diff options
Diffstat (limited to 'llvm/test/CodeGen')
-rw-r--r-- | llvm/test/CodeGen/AArch64/O3-pipeline.ll | 4 | ||||
-rw-r--r-- | llvm/test/CodeGen/AArch64/bcmp-inline-small.ll | 44 | ||||
-rw-r--r-- | llvm/test/CodeGen/ARM/O3-pipeline.ll | 4 | ||||
-rw-r--r-- | llvm/test/CodeGen/Generic/llc-start-stop.ll | 6 | ||||
-rw-r--r-- | llvm/test/CodeGen/PowerPC/memCmpUsedInZeroEqualityComparison.ll | 218 | ||||
-rw-r--r-- | llvm/test/CodeGen/PowerPC/memcmp-mergeexpand.ll | 40 | ||||
-rw-r--r-- | llvm/test/CodeGen/PowerPC/memcmp.ll | 70 | ||||
-rw-r--r-- | llvm/test/CodeGen/PowerPC/memcmpIR.ll | 192 | ||||
-rw-r--r-- | llvm/test/CodeGen/X86/O3-pipeline.ll | 4 | ||||
-rw-r--r-- | llvm/test/CodeGen/X86/memcmp-mergeexpand.ll | 51 | ||||
-rw-r--r-- | llvm/test/CodeGen/X86/memcmp-optsize.ll | 1013 | ||||
-rw-r--r-- | llvm/test/CodeGen/X86/memcmp.ll | 1685 |
12 files changed, 3 insertions, 3328 deletions
diff --git a/llvm/test/CodeGen/AArch64/O3-pipeline.ll b/llvm/test/CodeGen/AArch64/O3-pipeline.ll index 2d5f6675100..f7a3410ada1 100644 --- a/llvm/test/CodeGen/AArch64/O3-pipeline.ll +++ b/llvm/test/CodeGen/AArch64/O3-pipeline.ll @@ -32,10 +32,6 @@ ; CHECK-NEXT: Loop Pass Manager ; CHECK-NEXT: Induction Variable Users ; CHECK-NEXT: Loop Strength Reduction -; CHECK-NEXT: Basic Alias Analysis (stateless AA impl) -; CHECK-NEXT: Function Alias Analysis Results -; CHECK-NEXT: Merge contiguous icmps into a memcmp -; CHECK-NEXT: Expand memcmp() to load/stores ; CHECK-NEXT: Lower Garbage Collection Instructions ; CHECK-NEXT: Shadow Stack GC Lowering ; CHECK-NEXT: Remove unreachable blocks from the CFG diff --git a/llvm/test/CodeGen/AArch64/bcmp-inline-small.ll b/llvm/test/CodeGen/AArch64/bcmp-inline-small.ll deleted file mode 100644 index da42b1d6863..00000000000 --- a/llvm/test/CodeGen/AArch64/bcmp-inline-small.ll +++ /dev/null @@ -1,44 +0,0 @@ -; RUN: llc -O2 < %s -mtriple=aarch64-linux-gnu | FileCheck %s --check-prefixes=CHECK,CHECKN -; RUN: llc -O2 < %s -mtriple=aarch64-linux-gnu -mattr=strict-align | FileCheck %s --check-prefixes=CHECK,CHECKS - -declare i32 @bcmp(i8*, i8*, i64) nounwind readonly -declare i32 @memcmp(i8*, i8*, i64) nounwind readonly - -define i1 @bcmp_b2(i8* %s1, i8* %s2) { -entry: - %bcmp = call i32 @bcmp(i8* %s1, i8* %s2, i64 15) - %ret = icmp eq i32 %bcmp, 0 - ret i1 %ret - -; CHECK-LABEL: bcmp_b2: -; CHECK-NOT: bl bcmp -; CHECKN: ldr x -; CHECKN-NEXT: ldr x -; CHECKN-NEXT: ldur x -; CHECKN-NEXT: ldur x -; CHECKS: ldr x -; CHECKS-NEXT: ldr x -; CHECKS-NEXT: ldr w -; CHECKS-NEXT: ldr w -; CHECKS-NEXT: ldrh w -; CHECKS-NEXT: ldrh w -; CHECKS-NEXT: ldrb w -; CHECKS-NEXT: ldrb w -} - -define i1 @bcmp_bs(i8* %s1, i8* %s2) optsize { -entry: - %memcmp = call i32 @memcmp(i8* %s1, i8* %s2, i64 31) - %ret = icmp eq i32 %memcmp, 0 - ret i1 %ret - -; CHECK-LABEL: bcmp_bs: -; CHECKN-NOT: bl memcmp -; CHECKN: ldp x -; CHECKN-NEXT: ldp x -; CHECKN-NEXT: ldr x -; CHECKN-NEXT: ldr x -; CHECKN-NEXT: ldur x -; CHECKN-NEXT: ldur x -; CHECKS: bl memcmp -} diff --git a/llvm/test/CodeGen/ARM/O3-pipeline.ll b/llvm/test/CodeGen/ARM/O3-pipeline.ll index 7650d682736..2a64046236c 100644 --- a/llvm/test/CodeGen/ARM/O3-pipeline.ll +++ b/llvm/test/CodeGen/ARM/O3-pipeline.ll @@ -16,10 +16,6 @@ ; CHECK-NEXT: Loop Pass Manager ; CHECK-NEXT: Induction Variable Users ; CHECK-NEXT: Loop Strength Reduction -; CHECK-NEXT: Basic Alias Analysis (stateless AA impl) -; CHECK-NEXT: Function Alias Analysis Results -; CHECK-NEXT: Merge contiguous icmps into a memcmp -; CHECK-NEXT: Expand memcmp() to load/stores ; CHECK-NEXT: Lower Garbage Collection Instructions ; CHECK-NEXT: Shadow Stack GC Lowering ; CHECK-NEXT: Remove unreachable blocks from the CFG diff --git a/llvm/test/CodeGen/Generic/llc-start-stop.ll b/llvm/test/CodeGen/Generic/llc-start-stop.ll index fa34838a411..1fc01533d35 100644 --- a/llvm/test/CodeGen/Generic/llc-start-stop.ll +++ b/llvm/test/CodeGen/Generic/llc-start-stop.ll @@ -13,15 +13,15 @@ ; STOP-BEFORE-NOT: Loop Strength Reduction ; RUN: llc < %s -debug-pass=Structure -start-after=loop-reduce -o /dev/null 2>&1 | FileCheck %s -check-prefix=START-AFTER -; START-AFTER: -aa -mergeicmps +; START-AFTER: -gc-lowering ; START-AFTER: FunctionPass Manager -; START-AFTER-NEXT: Dominator Tree Construction +; START-AFTER-NEXT: Lower Garbage Collection Instructions ; RUN: llc < %s -debug-pass=Structure -start-before=loop-reduce -o /dev/null 2>&1 | FileCheck %s -check-prefix=START-BEFORE ; START-BEFORE: -machine-branch-prob -domtree ; START-BEFORE: FunctionPass Manager ; START-BEFORE: Loop Strength Reduction -; START-BEFORE-NEXT: Basic Alias Analysis (stateless AA impl) +; START-BEFORE-NEXT: Lower Garbage Collection Instructions ; RUN: not llc < %s -start-before=nonexistent -o /dev/null 2>&1 | FileCheck %s -check-prefix=NONEXISTENT-START-BEFORE ; RUN: not llc < %s -stop-before=nonexistent -o /dev/null 2>&1 | FileCheck %s -check-prefix=NONEXISTENT-STOP-BEFORE diff --git a/llvm/test/CodeGen/PowerPC/memCmpUsedInZeroEqualityComparison.ll b/llvm/test/CodeGen/PowerPC/memCmpUsedInZeroEqualityComparison.ll deleted file mode 100644 index 334dac9fcfc..00000000000 --- a/llvm/test/CodeGen/PowerPC/memCmpUsedInZeroEqualityComparison.ll +++ /dev/null @@ -1,218 +0,0 @@ -; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py -; RUN: llc -ppc-gpr-icmps=all -verify-machineinstrs -mcpu=pwr8 < %s | FileCheck %s -target datalayout = "e-m:e-i64:64-n32:64" -target triple = "powerpc64le-unknown-linux-gnu" - -@zeroEqualityTest01.buffer1 = private unnamed_addr constant [3 x i32] [i32 1, i32 2, i32 4], align 4 -@zeroEqualityTest01.buffer2 = private unnamed_addr constant [3 x i32] [i32 1, i32 2, i32 3], align 4 -@zeroEqualityTest02.buffer1 = private unnamed_addr constant [4 x i32] [i32 4, i32 0, i32 0, i32 0], align 4 -@zeroEqualityTest02.buffer2 = private unnamed_addr constant [4 x i32] [i32 3, i32 0, i32 0, i32 0], align 4 -@zeroEqualityTest03.buffer1 = private unnamed_addr constant [4 x i32] [i32 0, i32 0, i32 0, i32 3], align 4 -@zeroEqualityTest03.buffer2 = private unnamed_addr constant [4 x i32] [i32 0, i32 0, i32 0, i32 4], align 4 -@zeroEqualityTest04.buffer1 = private unnamed_addr constant [15 x i32] [i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14], align 4 -@zeroEqualityTest04.buffer2 = private unnamed_addr constant [15 x i32] [i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 13], align 4 - -declare signext i32 @memcmp(i8* nocapture, i8* nocapture, i64) local_unnamed_addr #1 - -; Check 4 bytes - requires 1 load for each param. -define signext i32 @zeroEqualityTest02(i8* %x, i8* %y) { -; CHECK-LABEL: zeroEqualityTest02: -; CHECK: # %bb.0: -; CHECK-NEXT: lwz 3, 0(3) -; CHECK-NEXT: lwz 4, 0(4) -; CHECK-NEXT: xor 3, 3, 4 -; CHECK-NEXT: cntlzw 3, 3 -; CHECK-NEXT: srwi 3, 3, 5 -; CHECK-NEXT: xori 3, 3, 1 -; CHECK-NEXT: blr - %call = tail call signext i32 @memcmp(i8* %x, i8* %y, i64 4) - %not.cmp = icmp ne i32 %call, 0 - %. = zext i1 %not.cmp to i32 - ret i32 %. -} - -; Check 16 bytes - requires 2 loads for each param (or use vectors?). -define signext i32 @zeroEqualityTest01(i8* %x, i8* %y) { -; CHECK-LABEL: zeroEqualityTest01: -; CHECK: # %bb.0: -; CHECK-NEXT: ld 5, 0(3) -; CHECK-NEXT: ld 6, 0(4) -; CHECK-NEXT: cmpld 5, 6 -; CHECK-NEXT: bne 0, .LBB1_2 -; CHECK-NEXT: # %bb.1: # %loadbb1 -; CHECK-NEXT: ld 3, 8(3) -; CHECK-NEXT: ld 4, 8(4) -; CHECK-NEXT: cmpld 3, 4 -; CHECK-NEXT: li 3, 0 -; CHECK-NEXT: beq 0, .LBB1_3 -; CHECK-NEXT: .LBB1_2: # %res_block -; CHECK-NEXT: li 3, 1 -; CHECK-NEXT: .LBB1_3: # %endblock -; CHECK-NEXT: clrldi 3, 3, 32 -; CHECK-NEXT: blr - %call = tail call signext i32 @memcmp(i8* %x, i8* %y, i64 16) - %not.tobool = icmp ne i32 %call, 0 - %. = zext i1 %not.tobool to i32 - ret i32 %. -} - -; Check 7 bytes - requires 3 loads for each param. -define signext i32 @zeroEqualityTest03(i8* %x, i8* %y) { -; CHECK-LABEL: zeroEqualityTest03: -; CHECK: # %bb.0: -; CHECK-NEXT: lwz 5, 0(3) -; CHECK-NEXT: lwz 6, 0(4) -; CHECK-NEXT: cmplw 5, 6 -; CHECK-NEXT: bne 0, .LBB2_3 -; CHECK-NEXT: # %bb.1: # %loadbb1 -; CHECK-NEXT: lhz 5, 4(3) -; CHECK-NEXT: lhz 6, 4(4) -; CHECK-NEXT: cmplw 5, 6 -; CHECK-NEXT: bne 0, .LBB2_3 -; CHECK-NEXT: # %bb.2: # %loadbb2 -; CHECK-NEXT: lbz 3, 6(3) -; CHECK-NEXT: lbz 4, 6(4) -; CHECK-NEXT: cmplw 3, 4 -; CHECK-NEXT: li 3, 0 -; CHECK-NEXT: beq 0, .LBB2_4 -; CHECK-NEXT: .LBB2_3: # %res_block -; CHECK-NEXT: li 3, 1 -; CHECK-NEXT: .LBB2_4: # %endblock -; CHECK-NEXT: clrldi 3, 3, 32 -; CHECK-NEXT: blr - %call = tail call signext i32 @memcmp(i8* %x, i8* %y, i64 7) - %not.lnot = icmp ne i32 %call, 0 - %cond = zext i1 %not.lnot to i32 - ret i32 %cond -} - -; Validate with > 0 -define signext i32 @zeroEqualityTest04() { -; CHECK-LABEL: zeroEqualityTest04: -; CHECK: # %bb.0: -; CHECK-NEXT: addis 3, 2, .LzeroEqualityTest02.buffer1@toc@ha -; CHECK-NEXT: addis 4, 2, .LzeroEqualityTest02.buffer2@toc@ha -; CHECK-NEXT: addi 6, 3, .LzeroEqualityTest02.buffer1@toc@l -; CHECK-NEXT: addi 5, 4, .LzeroEqualityTest02.buffer2@toc@l -; CHECK-NEXT: ldbrx 3, 0, 6 -; CHECK-NEXT: ldbrx 4, 0, 5 -; CHECK-NEXT: cmpld 3, 4 -; CHECK-NEXT: bne 0, .LBB3_2 -; CHECK-NEXT: # %bb.1: # %loadbb1 -; CHECK-NEXT: li 4, 8 -; CHECK-NEXT: ldbrx 3, 6, 4 -; CHECK-NEXT: ldbrx 4, 5, 4 -; CHECK-NEXT: li 5, 0 -; CHECK-NEXT: cmpld 3, 4 -; CHECK-NEXT: beq 0, .LBB3_3 -; CHECK-NEXT: .LBB3_2: # %res_block -; CHECK-NEXT: cmpld 3, 4 -; CHECK-NEXT: li 3, 1 -; CHECK-NEXT: li 4, -1 -; CHECK-NEXT: isel 5, 4, 3, 0 -; CHECK-NEXT: .LBB3_3: # %endblock -; CHECK-NEXT: extsw 3, 5 -; CHECK-NEXT: neg 3, 3 -; CHECK-NEXT: rldicl 3, 3, 1, 63 -; CHECK-NEXT: xori 3, 3, 1 -; CHECK-NEXT: blr - %call = tail call signext i32 @memcmp(i8* bitcast ([4 x i32]* @zeroEqualityTest02.buffer1 to i8*), i8* bitcast ([4 x i32]* @zeroEqualityTest02.buffer2 to i8*), i64 16) - %not.cmp = icmp slt i32 %call, 1 - %. = zext i1 %not.cmp to i32 - ret i32 %. -} - -; Validate with < 0 -define signext i32 @zeroEqualityTest05() { -; CHECK-LABEL: zeroEqualityTest05: -; CHECK: # %bb.0: -; CHECK-NEXT: addis 3, 2, .LzeroEqualityTest03.buffer1@toc@ha -; CHECK-NEXT: addis 4, 2, .LzeroEqualityTest03.buffer2@toc@ha -; CHECK-NEXT: addi 6, 3, .LzeroEqualityTest03.buffer1@toc@l -; CHECK-NEXT: addi 5, 4, .LzeroEqualityTest03.buffer2@toc@l -; CHECK-NEXT: ldbrx 3, 0, 6 -; CHECK-NEXT: ldbrx 4, 0, 5 -; CHECK-NEXT: cmpld 3, 4 -; CHECK-NEXT: bne 0, .LBB4_2 -; CHECK-NEXT: # %bb.1: # %loadbb1 -; CHECK-NEXT: li 4, 8 -; CHECK-NEXT: ldbrx 3, 6, 4 -; CHECK-NEXT: ldbrx 4, 5, 4 -; CHECK-NEXT: li 5, 0 -; CHECK-NEXT: cmpld 3, 4 -; CHECK-NEXT: beq 0, .LBB4_3 -; CHECK-NEXT: .LBB4_2: # %res_block -; CHECK-NEXT: cmpld 3, 4 -; CHECK-NEXT: li 3, 1 -; CHECK-NEXT: li 4, -1 -; CHECK-NEXT: isel 5, 4, 3, 0 -; CHECK-NEXT: .LBB4_3: # %endblock -; CHECK-NEXT: nor 3, 5, 5 -; CHECK-NEXT: rlwinm 3, 3, 1, 31, 31 -; CHECK-NEXT: blr - %call = tail call signext i32 @memcmp(i8* bitcast ([4 x i32]* @zeroEqualityTest03.buffer1 to i8*), i8* bitcast ([4 x i32]* @zeroEqualityTest03.buffer2 to i8*), i64 16) - %call.lobit = lshr i32 %call, 31 - %call.lobit.not = xor i32 %call.lobit, 1 - ret i32 %call.lobit.not -} - -; Validate with memcmp()?: -define signext i32 @equalityFoldTwoConstants() { -; CHECK-LABEL: equalityFoldTwoConstants: -; CHECK: # %bb.0: # %loadbb -; CHECK-NEXT: li 3, 1 -; CHECK-NEXT: blr - %call = tail call signext i32 @memcmp(i8* bitcast ([15 x