diff options
Diffstat (limited to 'llvm/test/Transforms/ExpandMemCmp/X86/memcmp.ll')
| -rw-r--r-- | llvm/test/Transforms/ExpandMemCmp/X86/memcmp.ll | 424 |
1 files changed, 334 insertions, 90 deletions
diff --git a/llvm/test/Transforms/ExpandMemCmp/X86/memcmp.ll b/llvm/test/Transforms/ExpandMemCmp/X86/memcmp.ll index 37bd85029b9..c1cbcc3272c 100644 --- a/llvm/test/Transforms/ExpandMemCmp/X86/memcmp.ll +++ b/llvm/test/Transforms/ExpandMemCmp/X86/memcmp.ll @@ -130,11 +130,11 @@ define i32 @cmp6(i8* nocapture readonly %x, i8* nocapture readonly %y) { ; ALL-NEXT: [[TMP9:%.*]] = icmp eq i32 [[TMP7]], [[TMP8]] ; ALL-NEXT: br i1 [[TMP9]], label [[LOADBB1]], label [[RES_BLOCK:%.*]] ; ALL: loadbb1: -; ALL-NEXT: [[TMP10:%.*]] = bitcast i8* [[X]] to i16* -; ALL-NEXT: [[TMP11:%.*]] = bitcast i8* [[Y]] to i16* -; ALL-NEXT: [[TMP12:%.*]] = getelementptr i16, i16* [[TMP10]], i16 2 -; ALL-NEXT: [[TMP13:%.*]] = getelementptr i16, i16* [[TMP11]], i16 2 -; ALL-NEXT: [[TMP14:%.*]] = load i16, i16* [[TMP12]] +; ALL-NEXT: [[TMP10:%.*]] = getelementptr i8, i8* [[X]], i8 4 +; ALL-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i16* +; ALL-NEXT: [[TMP12:%.*]] = getelementptr i8, i8* [[Y]], i8 4 +; ALL-NEXT: [[TMP13:%.*]] = bitcast i8* [[TMP12]] to i16* +; ALL-NEXT: [[TMP14:%.*]] = load i16, i16* [[TMP11]] ; ALL-NEXT: [[TMP15:%.*]] = load i16, i16* [[TMP13]] ; ALL-NEXT: [[TMP16:%.*]] = call i16 @llvm.bswap.i16(i16 [[TMP14]]) ; ALL-NEXT: [[TMP17:%.*]] = call i16 @llvm.bswap.i16(i16 [[TMP15]]) @@ -178,11 +178,11 @@ define i32 @cmp8(i8* nocapture readonly %x, i8* nocapture readonly %y) { ; X32-NEXT: [[TMP9:%.*]] = icmp eq i32 [[TMP7]], [[TMP8]] ; X32-NEXT: br i1 [[TMP9]], label [[LOADBB1]], label [[RES_BLOCK:%.*]] ; X32: loadbb1: -; X32-NEXT: [[TMP10:%.*]] = bitcast i8* [[X]] to i32* -; X32-NEXT: [[TMP11:%.*]] = bitcast i8* [[Y]] to i32* -; X32-NEXT: [[TMP12:%.*]] = getelementptr i32, i32* [[TMP10]], i32 1 -; X32-NEXT: [[TMP13:%.*]] = getelementptr i32, i32* [[TMP11]], i32 1 -; X32-NEXT: [[TMP14:%.*]] = load i32, i32* [[TMP12]] +; X32-NEXT: [[TMP10:%.*]] = getelementptr i8, i8* [[X]], i8 4 +; X32-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i32* +; X32-NEXT: [[TMP12:%.*]] = getelementptr i8, i8* [[Y]], i8 4 +; X32-NEXT: [[TMP13:%.*]] = bitcast i8* [[TMP12]] to i32* +; X32-NEXT: [[TMP14:%.*]] = load i32, i32* [[TMP11]] ; X32-NEXT: [[TMP15:%.*]] = load i32, i32* [[TMP13]] ; X32-NEXT: [[TMP16]] = call i32 @llvm.bswap.i32(i32 [[TMP14]]) ; X32-NEXT: [[TMP17]] = call i32 @llvm.bswap.i32(i32 [[TMP15]]) @@ -272,11 +272,11 @@ define i32 @cmp10(i8* nocapture readonly %x, i8* nocapture readonly %y) { ; X64-NEXT: [[TMP9:%.*]] = icmp eq i64 [[TMP7]], [[TMP8]] ; X64-NEXT: br i1 [[TMP9]], label [[LOADBB1]], label [[RES_BLOCK:%.*]] ; X64: loadbb1: -; X64-NEXT: [[TMP10:%.*]] = bitcast i8* [[X]] to i16* -; X64-NEXT: [[TMP11:%.*]] = bitcast i8* [[Y]] to i16* -; X64-NEXT: [[TMP12:%.*]] = getelementptr i16, i16* [[TMP10]], i16 4 -; X64-NEXT: [[TMP13:%.*]] = getelementptr i16, i16* [[TMP11]], i16 4 -; X64-NEXT: [[TMP14:%.*]] = load i16, i16* [[TMP12]] +; X64-NEXT: [[TMP10:%.*]] = getelementptr i8, i8* [[X]], i8 8 +; X64-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i16* +; X64-NEXT: [[TMP12:%.*]] = getelementptr i8, i8* [[Y]], i8 8 +; X64-NEXT: [[TMP13:%.*]] = bitcast i8* [[TMP12]] to i16* +; X64-NEXT: [[TMP14:%.*]] = load i16, i16* [[TMP11]] ; X64-NEXT: [[TMP15:%.*]] = load i16, i16* [[TMP13]] ; X64-NEXT: [[TMP16:%.*]] = call i16 @llvm.bswap.i16(i16 [[TMP14]]) ; X64-NEXT: [[TMP17:%.*]] = call i16 @llvm.bswap.i16(i16 [[TMP15]]) @@ -324,11 +324,11 @@ define i32 @cmp12(i8* nocapture readonly %x, i8* nocapture readonly %y) { ; X64-NEXT: [[TMP9:%.