diff options
Diffstat (limited to 'llvm/test/Transforms/ExpandMemCmp/X86/memcmp.ll')
| -rw-r--r-- | llvm/test/Transforms/ExpandMemCmp/X86/memcmp.ll | 497 |
1 files changed, 340 insertions, 157 deletions
diff --git a/llvm/test/Transforms/ExpandMemCmp/X86/memcmp.ll b/llvm/test/Transforms/ExpandMemCmp/X86/memcmp.ll index 1abfb20f369..37bd85029b9 100644 --- a/llvm/test/Transforms/ExpandMemCmp/X86/memcmp.ll +++ b/llvm/test/Transforms/ExpandMemCmp/X86/memcmp.ll @@ -1,6 +1,7 @@ ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py ; RUN: opt -S -expandmemcmp -mtriple=i686-unknown-unknown -data-layout=e-m:o-p:32:32-f64:32:64-f80:128-n8:16:32-S128 < %s | FileCheck %s --check-prefix=ALL --check-prefix=X32 -; RUN: opt -S -expandmemcmp -mtriple=x86_64-unknown-unknown -data-layout=e-m:o-i64:64-f80:128-n8:16:32:64-S128 < %s | FileCheck %s --check-prefix=ALL --check-prefix=X64 +; RUN: opt -S -expandmemcmp -memcmp-num-loads-per-block=1 -mtriple=x86_64-unknown-unknown -data-layout=e-m:o-i64:64-f80:128-n8:16:32:64-S128 < %s | FileCheck %s --check-prefix=ALL --check-prefix=X64 --check-prefix=X64_1LD +; RUN: opt -S -expandmemcmp -memcmp-num-loads-per-block=2 -mtriple=x86_64-unknown-unknown -data-layout=e-m:o-i64:64-f80:128-n8:16:32:64-S128 < %s | FileCheck %s --check-prefix=ALL --check-prefix=X64 --check-prefix=X64_2LD declare i32 @memcmp(i8* nocapture, i8* nocapture, i64) @@ -430,29 +431,69 @@ define i32 @cmp_eq2(i8* nocapture readonly %x, i8* nocapture readonly %y) { } define i32 @cmp_eq3(i8* nocapture readonly %x, i8* nocapture readonly %y) { -; ALL-LABEL: @cmp_eq3( -; ALL-NEXT: br label [[LOADBB:%.*]] -; ALL: res_block: -; ALL-NEXT: br label [[ENDBLOCK:%.*]] -; ALL: loadbb: -; ALL-NEXT: [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i16* -; ALL-NEXT: [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i16* -; ALL-NEXT: [[TMP3:%.*]] = load i16, i16* [[TMP1]] -; ALL-NEXT: [[TMP4:%.*]] = load i16, i16* [[TMP2]] -; ALL-NEXT: [[TMP5:%.*]] = icmp ne i16 [[TMP3]], [[TMP4]] -; ALL-NEXT: br i1 [[TMP5]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]] -; ALL: loadbb1: -; ALL-NEXT: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 2 -; ALL-NEXT: [[TMP7:%.*]] = getelementptr i8, i8* [[Y]], i8 2 -; ALL-NEXT: [[TMP8:%.*]] = load i8, i8* [[TMP6]] -; ALL-NEXT: [[TMP9:%.*]] = load i8, i8* [[TMP7]] -; ALL-NEXT: [[TMP10:%.*]] = icmp ne i8 [[TMP8]], [[TMP9]] -; ALL-NEXT: br i1 [[TMP10]], label [[RES_BLOCK]], label [[ENDBLOCK]] -; ALL: endblock: -; ALL-NEXT: [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ] -; ALL-NEXT: [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0 -; ALL-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 -; ALL-NEXT: ret i32 [[CONV]] +; X32-LABEL: @cmp_eq3( +; X32-NEXT: [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i16* +; X32-NEXT: [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i16* +; X32-NEXT: [[TMP3:%.*]] = load i16, i16* [[TMP1]] +; X32-NEXT: [[TMP4:%.*]] = load i16, i16* [[TMP2]] +; X32-NEXT: [[TMP5:%.*]] = xor i16 [[TMP3]], [[TMP4]] +; X32-NEXT: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 2 +; X32-NEXT: [[TMP7:%.*]] = getelementptr i8, i8* [[Y]], i8 2 +; X32-NEXT: [[TMP8:%.*]] = load i8, i8* [[TMP6]] +; X32-NEXT: [[TMP9:%.*]] = load i8, i8* [[TMP7]] +; X32-NEXT: [[TMP10:%.*]] = zext i8 [[TMP8]] to i16 +; X32-NEXT: [[TMP11:%.*]] = zext i8 [[TMP9]] to i16 +; X32-NEXT: [[TMP12:%.*]] = xor i16 [[TMP10]], [[TMP11]] +; X32-NEXT: [[TMP13:%.*]] = or i16 [[TMP5]], [[TMP12]] +; X32-NEXT: [[TMP14:%.*]] = icmp ne i16 [[TMP13]], 0 +; X32-NEXT: [[TMP15:%.*]] = zext i1 [[TMP14]] to i32 +; X32-NEXT: [[CMP:%.*]] = icmp eq i32 [[TMP15]], 0 +; X32-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 +; X32-NEXT: ret i32 [[CONV]] +; +; X64_1LD-LABEL: @cmp_eq3( +; X64_1LD-NEXT: br label [[LOADBB:%.