i32]* @zeroEqualityTest04.buffer1 to i8*), i8* bitcast ([15 x i32]* @zeroEqualityTest04.buffer2 to i8*), i64 16) - %not.tobool = icmp eq i32 %call, 0 - %cond = zext i1 %not.tobool to i32 - ret i32 %cond -} - -define signext i32 @equalityFoldOneConstant(i8* %X) { -; CHECK-LABEL: equalityFoldOneConstant: -; CHECK: # %bb.0: -; CHECK-NEXT: ld 4, 0(3) -; CHECK-NEXT: li 5, 1 -; CHECK-NEXT: sldi 5, 5, 32 -; CHECK-NEXT: cmpld 4, 5 -; CHECK-NEXT: bne 0, .LBB6_2 -; CHECK-NEXT: # %bb.1: # %loadbb1 -; CHECK-NEXT: li 4, 3 -; CHECK-NEXT: ld 3, 8(3) -; CHECK-NEXT: sldi 4, 4, 32 -; CHECK-NEXT: ori 4, 4, 2 -; CHECK-NEXT: cmpld 3, 4 -; CHECK-NEXT: li 3, 0 -; CHECK-NEXT: beq 0, .LBB6_3 -; CHECK-NEXT: .LBB6_2: # %res_block -; CHECK-NEXT: li 3, 1 -; CHECK-NEXT: .LBB6_3: # %endblock -; CHECK-NEXT: cntlzw 3, 3 -; CHECK-NEXT: srwi 3, 3, 5 -; CHECK-NEXT: blr - %call = tail call signext i32 @memcmp(i8* bitcast ([15 x i32]* @zeroEqualityTest04.buffer1 to i8*), i8* %X, i64 16) - %not.tobool = icmp eq i32 %call, 0 - %cond = zext i1 %not.tobool to i32 - ret i32 %cond -} - -define i1 @length2_eq_nobuiltin_attr(i8* %X, i8* %Y) nounwind { -; CHECK-LABEL: length2_eq_nobuiltin_attr: -; CHECK: # %bb.0: -; CHECK-NEXT: mflr 0 -; CHECK-NEXT: std 0, 16(1) -; CHECK-NEXT: stdu 1, -32(1) -; CHECK-NEXT: li 5, 2 -; CHECK-NEXT: bl memcmp -; CHECK-NEXT: nop -; CHECK-NEXT: cntlzw 3, 3 -; CHECK-NEXT: rlwinm 3, 3, 27, 31, 31 -; CHECK-NEXT: addi 1, 1, 32 -; CHECK-NEXT: ld 0, 16(1) -; CHECK-NEXT: mtlr 0 -; CHECK-NEXT: blr - %m = tail call signext i32 @memcmp(i8* %X, i8* %Y, i64 2) nobuiltin - %c = icmp eq i32 %m, 0 - ret i1 %c -} - diff --git a/llvm/test/CodeGen/PowerPC/memcmp-mergeexpand.ll b/llvm/test/CodeGen/PowerPC/memcmp-mergeexpand.ll deleted file mode 100644 index 298ce90b74e..00000000000 --- a/llvm/test/CodeGen/PowerPC/memcmp-mergeexpand.ll +++ /dev/null @@ -1,40 +0,0 @@ -; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py -; RUN: llc -verify-machineinstrs -mcpu=pwr8 -mtriple=powerpc64le-unknown-gnu-linux < %s | FileCheck %s -check-prefix=PPC64LE - -; This tests interaction between MergeICmp and ExpandMemCmp. - -%"struct.std::pair" = type { i32, i32 } - -define zeroext i1 @opeq1( -; PPC64LE-LABEL: opeq1: -; PPC64LE: # %bb.0: # %"entry+land.rhs.i" -; PPC64LE-NEXT: ld 3, 0(3) -; PPC64LE-NEXT: ld 4, 0(4) -; PPC64LE-NEXT: xor 3, 3, 4 -; PPC64LE-NEXT: cntlzd 3, 3 -; PPC64LE-NEXT: rldicl 3, 3, 58, 63 -; PPC64LE-NEXT: blr - %"struct.std::pair"* nocapture readonly dereferenceable(8) %a, - %"struct.std::pair"* nocapture readonly dereferenceable(8) %b) local_unnamed_addr #0 { -entry: - %first.i = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* %a, i64 0, i32 0 - %0 = load i32, i32* %first.i, align 4 - %first1.i = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* %b, i64 0, i32 0 - %1 = load i32, i32* %first1.i, align 4 - %cmp.i = icmp eq i32 %0, %1 - br i1 %cmp.i, label %land.rhs.i, label %opeq1.exit - -land.rhs.i: - %second.i = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* %a, i64 0, i32 1 - %2 = load i32, i32* %second.i, align 4 - %second2.i = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* %b, i64 0, i32 1 - %3 = load i32, i32* %second2.i, align 4 - %cmp3.i = icmp eq i32 %2, %3 - br label %opeq1.exit - -opeq1.exit: - %4 = phi i1 [ false, %entry ], [ %cmp3.i, %land.rhs.i ] - ret i1 %4 -} - - diff --git a/llvm/test/CodeGen/PowerPC/memcmp.ll b/llvm/test/CodeGen/PowerPC/memcmp.ll deleted file mode 100644 index 4aa5b400dd7..00000000000 --- a/llvm/test/CodeGen/PowerPC/memcmp.ll +++ /dev/null @@ -1,70 +0,0 @@ -; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py -; RUN: llc -verify-machineinstrs -mcpu=pwr8 -mtriple=powerpc64le-unknown-gnu-linux < %s | FileCheck %s -check-prefix=CHECK - -define signext i32 @memcmp8(i32* nocapture readonly %buffer1, i32* nocapture readonly %buffer2) { -; CHECK-LABEL: memcmp8: -; CHECK: # %bb.0: -; CHECK-NEXT: ldbrx 3, 0, 3 -; CHECK-NEXT: ldbrx 4, 0, 4 -; CHECK-NEXT: subfc 5, 3, 4 -; CHECK-NEXT: subfe 5, 4, 4 -; CHECK-NEXT: subfc 4, 4, 3 -; CHECK-NEXT: subfe 3, 3, 3 -; CHECK-NEXT: neg 4, 5 -; CHECK-NEXT: neg 3, 3 -; CHECK-NEXT: subf 3, 3, 4 -; CHECK-NEXT: extsw 3, 3 -; CHECK-NEXT: blr - %t0 = bitcast i32* %buffer1 to i8* - %t1 = bitcast i32* %buffer2 to i8* - %call = tail call signext i32 @memcmp(i8* %t0, i8* %t1, i64 8) - ret i32 %call -} - -define signext i32 @memcmp4(i32* nocapture readonly %buffer1, i32* nocapture readonly %buffer2) { -; CHECK-LABEL: memcmp4: -; CHECK: # %bb.0: -; CHECK-NEXT: lwbrx 3, 0, 3 -; CHECK-NEXT: lwbrx 4, 0, 4 -; CHECK-NEXT: sub 5, 4, 3 -; CHECK-NEXT: sub 3, 3, 4 -; CHECK-NEXT: rldicl 4, 5, 1, 63 -; CHECK-NEXT: rldicl 3, 3, 1, 63 -; CHECK-NEXT: subf 3, 3, 4 -; CHECK-NEXT: extsw 3, 3 -; CHECK-NEXT: blr - %t0 = bitcast i32* %buffer1 to i8* - %t1 = bitcast i32* %buffer2 to i8* - %call = tail call signext i32 @memcmp(i8* %t0, i8* %t1, i64 4) - ret i32 %call -} - -define signext i32 @memcmp2(i32* nocapture readonly %buffer1, i32* nocapture readonly %buffer2) { -; CHECK-LABEL: memcmp2: -; CHECK: # %bb.0: -; CHECK-NEXT: lhbrx 3, 0, 3 -; CHECK-NEXT: lhbrx 4, 0, 4 -; CHECK-NEXT: subf 3, 4, 3 -; CHECK-NEXT: extsw 3, 3 -; CHECK-NEXT: blr - %t0 = bitcast i32* %buffer1 to i8* - %t1 = bitcast i32* %buffer2 to i8* - %call = tail call signext i32 @memcmp(i8* %t0, i8* %t1, i64 2) - ret i32 %call -} - -define signext i32 @memcmp1(i32* nocapture readonly %buffer1, i32* nocapture readonly %buffer2) { -; CHECK-LABEL: memcmp1: -; CHECK: # %bb.0: -; CHECK-NEXT: lbz 3, 0(3) -; CHECK-NEXT: lbz 4, 0(4) -; CHECK-NEXT: subf 3, 4, 3 -; CHECK-NEXT: extsw 3, 3 -; CHECK-NEXT: blr - %t0 = bitcast i32* %buffer1 to i8* - %t1 = bitcast i32* %buffer2 to i8* - %call = tail call signext i32 @memcmp(i8* %t0, i8* %t1, i64 1) #2 - ret i32 %call -} - -declare signext i32 @memcmp(i8*, i8*, i64) diff --git a/llvm/test/CodeGen/PowerPC/memcmpIR.ll b/llvm/test/CodeGen/PowerPC/memcmpIR.ll deleted file mode 100644 index 4c0de720fc6..00000000000 --- a/llvm/test/CodeGen/PowerPC/memcmpIR.ll +++ /dev/null @@ -1,192 +0,0 @@ -; RUN: llc -o - -mtriple=powerpc64le-unknown-gnu-linux -stop-after codegenprepare %s | FileCheck %s -; RUN: llc -o - -mtriple=powerpc64-unknown-gnu-linux -stop-after codegenprepare %s | FileCheck %s --check-prefix=CHECK-BE - -define signext i32 @test1(i32* nocapture readonly %buffer1, i32* nocapture readonly %buffer2) { -entry: - ; CHECK-LABEL: @test1( - ; CHECK: [[LOAD1:%[0-9]+]] = load i64, i64* - ; CHECK-NEXT: [[LOAD2:%[0-9]+]] = load i64, i64* - ; CHECK-NEXT: [[BSWAP1:%[0-9]+]] = call i64 @llvm.bswap.i64(i64 [[LOAD1]]) - ; CHECK-NEXT: [[BSWAP2:%[0-9]+]] = call i64 @llvm.bswap.i64(i64 [[LOAD2]]) - ; CHECK-NEXT: [[ICMP:%[0-9]+]] = icmp eq i64 [[BSWAP1]], [[BSWAP2]] - ; CHECK-NEXT: br i1 [[ICMP]], label %loadbb1, label %res_block - - ; CHECK-LABEL: res_block:{{.*}} - ; CHECK: [[ICMP2:%[0-9]+]] = icmp ult i64 - ; CHECK-NEXT: [[SELECT:%[0-9]+]] = select i1 [[ICMP2]], i32 -1, i32 1 - ; CHECK-NEXT: br label %endblock - - ; CHECK-LABEL: loadbb1:{{.*}} - ; CHECK: [[BCC1:%[0-9]+]] = bitcast i32* {{.*}} to i8* - ; CHECK-NEXT: [[BCC2:%[0-9]+]] = bitcast i32* {{.*}} to i8* - ; CHECK-NEXT: [[GEP1:%[0-9]+]] = getelementptr i8, i8* [[BCC2]], i8 8 - ; CHECK-NEXT: [[BCL1:%[0-9]+]] = bitcast i8* [[GEP1]] to i64* - ; CHECK-NEXT: [[GEP2:%[0-9]+]] = getelementptr i8, i8* [[BCC1]], i8 8 - ; CHECK-NEXT: [[BCL2:%[0-9]+]] = bitcast i8* [[GEP2]] to i64* - ; CHECK-NEXT: [[LOAD1:%[0-9]+]] = load i64, i64* [[BCL1]] - ; CHECK-NEXT: [[LOAD2:%[0-9]+]] = load i64, i64* [[BCL2]] - ; CHECK-NEXT: [[BSWAP1:%[0-9]+]] = call i64 @llvm.bswap.i64(i64 [[LOAD1]]) - ; CHECK-NEXT: [[BSWAP2:%[0-9]+]] = call i64 @llvm.bswap.i64(i64 [[LOAD2]]) - ; CHECK-NEXT: [[ICMP:%[0-9]+]] = icmp eq i64 [[BSWAP1]], [[BSWAP2]] - ; CHECK-NEXT: br i1 [[ICMP]], label %endblock, label %res_block - - ; CHECK-BE-LABEL: @test1( - ; CHECK-BE: [[LOAD1:%[0-9]+]] = load i64, i64* - ; CHECK-BE-NEXT: [[LOAD2:%[0-9]+]] = load i64, i64* - ; CHECK-BE-NEXT: [[ICMP:%[0-9]+]] = icmp eq i64 [[LOAD1]], [[LOAD2]] - ; CHECK-BE-NEXT: br i1 [[ICMP]], label %loadbb1, label %res_block - - ; CHECK-BE-LABEL: res_block:{{.*}} - ; CHECK-BE: [[ICMP2:%[0-9]+]] = icmp ult i64 - ; CHECK-BE-NEXT: [[SELECT:%[0-9]+]] = select i1 [[ICMP2]], i32 -1, i32 1 - ; CHECK-BE-NEXT: br label %endblock - - ; CHECK-BE-LABEL: loadbb1:{{.*}} - ; CHECK-BE: [[BCC1:%[0-9]+]] = bitcast i32* {{.*}} to i8* - ; CHECK-BE-NEXT: [[BCC2:%[0-9]+]] = bitcast i32* {{.*}} to i8* - ; CHECK-BE-NEXT: [[GEP1:%[0-9]+]] = getelementptr i8, i8* [[BCC2]], i8 8 - ; CHECK-BE-NEXT: [[BCL1:%[0-9]+]] = bitcast i8* [[GEP1]] to i64* - ; CHECK-BE-NEXT: [[GEP2:%[0-9]+]] = getelementptr i8, i8* [[BCC1]], i8 8 - ; CHECK-BE-NEXT: [[BCL2:%[0-9]+]] = bitcast i8* [[GEP2]] to i64* - ; CHECK-BE-NEXT: [[LOAD1:%[0-9]+]] = load i64, i64* [[BCL1]] - ; CHECK-BE-NEXT: [[LOAD2:%[0-9]+]] = load i64, i64* [[BCL2]] - ; CHECK-BE-NEXT: [[ICMP:%[0-9]+]] = icmp eq i64 [[LOAD1]], [[LOAD2]] - ; CHECK-BE-NEXT: br i1 [[ICMP]], label %endblock, label %res_block - - %0 = bitcast i32* %buffer1 to i8* - %1 = bitcast i32* %buffer2 to i8* - %call = tail call signext i32 @memcmp(i8* %0, i8* %1, i64 16) - ret i32 %call -} - -declare signext i32 @memcmp(i8* nocapture, i8* nocapture, i64) local_unnamed_addr #1 - -define signext i32 @test2(i32* nocapture readonly %buffer1, i32* nocapture readonly %buffer2) { - ; CHECK-LABEL: @test2( - ; CHECK: [[LOAD1:%[0-9]+]] = load i32, i32* - ; CHECK-NEXT: [[LOAD2:%[0-9]+]] = load i32, i32* - ; CHECK-NEXT: [[BSWAP1:%[0-9]+]] = call i32 @llvm.bswap.i32(i32 [[LOAD1]]) - ; CHECK-NEXT: [[BSWAP2:%[0-9]+]] = call i32 @llvm.bswap.i32(i32 [[LOAD2]]) - ; CHECK-NEXT: [[CMP1:%[0-9]+]] = icmp ugt i32 [[BSWAP1]], [[BSWAP2]] - ; CHECK-NEXT: [[CMP2:%[0-9]+]] = icmp ult i32 [[BSWAP1]], [[BSWAP2]] - ; CHECK-NEXT: [[Z1:%[0-9]+]] = zext i1 [[CMP1]] to i32 - ; CHECK-NEXT: [[Z2:%[0-9]+]] = zext i1 [[CMP2]] to i32 - ; CHECK-NEXT: [[SUB:%[0-9]+]] = sub i32 [[Z1]], [[Z2]] - ; CHECK-NEXT: ret i32 [[SUB]] - - ; CHECK-BE-LABEL: @test2( - ; CHECK-BE: [[LOAD1:%[0-9]+]] = load i32, i32* - ; CHECK-BE-NEXT: [[LOAD2:%[0-9]+]] = load i32, i32* - ; CHECK-BE-NEXT: [[CMP1:%[0-9]+]] = icmp ugt i32 [[LOAD1]], [[LOAD2]] - ; CHECK-BE-NEXT: [[CMP2:%[0-9]+]] = icmp ult i32 [[LOAD1]], [[LOAD2]] - ; CHECK-BE-NEXT: [[Z1:%[0-9]+]] = zext i1 [[CMP1]] to i32 - ; CHECK-BE-NEXT: [[Z2:%[0-9]+]] = zext i1 [[CMP2]] to i32 - ; CHECK-BE-NEXT: [[SUB:%[0-9]+]] = sub i32 [[Z1]], [[Z2]] - ; CHECK-BE-NEXT: ret i32 [[SUB]] - -entry: - %0 = bitcast i32* %buffer1 to i8* - %1 = bitcast i32* %buffer2 to i8* - %call = tail call signext i32 @memcmp(i8* %0, i8* %1, i64 4) - ret i32 %call -} - -define signext i32 @test3(i32* nocapture readonly %buffer1, i32* nocapture readonly %buffer2) { - ; CHECK: [[LOAD1:%[0-9]+]] = load i64, i64* - ; CHECK-NEXT: [[LOAD2:%[0-9]+]] = load i64, i64* - ; CHECK-NEXT: [[BSWAP1:%[0-9]+]] = call i64 @llvm.bswap.i64(i64 [[LOAD1]]) - ; CHECK-NEXT: [[BSWAP2:%[0-9]+]] = call i64 @llvm.bswap.i64(i64 [[LOAD2]]) - ; CHECK-NEXT: [[ICMP:%[0-9]+]] = icmp eq i64 [[BSWAP1]], [[BSWAP2]] - ; CHECK-NEXT: br i1 [[ICMP]], label %loadbb1, label %res_block - - ; CHECK-LABEL: res_block:{{.*}} - ; CHECK: [[ICMP2:%[0-9]+]] = icmp ult i64 - ; CHECK-NEXT: [[SELECT:%[0-9]+]] = select i1 [[ICMP2]], i32 -1, i32 1 - ; CHECK-NEXT: br label %endblock - - ; CHECK-LABEL: loadbb1:{{.