*]] = icmp eq i64 [[TMP7]], [[TMP8]] ; X64-NEXT: br i1 [[TMP9]], label [[LOADBB1]], label [[RES_BLOCK:%.*]] ; X64: loadbb1: -; X64-NEXT: [[TMP10:%.*]] = bitcast i8* [[X]] to i32* -; X64-NEXT: [[TMP11:%.*]] = bitcast i8* [[Y]] to i32* -; X64-NEXT: [[TMP12:%.*]] = getelementptr i32, i32* [[TMP10]], i32 2 -; X64-NEXT: [[TMP13:%.*]] = getelementptr i32, i32* [[TMP11]], i32 2 -; X64-NEXT: [[TMP14:%.*]] = load i32, i32* [[TMP12]] +; X64-NEXT: [[TMP10:%.*]] = getelementptr i8, i8* [[X]], i8 8 +; X64-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i32* +; X64-NEXT: [[TMP12:%.*]] = getelementptr i8, i8* [[Y]], i8 8 +; X64-NEXT: [[TMP13:%.*]] = bitcast i8* [[TMP12]] to i32* +; X64-NEXT: [[TMP14:%.*]] = load i32, i32* [[TMP11]] ; X64-NEXT: [[TMP15:%.*]] = load i32, i32* [[TMP13]] ; X64-NEXT: [[TMP16:%.*]] = call i32 @llvm.bswap.i32(i32 [[TMP14]]) ; X64-NEXT: [[TMP17:%.*]] = call i32 @llvm.bswap.i32(i32 [[TMP15]]) @@ -394,11 +394,11 @@ define i32 @cmp16(i8* nocapture readonly %x, i8* nocapture readonly %y) { ; X64-NEXT: [[TMP9:%.*]] = icmp eq i64 [[TMP7]], [[TMP8]] ; X64-NEXT: br i1 [[TMP9]], label [[LOADBB1]], label [[RES_BLOCK:%.*]] ; X64: loadbb1: -; X64-NEXT: [[TMP10:%.*]] = bitcast i8* [[X]] to i64* -; X64-NEXT: [[TMP11:%.*]] = bitcast i8* [[Y]] to i64* -; X64-NEXT: [[TMP12:%.*]] = getelementptr i64, i64* [[TMP10]], i64 1 -; X64-NEXT: [[TMP13:%.*]] = getelementptr i64, i64* [[TMP11]], i64 1 -; X64-NEXT: [[TMP14:%.*]] = load i64, i64* [[TMP12]] +; X64-NEXT: [[TMP10:%.*]] = getelementptr i8, i8* [[X]], i8 8 +; X64-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i64* +; X64-NEXT: [[TMP12:%.*]] = getelementptr i8, i8* [[Y]], i8 8 +; X64-NEXT: [[TMP13:%.*]] = bitcast i8* [[TMP12]] to i64* +; X64-NEXT: [[TMP14:%.*]] = load i64, i64* [[TMP11]] ; X64-NEXT: [[TMP15:%.*]] = load i64, i64* [[TMP13]] ; X64-NEXT: [[TMP16]] = call i64 @llvm.bswap.i64(i64 [[TMP14]]) ; X64-NEXT: [[TMP17]] = call i64 @llvm.bswap.i64(i64 [[TMP15]]) @@ -597,11 +597,11 @@ define i32 @cmp_eq6(i8* nocapture readonly %x, i8* nocapture readonly %y) { ; 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: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 4 +; X32-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i16* +; X32-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 4 +; X32-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i16* +; X32-NEXT: [[TMP10:%.*]] = load i16, i16* [[TMP7]] ; X32-NEXT: [[TMP11:%.*]] = load i16, i16* [[TMP9]] ; X32-NEXT: [[TMP12:%.*]] = zext i16 [[TMP10]] to i32 ; X32-NEXT: [[TMP13:%.*]] = zext i16 [[TMP11]] to i32 @@ -625,11 +625,11 @@ define i32 @cmp_eq6(i8* nocapture readonly %x, i8* nocapture readonly %y) { ; 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: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 4 +; X64_1LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i16* +; X64_1LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 4 +; X64_1LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i16* +; X64_1LD-NEXT: [[TMP10:%.*]] = load i16, i16* [[TMP7]] ; 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]] @@ -645,11 +645,11 @@ define i32 @cmp_eq6(i8* nocapture readonly %x, i8* nocapture readonly %y) { ; 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: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 4 +; X64_2LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i16* +; X64_2LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 4 +; X64_2LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i16* +; X64_2LD-NEXT: [[TMP10:%.*]] = load i16, i16* [[TMP7]] ; 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 @@ -668,11 +668,71 @@ define i32 @cmp_eq6(i8* nocapture readonly %x, i8* nocapture readonly %y) { } define i32 @cmp_eq7(i8* nocapture readonly %x, i8* nocapture readonly %y) { -; ALL-LABEL: @cmp_eq7( -; ALL-NEXT: [[CALL:%.