*]] +; X64_1LD: res_block: +; X64_1LD-NEXT: br label [[ENDBLOCK:%.*]] +; X64_1LD: loadbb: +; X64_1LD-NEXT: [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i16* +; X64_1LD-NEXT: [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i16* +; X64_1LD-NEXT: [[TMP3:%.*]] = load i16, i16* [[TMP1]] +; X64_1LD-NEXT: [[TMP4:%.*]] = load i16, i16* [[TMP2]] +; X64_1LD-NEXT: [[TMP5:%.*]] = icmp ne i16 [[TMP3]], [[TMP4]] +; X64_1LD-NEXT: br i1 [[TMP5]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]] +; X64_1LD: loadbb1: +; X64_1LD-NEXT: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 2 +; X64_1LD-NEXT: [[TMP7:%.*]] = getelementptr i8, i8* [[Y]], i8 2 +; X64_1LD-NEXT: [[TMP8:%.*]] = load i8, i8* [[TMP6]] +; X64_1LD-NEXT: [[TMP9:%.*]] = load i8, i8* [[TMP7]] +; X64_1LD-NEXT: [[TMP10:%.*]] = icmp ne i8 [[TMP8]], [[TMP9]] +; X64_1LD-NEXT: br i1 [[TMP10]], label [[RES_BLOCK]], label [[ENDBLOCK]] +; X64_1LD: endblock: +; X64_1LD-NEXT: [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ] +; X64_1LD-NEXT: [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0 +; X64_1LD-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 +; X64_1LD-NEXT: ret i32 [[CONV]] +; +; X64_2LD-LABEL: @cmp_eq3( +; X64_2LD-NEXT: [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i16* +; X64_2LD-NEXT: [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i16* +; X64_2LD-NEXT: [[TMP3:%.*]] = load i16, i16* [[TMP1]] +; X64_2LD-NEXT: [[TMP4:%.*]] = load i16, i16* [[TMP2]] +; X64_2LD-NEXT: [[TMP5:%.*]] = xor i16 [[TMP3]], [[TMP4]] +; X64_2LD-NEXT: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 2 +; X64_2LD-NEXT: [[TMP7:%.*]] = getelementptr i8, i8* [[Y]], i8 2 +; X64_2LD-NEXT: [[TMP8:%.*]] = load i8, i8* [[TMP6]] +; X64_2LD-NEXT: [[TMP9:%.*]] = load i8, i8* [[TMP7]] +; X64_2LD-NEXT: [[TMP10:%.*]] = zext i8 [[TMP8]] to i16 +; X64_2LD-NEXT: [[TMP11:%.*]] = zext i8 [[TMP9]] to i16 +; X64_2LD-NEXT: [[TMP12:%.*]] = xor i16 [[TMP10]], [[TMP11]] +; X64_2LD-NEXT: [[TMP13:%.*]] = or i16 [[TMP5]], [[TMP12]] +; X64_2LD-NEXT: [[TMP14:%.*]] = icmp ne i16 [[TMP13]], 0 +; X64_2LD-NEXT: [[TMP15:%.*]] = zext i1 [[TMP14]] to i32 +; X64_2LD-NEXT: [[CMP:%.*]] = icmp eq i32 [[TMP15]], 0 +; X64_2LD-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 +; X64_2LD-NEXT: ret i32 [[CONV]] ; %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 3) %cmp = icmp eq i32 %call, 0 @@ -479,29 +520,69 @@ define i32 @cmp_eq4(i8* nocapture readonly %x, i8* nocapture readonly %y) { } define i32 @cmp_eq5(i8* nocapture readonly %x, i8* nocapture readonly %y) { -; ALL-LABEL: @cmp_eq5( -; ALL-NEXT: br label [[LOADBB:%.*]] -; ALL: res_block: -; ALL-NEXT: br label [[ENDBLOCK:%.*]] -; ALL: loadbb: -; ALL-NEXT: [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i32* -; ALL-NEXT: [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i32* -; ALL-NEXT: [[TMP3:%.*]] = load i32, i32* [[TMP1]] -; ALL-NEXT: [[TMP4:%.*]] = load i32, i32* [[TMP2]] -; ALL-NEXT: [[TMP5:%.*]] = icmp ne i32 [[TMP3]], [[TMP4]] -; ALL-NEXT: br i1 [[TMP5]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]] -; ALL: loadbb1: -; ALL-NEXT: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 4 -; ALL-NEXT: [[TMP7:%.*]] = getelementptr i8, i8* [[Y]], i8 4 -; ALL-NEXT: [[TMP8:%.*]] = load i8, i8* [[TMP6]] -; ALL-NEXT: [[TMP9:%.*]] = load i8, i8* [[TMP7]] -; ALL-NEXT: [[TMP10:%.*]] = icmp ne i8 [[TMP8]], [[TMP9]] -; ALL-NEXT: br i1 [[TMP10]], label [[RES_BLOCK]], label [[ENDBLOCK]] -; ALL: endblock: -; ALL-NEXT: [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ] -; ALL-NEXT: [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0 -; ALL-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 -; ALL-NEXT: ret i32 [[CONV]] +; X32-LABEL: @cmp_eq5( +; X32-NEXT: [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i32* +; X32-NEXT: [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i32* +; X32-NEXT: [[TMP3:%.