*}} - ; CHECK: [[LOAD1:%[0-9]+]] = load i32, i32* - ; CHECK-NEXT: [[LOAD2:%[0-9]+]] = load i32, i32* - ; CHECK-NEXT: [[BSWAP1:%[0-9]+]] = call i32 @llvm.bswap.i32(i32 [[LOAD1]]) - ; CHECK-NEXT: [[BSWAP2:%[0-9]+]] = call i32 @llvm.bswap.i32(i32 [[LOAD2]]) - ; CHECK-NEXT: [[ZEXT1:%[0-9]+]] = zext i32 [[BSWAP1]] to i64 - ; CHECK-NEXT: [[ZEXT2:%[0-9]+]] = zext i32 [[BSWAP2]] to i64 - ; CHECK-NEXT: [[ICMP:%[0-9]+]] = icmp eq i64 [[ZEXT1]], [[ZEXT2]] - ; CHECK-NEXT: br i1 [[ICMP]], label %loadbb2, label %res_block - - ; CHECK-LABEL: loadbb2:{{.*}} - ; CHECK: [[LOAD1:%[0-9]+]] = load i16, i16* - ; CHECK-NEXT: [[LOAD2:%[0-9]+]] = load i16, i16* - ; CHECK-NEXT: [[BSWAP1:%[0-9]+]] = call i16 @llvm.bswap.i16(i16 [[LOAD1]]) - ; CHECK-NEXT: [[BSWAP2:%[0-9]+]] = call i16 @llvm.bswap.i16(i16 [[LOAD2]]) - ; CHECK-NEXT: [[ZEXT1:%[0-9]+]] = zext i16 [[BSWAP1]] to i64 - ; CHECK-NEXT: [[ZEXT2:%[0-9]+]] = zext i16 [[BSWAP2]] to i64 - ; CHECK-NEXT: [[ICMP:%[0-9]+]] = icmp eq i64 [[ZEXT1]], [[ZEXT2]] - ; CHECK-NEXT: br i1 [[ICMP]], label %loadbb3, label %res_block - - ; CHECK-LABEL: loadbb3:{{.*}} - ; CHECK: [[LOAD1:%[0-9]+]] = load i8, i8* - ; CHECK-NEXT: [[LOAD2:%[0-9]+]] = load i8, i8* - ; CHECK-NEXT: [[ZEXT1:%[0-9]+]] = zext i8 [[LOAD1]] to i32 - ; CHECK-NEXT: [[ZEXT2:%[0-9]+]] = zext i8 [[LOAD2]] to i32 - ; CHECK-NEXT: [[SUB:%[0-9]+]] = sub i32 [[ZEXT1]], [[ZEXT2]] - ; CHECK-NEXT: br label %endblock - - ; CHECK-BE: [[LOAD1:%[0-9]+]] = load i64, i64* - ; CHECK-BE-NEXT: [[LOAD2:%[0-9]+]] = load i64, i64* - ; CHECK-BE-NEXT: [[ICMP:%[0-9]+]] = icmp eq i64 [[LOAD1]], [[LOAD2]] - ; CHECK-BE-NEXT: br i1 [[ICMP]], label %loadbb1, label %res_block - - ; CHECK-BE-LABEL: res_block:{{.*}} - ; CHECK-BE: [[ICMP2:%[0-9]+]] = icmp ult i64 - ; CHECK-BE-NEXT: [[SELECT:%[0-9]+]] = select i1 [[ICMP2]], i32 -1, i32 1 - ; CHECK-BE-NEXT: br label %endblock - - ; CHECK-BE: [[LOAD1:%[0-9]+]] = load i32, i32* - ; CHECK-BE-NEXT: [[LOAD2:%[0-9]+]] = load i32, i32* - ; CHECK-BE-NEXT: [[ZEXT1:%[0-9]+]] = zext i32 [[LOAD1]] to i64 - ; CHECK-BE-NEXT: [[ZEXT2:%[0-9]+]] = zext i32 [[LOAD2]] to i64 - ; CHECK-BE-NEXT: [[ICMP:%[0-9]+]] = icmp eq i64 [[ZEXT1]], [[ZEXT2]] - ; CHECK-BE-NEXT: br i1 [[ICMP]], label %loadbb2, label %res_block - - ; CHECK-BE: [[LOAD1:%[0-9]+]] = load i16, i16* - ; CHECK-BE-NEXT: [[LOAD2:%[0-9]+]] = load i16, i16* - ; CHECK-BE-NEXT: [[ZEXT1:%[0-9]+]] = zext i16 [[LOAD1]] to i64 - ; CHECK-BE-NEXT: [[ZEXT2:%[0-9]+]] = zext i16 [[LOAD2]] to i64 - ; CHECK-BE-NEXT: [[ICMP:%[0-9]+]] = icmp eq i64 [[ZEXT1]], [[ZEXT2]] - ; CHECK-BE-NEXT: br i1 [[ICMP]], label %loadbb3, label %res_block - - ; CHECK-BE: [[LOAD1:%[0-9]+]] = load i8, i8* - ; CHECK-BE-NEXT: [[LOAD2:%[0-9]+]] = load i8, i8* - ; CHECK-BE-NEXT: [[ZEXT1:%[0-9]+]] = zext i8 [[LOAD1]] to i32 - ; CHECK-BE-NEXT: [[ZEXT2:%[0-9]+]] = zext i8 [[LOAD2]] to i32 - ; CHECK-BE-NEXT: [[SUB:%[0-9]+]] = sub i32 [[ZEXT1]], [[ZEXT2]] - ; CHECK-BE-NEXT: br label %endblock - -entry: - %0 = bitcast i32* %buffer1 to i8* - %1 = bitcast i32* %buffer2 to i8* - %call = tail call signext i32 @memcmp(i8* %0, i8* %1, i64 15) - ret i32 %call -} - ; CHECK: call = tail call signext i32 @memcmp - ; CHECK-BE: call = tail call signext i32 @memcmp -define signext i32 @test4(i32* nocapture readonly %buffer1, i32* nocapture readonly %buffer2) { - -entry: - %0 = bitcast i32* %buffer1 to i8* - %1 = bitcast i32* %buffer2 to i8* - %call = tail call signext i32 @memcmp(i8* %0, i8* %1, i64 65) - ret i32 %call -} - -define signext i32 @test5(i32* nocapture readonly %buffer1, i32* nocapture readonly %buffer2, i32 signext %SIZE) { - ; CHECK: call = tail call signext i32 @memcmp - ; CHECK-BE: call = tail call signext i32 @memcmp -entry: - %0 = bitcast i32* %buffer1 to i8* - %1 = bitcast i32* %buffer2 to i8* - %conv = sext i32 %SIZE to i64 - %call = tail call signext i32 @memcmp(i8* %0, i8* %1, i64 %conv) - ret i32 %call -} diff --git a/llvm/test/CodeGen/X86/O3-pipeline.ll b/llvm/test/CodeGen/X86/O3-pipeline.ll index 48bc2992a7e..bc5fd0ee345 100644 --- a/llvm/test/CodeGen/X86/O3-pipeline.ll +++ b/llvm/test/CodeGen/X86/O3-pipeline.ll @@ -29,10 +29,6 @@ ; CHECK-NEXT: Loop Pass Manager ; CHECK-NEXT: Induction Variable Users ; CHECK-NEXT: Loop Strength Reduction -; CHECK-NEXT: Basic Alias Analysis (stateless AA impl) -; CHECK-NEXT: Function Alias Analysis Results -; CHECK-NEXT: Merge contiguous icmps into a memcmp -; CHECK-NEXT: Expand memcmp() to load/stores ; CHECK-NEXT: Lower Garbage Collection Instructions ; CHECK-NEXT: Shadow Stack GC Lowering ; CHECK-NEXT: Remove unreachable blocks from the CFG diff --git a/llvm/test/CodeGen/X86/memcmp-mergeexpand.ll b/llvm/test/CodeGen/X86/memcmp-mergeexpand.ll deleted file mode 100644 index 0be463daaeb..00000000000 --- a/llvm/test/CodeGen/X86/memcmp-mergeexpand.ll +++ /dev/null @@ -1,51 +0,0 @@ -; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py -; RUN: llc < %s -mtriple=i686-unknown-unknown | FileCheck %s --check-prefix=X86 -; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s --check-prefix=X64 - -; This tests interaction between MergeICmp and ExpandMemCmp. - -%"struct.std::pair" = type { i32, i32 } - -define zeroext i1 @opeq1( -; X86-LABEL: opeq1: -; X86: # %bb.0: # %"entry+land.rhs.i" -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-NEXT: movl (%ecx), %edx -; X86-NEXT: movl 4(%ecx), %ecx -; X86-NEXT: xorl (%eax), %edx -; X86-NEXT: xorl 4(%eax), %ecx -; X86-NEXT: orl %edx, %ecx -; X86-NEXT: sete %al -; X86-NEXT: retl -; -; X64-LABEL: opeq1: -; X64: # %bb.0: # %"entry+land.rhs.i" -; X64-NEXT: movq (%rdi), %rax -; X64-NEXT: cmpq (%rsi), %rax -; X64-NEXT: sete %al -; X64-NEXT: retq - %"struct.std::pair"* nocapture readonly dereferenceable(8) %a, - %"struct.std::pair"* nocapture readonly dereferenceable(8) %b) local_unnamed_addr #0 { -entry: - %first.i = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* %a, i64 0, i32 0 - %0 = load i32, i32* %first.i, align 4 - %first1.i = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* %b, i64 0, i32 0 - %1 = load i32, i32* %first1.i, align 4 - %cmp.i = icmp eq i32 %0, %1 - br i1 %cmp.i, label %land.rhs.i, label %opeq1.exit - -land.rhs.i: - %second.i = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* %a, i64 0, i32 1 - %2 = load i32, i32* %second.i, align 4 - %second2.i = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* %b, i64 0, i32 1 - %3 = load i32, i32* %second2.i, align 4 - %cmp3.i = icmp eq i32 %2, %3 - br label %opeq1.exit - -opeq1.exit: - %4 = phi i1 [ false, %entry ], [ %cmp3.i, %land.rhs.i ] - ret i1 %4 -} - - diff --git a/llvm/test/CodeGen/X86/memcmp-optsize.ll b/llvm/test/CodeGen/X86/memcmp-optsize.ll deleted file mode 100644 index b3bb3ab506f..00000000000 --- a/llvm/test/CodeGen/X86/memcmp-optsize.ll +++ /dev/null @@ -1,1013 +0,0 @@ -; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py -; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=cmov | FileCheck %s --check-prefix=X86 --check-prefix=X86-NOSSE -; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=X86 --check-prefix=X86-SSE2 -; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s --check-prefix=X64 --check-prefix=X64-SSE2 -; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx2 | FileCheck %s --check-prefix=X64 --check-prefix=X64-AVX2 - -; This tests codegen time inlining/optimization of memcmp -; rdar://6480398 - -@.str = private constant [65 x i8] c"0123456789012345678901234567890123456789012345678901234567890123\00", align 1 - -declare i32 @memcmp(i8*, i8*, i64) -declare i32 @bcmp(i8*, i8*, i64) - -define i32 @length2(i8* %X, i8* %Y) nounwind optsize { -; X86-LABEL: length2: -; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-NEXT: movzwl (%ecx), %ecx -; X86-NEXT: movzwl (%eax), %edx -; X86-NEXT: rolw $8, %cx -; X86-NEXT: rolw $8, %dx -; X86-NEXT: movzwl %cx, %eax -; X86-NEXT: movzwl %dx, %ecx -; X86-NEXT: subl %ecx, %eax -; X86-NEXT: retl -; -; X64-LABEL: length2: -; X64: # %bb.0: -; X64-NEXT: movzwl (%rdi), %eax -; X64-NEXT: movzwl (%rsi), %ecx -; X64-NEXT: rolw $8, %ax -; X64-NEXT: rolw $8, %cx -; X64-NEXT: movzwl %ax, %eax -; X64-NEXT: movzwl %cx, %ecx -; X64-NEXT: subl %ecx, %eax -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 2) nounwind - ret i32 %m -} - -define i1 @length2_eq(i8* %X, i8* %Y) nounwind optsize { -; X86-LABEL: length2_eq: -; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-NEXT: movzwl (%ecx), %ecx -; X86-NEXT: cmpw (%eax), %cx -; X86-NEXT: sete %al -; X86-NEXT: retl -; -; X64-LABEL: length2_eq: -; X64: # %bb.0: -; X64-NEXT: movzwl (%rdi), %eax -; X64-NEXT: cmpw (%rsi), %ax -; X64-NEXT: sete %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 2) nounwind - %c = icmp eq i32 %m, 0 - ret i1 %c -} - -define i1 @length2_eq_const(i8* %X) nounwind optsize { -; X86-LABEL: length2_eq_const: -; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movzwl (%eax), %eax -; X86-NEXT: cmpl $12849, %eax # imm = 0x3231 -; X86-NEXT: setne %al -; X86-NEXT: retl -; -; X64-LABEL: length2_eq_const: -; X64: # %bb.0: -; X64-NEXT: movzwl (%rdi), %eax -; X64-NEXT: cmpl $12849, %eax # imm = 0x3231 -; X64-NEXT: setne %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* getelementptr inbounds ([65 x i8], [65 x i8]* @.str, i32 0, i32 1), i64 2) nounwind - %c = icmp ne i32 %m, 0 - ret i1 %c -} - -define i1 @length2_eq_nobuiltin_attr(i8* %X, i8* %Y) nounwind optsize { -; X86-LABEL: length2_eq_nobuiltin_attr: -; X86: # %bb.0: -; X86-NEXT: pushl $0 -; X86-NEXT: pushl $2 -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: testl %eax, %eax -; X86-NEXT: sete %al -; X86-NEXT: retl -; -; X64-LABEL: length2_eq_nobuiltin_attr: -; X64: # %bb.0: -; X64-NEXT: pushq %rax -; X64-NEXT: movl $2, %edx -; X64-NEXT: callq memcmp -; X64-NEXT: testl %eax, %eax -; X64-NEXT: sete %al -; X64-NEXT: popq %rcx -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 2) nounwind nobuiltin - %c = icmp eq i32 %m, 0 - ret i1 %c -} - -define i32 @length3(i8* %X, i8* %Y) nounwind optsize { -; X86-LABEL: length3: -; X86: # %bb.0: # %loadbb -; X86-NEXT: pushl %esi -; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movzwl (%eax), %edx -; X86-NEXT: movzwl (%ecx), %esi -; X86-NEXT: rolw $8, %dx -; X86-NEXT: rolw $8, %si -; X86-NEXT: cmpw %si, %dx -; X86-NEXT: jne .LBB4_1 -; X86-NEXT: # %bb.2: # %loadbb1 -; X86-NEXT: movzbl 2(%eax), %eax -; X86-NEXT: movzbl 2(%ecx), %ecx -; X86-NEXT: subl %ecx, %eax -; X86-NEXT: jmp .LBB4_3 -; X86-NEXT: .LBB4_1: # %res_block -; X86-NEXT: setae %al -; X86-NEXT: movzbl %al, %eax -; X86-NEXT: leal -1(%eax,%eax), %eax -; X86-NEXT: .LBB4_3: # %endblock -; X86-NEXT: popl %esi -; X86-NEXT: retl -; -; X64-LABEL: length3: -; X64: # %bb.0: # %loadbb -; X64-NEXT: movzwl (%rdi), %eax -; X64-NEXT: movzwl (%rsi), %ecx -; X64-NEXT: rolw $8, %ax -; X64-NEXT: rolw $8, %cx -; X64-NEXT: cmpw %cx, %ax -; X64-NEXT: jne .LBB4_1 -; X64-NEXT: # %bb.2: # %loadbb1 -; X64-NEXT: movzbl 2(%rdi), %eax -; X64-NEXT: movzbl 2(%rsi), %ecx -; X64-NEXT: subl %ecx, %eax -; X64-NEXT: retq -; X64-NEXT: .LBB4_1: # %res_block -; X64-NEXT: setae %al -; X64-NEXT: movzbl %al, %eax -; X64-NEXT: leal -1(%rax,%rax), %eax -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 3) nounwind - ret i32 %m -} - -define i1 @length3_eq(i8* %X, i8* %Y) nounwind optsize { -; X86-LABEL: length3_eq: -; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-NEXT: movzwl (%ecx), %edx -; X86-NEXT: xorw (%eax), %dx -; X86-NEXT: movb 2(%ecx), %cl -; X86-NEXT: xorb 2(%eax), %cl -; X86-NEXT: movzbl %cl, %eax -; X86-NEXT: orw %dx, %ax -; X86-NEXT: setne %al -; X86-NEXT: retl -; -; X64-LABEL: length3_eq: -; X64: # %bb.0: -; X64-NEXT: movzwl (%rdi), %eax -; X64-NEXT: xorw (%rsi), %ax -; X64-NEXT: movb 2(%rdi), %cl -; X64-NEXT: xorb 2(%rsi), %cl -; X64-NEXT: movzbl %cl, %ecx -; X64-NEXT: orw %ax, %cx -; X64-NEXT: setne %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 3) nounwind - %c = icmp ne i32 %m, 0 - ret i1 %c -} - -define i32 @length4(i8* %X, i8* %Y) nounwind optsize { -; X86-LABEL: length4: -; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-NEXT: movl (%ecx), %ecx -; X86-NEXT: movl (%eax), %edx -; X86-NEXT: bswapl %ecx -; X86-NEXT: bswapl %edx -; X86-NEXT: xorl %eax, %eax -; X86-NEXT: cmpl %edx, %ecx -; X86-NEXT: seta %al -; X86-NEXT: sbbl $0, %eax -; X86-NEXT: retl -; -; X64-LABEL: length4: -; X64: # %bb.0: -; X64-NEXT: movl (%rdi), %ecx -; X64-NEXT: movl (%rsi), %edx -; X64-NEXT: bswapl %ecx -; X64-NEXT: bswapl %edx -; X64-NEXT: xorl %eax, %eax -; X64-NEXT: cmpl %edx, %ecx -; X64-NEXT: seta %al -; X64-NEXT: sbbl $0, %eax -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 4) nounwind - ret i32 %m -} - -define i1 @length4_eq(i8* %X, i8* %Y) nounwind optsize { -; X86-LABEL: length4_eq: -; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-NEXT: movl (%ecx), %ecx -; X86-NEXT: cmpl (%eax), %ecx -; X86-NEXT: setne %al -; X86-NEXT: retl -; -; X64-LABEL: length4_eq: -; X64: # %bb.0: -; X64-NEXT: movl (%rdi), %eax -; X64-NEXT: cmpl (%rsi), %eax -; X64-NEXT: setne %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 4) nounwind - %c = icmp ne i32 %m, 0 - ret i1 %c -} - -define i1 @length4_eq_const(i8* %X) nounwind optsize { -; X86-LABEL: length4_eq_const: -; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: cmpl $875770417, (%eax) # imm = 0x34333231 -; X86-NEXT: sete %al -; X86-NEXT: retl -; -; X64-LABEL: length4_eq_const: -; X64: # %bb.0: -; X64-NEXT: cmpl $875770417, (%rdi) # imm = 0x34333231 -; X64-NEXT: sete %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* getelementptr inbounds ([65 x i8], [65 x i8]* @.str, i32 0, i32 1), i64 4) nounwind - %c = icmp eq i32 %m, 0 - ret i1 %c -} - -define i32 @length5(i8* %X, i8* %Y) nounwind optsize { -; X86-LABEL: length5: -; X86: # %bb.0: # %loadbb -; X86-NEXT: pushl %esi -; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl (%eax), %edx -; X86-NEXT: movl (%ecx), %esi -; X86-NEXT: bswapl %edx -; X86-NEXT: bswapl %esi -; X86-NEXT: cmpl %esi, %edx -; X86-NEXT: jne .LBB9_1 -; X86-NEXT: # %bb.2: # %loadbb1 -; X86-NEXT: movzbl 4(%eax), %eax -; X86-NEXT: movzbl 4(%ecx), %ecx -; X86-NEXT: subl %ecx, %eax -; X86-NEXT: jmp .LBB9_3 -; X86-NEXT: .LBB9_1: # %res_block -; X86-NEXT: setae %al -; X86-NEXT: movzbl %al, %eax -; X86-NEXT: leal -1(%eax,%eax), %eax -; X86-NEXT: .LBB9_3: # %endblock -; X86-NEXT: popl %esi -; X86-NEXT: retl -; -; X64-LABEL: length5: -; X64: # %bb.0: # %loadbb -; X64-NEXT: movl (%rdi), %eax -; X64-NEXT: movl (%rsi), %ecx -; X64-NEXT: bswapl %eax -; X64-NEXT: bswapl %ecx -; X64-NEXT: cmpl %ecx, %eax -; X64-NEXT: jne .LBB9_1 -; X64-NEXT: # %bb.2: # %loadbb1 -; X64-NEXT: movzbl 4(%rdi), %eax -; X64-NEXT: movzbl 4(%rsi), %ecx -; X64-NEXT: subl %ecx, %eax -; X64-NEXT: retq -; X64-NEXT: .LBB9_1: # %res_block -; X64-NEXT: setae %al -; X64-NEXT: movzbl %al, %eax -; X64-NEXT: leal -1(%rax,%rax), %eax -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 5) nounwind - ret i32 %m -} - -define i1 @length5_eq(i8* %X, i8* %Y) nounwind optsize { -; X86-LABEL: length5_eq: -; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-NEXT: movl (%ecx), %edx -; X86-NEXT: xorl (%eax), %edx -; X86-NEXT: movb 4(%ecx), %cl -; X86-NEXT: xorb 4(%eax), %cl -; X86-NEXT: movzbl %cl, %eax -; X86-NEXT: orl %edx, %eax -; X86-NEXT: setne %al -; X86-NEXT: retl -; -; X64-LABEL: length5_eq: -; X64: # %bb.0: -; X64-NEXT: movl (%rdi), %eax -; X64-NEXT: xorl (%rsi), %eax -; X64-NEXT: movb 4(%rdi), %cl -; X64-NEXT: xorb 4(%rsi), %cl -; X64-NEXT: movzbl %cl, %ecx -; X64-NEXT: orl %eax, %ecx -; X64-NEXT: setne %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 5) nounwind - %c = icmp ne i32 %m, 0 - ret i1 %c -} - -define i32 @length8(i8* %X, i8* %Y) nounwind optsize { -; X86-LABEL: length8: -; X86: # %bb.0: -; X86-NEXT: pushl %esi -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl {{[0-9]+}}(%esp), %esi -; X86-NEXT: movl (%esi), %ecx -; X86-NEXT: movl (%eax), %edx -; X86-NEXT: bswapl %ecx -; X86-NEXT: bswapl %edx -; X86-NEXT: cmpl %edx, %ecx -; X86-NEXT: jne .LBB11_2 -; X86-NEXT: # %bb.1: # %loadbb1 -; X86-NEXT: movl 4(%esi), %ecx -; X86-NEXT: movl 4(%eax), %edx -; X86-NEXT: bswapl %ecx -; X86-NEXT: bswapl %edx -; X86-NEXT: xorl %eax, %eax -; X86-NEXT: cmpl %edx, %ecx -; X86-NEXT: je .LBB11_3 -; X86-NEXT: .LBB11_2: # %res_block -; X86-NEXT: xorl %eax, %eax -; X86-NEXT: cmpl %edx, %ecx -; X86-NEXT: setae %al -; X86-NEXT: leal -1(%eax,%eax), %eax -; X86-NEXT: .LBB11_3: # %endblock -; X86-NEXT: popl %esi -; X86-NEXT: retl -; -; X64-LABEL: length8: -; X64: # %bb.0: -; X64-NEXT: movq (%rdi), %rcx -; X64-NEXT: movq (%rsi), %rdx -; X64-NEXT: bswapq %rcx -; X64-NEXT: bswapq %rdx -; X64-NEXT: xorl %eax, %eax -; X64-NEXT: cmpq %rdx, %rcx -; X64-NEXT: seta %al -; X64-NEXT: sbbl $0, %eax -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 8) nounwind - ret i32 %m -} - -define i1 @length8_eq(i8* %X, i8* %Y) nounwind optsize { -; X86-LABEL: length8_eq: -; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-NEXT: movl (%ecx), %edx -; X86-NEXT: movl 4(%ecx), %ecx -; X86-NEXT: xorl (%eax), %edx -; X86-NEXT: xorl 4(%eax), %ecx -; X86-NEXT: orl %edx, %ecx -; X86-NEXT: sete %al -; X86-NEXT: retl -; -; X64-LABEL: length8_eq: -; X64: # %bb.0: -; X64-NEXT: movq (%rdi), %rax -; X64-NEXT: cmpq (%rsi), %rax -; X64-NEXT: sete %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 8) nounwind - %c = icmp eq i32 %m, 0 - ret i1 %c -} - -define i1 @length8_eq_const(i8* %X) nounwind optsize { -; X86-LABEL: length8_eq_const: -; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl $858927408, %ecx # imm = 0x33323130 -; X86-NEXT: xorl (%eax), %ecx -; X86-NEXT: movl $926299444, %edx # imm = 0x37363534 -; X86-NEXT: xorl 4(%eax), %edx -; X86-NEXT: orl %ecx, %edx -; X86-NEXT: setne %al -; X86-NEXT: retl -; -; X64-LABEL: length8_eq_const: -; X64: # %bb.0: -; X64-NEXT: movabsq $3978425819141910832, %rax # imm = 0x3736353433323130 -; X64-NEXT: cmpq %rax, (%rdi) -; X64-NEXT: setne %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* getelementptr inbounds ([65 x i8], [65 x i8]* @.str, i32 0, i32 0), i64 8) nounwind - %c = icmp ne i32 %m, 0 - ret i1 %c -} - -define i1 @length12_eq(i8* %X, i8* %Y) nounwind optsize { -; X86-LABEL: length12_eq: -; X86: # %bb.0: -; X86-NEXT: pushl $0 -; X86-NEXT: pushl $12 -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: testl %eax, %eax -; X86-NEXT: setne %al -; X86-NEXT: retl -; -; X64-LABEL: length12_eq: -; X64: # %bb.0: -; X64-NEXT: movq (%rdi), %rax -; X64-NEXT: xorq (%rsi), %rax -; X64-NEXT: movl 8(%rdi), %ecx -; X64-NEXT: xorl 8(%rsi), %ecx -; X64-NEXT: orq %rax, %rcx -; X64-NEXT: setne %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 12) nounwind - %c = icmp ne i32 %m, 0 - ret i1 %c -} - -define i32 @length12(i8* %X, i8* %Y) nounwind optsize { -; X86-LABEL: length12: -; X86: # %bb.0: -; X86-NEXT: pushl $0 -; X86-NEXT: pushl $12 -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: retl -; -; X64-LABEL: length12: -; X64: # %bb.0: -; X64-NEXT: movq (%rdi), %rcx -; X64-NEXT: movq (%rsi), %rdx -; X64-NEXT: bswapq %rcx -; X64-NEXT: bswapq %rdx -; X64-NEXT: cmpq %rdx, %rcx -; X64-NEXT: jne .LBB15_2 -; X64-NEXT: # %bb.1: # %loadbb1 -; X64-NEXT: movl 8(%rdi), %ecx -; X64-NEXT: movl 8(%rsi), %edx -; X64-NEXT: bswapl %ecx -; X64-NEXT: bswapl %edx -; X64-NEXT: xorl %eax, %eax -; X64-NEXT: cmpq %rdx, %rcx -; X64-NEXT: je .LBB15_3 -; X64-NEXT: .LBB15_2: # %res_block -; X64-NEXT: xorl %eax, %eax -; X64-NEXT: cmpq %rdx, %rcx -; X64-NEXT: setae %al -; X64-NEXT: leal -1(%rax,%rax), %eax -; X64-NEXT: .LBB15_3: # %endblock -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 12) nounwind - ret i32 %m -} - -; PR33329 - https://bugs.llvm.org/show_bug.cgi?id=33329 - -define i32 @length16(i8* %X, i8* %Y) nounwind optsize { -; X86-LABEL: length16: -; X86: # %bb.0: -; X86-NEXT: pushl $0 -; X86-NEXT: pushl $16 -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: retl -; -; X64-LABEL: length16: -; X64: # %bb.0: -; X64-NEXT: movq (%rdi), %rcx -; X64-NEXT: movq (%rsi), %rdx -; X64-NEXT: bswapq %rcx -; X64-NEXT: bswapq %rdx -; X64-NEXT: cmpq %rdx, %rcx -; X64-NEXT: jne .LBB16_2 -; X64-NEXT: # %bb.1: # %loadbb1 -; X64-NEXT: movq 8(%rdi), %rcx -; X64-NEXT: movq 8(%rsi), %rdx -; X64-NEXT: bswapq %rcx -; X64-NEXT: bswapq %rdx -; X64-NEXT: xorl %eax, %eax -; X64-NEXT: cmpq %rdx, %rcx -; X64-NEXT: je .LBB16_3 -; X64-NEXT: .LBB16_2: # %res_block -; X64-NEXT: xorl %eax, %eax -; X64-NEXT: cmpq %rdx, %rcx -; X64-NEXT: setae %al -; X64-NEXT: leal -1(%rax,%rax), %eax -; X64-NEXT: .LBB16_3: # %endblock -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 16) nounwind - ret i32 %m -} - -define i1 @length16_eq(i8* %x, i8* %y) nounwind optsize { -; X86-NOSSE-LABEL: length16_eq: -; X86-NOSSE: # %bb.0: -; X86-NOSSE-NEXT: pushl $0 -; X86-NOSSE-NEXT: pushl $16 -; X86-NOSSE-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NOSSE-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NOSSE-NEXT: calll memcmp -; X86-NOSSE-NEXT: addl $16, %esp -; X86-NOSSE-NEXT: testl %eax, %eax -; X86-NOSSE-NEXT: setne %al -; X86-NOSSE-NEXT: retl -; -; X86-SSE2-LABEL: length16_eq: -; X86-SSE2: # %bb.0: -; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-SSE2-NEXT: movdqu (%ecx), %xmm0 -; X86-SSE2-NEXT: movdqu (%eax), %xmm1 -; X86-SSE2-NEXT: pcmpeqb %xmm0, %xmm1 -; X86-SSE2-NEXT: pmovmskb %xmm1, %eax -; X86-SSE2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X86-SSE2-NEXT: setne %al -; X86-SSE2-NEXT: retl -; -; X64-SSE2-LABEL: length16_eq: -; X64-SSE2: # %bb.0: -; X64-SSE2-NEXT: movdqu (%rdi), %xmm0 -; X64-SSE2-NEXT: movdqu (%rsi), %xmm1 -; X64-SSE2-NEXT: pcmpeqb %xmm0, %xmm1 -; X64-SSE2-NEXT: pmovmskb %xmm1, %eax -; X64-SSE2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X64-SSE2-NEXT: setne %al -; X64-SSE2-NEXT: retq -; -; X64-AVX2-LABEL: length16_eq: -; X64-AVX2: # %bb.0: -; X64-AVX2-NEXT: vmovdqu (%rdi), %xmm0 -; X64-AVX2-NEXT: vpcmpeqb (%rsi), %xmm0, %xmm0 -; X64-AVX2-NEXT: vpmovmskb %xmm0, %eax -; X64-AVX2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X64-AVX2-NEXT: setne %al -; X64-AVX2-NEXT: retq - %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 16) nounwind - %cmp = icmp ne i32 %call, 0 - ret i1 %cmp -} - -define i1 @length16_eq_const(i8* %X) nounwind optsize { -; X86-NOSSE-LABEL: length16_eq_const: -; X86-NOSSE: # %bb.0: -; X86-NOSSE-NEXT: pushl $0 -; X86-NOSSE-NEXT: pushl $16 -; X86-NOSSE-NEXT: pushl $.L.str -; X86-NOSSE-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NOSSE-NEXT: calll memcmp -; X86-NOSSE-NEXT: addl $16, %esp -; X86-NOSSE-NEXT: testl %eax, %eax -; X86-NOSSE-NEXT: sete %al -; X86-NOSSE-NEXT: retl -; -; X86-SSE2-LABEL: length16_eq_const: -; X86-SSE2: # %bb.0: -; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-SSE2-NEXT: movdqu (%eax), %xmm0 -; X86-SSE2-NEXT: pcmpeqb {{\.LCPI.