*]] = tail call i32 @memcmp(i8* [[X:%.*]], i8* [[Y:%.*]], i64 7) -; ALL-NEXT: [[CMP:%.*]] = icmp eq i32 [[CALL]], 0 -; ALL-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 -; ALL-NEXT: ret i32 [[CONV]] +; X32-LABEL: @cmp_eq7( +; 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 3 +; X32-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i32* +; X32-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 3 +; X32-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i32* +; X32-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP7]] +; X32-NEXT: [[TMP11:%.*]] = load i32, i32* [[TMP9]] +; 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_eq7( +; 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 3 +; X64_1LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i32* +; X64_1LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 3 +; X64_1LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i32* +; X64_1LD-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP7]] +; 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_eq7( +; 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 3 +; X64_2LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i32* +; X64_2LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 3 +; X64_2LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i32* +; X64_2LD-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP7]] +; X64_2LD-NEXT: [[TMP11:%.*]] = load i32, i32* [[TMP9]] +; 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 7) %cmp = icmp eq i32 %call, 0 @@ -687,11 +747,11 @@ define i32 @cmp_eq8(i8* nocapture readonly %x, i8* nocapture readonly %y) { ; 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 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: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 4 +; X32-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i32* +; X32-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 4 +; X32-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i32* +; X32-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP7]] ; X32-NEXT: [[TMP11:%.*]] = load i32, i32* [[TMP9]] ; X32-NEXT: [[TMP12:%.*]] = xor i32 [[TMP10]], [[TMP11]] ; X32-NEXT: [[TMP13:%.*]] = or i32 [[TMP5]], [[TMP12]] @@ -794,11 +854,11 @@ define i32 @cmp_eq10(i8* nocapture readonly %x, i8* nocapture readonly %y) { ; 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: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 8 +; X64_1LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i16* +; X64_1LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 8 +; X64_1LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i16* +; X64_1LD-NEXT: [[TMP10:%.*]] = load i16, i16* [[TMP7]] ; 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]] @@ -814,11 +874,11 @@ define i32 @cmp_eq10(i8* nocapture readonly %x, i8* nocapture readonly %y) { ; 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: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 8 +; X64_2LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i16* +; X64_2LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 8 +; X64_2LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i16* +; X64_2LD-NEXT: [[TMP10:%.*]] = load i16, i16* [[TMP7]] ; 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 @@ -837,11 +897,57 @@ define i32 @cmp_eq10(i8* nocapture readonly %x, i8* nocapture readonly %y) { } define i32 @cmp_eq11(i8* nocapture readonly %x, i8* nocapture readonly %y) { -; ALL-LABEL: @cmp_eq11( -; ALL-NEXT: [[CALL:%.*]] = tail call i32 @memcmp(i8* [[X:%.*]], i8* [[Y:%.*]], i64 11) -; ALL-NEXT: [[CMP:%.