*]] = load i32, i32* [[TMP1]] +; X32-NEXT: [[TMP4:%.*]] = load i32, i32* [[TMP2]] +; X32-NEXT: [[TMP5:%.*]] = xor i32 [[TMP3]], [[TMP4]] +; X32-NEXT: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 4 +; X32-NEXT: [[TMP7:%.*]] = getelementptr i8, i8* [[Y]], i8 4 +; X32-NEXT: [[TMP8:%.*]] = load i8, i8* [[TMP6]] +; X32-NEXT: [[TMP9:%.*]] = load i8, i8* [[TMP7]] +; X32-NEXT: [[TMP10:%.*]] = zext i8 [[TMP8]] to i32 +; X32-NEXT: [[TMP11:%.*]] = zext i8 [[TMP9]] to i32 +; X32-NEXT: [[TMP12:%.*]] = xor i32 [[TMP10]], [[TMP11]] +; X32-NEXT: [[TMP13:%.*]] = or i32 [[TMP5]], [[TMP12]] +; X32-NEXT: [[TMP14:%.*]] = icmp ne i32 [[TMP13]], 0 +; X32-NEXT: [[TMP15:%.*]] = zext i1 [[TMP14]] to i32 +; X32-NEXT: [[CMP:%.*]] = icmp eq i32 [[TMP15]], 0 +; X32-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 +; X32-NEXT: ret i32 [[CONV]] +; +; X64_1LD-LABEL: @cmp_eq5( +; X64_1LD-NEXT: br label [[LOADBB:%.*]] +; X64_1LD: res_block: +; X64_1LD-NEXT: br label [[ENDBLOCK:%.*]] +; X64_1LD: loadbb: +; X64_1LD-NEXT: [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i32* +; X64_1LD-NEXT: [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i32* +; X64_1LD-NEXT: [[TMP3:%.*]] = load i32, i32* [[TMP1]] +; X64_1LD-NEXT: [[TMP4:%.*]] = load i32, i32* [[TMP2]] +; X64_1LD-NEXT: [[TMP5:%.*]] = icmp ne i32 [[TMP3]], [[TMP4]] +; X64_1LD-NEXT: br i1 [[TMP5]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]] +; X64_1LD: loadbb1: +; X64_1LD-NEXT: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 4 +; X64_1LD-NEXT: [[TMP7:%.*]] = getelementptr i8, i8* [[Y]], i8 4 +; X64_1LD-NEXT: [[TMP8:%.*]] = load i8, i8* [[TMP6]] +; X64_1LD-NEXT: [[TMP9:%.*]] = load i8, i8* [[TMP7]] +; X64_1LD-NEXT: [[TMP10:%.*]] = icmp ne i8 [[TMP8]], [[TMP9]] +; X64_1LD-NEXT: br i1 [[TMP10]], label [[RES_BLOCK]], label [[ENDBLOCK]] +; X64_1LD: endblock: +; X64_1LD-NEXT: [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ] +; X64_1LD-NEXT: [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0 +; X64_1LD-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 +; X64_1LD-NEXT: ret i32 [[CONV]] +; +; X64_2LD-LABEL: @cmp_eq5( +; X64_2LD-NEXT: [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i32* +; X64_2LD-NEXT: [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i32* +; X64_2LD-NEXT: [[TMP3:%.*]] = load i32, i32* [[TMP1]] +; X64_2LD-NEXT: [[TMP4:%.*]] = load i32, i32* [[TMP2]] +; X64_2LD-NEXT: [[TMP5:%.*]] = xor i32 [[TMP3]], [[TMP4]] +; X64_2LD-NEXT: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 4 +; X64_2LD-NEXT: [[TMP7:%.*]] = getelementptr i8, i8* [[Y]], i8 4 +; X64_2LD-NEXT: [[TMP8:%.*]] = load i8, i8* [[TMP6]] +; X64_2LD-NEXT: [[TMP9:%.*]] = load i8, i8* [[TMP7]] +; X64_2LD-NEXT: [[TMP10:%.*]] = zext i8 [[TMP8]] to i32 +; X64_2LD-NEXT: [[TMP11:%.*]] = zext i8 [[TMP9]] to i32 +; X64_2LD-NEXT: [[TMP12:%.*]] = xor i32 [[TMP10]], [[TMP11]] +; X64_2LD-NEXT: [[TMP13:%.*]] = or i32 [[TMP5]], [[TMP12]] +; X64_2LD-NEXT: [[TMP14:%.*]] = icmp ne i32 [[TMP13]], 0 +; X64_2LD-NEXT: [[TMP15:%.*]] = zext i1 [[TMP14]] to i32 +; X64_2LD-NEXT: [[CMP:%.*]] = icmp eq i32 [[TMP15]], 0 +; X64_2LD-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 +; X64_2LD-NEXT: ret i32 [[CONV]] ; %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 5) %cmp = icmp eq i32 %call, 0 @@ -510,31 +591,75 @@ define i32 @cmp_eq5(i8* nocapture readonly %x, i8* nocapture readonly %y) { } define i32 @cmp_eq6(i8* nocapture readonly %x, i8* nocapture readonly %y) { -; ALL-LABEL: @cmp_eq6( -; ALL-NEXT: br label [[LOADBB:%.*]] -; ALL: res_block: -; ALL-NEXT: br label [[ENDBLOCK:%.*]] -; ALL: loadbb: -; ALL-NEXT: [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i32* -; ALL-NEXT: [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i32* -; ALL-NEXT: [[TMP3:%.