*}}, %xmm0 -; X86-SSE2-NEXT: pmovmskb %xmm0, %eax -; X86-SSE2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X86-SSE2-NEXT: sete %al -; X86-SSE2-NEXT: retl -; -; X64-SSE2-LABEL: length16_eq_const: -; X64-SSE2: # %bb.0: -; X64-SSE2-NEXT: movdqu (%rdi), %xmm0 -; X64-SSE2-NEXT: pcmpeqb {{.*}}(%rip), %xmm0 -; X64-SSE2-NEXT: pmovmskb %xmm0, %eax -; X64-SSE2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X64-SSE2-NEXT: sete %al -; X64-SSE2-NEXT: retq -; -; X64-AVX2-LABEL: length16_eq_const: -; X64-AVX2: # %bb.0: -; X64-AVX2-NEXT: vmovdqu (%rdi), %xmm0 -; X64-AVX2-NEXT: vpcmpeqb {{.*}}(%rip), %xmm0, %xmm0 -; X64-AVX2-NEXT: vpmovmskb %xmm0, %eax -; X64-AVX2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X64-AVX2-NEXT: sete %al -; X64-AVX2-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* getelementptr inbounds ([65 x i8], [65 x i8]* @.str, i32 0, i32 0), i64 16) nounwind - %c = icmp eq i32 %m, 0 - ret i1 %c -} - -; PR33914 - https://bugs.llvm.org/show_bug.cgi?id=33914 - -define i32 @length24(i8* %X, i8* %Y) nounwind optsize { -; X86-LABEL: length24: -; X86: # %bb.0: -; X86-NEXT: pushl $0 -; X86-NEXT: pushl $24 -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: retl -; -; X64-LABEL: length24: -; X64: # %bb.0: -; X64-NEXT: movl $24, %edx -; X64-NEXT: jmp memcmp # TAILCALL - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 24) nounwind - ret i32 %m -} - -define i1 @length24_eq(i8* %x, i8* %y) nounwind optsize { -; X86-NOSSE-LABEL: length24_eq: -; X86-NOSSE: # %bb.0: -; X86-NOSSE-NEXT: pushl $0 -; X86-NOSSE-NEXT: pushl $24 -; X86-NOSSE-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NOSSE-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NOSSE-NEXT: calll memcmp -; X86-NOSSE-NEXT: addl $16, %esp -; X86-NOSSE-NEXT: testl %eax, %eax -; X86-NOSSE-NEXT: sete %al -; X86-NOSSE-NEXT: retl -; -; X86-SSE2-LABEL: length24_eq: -; X86-SSE2: # %bb.0: -; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-SSE2-NEXT: movdqu (%ecx), %xmm0 -; X86-SSE2-NEXT: movdqu 8(%ecx), %xmm1 -; X86-SSE2-NEXT: movdqu (%eax), %xmm2 -; X86-SSE2-NEXT: pcmpeqb %xmm0, %xmm2 -; X86-SSE2-NEXT: movdqu 8(%eax), %xmm0 -; X86-SSE2-NEXT: pcmpeqb %xmm1, %xmm0 -; X86-SSE2-NEXT: pand %xmm2, %xmm0 -; X86-SSE2-NEXT: pmovmskb %xmm0, %eax -; X86-SSE2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X86-SSE2-NEXT: sete %al -; X86-SSE2-NEXT: retl -; -; X64-SSE2-LABEL: length24_eq: -; X64-SSE2: # %bb.0: -; X64-SSE2-NEXT: movdqu (%rdi), %xmm0 -; X64-SSE2-NEXT: movdqu (%rsi), %xmm1 -; X64-SSE2-NEXT: pcmpeqb %xmm0, %xmm1 -; X64-SSE2-NEXT: movq {{.*#+}} xmm0 = mem[0],zero -; X64-SSE2-NEXT: movq {{.*#+}} xmm2 = mem[0],zero -; X64-SSE2-NEXT: pcmpeqb %xmm0, %xmm2 -; X64-SSE2-NEXT: pand %xmm1, %xmm2 -; X64-SSE2-NEXT: pmovmskb %xmm2, %eax -; X64-SSE2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X64-SSE2-NEXT: sete %al -; X64-SSE2-NEXT: retq -; -; X64-AVX2-LABEL: length24_eq: -; X64-AVX2: # %bb.0: -; X64-AVX2-NEXT: vmovdqu (%rdi), %xmm0 -; X64-AVX2-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero -; X64-AVX2-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero -; X64-AVX2-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm1 -; X64-AVX2-NEXT: vpcmpeqb (%rsi), %xmm0, %xmm0 -; X64-AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0 -; X64-AVX2-NEXT: vpmovmskb %xmm0, %eax -; X64-AVX2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X64-AVX2-NEXT: sete %al -; X64-AVX2-NEXT: retq - %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 24) nounwind - %cmp = icmp eq i32 %call, 0 - ret i1 %cmp -} - -define i1 @length24_eq_const(i8* %X) nounwind optsize { -; X86-NOSSE-LABEL: length24_eq_const: -; X86-NOSSE: # %bb.0: -; X86-NOSSE-NEXT: pushl $0 -; X86-NOSSE-NEXT: pushl $24 -; X86-NOSSE-NEXT: pushl $.L.str -; X86-NOSSE-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NOSSE-NEXT: calll memcmp -; X86-NOSSE-NEXT: addl $16, %esp -; X86-NOSSE-NEXT: testl %eax, %eax -; X86-NOSSE-NEXT: setne %al -; X86-NOSSE-NEXT: retl -; -; X86-SSE2-LABEL: length24_eq_const: -; X86-SSE2: # %bb.0: -; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-SSE2-NEXT: movdqu (%eax), %xmm0 -; X86-SSE2-NEXT: movdqu 8(%eax), %xmm1 -; X86-SSE2-NEXT: pcmpeqb {{\.LCPI.*}}, %xmm1 -; X86-SSE2-NEXT: pcmpeqb {{\.LCPI.*}}, %xmm0 -; X86-SSE2-NEXT: pand %xmm1, %xmm0 -; X86-SSE2-NEXT: pmovmskb %xmm0, %eax -; X86-SSE2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X86-SSE2-NEXT: setne %al -; X86-SSE2-NEXT: retl -; -; X64-SSE2-LABEL: length24_eq_const: -; X64-SSE2: # %bb.0: -; X64-SSE2-NEXT: movdqu (%rdi), %xmm0 -; X64-SSE2-NEXT: movq {{.*#+}} xmm1 = mem[0],zero -; X64-SSE2-NEXT: pcmpeqb {{.*}}(%rip), %xmm1 -; X64-SSE2-NEXT: pcmpeqb {{.*}}(%rip), %xmm0 -; X64-SSE2-NEXT: pand %xmm1, %xmm0 -; X64-SSE2-NEXT: pmovmskb %xmm0, %eax -; X64-SSE2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X64-SSE2-NEXT: setne %al -; X64-SSE2-NEXT: retq -; -; X64-AVX2-LABEL: length24_eq_const: -; X64-AVX2: # %bb.0: -; X64-AVX2-NEXT: vmovdqu (%rdi), %xmm0 -; X64-AVX2-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero -; X64-AVX2-NEXT: vpcmpeqb {{.*}}(%rip), %xmm1, %xmm1 -; X64-AVX2-NEXT: vpcmpeqb {{.*}}(%rip), %xmm0, %xmm0 -; X64-AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0 -; X64-AVX2-NEXT: vpmovmskb %xmm0, %eax -; X64-AVX2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X64-AVX2-NEXT: setne %al -; X64-AVX2-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* getelementptr inbounds ([65 x i8], [65 x i8]* @.str, i32 0, i32 0), i64 24) nounwind - %c = icmp ne i32 %m, 0 - ret i1 %c -} - -define i32 @length32(i8* %X, i8* %Y) nounwind optsize { -; X86-LABEL: length32: -; X86: # %bb.0: -; X86-NEXT: pushl $0 -; X86-NEXT: pushl $32 -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: retl -; -; X64-LABEL: length32: -; X64: # %bb.0: -; X64-NEXT: movl $32, %edx -; X64-NEXT: jmp memcmp # TAILCALL - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 32) nounwind - ret i32 %m -} - -; PR33325 - https://bugs.llvm.org/show_bug.cgi?id=33325 - -define i1 @length32_eq(i8* %x, i8* %y) nounwind optsize { -; X86-NOSSE-LABEL: length32_eq: -; X86-NOSSE: # %bb.0: -; X86-NOSSE-NEXT: pushl $0 -; X86-NOSSE-NEXT: pushl $32 -; X86-NOSSE-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NOSSE-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NOSSE-NEXT: calll memcmp -; X86-NOSSE-NEXT: addl $16, %esp -; X86-NOSSE-NEXT: testl %eax, %eax -; X86-NOSSE-NEXT: sete %al -; X86-NOSSE-NEXT: retl -; -; X86-SSE2-LABEL: length32_eq: -; X86-SSE2: # %bb.0: -; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-SSE2-NEXT: movdqu (%ecx), %xmm0 -; X86-SSE2-NEXT: movdqu 16(%ecx), %xmm1 -; X86-SSE2-NEXT: movdqu (%eax), %xmm2 -; X86-SSE2-NEXT: pcmpeqb %xmm0, %xmm2 -; X86-SSE2-NEXT: movdqu 16(%eax), %xmm0 -; X86-SSE2-NEXT: pcmpeqb %xmm1, %xmm0 -; X86-SSE2-NEXT: pand %xmm2, %xmm0 -; X86-SSE2-NEXT: pmovmskb %xmm0, %eax -; X86-SSE2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X86-SSE2-NEXT: sete %al -; X86-SSE2-NEXT: retl -; -; X64-SSE2-LABEL: length32_eq: -; X64-SSE2: # %bb.0: -; X64-SSE2-NEXT: movdqu (%rdi), %xmm0 -; X64-SSE2-NEXT: movdqu 16(%rdi), %xmm1 -; X64-SSE2-NEXT: movdqu (%rsi), %xmm2 -; X64-SSE2-NEXT: pcmpeqb %xmm0, %xmm2 -; X64-SSE2-NEXT: movdqu 16(%rsi), %xmm0 -; X64-SSE2-NEXT: pcmpeqb %xmm1, %xmm0 -; X64-SSE2-NEXT: pand %xmm2, %xmm0 -; X64-SSE2-NEXT: pmovmskb %xmm0, %eax -; X64-SSE2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X64-SSE2-NEXT: sete %al -; X64-SSE2-NEXT: retq -; -; X64-AVX2-LABEL: length32_eq: -; X64-AVX2: # %bb.0: -; X64-AVX2-NEXT: vmovdqu (%rdi), %ymm0 -; X64-AVX2-NEXT: vpcmpeqb (%rsi), %ymm0, %ymm0 -; X64-AVX2-NEXT: vpmovmskb %ymm0, %eax -; X64-AVX2-NEXT: cmpl $-1, %eax -; X64-AVX2-NEXT: sete %al -; X64-AVX2-NEXT: vzeroupper -; X64-AVX2-NEXT: retq - %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 32) nounwind - %cmp = icmp eq i32 %call, 0 - ret i1 %cmp -} - -define i1 @length32_eq_const(i8* %X) nounwind optsize { -; X86-NOSSE-LABEL: length32_eq_const: -; X86-NOSSE: # %bb.0: -; X86-NOSSE-NEXT: pushl $0 -; X86-NOSSE-NEXT: pushl $32 -; X86-NOSSE-NEXT: pushl $.L.str -; X86-NOSSE-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NOSSE-NEXT: calll memcmp -; X86-NOSSE-NEXT: addl $16, %esp -; X86-NOSSE-NEXT: testl %eax, %eax -; X86-NOSSE-NEXT: setne %al -; X86-NOSSE-NEXT: retl -; -; X86-SSE2-LABEL: length32_eq_const: -; X86-SSE2: # %bb.0: -; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-SSE2-NEXT: movdqu (%eax), %xmm0 -; X86-SSE2-NEXT: movdqu 16(%eax), %xmm1 -; X86-SSE2-NEXT: pcmpeqb {{\.LCPI.*}}, %xmm1 -; X86-SSE2-NEXT: pcmpeqb {{\.LCPI.*}}, %xmm0 -; X86-SSE2-NEXT: pand %xmm1, %xmm0 -; X86-SSE2-NEXT: pmovmskb %xmm0, %eax -; X86-SSE2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X86-SSE2-NEXT: setne %al -; X86-SSE2-NEXT: retl -; -; X64-SSE2-LABEL: length32_eq_const: -; X64-SSE2: # %bb.0: -; X64-SSE2-NEXT: movdqu (%rdi), %xmm0 -; X64-SSE2-NEXT: movdqu 16(%rdi), %xmm1 -; X64-SSE2-NEXT: pcmpeqb {{.*}}(%rip), %xmm1 -; X64-SSE2-NEXT: pcmpeqb {{.*}}(%rip), %xmm0 -; X64-SSE2-NEXT: pand %xmm1, %xmm0 -; X64-SSE2-NEXT: pmovmskb %xmm0, %eax -; X64-SSE2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X64-SSE2-NEXT: setne %al -; X64-SSE2-NEXT: retq -; -; X64-AVX2-LABEL: length32_eq_const: -; X64-AVX2: # %bb.0: -; X64-AVX2-NEXT: vmovdqu (%rdi), %ymm0 -; X64-AVX2-NEXT: vpcmpeqb {{.*}}(%rip), %ymm0, %ymm0 -; X64-AVX2-NEXT: vpmovmskb %ymm0, %eax -; X64-AVX2-NEXT: cmpl $-1, %eax -; X64-AVX2-NEXT: setne %al -; X64-AVX2-NEXT: vzeroupper -; X64-AVX2-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* getelementptr inbounds ([65 x i8], [65 x i8]* @.str, i32 0, i32 0), i64 32) nounwind - %c = icmp ne i32 %m, 0 - ret i1 %c -} - -define i32 @length64(i8* %X, i8* %Y) nounwind optsize { -; X86-LABEL: length64: -; X86: # %bb.0: -; X86-NEXT: pushl $0 -; X86-NEXT: pushl $64 -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: retl -; -; X64-LABEL: length64: -; X64: # %bb.0: -; X64-NEXT: movl $64, %edx -; X64-NEXT: jmp memcmp # TAILCALL - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 64) nounwind - ret i32 %m -} - -define i1 @length64_eq(i8* %x, i8* %y) nounwind optsize { -; X86-LABEL: length64_eq: -; X86: # %bb.0: -; X86-NEXT: pushl $0 -; X86-NEXT: pushl $64 -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: testl %eax, %eax -; X86-NEXT: setne %al -; X86-NEXT: retl -; -; X64-SSE2-LABEL: length64_eq: -; X64-SSE2: # %bb.0: -; X64-SSE2-NEXT: pushq %rax -; X64-SSE2-NEXT: movl $64, %edx -; X64-SSE2-NEXT: callq memcmp -; X64-SSE2-NEXT: testl %eax, %eax -; X64-SSE2-NEXT: setne %al -; X64-SSE2-NEXT: popq %rcx -; X64-SSE2-NEXT: retq -; -; X64-AVX2-LABEL: length64_eq: -; X64-AVX2: # %bb.0: -; X64-AVX2-NEXT: vmovdqu (%rdi), %ymm0 -; X64-AVX2-NEXT: vmovdqu 32(%rdi), %ymm1 -; X64-AVX2-NEXT: vpcmpeqb 32(%rsi), %ymm1, %ymm1 -; X64-AVX2-NEXT: vpcmpeqb (%rsi), %ymm0, %ymm0 -; X64-AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0 -; X64-AVX2-NEXT: vpmovmskb %ymm0, %eax -; X64-AVX2-NEXT: cmpl $-1, %eax -; X64-AVX2-NEXT: setne %al -; X64-AVX2-NEXT: vzeroupper -; X64-AVX2-NEXT: retq - %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 64) nounwind - %cmp = icmp ne i32 %call, 0 - ret i1 %cmp -} - -define i1 @length64_eq_const(i8* %X) nounwind optsize { -; X86-LABEL: length64_eq_const: -; X86: # %bb.0: -; X86-NEXT: pushl $0 -; X86-NEXT: pushl $64 -; X86-NEXT: pushl $.L.str -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: testl %eax, %eax -; X86-NEXT: sete %al -; X86-NEXT: retl -; -; X64-SSE2-LABEL: length64_eq_const: -; X64-SSE2: # %bb.0: -; X64-SSE2-NEXT: pushq %rax -; X64-SSE2-NEXT: movl $.L.str, %esi -; X64-SSE2-NEXT: movl $64, %edx -; X64-SSE2-NEXT: callq memcmp -; X64-SSE2-NEXT: testl %eax, %eax -; X64-SSE2-NEXT: sete %al -; X64-SSE2-NEXT: popq %rcx -; X64-SSE2-NEXT: retq -; -; X64-AVX2-LABEL: length64_eq_const: -; X64-AVX2: # %bb.0: -; X64-AVX2-NEXT: vmovdqu (%rdi), %ymm0 -; X64-AVX2-NEXT: vmovdqu 32(%rdi), %ymm1 -; X64-AVX2-NEXT: vpcmpeqb {{.