: li 3, 112 ; PC64LE-NEXT: vmr 2, 30 -; PC64LE-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE-NEXT: xxmrghd 35, 60, 1 ; PC64LE-NEXT: lxvd2x 63, 1, 3 # 16-byte Folded Reload ; PC64LE-NEXT: li 3, 96 @@ -8891,7 +8717,6 @@ define <4 x double> @constrained_vector_atan2_v4f64(<4 x double> %x, <4 x double ; PC64LE9-NEXT: xxswapd 2, 62 ; PC64LE9-NEXT: bl atan2 ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 62, 59, 1 ; PC64LE9-NEXT: xscpsgndp 1, 61, 61 ; PC64LE9-NEXT: xscpsgndp 2, 63, 63 @@ -8902,7 +8727,6 @@ define <4 x double> @constrained_vector_atan2_v4f64(<4 x double> %x, <4 x double ; PC64LE9-NEXT: xxswapd 2, 63 ; PC64LE9-NEXT: bl atan2 ; PC64LE9-NEXT: nop -; PC64LE9-NEXT: # kill: def $f1 killed $f1 def $vsl1 ; PC64LE9-NEXT: xxmrghd 35, 60, 1 ; PC64LE9-NEXT: vmr 2, 30 ; PC64LE9-NEXT: lxv 63, 96(1) # 16-byte Folded Reload |