*]] = load i32, i32* [[TMP1]] -; ALL-NEXT: [[TMP4:%.*]] = load i32, i32* [[TMP2]] -; ALL-NEXT: [[TMP5:%.*]] = icmp ne i32 [[TMP3]], [[TMP4]] -; ALL-NEXT: br i1 [[TMP5]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]] -; ALL: loadbb1: -; ALL-NEXT: [[TMP6:%.*]] = bitcast i8* [[X]] to i16* -; ALL-NEXT: [[TMP7:%.*]] = bitcast i8* [[Y]] to i16* -; ALL-NEXT: [[TMP8:%.*]] = getelementptr i16, i16* [[TMP6]], i16 2 -; ALL-NEXT: [[TMP9:%.*]] = getelementptr i16, i16* [[TMP7]], i16 2 -; ALL-NEXT: [[TMP10:%.*]] = load i16, i16* [[TMP8]] -; ALL-NEXT: [[TMP11:%.*]] = load i16, i16* [[TMP9]] -; ALL-NEXT: [[TMP12:%.*]] = icmp ne i16 [[TMP10]], [[TMP11]] -; ALL-NEXT: br i1 [[TMP12]], label [[RES_BLOCK]], label [[ENDBLOCK]] -; ALL: endblock: -; ALL-NEXT: [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ] -; ALL-NEXT: [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0 -; ALL-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 -; ALL-NEXT: ret i32 [[CONV]] +; X32-LABEL: @cmp_eq6( +; X32-NEXT: [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i32* +; X32-NEXT: [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i32* +; X32-NEXT: [[TMP3:%.*]] = load i32, i32* [[TMP1]] +; X32-NEXT: [[TMP4:%.*]] = load i32, i32* [[TMP2]] +; X32-NEXT: [[TMP5:%.*]] = xor i32 [[TMP3]], [[TMP4]] +; X32-NEXT: [[TMP6:%.*]] = bitcast i8* [[X]] to i16* +; X32-NEXT: [[TMP7:%.*]] = bitcast i8* [[Y]] to i16* +; X32-NEXT: [[TMP8:%.*]] = getelementptr i16, i16* [[TMP6]], i16 2 +; X32-NEXT: [[TMP9:%.*]] = getelementptr i16, i16* [[TMP7]], i16 2 +; X32-NEXT: [[TMP10:%.*]] = load i16, i16* [[TMP8]] +; X32-NEXT: [[TMP11:%.*]] = load i16, i16* [[TMP9]] +; X32-NEXT: [[TMP12:%.*]] = zext i16 [[TMP10]] to i32 +; X32-NEXT: [[TMP13:%.*]] = zext i16 [[TMP11]] to i32 +; X32-NEXT: [[TMP14:%.*]] = xor i32 [[TMP12]], [[TMP13]] +; X32-NEXT: [[TMP15:%.*]] = or i32 [[TMP5]], [[TMP14]] +; X32-NEXT: [[TMP16:%.*]] = icmp ne i32 [[TMP15]], 0 +; X32-NEXT: [[TMP17:%.*]] = zext i1 [[TMP16]] to i32 +; X32-NEXT: [[CMP:%.*]] = icmp eq i32 [[TMP17]], 0 +; X32-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 +; X32-NEXT: ret i32 [[CONV]] +; +; X64_1LD-LABEL: @cmp_eq6( +; X64_1LD-NEXT: br label [[LOADBB:%.*]] +; X64_1LD: res_block: +; X64_1LD-NEXT: br label [[ENDBLOCK:%.*]] +; X64_1LD: loadbb: +; X64_1LD-NEXT: [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i32* +; X64_1LD-NEXT: [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i32* +; X64_1LD-NEXT: [[TMP3:%.*]] = load i32, i32* [[TMP1]] +; X64_1LD-NEXT: [[TMP4:%.*]] = load i32, i32* [[TMP2]] +; X64_1LD-NEXT: [[TMP5:%.*]] = icmp ne i32 [[TMP3]], [[TMP4]] +; X64_1LD-NEXT: br i1 [[TMP5]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]] +; X64_1LD: loadbb1: +; X64_1LD-NEXT: [[TMP6:%.*]] = bitcast i8* [[X]] to i16* +; X64_1LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[Y]] to i16* +; X64_1LD-NEXT: [[TMP8:%.*]] = getelementptr i16, i16* [[TMP6]], i16 2 +; X64_1LD-NEXT: [[TMP9:%.*]] = getelementptr i16, i16* [[TMP7]], i16 2 +; X64_1LD-NEXT: [[TMP10:%.*]] = load i16, i16* [[TMP8]] +; X64_1LD-NEXT: [[TMP11:%.*]] = load i16, i16* [[TMP9]] +; X64_1LD-NEXT: [[TMP12:%.*]] = icmp ne i16 [[TMP10]], [[TMP11]] +; X64_1LD-NEXT: br i1 [[TMP12]], label [[RES_BLOCK]], label [[ENDBLOCK]] +; X64_1LD: endblock: +; X64_1LD-NEXT: [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ] +; X64_1LD-NEXT: [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0 +; X64_1LD-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 +; X64_1LD-NEXT: ret i32 [[CONV]] +; +; X64_2LD-LABEL: @cmp_eq6( +; X64_2LD-NEXT: [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i32* +; X64_2LD-NEXT: [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i32* +; X64_2LD-NEXT: [[TMP3:%.