*}}(%rip), %ymm1, %ymm1 -; X64-AVX2-NEXT: vpcmpeqb {{.*}}(%rip), %ymm0, %ymm0 -; X64-AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0 -; X64-AVX2-NEXT: vpmovmskb %ymm0, %eax -; X64-AVX2-NEXT: cmpl $-1, %eax -; X64-AVX2-NEXT: sete %al -; X64-AVX2-NEXT: vzeroupper -; X64-AVX2-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* getelementptr inbounds ([65 x i8], [65 x i8]* @.str, i32 0, i32 0), i64 64) nounwind - %c = icmp eq i32 %m, 0 - ret i1 %c -} - -define i32 @bcmp_length2(i8* %X, i8* %Y) nounwind optsize { -; X86-LABEL: bcmp_length2: -; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-NEXT: movzwl (%ecx), %ecx -; X86-NEXT: movzwl (%eax), %edx -; X86-NEXT: rolw $8, %cx -; X86-NEXT: rolw $8, %dx -; X86-NEXT: movzwl %cx, %eax -; X86-NEXT: movzwl %dx, %ecx -; X86-NEXT: subl %ecx, %eax -; X86-NEXT: retl -; -; X64-LABEL: bcmp_length2: -; X64: # %bb.0: -; X64-NEXT: movzwl (%rdi), %eax -; X64-NEXT: movzwl (%rsi), %ecx -; X64-NEXT: rolw $8, %ax -; X64-NEXT: rolw $8, %cx -; X64-NEXT: movzwl %ax, %eax -; X64-NEXT: movzwl %cx, %ecx -; X64-NEXT: subl %ecx, %eax -; X64-NEXT: retq - %m = tail call i32 @bcmp(i8* %X, i8* %Y, i64 2) nounwind - ret i32 %m -} - diff --git a/llvm/test/CodeGen/X86/memcmp.ll b/llvm/test/CodeGen/X86/memcmp.ll deleted file mode 100644 index 8a7c7847fe0..00000000000 --- a/llvm/test/CodeGen/X86/memcmp.ll +++ /dev/null @@ -1,1685 +0,0 @@ -; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py -; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=cmov | FileCheck %s --check-prefix=X86 --check-prefix=X86-NOSSE -; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse | FileCheck %s --check-prefix=X86 --check-prefix=SSE --check-prefix=X86-SSE1 -; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=X86 --check-prefix=SSE --check-prefix=X86-SSE2 -; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s --check-prefix=X64 --check-prefix=X64-SSE2 -; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx | FileCheck %s --check-prefix=X64 --check-prefix=X64-AVX --check-prefix=X64-AVX1 -; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx2 | FileCheck %s --check-prefix=X64 --check-prefix=X64-AVX --check-prefix=X64-AVX2 - -; This tests codegen time inlining/optimization of memcmp -; rdar://6480398 - -@.str = private constant [65 x i8] c"0123456789012345678901234567890123456789012345678901234567890123\00", align 1 - -declare i32 @memcmp(i8*, i8*, i64) - -define i32 @length0(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length0: -; X86: # %bb.0: -; X86-NEXT: xorl %eax, %eax -; X86-NEXT: retl -; -; X64-LABEL: length0: -; X64: # %bb.0: -; X64-NEXT: xorl %eax, %eax -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 0) nounwind - ret i32 %m - } - -define i1 @length0_eq(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length0_eq: -; X86: # %bb.0: -; X86-NEXT: movb $1, %al -; X86-NEXT: retl -; -; X64-LABEL: length0_eq: -; X64: # %bb.0: -; X64-NEXT: movb $1, %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 0) nounwind - %c = icmp eq i32 %m, 0 - ret i1 %c -} - -define i1 @length0_lt(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length0_lt: -; X86: # %bb.0: -; X86-NEXT: xorl %eax, %eax -; X86-NEXT: retl -; -; X64-LABEL: length0_lt: -; X64: # %bb.0: -; X64-NEXT: xorl %eax, %eax -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 0) nounwind - %c = icmp slt i32 %m, 0 - ret i1 %c -} - -define i32 @length2(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length2: -; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-NEXT: movzwl (%ecx), %ecx -; X86-NEXT: movzwl (%eax), %edx -; X86-NEXT: rolw $8, %cx -; X86-NEXT: rolw $8, %dx -; X86-NEXT: movzwl %cx, %eax -; X86-NEXT: movzwl %dx, %ecx -; X86-NEXT: subl %ecx, %eax -; X86-NEXT: retl -; -; X64-LABEL: length2: -; X64: # %bb.0: -; X64-NEXT: movzwl (%rdi), %eax -; X64-NEXT: movzwl (%rsi), %ecx -; X64-NEXT: rolw $8, %ax -; X64-NEXT: rolw $8, %cx -; X64-NEXT: movzwl %ax, %eax -; X64-NEXT: movzwl %cx, %ecx -; X64-NEXT: subl %ecx, %eax -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 2) nounwind - ret i32 %m -} - -define i1 @length2_eq(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length2_eq: -; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-NEXT: movzwl (%ecx), %ecx -; X86-NEXT: cmpw (%eax), %cx -; X86-NEXT: sete %al -; X86-NEXT: retl -; -; X64-LABEL: length2_eq: -; X64: # %bb.0: -; X64-NEXT: movzwl (%rdi), %eax -; X64-NEXT: cmpw (%rsi), %ax -; X64-NEXT: sete %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 2) nounwind - %c = icmp eq i32 %m, 0 - ret i1 %c -} - -define i1 @length2_lt(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length2_lt: -; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-NEXT: movzwl (%ecx), %ecx -; X86-NEXT: movzwl (%eax), %edx -; X86-NEXT: rolw $8, %cx -; X86-NEXT: rolw $8, %dx -; X86-NEXT: movzwl %cx, %eax -; X86-NEXT: movzwl %dx, %ecx -; X86-NEXT: subl %ecx, %eax -; X86-NEXT: shrl $31, %eax -; X86-NEXT: # kill: def $al killed $al killed $eax -; X86-NEXT: retl -; -; X64-LABEL: length2_lt: -; X64: # %bb.0: -; X64-NEXT: movzwl (%rdi), %eax -; X64-NEXT: movzwl (%rsi), %ecx -; X64-NEXT: rolw $8, %ax -; X64-NEXT: rolw $8, %cx -; X64-NEXT: movzwl %ax, %eax -; X64-NEXT: movzwl %cx, %ecx -; X64-NEXT: subl %ecx, %eax -; X64-NEXT: shrl $31, %eax -; X64-NEXT: # kill: def $al killed $al killed $eax -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 2) nounwind - %c = icmp slt i32 %m, 0 - ret i1 %c -} - -define i1 @length2_gt(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length2_gt: -; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-NEXT: movzwl (%ecx), %ecx -; X86-NEXT: movzwl (%eax), %eax -; X86-NEXT: rolw $8, %cx -; X86-NEXT: rolw $8, %ax -; X86-NEXT: movzwl %cx, %ecx -; X86-NEXT: movzwl %ax, %eax -; X86-NEXT: subl %eax, %ecx -; X86-NEXT: testl %ecx, %ecx -; X86-NEXT: setg %al -; X86-NEXT: retl -; -; X64-LABEL: length2_gt: -; X64: # %bb.0: -; X64-NEXT: movzwl (%rdi), %eax -; X64-NEXT: movzwl (%rsi), %ecx -; X64-NEXT: rolw $8, %ax -; X64-NEXT: rolw $8, %cx -; X64-NEXT: movzwl %ax, %eax -; X64-NEXT: movzwl %cx, %ecx -; X64-NEXT: subl %ecx, %eax -; X64-NEXT: testl %eax, %eax -; X64-NEXT: setg %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 2) nounwind - %c = icmp sgt i32 %m, 0 - ret i1 %c -} - -define i1 @length2_eq_const(i8* %X) nounwind { -; X86-LABEL: length2_eq_const: -; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movzwl (%eax), %eax -; X86-NEXT: cmpl $12849, %eax # imm = 0x3231 -; X86-NEXT: setne %al -; X86-NEXT: retl -; -; X64-LABEL: length2_eq_const: -; X64: # %bb.0: -; X64-NEXT: movzwl (%rdi), %eax -; X64-NEXT: cmpl $12849, %eax # imm = 0x3231 -; X64-NEXT: setne %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* getelementptr inbounds ([65 x i8], [65 x i8]* @.str, i32 0, i32 1), i64 2) nounwind - %c = icmp ne i32 %m, 0 - ret i1 %c -} - -define i1 @length2_eq_nobuiltin_attr(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length2_eq_nobuiltin_attr: -; X86: # %bb.0: -; X86-NEXT: pushl $0 -; X86-NEXT: pushl $2 -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: testl %eax, %eax -; X86-NEXT: sete %al -; X86-NEXT: retl -; -; X64-LABEL: length2_eq_nobuiltin_attr: -; X64: # %bb.0: -; X64-NEXT: pushq %rax -; X64-NEXT: movl $2, %edx -; X64-NEXT: callq memcmp -; X64-NEXT: testl %eax, %eax -; X64-NEXT: sete %al -; X64-NEXT: popq %rcx -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 2) nounwind nobuiltin - %c = icmp eq i32 %m, 0 - ret i1 %c -} - -define i32 @length3(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length3: -; X86: # %bb.0: # %loadbb -; X86-NEXT: pushl %esi -; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movzwl (%eax), %edx -; X86-NEXT: movzwl (%ecx), %esi -; X86-NEXT: rolw $8, %dx -; X86-NEXT: rolw $8, %si -; X86-NEXT: cmpw %si, %dx -; X86-NEXT: jne .LBB9_1 -; X86-NEXT: # %bb.2: # %loadbb1 -; X86-NEXT: movzbl 2(%eax), %eax -; X86-NEXT: movzbl 2(%ecx), %ecx -; X86-NEXT: subl %ecx, %eax -; X86-NEXT: popl %esi -; X86-NEXT: retl -; X86-NEXT: .LBB9_1: # %res_block -; X86-NEXT: setae %al -; X86-NEXT: movzbl %al, %eax -; X86-NEXT: leal -1(%eax,%eax), %eax -; X86-NEXT: popl %esi -; X86-NEXT: retl -; -; X64-LABEL: length3: -; X64: # %bb.0: # %loadbb -; X64-NEXT: movzwl (%rdi), %eax -; X64-NEXT: movzwl (%rsi), %ecx -; X64-NEXT: rolw $8, %ax -; X64-NEXT: rolw $8, %cx -; X64-NEXT: cmpw %cx, %ax -; X64-NEXT: jne .LBB9_1 -; X64-NEXT: # %bb.2: # %loadbb1 -; X64-NEXT: movzbl 2(%rdi), %eax -; X64-NEXT: movzbl 2(%rsi), %ecx -; X64-NEXT: subl %ecx, %eax -; X64-NEXT: retq -; X64-NEXT: .LBB9_1: # %res_block -; X64-NEXT: setae %al -; X64-NEXT: movzbl %al, %eax -; X64-NEXT: leal -1(%rax,%rax), %eax -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 3) nounwind - ret i32 %m -} - -define i1 @length3_eq(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length3_eq: -; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-NEXT: movzwl (%ecx), %edx -; X86-NEXT: xorw (%eax), %dx -; X86-NEXT: movb 2(%ecx), %cl -; X86-NEXT: xorb 2(%eax), %cl -; X86-NEXT: movzbl %cl, %eax -; X86-NEXT: orw %dx, %ax -; X86-NEXT: setne %al -; X86-NEXT: retl -; -; X64-LABEL: length3_eq: -; X64: # %bb.0: -; X64-NEXT: movzwl (%rdi), %eax -; X64-NEXT: xorw (%rsi), %ax -; X64-NEXT: movb 2(%rdi), %cl -; X64-NEXT: xorb 2(%rsi), %cl -; X64-NEXT: movzbl %cl, %ecx -; X64-NEXT: orw %ax, %cx -; X64-NEXT: setne %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 3) nounwind - %c = icmp ne i32 %m, 0 - ret i1 %c -} - -define i32 @length4(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length4: -; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-NEXT: movl (%ecx), %ecx -; X86-NEXT: movl (%eax), %edx -; X86-NEXT: bswapl %ecx -; X86-NEXT: bswapl %edx -; X86-NEXT: xorl %eax, %eax -; X86-NEXT: cmpl %edx, %ecx -; X86-NEXT: seta %al -; X86-NEXT: sbbl $0, %eax -; X86-NEXT: retl -; -; X64-LABEL: length4: -; X64: # %bb.0: -; X64-NEXT: movl (%rdi), %ecx -; X64-NEXT: movl (%rsi), %edx -; X64-NEXT: bswapl %ecx -; X64-NEXT: bswapl %edx -; X64-NEXT: xorl %eax, %eax -; X64-NEXT: cmpl %edx, %ecx -; X64-NEXT: seta %al -; X64-NEXT: sbbl $0, %eax -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 4) nounwind - ret i32 %m -} - -define i1 @length4_eq(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length4_eq: -; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-NEXT: movl (%ecx), %ecx -; X86-NEXT: cmpl (%eax), %ecx -; X86-NEXT: setne %al -; X86-NEXT: retl -; -; X64-LABEL: length4_eq: -; X64: # %bb.0: -; X64-NEXT: movl (%rdi), %eax -; X64-NEXT: cmpl (%rsi), %eax -; X64-NEXT: setne %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 4) nounwind - %c = icmp ne i32 %m, 0 - ret i1 %c -} - -define i1 @length4_lt(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length4_lt: -; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-NEXT: movl (%ecx), %ecx -; X86-NEXT: movl (%eax), %edx -; X86-NEXT: bswapl %ecx -; X86-NEXT: bswapl %edx -; X86-NEXT: xorl %eax, %eax -; X86-NEXT: cmpl %edx, %ecx -; X86-NEXT: seta %al -; X86-NEXT: sbbl $0, %eax -; X86-NEXT: shrl $31, %eax -; X86-NEXT: # kill: def $al killed $al killed $eax -; X86-NEXT: retl -; -; X64-LABEL: length4_lt: -; X64: # %bb.0: -; X64-NEXT: movl (%rdi), %ecx -; X64-NEXT: movl (%rsi), %edx -; X64-NEXT: bswapl %ecx -; X64-NEXT: bswapl %edx -; X64-NEXT: xorl %eax, %eax -; X64-NEXT: cmpl %edx, %ecx -; X64-NEXT: seta %al -; X64-NEXT: sbbl $0, %eax -; X64-NEXT: shrl $31, %eax -; X64-NEXT: # kill: def $al killed $al killed $eax -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 4) nounwind - %c = icmp slt i32 %m, 0 - ret i1 %c -} - -define i1 @length4_gt(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length4_gt: -; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-NEXT: movl (%ecx), %ecx -; X86-NEXT: movl (%eax), %eax -; X86-NEXT: bswapl %ecx -; X86-NEXT: bswapl %eax -; X86-NEXT: xorl %edx, %edx -; X86-NEXT: cmpl %eax, %ecx -; X86-NEXT: seta %dl -; X86-NEXT: sbbl $0, %edx -; X86-NEXT: testl %edx, %edx -; X86-NEXT: setg %al -; X86-NEXT: retl -; -; X64-LABEL: length4_gt: -; X64: # %bb.0: -; X64-NEXT: movl (%rdi), %eax -; X64-NEXT: movl (%rsi), %ecx -; X64-NEXT: bswapl %eax -; X64-NEXT: bswapl %ecx -; X64-NEXT: xorl %edx, %edx -; X64-NEXT: cmpl %ecx, %eax -; X64-NEXT: seta %dl -; X64-NEXT: sbbl $0, %edx -; X64-NEXT: testl %edx, %edx -; X64-NEXT: setg %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 4) nounwind - %c = icmp sgt i32 %m, 0 - ret i1 %c -} - -define i1 @length4_eq_const(i8* %X) nounwind { -; X86-LABEL: length4_eq_const: -; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: cmpl $875770417, (%eax) # imm = 0x34333231 -; X86-NEXT: sete %al -; X86-NEXT: retl -; -; X64-LABEL: length4_eq_const: -; X64: # %bb.0: -; X64-NEXT: cmpl $875770417, (%rdi) # imm = 0x34333231 -; X64-NEXT: sete %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* getelementptr inbounds ([65 x i8], [65 x i8]* @.str, i32 0, i32 1), i64 4) nounwind - %c = icmp eq i32 %m, 0 - ret i1 %c -} - -define i32 @length5(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length5: -; X86: # %bb.0: # %loadbb -; X86-NEXT: pushl %esi -; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl (%eax), %edx -; X86-NEXT: movl (%ecx), %esi -; X86-NEXT: bswapl %edx -; X86-NEXT: bswapl %esi -; X86-NEXT: cmpl %esi, %edx -; X86-NEXT: jne .LBB16_1 -; X86-NEXT: # %bb.2: # %loadbb1 -; X86-NEXT: movzbl 4(%eax), %eax -; X86-NEXT: movzbl 4(%ecx), %ecx -; X86-NEXT: subl %ecx, %eax -; X86-NEXT: popl %esi -; X86-NEXT: retl -; X86-NEXT: .LBB16_1: # %res_block -; X86-NEXT: setae %al -; X86-NEXT: movzbl %al, %eax -; X86-NEXT: leal -1(%eax,%eax), %eax -; X86-NEXT: popl %esi -; X86-NEXT: retl -; -; X64-LABEL: length5: -; X64: # %bb.0: # %loadbb -; X64-NEXT: movl (%rdi), %eax -; X64-NEXT: movl (%rsi), %ecx -; X64-NEXT: bswapl %eax -; X64-NEXT: bswapl %ecx -; X64-NEXT: cmpl %ecx, %eax -; X64-NEXT: jne .LBB16_1 -; X64-NEXT: # %bb.2: # %loadbb1 -; X64-NEXT: movzbl 4(%rdi), %eax -; X64-NEXT: movzbl 4(%rsi), %ecx -; X64-NEXT: subl %ecx, %eax -; X64-NEXT: retq -; X64-NEXT: .LBB16_1: # %res_block -; X64-NEXT: setae %al -; X64-NEXT: movzbl %al, %eax -; X64-NEXT: leal -1(%rax,%rax), %eax -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 5) nounwind - ret i32 %m -} - -define i1 @length5_eq(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length5_eq: -; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-NEXT: movl (%ecx), %edx -; X86-NEXT: xorl (%eax), %edx -; X86-NEXT: movb 4(%ecx), %cl -; X86-NEXT: xorb 4(%eax), %cl -; X86-NEXT: movzbl %cl, %eax -; X86-NEXT: orl %edx, %eax -; X86-NEXT: setne %al -; X86-NEXT: retl -; -; X64-LABEL: length5_eq: -; X64: # %bb.0: -; X64-NEXT: movl (%rdi), %eax -; X64-NEXT: xorl (%rsi), %eax -; X64-NEXT: movb 4(%rdi), %cl -; X64-NEXT: xorb 4(%rsi), %cl -; X64-NEXT: movzbl %cl, %ecx -; X64-NEXT: orl %eax, %ecx -; X64-NEXT: setne %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 5) nounwind - %c = icmp ne i32 %m, 0 - ret i1 %c -} - -define i1 @length5_lt(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length5_lt: -; X86: # %bb.0: # %loadbb -; X86-NEXT: pushl %esi -; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl (%eax), %edx -; X86-NEXT: movl (%ecx), %esi -; X86-NEXT: bswapl %edx -; X86-NEXT: bswapl %esi -; X86-NEXT: cmpl %esi, %edx -; X86-NEXT: jne .LBB18_1 -; X86-NEXT: # %bb.2: # %loadbb1 -; X86-NEXT: movzbl 4(%eax), %eax -; X86-NEXT: movzbl 4(%ecx), %ecx -; X86-NEXT: subl %ecx, %eax -; X86-NEXT: jmp .LBB18_3 -; X86-NEXT: .LBB18_1: # %res_block -; X86-NEXT: setae %al -; X86-NEXT: movzbl %al, %eax -; X86-NEXT: leal -1(%eax,%eax), %eax -; X86-NEXT: .LBB18_3: # %endblock -; X86-NEXT: shrl $31, %eax -; X86-NEXT: # kill: def $al killed $al killed $eax -; X86-NEXT: popl %esi -; X86-NEXT: retl -; -; X64-LABEL: length5_lt: -; X64: # %bb.0: # %loadbb -; X64-NEXT: movl (%rdi), %eax -; X64-NEXT: movl (%rsi), %ecx -; X64-NEXT: bswapl %eax -; X64-NEXT: bswapl %ecx -; X64-NEXT: cmpl %ecx, %eax -; X64-NEXT: jne .LBB18_1 -; X64-NEXT: # %bb.2: # %loadbb1 -; X64-NEXT: movzbl 4(%rdi), %eax -; X64-NEXT: movzbl 4(%rsi), %ecx -; X64-NEXT: subl %ecx, %eax -; X64-NEXT: shrl $31, %eax -; X64-NEXT: # kill: def $al killed $al killed $eax -; X64-NEXT: retq -; X64-NEXT: .LBB18_1: # %res_block -; X64-NEXT: setae %al -; X64-NEXT: movzbl %al, %eax -; X64-NEXT: leal -1(%rax,%rax), %eax -; X64-NEXT: shrl $31, %eax -; X64-NEXT: # kill: def $al killed $al killed $eax -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 5) nounwind - %c = icmp slt i32 %m, 0 - ret i1 %c -} - -define i1 @length7_eq(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length7_eq: -; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-NEXT: movl (%ecx), %edx -; X86-NEXT: movl 3(%ecx), %ecx -; X86-NEXT: xorl (%eax), %edx -; X86-NEXT: xorl 3(%eax), %ecx -; X86-NEXT: orl %edx, %ecx -; X86-NEXT: setne %al -; X86-NEXT: retl -; -; X64-LABEL: length7_eq: -; X64: # %bb.0: -; X64-NEXT: movl (%rdi), %eax -; X64-NEXT: movl 3(%rdi), %ecx -; X64-NEXT: xorl (%rsi), %eax -; X64-NEXT: xorl 3(%rsi), %ecx -; X64-NEXT: orl %eax, %ecx -; X64-NEXT: setne %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 7) nounwind - %c = icmp ne i32 %m, 0 - ret i1 %c -} - -define i32 @length8(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length8: -; X86: # %bb.0: -; X86-NEXT: pushl %esi -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl {{[0-9]+}}(%esp), %esi -; X86-NEXT: movl (%esi), %ecx -; X86-NEXT: movl (%eax), %edx -; X86-NEXT: bswapl %ecx -; X86-NEXT: bswapl %edx -; X86-NEXT: cmpl %edx, %ecx -; X86-NEXT: jne .LBB20_2 -; X86-NEXT: # %bb.1: # %loadbb1 -; X86-NEXT: movl 4(%esi), %ecx -; X86-NEXT: movl 4(%eax), %edx -; X86-NEXT: bswapl %ecx -; X86-NEXT: bswapl %edx -; X86-NEXT: xorl %eax, %eax -; X86-NEXT: cmpl %edx, %ecx -; X86-NEXT: je .LBB20_3 -; X86-NEXT: .LBB20_2: # %res_block -; X86-NEXT: xorl %eax, %eax -; X86-NEXT: cmpl %edx, %ecx -; X86-NEXT: setae %al -; X86-NEXT: leal -1(%eax,%eax), %eax -; X86-NEXT: .LBB20_3: # %endblock -; X86-NEXT: popl %esi -; X86-NEXT: retl -; -; X64-LABEL: length8: -; X64: # %bb.0: -; X64-NEXT: movq (%rdi), %rcx -; X64-NEXT: movq (%rsi), %rdx -; X64-NEXT: bswapq %rcx -; X64-NEXT: bswapq %rdx -; X64-NEXT: xorl %eax, %eax -; X64-NEXT: cmpq %rdx, %rcx -; X64-NEXT: seta %al -; X64-NEXT: sbbl $0, %eax -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 8) nounwind - ret i32 %m -} - -define i1 @length8_eq(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length8_eq: -; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-NEXT: movl (%ecx), %edx -; X86-NEXT: movl 4(%ecx), %ecx -; X86-NEXT: xorl (%eax), %edx -; X86-NEXT: xorl 4(%eax), %ecx -; X86-NEXT: orl %edx, %ecx -; X86-NEXT: sete %al -; X86-NEXT: retl -; -; X64-LABEL: length8_eq: -; X64: # %bb.0: -; X64-NEXT: movq (%rdi), %rax -; X64-NEXT: cmpq (%rsi), %rax -; X64-NEXT: sete %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 8) nounwind - %c = icmp eq i32 %m, 0 - ret i1 %c -} - -define i1 @length8_eq_const(i8* %X) nounwind { -; X86-LABEL: length8_eq_const: -; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: movl $858927408, %ecx # imm = 0x33323130 -; X86-NEXT: xorl (%eax), %ecx -; X86-NEXT: movl $926299444, %edx # imm = 0x37363534 -; X86-NEXT: xorl 4(%eax), %edx -; X86-NEXT: orl %ecx, %edx -; X86-NEXT: setne %al -; X86-NEXT: retl -; -; X64-LABEL: length8_eq_const: -; X64: # %bb.0: -; X64-NEXT: movabsq $3978425819141910832, %rax # imm = 0x3736353433323130 -; X64-NEXT: cmpq %rax, (%rdi) -; X64-NEXT: setne %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* getelementptr inbounds ([65 x i8], [65 x i8]* @.str, i32 0, i32 0), i64 8) nounwind - %c = icmp ne i32 %m, 0 - ret i1 %c -} - -define i1 @length9_eq(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length9_eq: -; X86: # %bb.0: -; X86-NEXT: pushl $0 -; X86-NEXT: pushl $9 -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: testl %eax, %eax -; X86-NEXT: sete %al -; X86-NEXT: retl -; -; X64-LABEL: length9_eq: -; X64: # %bb.0: -; X64-NEXT: movq (%rdi), %rax -; X64-NEXT: xorq (%rsi), %rax -; X64-NEXT: movb 8(%rdi), %cl -; X64-NEXT: xorb 8(%rsi), %cl -; X64-NEXT: movzbl %cl, %ecx -; X64-NEXT: orq %rax, %rcx -; X64-NEXT: sete %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 9) nounwind - %c = icmp eq i32 %m, 0 - ret i1 %c -} - -define i1 @length10_eq(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length10_eq: -; X86: # %bb.0: -; X86-NEXT: pushl $0 -; X86-NEXT: pushl $10 -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: testl %eax, %eax -; X86-NEXT: sete %al -; X86-NEXT: retl -; -; X64-LABEL: length10_eq: -; X64: # %bb.0: -; X64-NEXT: movq (%rdi), %rax -; X64-NEXT: xorq (%rsi), %rax -; X64-NEXT: movzwl 8(%rdi), %ecx -; X64-NEXT: xorw 8(%rsi), %cx -; X64-NEXT: movzwl %cx, %ecx -; X64-NEXT: orq %rax, %rcx -; X64-NEXT: sete %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 10) nounwind - %c = icmp eq i32 %m, 0 - ret i1 %c -} - -define i1 @length11_eq(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length11_eq: -; X86: # %bb.0: -; X86-NEXT: pushl $0 -; X86-NEXT: pushl $11 -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: testl %eax, %eax -; X86-NEXT: sete %al -; X86-NEXT: retl -; -; X64-LABEL: length11_eq: -; X64: # %bb.0: -; X64-NEXT: movq (%rdi), %rax -; X64-NEXT: movq 3(%rdi), %rcx -; X64-NEXT: xorq (%rsi), %rax -; X64-NEXT: xorq 3(%rsi), %rcx -; X64-NEXT: orq %rax, %rcx -; X64-NEXT: sete %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 11) nounwind - %c = icmp eq i32 %m, 0 - ret i1 %c -} - -define i1 @length12_eq(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length12_eq: -; X86: # %bb.0: -; X86-NEXT: pushl $0 -; X86-NEXT: pushl $12 -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: testl %eax, %eax -; X86-NEXT: setne %al -; X86-NEXT: retl -; -; X64-LABEL: length12_eq: -; X64: # %bb.0: -; X64-NEXT: movq (%rdi), %rax -; X64-NEXT: xorq (%rsi), %rax -; X64-NEXT: movl 8(%rdi), %ecx -; X64-NEXT: xorl 8(%rsi), %ecx -; X64-NEXT: orq %rax, %rcx -; X64-NEXT: setne %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 12) nounwind - %c = icmp ne i32 %m, 0 - ret