*]] = icmp eq i32 [[CALL]], 0 -; ALL-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 -; ALL-NEXT: ret i32 [[CONV]] +; X32-LABEL: @cmp_eq11( +; X32-NEXT: [[CALL:%.*]] = tail call i32 @memcmp(i8* [[X:%.*]], i8* [[Y:%.*]], i64 11) +; X32-NEXT: [[CMP:%.*]] = icmp eq i32 [[CALL]], 0 +; X32-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 +; X32-NEXT: ret i32 [[CONV]] +; +; X64_1LD-LABEL: @cmp_eq11( +; 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 3 +; X64_1LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i64* +; X64_1LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 3 +; X64_1LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i64* +; X64_1LD-NEXT: [[TMP10:%.*]] = load i64, i64* [[TMP7]] +; X64_1LD-NEXT: [[TMP11:%.*]] = load i64, i64* [[TMP9]] +; X64_1LD-NEXT: [[TMP12:%.*]] = icmp ne i64 [[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_eq11( +; 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 3 +; X64_2LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i64* +; X64_2LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 3 +; X64_2LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i64* +; X64_2LD-NEXT: [[TMP10:%.*]] = load i64, i64* [[TMP7]] +; X64_2LD-NEXT: [[TMP11:%.*]] = load i64, i64* [[TMP9]] +; 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 11) %cmp = icmp eq i32 %call, 0 @@ -868,11 +974,11 @@ define i32 @cmp_eq12(i8* nocapture readonly %x, i8* nocapture readonly %y) { ; 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: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 8 +; X64_1LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i32* +; X64_1LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 8 +; X64_1LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i32* +; X64_1LD-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP7]] ; 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]] @@ -888,11 +994,11 @@ define i32 @cmp_eq12(i8* nocapture readonly %x, i8* nocapture readonly %y) { ; 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: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 8 +; X64_2LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i32* +; X64_2LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 8 +; X64_2LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i32* +; X64_2LD-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP7]] ; 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 @@ -911,11 +1017,57 @@ define i32 @cmp_eq12(i8* nocapture readonly %x, i8* nocapture readonly %y) { } define i32 @cmp_eq13(i8* nocapture readonly %x, i8* nocapture readonly %y) { -; ALL-LABEL: @cmp_eq13( -; ALL-NEXT: [[CALL:%.*]] = tail call i32 @memcmp(i8* [[X:%.*]], i8* [[Y:%.*]], i64 13) -; ALL-NEXT: [[CMP:%.*]] = icmp eq i32 [[CALL]], 0 -; ALL-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 -; ALL-NEXT: ret i32 [[CONV]] +; X32-LABEL: @cmp_eq13( +; X32-NEXT: [[CALL:%.*]] = tail call i32 @memcmp(i8* [[X:%.*]], i8* [[Y:%.*]], i64 13) +; X32-NEXT: [[CMP:%.*]] = icmp eq i32 [[CALL]], 0 +; X32-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 +; X32-NEXT: ret i32 [[CONV]] +; +; X64_1LD-LABEL: @cmp_eq13( +; 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 5 +; X64_1LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i64* +; X64_1LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 5 +; X64_1LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i64* +; X64_1LD-NEXT: [[TMP10:%.*]] = load i64, i64* [[TMP7]] +; X64_1LD-NEXT: [[TMP11:%.*]] = load i64, i64* [[TMP9]] +; X64_1LD-NEXT: [[TMP12:%.