*]] = load i32, i32* [[TMP1]] +; X64_2LD-NEXT: [[TMP4:%.*]] = load i32, i32* [[TMP2]] +; X64_2LD-NEXT: [[TMP5:%.*]] = xor i32 [[TMP3]], [[TMP4]] +; X64_2LD-NEXT: [[TMP6:%.*]] = bitcast i8* [[X]] to i16* +; X64_2LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[Y]] to i16* +; X64_2LD-NEXT: [[TMP8:%.*]] = getelementptr i16, i16* [[TMP6]], i16 2 +; X64_2LD-NEXT: [[TMP9:%.*]] = getelementptr i16, i16* [[TMP7]], i16 2 +; X64_2LD-NEXT: [[TMP10:%.*]] = load i16, i16* [[TMP8]] +; X64_2LD-NEXT: [[TMP11:%.*]] = load i16, i16* [[TMP9]] +; X64_2LD-NEXT: [[TMP12:%.*]] = zext i16 [[TMP10]] to i32 +; X64_2LD-NEXT: [[TMP13:%.*]] = zext i16 [[TMP11]] to i32 +; X64_2LD-NEXT: [[TMP14:%.*]] = xor i32 [[TMP12]], [[TMP13]] +; X64_2LD-NEXT: [[TMP15:%.*]] = or i32 [[TMP5]], [[TMP14]] +; X64_2LD-NEXT: [[TMP16:%.*]] = icmp ne i32 [[TMP15]], 0 +; X64_2LD-NEXT: [[TMP17:%.*]] = zext i1 [[TMP16]] to i32 +; X64_2LD-NEXT: [[CMP:%.*]] = icmp eq i32 [[TMP17]], 0 +; X64_2LD-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 +; X64_2LD-NEXT: ret i32 [[CONV]] ; %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 6) %cmp = icmp eq i32 %call, 0 @@ -557,28 +682,22 @@ define i32 @cmp_eq7(i8* nocapture readonly %x, i8* nocapture readonly %y) { define i32 @cmp_eq8(i8* nocapture readonly %x, i8* nocapture readonly %y) { ; X32-LABEL: @cmp_eq8( -; X32-NEXT: br label [[LOADBB:%.*]] -; X32: res_block: -; X32-NEXT: br label [[ENDBLOCK:%.*]] -; X32: loadbb: ; X32-NEXT: [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i32* ; X32-NEXT: [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i32* ; X32-NEXT: [[TMP3:%.*]] = load i32, i32* [[TMP1]] ; X32-NEXT: [[TMP4:%.*]] = load i32, i32* [[TMP2]] -; X32-NEXT: [[TMP5:%.*]] = icmp ne i32 [[TMP3]], [[TMP4]] -; X32-NEXT: br i1 [[TMP5]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]] -; X32: loadbb1: +; X32-NEXT: [[TMP5:%.*]] = xor i32 [[TMP3]], [[TMP4]] ; X32-NEXT: [[TMP6:%.*]] = bitcast i8* [[X]] to i32* ; X32-NEXT: [[TMP7:%.*]] = bitcast i8* [[Y]] to i32* ; X32-NEXT: [[TMP8:%.*]] = getelementptr i32, i32* [[TMP6]], i32 1 ; X32-NEXT: [[TMP9:%.*]] = getelementptr i32, i32* [[TMP7]], i32 1 ; X32-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP8]] ; X32-NEXT: [[TMP11:%.*]] = load i32, i32* [[TMP9]] -; X32-NEXT: [[TMP12:%.*]] = icmp ne i32 [[TMP10]], [[TMP11]] -; X32-NEXT: br i1 [[TMP12]], label [[RES_BLOCK]], label [[ENDBLOCK]] -; X32: endblock: -; X32-NEXT: [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ] -; X32-NEXT: [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0 +; X32-NEXT: [[TMP12:%.*]] = xor i32 [[TMP10]], [[TMP11]] +; X32-NEXT: [[TMP13:%.*]] = or i32 [[TMP5]], [[TMP12]] +; X32-NEXT: [[TMP14:%.*]] = icmp ne i32 [[TMP13]], 0 +; X32-NEXT: [[TMP15:%.*]] = zext i1 [[TMP14]] to i32 +; X32-NEXT: [[CMP:%.*]] = icmp eq i32 [[TMP15]], 0 ; X32-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 ; X32-NEXT: ret i32 [[CONV]] ; @@ -606,29 +725,49 @@ define i32 @cmp_eq9(i8* nocapture readonly %x, i8* nocapture readonly %y) { ; X32-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 ; X32-NEXT: ret i32 [[CONV]] ; -; X64-LABEL: @cmp_eq9( -; X64-NEXT: br label [[LOADBB:%.*]] -; X64: res_block: -; X64-NEXT: br label [[ENDBLOCK:%.*]] -; X64: loadbb: -; X64-NEXT: [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i64* -; X64-NEXT: [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i64* -; X64-NEXT: [[TMP3:%.*]] = load i64, i64* [[TMP1]] -; X64-NEXT: [[TMP4:%.*]] = load i64, i64* [[TMP2]] -; X64-NEXT: [[TMP5:%.*]] = icmp ne i64 [[TMP3]], [[TMP4]] -; X64-NEXT: br i1 [[TMP5]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]] -; X64: loadbb1: -; X64-NEXT: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 8 -; X64-NEXT: [[TMP7:%.*]] = getelementptr i8, i8* [[Y]], i8 8 -; X64-NEXT: [[TMP8:%.