*]] = icmp ne i64 [[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_eq13( +; 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 5 +; X64_2LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i64* +; X64_2LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 5 +; X64_2LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i64* +; X64_2LD-NEXT: [[TMP10:%.*]] = load i64, i64* [[TMP7]] +; X64_2LD-NEXT: [[TMP11:%.*]] = load i64, i64* [[TMP9]] +; 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 13) %cmp = icmp eq i32 %call, 0 @@ -924,11 +1076,57 @@ define i32 @cmp_eq13(i8* nocapture readonly %x, i8* nocapture readonly %y) { } define i32 @cmp_eq14(i8* nocapture readonly %x, i8* nocapture readonly %y) { -; ALL-LABEL: @cmp_eq14( -; ALL-NEXT: [[CALL:%.*]] = tail call i32 @memcmp(i8* [[X:%.*]], i8* [[Y:%.*]], i64 14) -; ALL-NEXT: [[CMP:%.*]] = icmp eq i32 [[CALL]], 0 -; ALL-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 -; ALL-NEXT: ret i32 [[CONV]] +; X32-LABEL: @cmp_eq14( +; X32-NEXT: [[CALL:%.*]] = tail call i32 @memcmp(i8* [[X:%.*]], i8* [[Y:%.*]], i64 14) +; X32-NEXT: [[CMP:%.*]] = icmp eq i32 [[CALL]], 0 +; X32-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 +; X32-NEXT: ret i32 [[CONV]] +; +; X64_1LD-LABEL: @cmp_eq14( +; 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 6 +; X64_1LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i64* +; X64_1LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 6 +; X64_1LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i64* +; X64_1LD-NEXT: [[TMP10:%.*]] = load i64, i64* [[TMP7]] +; X64_1LD-NEXT: [[TMP11:%.*]] = load i64, i64* [[TMP9]] +; X64_1LD-NEXT: [[TMP12:%.*]] = icmp ne i64 [[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_eq14( +; 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 6 +; X64_2LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i64* +; X64_2LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 6 +; X64_2LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i64* +; X64_2LD-NEXT: [[TMP10:%.*]] = load i64, i64* [[TMP7]] +; X64_2LD-NEXT: [[TMP11:%.*]] = load i64, i64* [[TMP9]] +; 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 14) %cmp = icmp eq i32 %call, 0 @@ -937,11 +1135,57 @@ define i32 @cmp_eq14(i8* nocapture readonly %x, i8* nocapture readonly %y) { } define i32 @cmp_eq15(i8* nocapture readonly %x, i8* nocapture readonly %y) { -; ALL-LABEL: @cmp_eq15( -; ALL-NEXT: [[CALL:%.*]] = tail call i32 @memcmp(i8* [[X:%.*]], i8* [[Y:%.*]], i64 15) -; ALL-NEXT: [[CMP:%.*]] = icmp eq i32 [[CALL]], 0 -; ALL-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 -; ALL-NEXT: ret i32 [[CONV]] +; X32-LABEL: @cmp_eq15( +; X32-NEXT: [[CALL:%.*]] = tail call i32 @memcmp(i8* [[X:%.*]], i8* [[Y:%.*]], i64 15) +; X32-NEXT: [[CMP:%.*]] = icmp eq i32 [[CALL]], 0 +; X32-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 +; X32-NEXT: ret i32 [[CONV]] +; +; X64_1LD-LABEL: @cmp_eq15( +; 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 7 +; X64_1LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i64* +; X64_1LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 7 +; X64_1LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i64* +; X64_1LD-NEXT: [[TMP10:%.*]] = load i64, i64* [[TMP7]] +; X64_1LD-NEXT: [[TMP11:%.*]] = load i64, i64* [[TMP9]] +; X64_1LD-NEXT: [[TMP12:%.*]] = icmp ne i64 [[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_eq15( +; 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 7 +; X64_2LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i64* +; X64_2LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 7 +; X64_2LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i64* +; X64_2LD-NEXT: [[TMP10:%.*]] = load i64, i64* [[TMP7]] +; X64_2LD-NEXT: [[TMP11:%.*]] = load i64, i64* [[TMP9]] +; 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 15) %cmp = icmp eq i32 %call, 0 |