*]] = load i8, i8* [[TMP6]] -; X64-NEXT: [[TMP9:%.*]] = load i8, i8* [[TMP7]] -; X64-NEXT: [[TMP10:%.*]] = icmp ne i8 [[TMP8]], [[TMP9]] -; X64-NEXT: br i1 [[TMP10]], label [[RES_BLOCK]], label [[ENDBLOCK]] -; X64: endblock: -; X64-NEXT: [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ] -; X64-NEXT: [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0 -; X64-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 -; X64-NEXT: ret i32 [[CONV]] +; X64_1LD-LABEL: @cmp_eq9( +; X64_1LD-NEXT: br label [[LOADBB:%.*]] +; X64_1LD: res_block: +; X64_1LD-NEXT: br label [[ENDBLOCK:%.*]] +; X64_1LD: loadbb: +; X64_1LD-NEXT: [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i64* +; X64_1LD-NEXT: [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i64* +; X64_1LD-NEXT: [[TMP3:%.*]] = load i64, i64* [[TMP1]] +; X64_1LD-NEXT: [[TMP4:%.*]] = load i64, i64* [[TMP2]] +; X64_1LD-NEXT: [[TMP5:%.*]] = icmp ne i64 [[TMP3]], [[TMP4]] +; X64_1LD-NEXT: br i1 [[TMP5]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]] +; X64_1LD: loadbb1: +; X64_1LD-NEXT: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 8 +; X64_1LD-NEXT: [[TMP7:%.*]] = getelementptr i8, i8* [[Y]], i8 8 +; X64_1LD-NEXT: [[TMP8:%.*]] = load i8, i8* [[TMP6]] +; X64_1LD-NEXT: [[TMP9:%.*]] = load i8, i8* [[TMP7]] +; X64_1LD-NEXT: [[TMP10:%.*]] = icmp ne i8 [[TMP8]], [[TMP9]] +; X64_1LD-NEXT: br i1 [[TMP10]], label [[RES_BLOCK]], label [[ENDBLOCK]] +; X64_1LD: endblock: +; X64_1LD-NEXT: [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ] +; X64_1LD-NEXT: [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0 +; X64_1LD-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 +; X64_1LD-NEXT: ret i32 [[CONV]] +; +; X64_2LD-LABEL: @cmp_eq9( +; X64_2LD-NEXT: [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i64* +; X64_2LD-NEXT: [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i64* +; X64_2LD-NEXT: [[TMP3:%.*]] = load i64, i64* [[TMP1]] +; X64_2LD-NEXT: [[TMP4:%.*]] = load i64, i64* [[TMP2]] +; X64_2LD-NEXT: [[TMP5:%.*]] = xor i64 [[TMP3]], [[TMP4]] +; X64_2LD-NEXT: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 8 +; X64_2LD-NEXT: [[TMP7:%.*]] = getelementptr i8, i8* [[Y]], i8 8 +; X64_2LD-NEXT: [[TMP8:%.*]] = load i8, i8* [[TMP6]] +; X64_2LD-NEXT: [[TMP9:%.*]] = load i8, i8* [[TMP7]] +; X64_2LD-NEXT: [[TMP10:%.*]] = zext i8 [[TMP8]] to i64 +; X64_2LD-NEXT: [[TMP11:%.*]] = zext i8 [[TMP9]] to i64 +; X64_2LD-NEXT: [[TMP12:%.*]] = xor i64 [[TMP10]], [[TMP11]] +; X64_2LD-NEXT: [[TMP13:%.*]] = or i64 [[TMP5]], [[TMP12]] +; X64_2LD-NEXT: [[TMP14:%.*]] = icmp ne i64 [[TMP13]], 0 +; X64_2LD-NEXT: [[TMP15:%.*]] = zext i1 [[TMP14]] to i32 +; X64_2LD-NEXT: [[CMP:%.*]] = icmp eq i32 [[TMP15]], 0 +; X64_2LD-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 +; X64_2LD-NEXT: ret i32 [[CONV]] ; %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 9) %cmp = icmp eq i32 %call, 0 @@ -643,31 +782,53 @@ define i32 @cmp_eq10(i8* nocapture readonly %x, i8* nocapture readonly %y) { ; X32-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 ; X32-NEXT: ret i32 [[CONV]] ; -; X64-LABEL: @cmp_eq10( -; X64-NEXT: br label [[LOADBB:%.*]] -; X64: res_block: -; X64-NEXT: br label [[ENDBLOCK:%.*]] -; X64: loadbb: -; X64-NEXT: [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i64* -; X64-NEXT: [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i64* -; X64-NEXT: [[TMP3:%.*]] = load i64, i64* [[TMP1]] -; X64-NEXT: [[TMP4:%.*]] = load i64, i64* [[TMP2]] -; X64-NEXT: [[TMP5:%.*]] = icmp ne i64 [[TMP3]], [[TMP4]] -; X64-NEXT: br i1 [[TMP5]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]] -; X64: loadbb1: -; X64-NEXT: [[TMP6:%.*]] = bitcast i8* [[X]] to i16* -; X64-NEXT: [[TMP7:%.*]] = bitcast i8* [[Y]] to i16* -; X64-NEXT: [[TMP8:%.*]] = getelementptr i16, i16* [[TMP6]], i16 4 -; X64-NEXT: [[TMP9:%.*]] = getelementptr i16, i16* [[TMP7]], i16 4 -; X64-NEXT: [[TMP10:%.*]] = load i16, i16* [[TMP8]] -; X64-NEXT: [[TMP11:%.*]] = load i16, i16* [[TMP9]] -; X64-NEXT: [[TMP12:%.*]] = icmp ne i16 [[TMP10]], [[TMP11]] -; X64-NEXT: br i1 [[TMP12]], label [[RES_BLOCK]], label [[ENDBLOCK]] -; X64: endblock: -; X64-NEXT: [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ] -; X64-NEXT: [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0 -; X64-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 -; X64-NEXT: ret i32 [[CONV]] +; X64_1LD-LABEL: @cmp_eq10( +; X64_1LD-NEXT: br label [[LOADBB:%.*]] +; X64_1LD: res_block: +; X64_1LD-NEXT: br label [[ENDBLOCK:%.*]] +; X64_1LD: loadbb: +; X64_1LD-NEXT: [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i64* +; X64_1LD-NEXT: [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i64* +; X64_1LD-NEXT: [[TMP3:%.*]] = load i64, i64* [[TMP1]] +; X64_1LD-NEXT: [[TMP4:%.*]] = load i64, i64* [[TMP2]] +; X64_1LD-NEXT: [[TMP5:%.*]] = icmp ne i64 [[TMP3]], [[TMP4]] +; X64_1LD-NEXT: br i1 [[TMP5]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]] +; X64_1LD: loadbb1: +; X64_1LD-NEXT: [[TMP6:%.*]] = bitcast i8* [[X]] to i16* +; X64_1LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[Y]] to i16* +; X64_1LD-NEXT: [[TMP8:%.*]] = getelementptr i16, i16* [[TMP6]], i16 4 +; X64_1LD-NEXT: [[TMP9:%.*]] = getelementptr i16, i16* [[TMP7]], i16 4 +; X64_1LD-NEXT: [[TMP10:%.*]] = load i16, i16* [[TMP8]] +; X64_1LD-NEXT: [[TMP11:%.*]] = load i16, i16* [[TMP9]] +; X64_1LD-NEXT: [[TMP12:%.*]] = icmp ne i16 [[TMP10]], [[TMP11]] +; X64_1LD-NEXT: br i1 [[TMP12]], label [[RES_BLOCK]], label [[ENDBLOCK]] +; X64_1LD: endblock: +; X64_1LD-NEXT: [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ] +; X64_1LD-NEXT: [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0 +; X64_1LD-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 +; X64_1LD-NEXT: ret i32 [[CONV]] +; +; X64_2LD-LABEL: @cmp_eq10( +; X64_2LD-NEXT: [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i64* +; X64_2LD-NEXT: [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i64* +; X64_2LD-NEXT: [[TMP3:%.*]] = load i64, i64* [[TMP1]] +; X64_2LD-NEXT: [[TMP4:%.*]] = load i64, i64* [[TMP2]] +; X64_2LD-NEXT: [[TMP5:%.*]] = xor i64 [[TMP3]], [[TMP4]] +; X64_2LD-NEXT: [[TMP6:%.*]] = bitcast i8* [[X]] to i16* +; X64_2LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[Y]] to i16* +; X64_2LD-NEXT: [[TMP8:%.*]] = getelementptr i16, i16* [[TMP6]], i16 4 +; X64_2LD-NEXT: [[TMP9:%.*]] = getelementptr i16, i16* [[TMP7]], i16 4 +; X64_2LD-NEXT: [[TMP10:%.*]] = load i16, i16* [[TMP8]] +; X64_2LD-NEXT: [[TMP11:%.*]] = load i16, i16* [[TMP9]] +; X64_2LD-NEXT: [[TMP12:%.*]] = zext i16 [[TMP10]] to i64 +; X64_2LD-NEXT: [[TMP13:%.*]] = zext i16 [[TMP11]] to i64 +; X64_2LD-NEXT: [[TMP14:%.*]] = xor i64 [[TMP12]], [[TMP13]] +; X64_2LD-NEXT: [[TMP15:%.*]] = or i64 [[TMP5]], [[TMP14]] +; X64_2LD-NEXT: [[TMP16:%.*]] = icmp ne i64 [[TMP15]], 0 +; X64_2LD-NEXT: [[TMP17:%.*]] = zext i1 [[TMP16]] to i32 +; X64_2LD-NEXT: [[CMP:%.*]] = icmp eq i32 [[TMP17]], 0 +; X64_2LD-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 +; X64_2LD-NEXT: ret i32 [[CONV]] ; %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 10) %cmp = icmp eq i32 %call, 0 @@ -695,31 +856,53 @@ define i32 @cmp_eq12(i8* nocapture readonly %x, i8* nocapture readonly %y) { ; X32-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 ; X32-NEXT: ret i32 [[CONV]] ; -; X64-LABEL: @cmp_eq12( -; X64-NEXT: br label [[LOADBB:%.*]] -; X64: res_block: -; X64-NEXT: br label [[ENDBLOCK:%.*]] -; X64: loadbb: -; X64-NEXT: [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i64* -; X64-NEXT: [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i64* -; X64-NEXT: [[TMP3:%.*]] = load i64, i64* [[TMP1]] -; X64-NEXT: [[TMP4:%.*]] = load i64, i64* [[TMP2]] -; X64-NEXT: [[TMP5:%.*]] = icmp ne i64 [[TMP3]], [[TMP4]] -; X64-NEXT: br i1 [[TMP5]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]] -; X64: loadbb1: -; X64-NEXT: [[TMP6:%.*]] = bitcast i8* [[X]] to i32* -; X64-NEXT: [[TMP7:%.*]] = bitcast i8* [[Y]] to i32* -; X64-NEXT: [[TMP8:%.*]] = getelementptr i32, i32* [[TMP6]], i32 2 -; X64-NEXT: [[TMP9:%.*]] = getelementptr i32, i32* [[TMP7]], i32 2 -; X64-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP8]] -; X64-NEXT: [[TMP11:%.*]] = load i32, i32* [[TMP9]] -; X64-NEXT: [[TMP12:%.*]] = icmp ne i32 [[TMP10]], [[TMP11]] -; X64-NEXT: br i1 [[TMP12]], label [[RES_BLOCK]], label [[ENDBLOCK]] -; X64: endblock: -; X64-NEXT: [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ] -; X64-NEXT: [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0 -; X64-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 -; X64-NEXT: ret i32 [[CONV]] +; X64_1LD-LABEL: @cmp_eq12( +; X64_1LD-NEXT: br label [[LOADBB:%.*]] +; X64_1LD: res_block: +; X64_1LD-NEXT: br label [[ENDBLOCK:%.*]] +; X64_1LD: loadbb: +; X64_1LD-NEXT: [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i64* +; X64_1LD-NEXT: [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i64* +; X64_1LD-NEXT: [[TMP3:%.*]] = load i64, i64* [[TMP1]] +; X64_1LD-NEXT: [[TMP4:%.*]] = load i64, i64* [[TMP2]] +; X64_1LD-NEXT: [[TMP5:%.*]] = icmp ne i64 [[TMP3]], [[TMP4]] +; X64_1LD-NEXT: br i1 [[TMP5]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]] +; X64_1LD: loadbb1: +; X64_1LD-NEXT: [[TMP6:%.*]] = bitcast i8* [[X]] to i32* +; X64_1LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[Y]] to i32* +; X64_1LD-NEXT: [[TMP8:%.*]] = getelementptr i32, i32* [[TMP6]], i32 2 +; X64_1LD-NEXT: [[TMP9:%.*]] = getelementptr i32, i32* [[TMP7]], i32 2 +; X64_1LD-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP8]] +; X64_1LD-NEXT: [[TMP11:%.*]] = load i32, i32* [[TMP9]] +; X64_1LD-NEXT: [[TMP12:%.*]] = icmp ne i32 [[TMP10]], [[TMP11]] +; X64_1LD-NEXT: br i1 [[TMP12]], label [[RES_BLOCK]], label [[ENDBLOCK]] +; X64_1LD: endblock: +; X64_1LD-NEXT: [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ] +; X64_1LD-NEXT: [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0 +; X64_1LD-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 +; X64_1LD-NEXT: ret i32 [[CONV]] +; +; X64_2LD-LABEL: @cmp_eq12( +; X64_2LD-NEXT: [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i64* +; X64_2LD-NEXT: [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i64* +; X64_2LD-NEXT: [[TMP3:%.*]] = load i64, i64* [[TMP1]] +; X64_2LD-NEXT: [[TMP4:%.*]] = load i64, i64* [[TMP2]] +; X64_2LD-NEXT: [[TMP5:%.*]] = xor i64 [[TMP3]], [[TMP4]] +; X64_2LD-NEXT: [[TMP6:%.*]] = bitcast i8* [[X]] to i32* +; X64_2LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[Y]] to i32* +; X64_2LD-NEXT: [[TMP8:%.*]] = getelementptr i32, i32* [[TMP6]], i32 2 +; X64_2LD-NEXT: [[TMP9:%.*]] = getelementptr i32, i32* [[TMP7]], i32 2 +; X64_2LD-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP8]] +; X64_2LD-NEXT: [[TMP11:%.*]] = load i32, i32* [[TMP9]] +; X64_2LD-NEXT: [[TMP12:%.*]] = zext i32 [[TMP10]] to i64 +; X64_2LD-NEXT: [[TMP13:%.*]] = zext i32 [[TMP11]] to i64 +; X64_2LD-NEXT: [[TMP14:%.*]] = xor i64 [[TMP12]], [[TMP13]] +; X64_2LD-NEXT: [[TMP15:%.*]] = or i64 [[TMP5]], [[TMP14]] +; X64_2LD-NEXT: [[TMP16:%.*]] = icmp ne i64 [[TMP15]], 0 +; X64_2LD-NEXT: [[TMP17:%.*]] = zext i1 [[TMP16]] to i32 +; X64_2LD-NEXT: [[CMP:%.*]] = icmp eq i32 [[TMP17]], 0 +; X64_2LD-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 +; X64_2LD-NEXT: ret i32 [[CONV]] ; %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 12) %cmp = icmp eq i32 %call, 0 |