i1 %c -} - -define i32 @length12(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length12: -; X86: # %bb.0: -; X86-NEXT: pushl $0 -; X86-NEXT: pushl $12 -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: retl -; -; X64-LABEL: length12: -; X64: # %bb.0: -; X64-NEXT: movq (%rdi), %rcx -; X64-NEXT: movq (%rsi), %rdx -; X64-NEXT: bswapq %rcx -; X64-NEXT: bswapq %rdx -; X64-NEXT: cmpq %rdx, %rcx -; X64-NEXT: jne .LBB27_2 -; X64-NEXT: # %bb.1: # %loadbb1 -; X64-NEXT: movl 8(%rdi), %ecx -; X64-NEXT: movl 8(%rsi), %edx -; X64-NEXT: bswapl %ecx -; X64-NEXT: bswapl %edx -; X64-NEXT: xorl %eax, %eax -; X64-NEXT: cmpq %rdx, %rcx -; X64-NEXT: je .LBB27_3 -; X64-NEXT: .LBB27_2: # %res_block -; X64-NEXT: xorl %eax, %eax -; X64-NEXT: cmpq %rdx, %rcx -; X64-NEXT: setae %al -; X64-NEXT: leal -1(%rax,%rax), %eax -; X64-NEXT: .LBB27_3: # %endblock -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 12) nounwind - ret i32 %m -} - -define i1 @length13_eq(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length13_eq: -; X86: # %bb.0: -; X86-NEXT: pushl $0 -; X86-NEXT: pushl $13 -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: testl %eax, %eax -; X86-NEXT: sete %al -; X86-NEXT: retl -; -; X64-LABEL: length13_eq: -; X64: # %bb.0: -; X64-NEXT: movq (%rdi), %rax -; X64-NEXT: movq 5(%rdi), %rcx -; X64-NEXT: xorq (%rsi), %rax -; X64-NEXT: xorq 5(%rsi), %rcx -; X64-NEXT: orq %rax, %rcx -; X64-NEXT: sete %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 13) nounwind - %c = icmp eq i32 %m, 0 - ret i1 %c -} - -define i1 @length14_eq(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length14_eq: -; X86: # %bb.0: -; X86-NEXT: pushl $0 -; X86-NEXT: pushl $14 -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: testl %eax, %eax -; X86-NEXT: sete %al -; X86-NEXT: retl -; -; X64-LABEL: length14_eq: -; X64: # %bb.0: -; X64-NEXT: movq (%rdi), %rax -; X64-NEXT: movq 6(%rdi), %rcx -; X64-NEXT: xorq (%rsi), %rax -; X64-NEXT: xorq 6(%rsi), %rcx -; X64-NEXT: orq %rax, %rcx -; X64-NEXT: sete %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 14) nounwind - %c = icmp eq i32 %m, 0 - ret i1 %c -} - -define i1 @length15_eq(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length15_eq: -; X86: # %bb.0: -; X86-NEXT: pushl $0 -; X86-NEXT: pushl $15 -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: testl %eax, %eax -; X86-NEXT: sete %al -; X86-NEXT: retl -; -; X64-LABEL: length15_eq: -; X64: # %bb.0: -; X64-NEXT: movq (%rdi), %rax -; X64-NEXT: movq 7(%rdi), %rcx -; X64-NEXT: xorq (%rsi), %rax -; X64-NEXT: xorq 7(%rsi), %rcx -; X64-NEXT: orq %rax, %rcx -; X64-NEXT: sete %al -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 15) nounwind - %c = icmp eq i32 %m, 0 - ret i1 %c -} - -; PR33329 - https://bugs.llvm.org/show_bug.cgi?id=33329 - -define i32 @length16(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length16: -; X86: # %bb.0: -; X86-NEXT: pushl $0 -; X86-NEXT: pushl $16 -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: retl -; -; X64-LABEL: length16: -; X64: # %bb.0: -; X64-NEXT: movq (%rdi), %rcx -; X64-NEXT: movq (%rsi), %rdx -; X64-NEXT: bswapq %rcx -; X64-NEXT: bswapq %rdx -; X64-NEXT: cmpq %rdx, %rcx -; X64-NEXT: jne .LBB31_2 -; X64-NEXT: # %bb.1: # %loadbb1 -; X64-NEXT: movq 8(%rdi), %rcx -; X64-NEXT: movq 8(%rsi), %rdx -; X64-NEXT: bswapq %rcx -; X64-NEXT: bswapq %rdx -; X64-NEXT: xorl %eax, %eax -; X64-NEXT: cmpq %rdx, %rcx -; X64-NEXT: je .LBB31_3 -; X64-NEXT: .LBB31_2: # %res_block -; X64-NEXT: xorl %eax, %eax -; X64-NEXT: cmpq %rdx, %rcx -; X64-NEXT: setae %al -; X64-NEXT: leal -1(%rax,%rax), %eax -; X64-NEXT: .LBB31_3: # %endblock -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 16) nounwind - ret i32 %m -} - -define i1 @length16_eq(i8* %x, i8* %y) nounwind { -; X86-NOSSE-LABEL: length16_eq: -; X86-NOSSE: # %bb.0: -; X86-NOSSE-NEXT: pushl $0 -; X86-NOSSE-NEXT: pushl $16 -; X86-NOSSE-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NOSSE-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NOSSE-NEXT: calll memcmp -; X86-NOSSE-NEXT: addl $16, %esp -; X86-NOSSE-NEXT: testl %eax, %eax -; X86-NOSSE-NEXT: setne %al -; X86-NOSSE-NEXT: retl -; -; X86-SSE1-LABEL: length16_eq: -; X86-SSE1: # %bb.0: -; X86-SSE1-NEXT: pushl $0 -; X86-SSE1-NEXT: pushl $16 -; X86-SSE1-NEXT: pushl {{[0-9]+}}(%esp) -; X86-SSE1-NEXT: pushl {{[0-9]+}}(%esp) -; X86-SSE1-NEXT: calll memcmp -; X86-SSE1-NEXT: addl $16, %esp -; X86-SSE1-NEXT: testl %eax, %eax -; X86-SSE1-NEXT: setne %al -; X86-SSE1-NEXT: retl -; -; X86-SSE2-LABEL: length16_eq: -; X86-SSE2: # %bb.0: -; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-SSE2-NEXT: movdqu (%ecx), %xmm0 -; X86-SSE2-NEXT: movdqu (%eax), %xmm1 -; X86-SSE2-NEXT: pcmpeqb %xmm0, %xmm1 -; X86-SSE2-NEXT: pmovmskb %xmm1, %eax -; X86-SSE2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X86-SSE2-NEXT: setne %al -; X86-SSE2-NEXT: retl -; -; X64-SSE2-LABEL: length16_eq: -; X64-SSE2: # %bb.0: -; X64-SSE2-NEXT: movdqu (%rdi), %xmm0 -; X64-SSE2-NEXT: movdqu (%rsi), %xmm1 -; X64-SSE2-NEXT: pcmpeqb %xmm0, %xmm1 -; X64-SSE2-NEXT: pmovmskb %xmm1, %eax -; X64-SSE2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X64-SSE2-NEXT: setne %al -; X64-SSE2-NEXT: retq -; -; X64-AVX-LABEL: length16_eq: -; X64-AVX: # %bb.0: -; X64-AVX-NEXT: vmovdqu (%rdi), %xmm0 -; X64-AVX-NEXT: vpcmpeqb (%rsi), %xmm0, %xmm0 -; X64-AVX-NEXT: vpmovmskb %xmm0, %eax -; X64-AVX-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X64-AVX-NEXT: setne %al -; X64-AVX-NEXT: retq - %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 16) nounwind - %cmp = icmp ne i32 %call, 0 - ret i1 %cmp -} - -define i1 @length16_eq_const(i8* %X) nounwind { -; X86-NOSSE-LABEL: length16_eq_const: -; X86-NOSSE: # %bb.0: -; X86-NOSSE-NEXT: pushl $0 -; X86-NOSSE-NEXT: pushl $16 -; X86-NOSSE-NEXT: pushl $.L.str -; X86-NOSSE-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NOSSE-NEXT: calll memcmp -; X86-NOSSE-NEXT: addl $16, %esp -; X86-NOSSE-NEXT: testl %eax, %eax -; X86-NOSSE-NEXT: sete %al -; X86-NOSSE-NEXT: retl -; -; X86-SSE1-LABEL: length16_eq_const: -; X86-SSE1: # %bb.0: -; X86-SSE1-NEXT: pushl $0 -; X86-SSE1-NEXT: pushl $16 -; X86-SSE1-NEXT: pushl $.L.str -; X86-SSE1-NEXT: pushl {{[0-9]+}}(%esp) -; X86-SSE1-NEXT: calll memcmp -; X86-SSE1-NEXT: addl $16, %esp -; X86-SSE1-NEXT: testl %eax, %eax -; X86-SSE1-NEXT: sete %al -; X86-SSE1-NEXT: retl -; -; X86-SSE2-LABEL: length16_eq_const: -; X86-SSE2: # %bb.0: -; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-SSE2-NEXT: movdqu (%eax), %xmm0 -; X86-SSE2-NEXT: pcmpeqb {{\.LCPI.*}}, %xmm0 -; X86-SSE2-NEXT: pmovmskb %xmm0, %eax -; X86-SSE2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X86-SSE2-NEXT: sete %al -; X86-SSE2-NEXT: retl -; -; X64-SSE2-LABEL: length16_eq_const: -; X64-SSE2: # %bb.0: -; X64-SSE2-NEXT: movdqu (%rdi), %xmm0 -; X64-SSE2-NEXT: pcmpeqb {{.*}}(%rip), %xmm0 -; X64-SSE2-NEXT: pmovmskb %xmm0, %eax -; X64-SSE2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X64-SSE2-NEXT: sete %al -; X64-SSE2-NEXT: retq -; -; X64-AVX-LABEL: length16_eq_const: -; X64-AVX: # %bb.0: -; X64-AVX-NEXT: vmovdqu (%rdi), %xmm0 -; X64-AVX-NEXT: vpcmpeqb {{.*}}(%rip), %xmm0, %xmm0 -; X64-AVX-NEXT: vpmovmskb %xmm0, %eax -; X64-AVX-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X64-AVX-NEXT: sete %al -; X64-AVX-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* getelementptr inbounds ([65 x i8], [65 x i8]* @.str, i32 0, i32 0), i64 16) nounwind - %c = icmp eq i32 %m, 0 - ret i1 %c -} - -; PR33914 - https://bugs.llvm.org/show_bug.cgi?id=33914 - -define i32 @length24(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length24: -; X86: # %bb.0: -; X86-NEXT: pushl $0 -; X86-NEXT: pushl $24 -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: retl -; -; X64-LABEL: length24: -; X64: # %bb.0: -; X64-NEXT: movl $24, %edx -; X64-NEXT: jmp memcmp # TAILCALL - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 24) nounwind - ret i32 %m -} - -define i1 @length24_eq(i8* %x, i8* %y) nounwind { -; X86-NOSSE-LABEL: length24_eq: -; X86-NOSSE: # %bb.0: -; X86-NOSSE-NEXT: pushl $0 -; X86-NOSSE-NEXT: pushl $24 -; X86-NOSSE-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NOSSE-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NOSSE-NEXT: calll memcmp -; X86-NOSSE-NEXT: addl $16, %esp -; X86-NOSSE-NEXT: testl %eax, %eax -; X86-NOSSE-NEXT: sete %al -; X86-NOSSE-NEXT: retl -; -; X86-SSE1-LABEL: length24_eq: -; X86-SSE1: # %bb.0: -; X86-SSE1-NEXT: pushl $0 -; X86-SSE1-NEXT: pushl $24 -; X86-SSE1-NEXT: pushl {{[0-9]+}}(%esp) -; X86-SSE1-NEXT: pushl {{[0-9]+}}(%esp) -; X86-SSE1-NEXT: calll memcmp -; X86-SSE1-NEXT: addl $16, %esp -; X86-SSE1-NEXT: testl %eax, %eax -; X86-SSE1-NEXT: sete %al -; X86-SSE1-NEXT: retl -; -; X86-SSE2-LABEL: length24_eq: -; X86-SSE2: # %bb.0: -; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-SSE2-NEXT: movdqu (%ecx), %xmm0 -; X86-SSE2-NEXT: movdqu 8(%ecx), %xmm1 -; X86-SSE2-NEXT: movdqu (%eax), %xmm2 -; X86-SSE2-NEXT: pcmpeqb %xmm0, %xmm2 -; X86-SSE2-NEXT: movdqu 8(%eax), %xmm0 -; X86-SSE2-NEXT: pcmpeqb %xmm1, %xmm0 -; X86-SSE2-NEXT: pand %xmm2, %xmm0 -; X86-SSE2-NEXT: pmovmskb %xmm0, %eax -; X86-SSE2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X86-SSE2-NEXT: sete %al -; X86-SSE2-NEXT: retl -; -; X64-SSE2-LABEL: length24_eq: -; X64-SSE2: # %bb.0: -; X64-SSE2-NEXT: movdqu (%rdi), %xmm0 -; X64-SSE2-NEXT: movdqu (%rsi), %xmm1 -; X64-SSE2-NEXT: pcmpeqb %xmm0, %xmm1 -; X64-SSE2-NEXT: movq {{.*#+}} xmm0 = mem[0],zero -; X64-SSE2-NEXT: movq {{.*#+}} xmm2 = mem[0],zero -; X64-SSE2-NEXT: pcmpeqb %xmm0, %xmm2 -; X64-SSE2-NEXT: pand %xmm1, %xmm2 -; X64-SSE2-NEXT: pmovmskb %xmm2, %eax -; X64-SSE2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X64-SSE2-NEXT: sete %al -; X64-SSE2-NEXT: retq -; -; X64-AVX-LABEL: length24_eq: -; X64-AVX: # %bb.0: -; X64-AVX-NEXT: vmovdqu (%rdi), %xmm0 -; X64-AVX-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero -; X64-AVX-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero -; X64-AVX-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm1 -; X64-AVX-NEXT: vpcmpeqb (%rsi), %xmm0, %xmm0 -; X64-AVX-NEXT: vpand %xmm1, %xmm0, %xmm0 -; X64-AVX-NEXT: vpmovmskb %xmm0, %eax -; X64-AVX-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X64-AVX-NEXT: sete %al -; X64-AVX-NEXT: retq - %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 24) nounwind - %cmp = icmp eq i32 %call, 0 - ret i1 %cmp -} - -define i1 @length24_eq_const(i8* %X) nounwind { -; X86-NOSSE-LABEL: length24_eq_const: -; X86-NOSSE: # %bb.0: -; X86-NOSSE-NEXT: pushl $0 -; X86-NOSSE-NEXT: pushl $24 -; X86-NOSSE-NEXT: pushl $.L.str -; X86-NOSSE-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NOSSE-NEXT: calll memcmp -; X86-NOSSE-NEXT: addl $16, %esp -; X86-NOSSE-NEXT: testl %eax, %eax -; X86-NOSSE-NEXT: setne %al -; X86-NOSSE-NEXT: retl -; -; X86-SSE1-LABEL: length24_eq_const: -; X86-SSE1: # %bb.0: -; X86-SSE1-NEXT: pushl $0 -; X86-SSE1-NEXT: pushl $24 -; X86-SSE1-NEXT: pushl $.L.str -; X86-SSE1-NEXT: pushl {{[0-9]+}}(%esp) -; X86-SSE1-NEXT: calll memcmp -; X86-SSE1-NEXT: addl $16, %esp -; X86-SSE1-NEXT: testl %eax, %eax -; X86-SSE1-NEXT: setne %al -; X86-SSE1-NEXT: retl -; -; X86-SSE2-LABEL: length24_eq_const: -; X86-SSE2: # %bb.0: -; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-SSE2-NEXT: movdqu (%eax), %xmm0 -; X86-SSE2-NEXT: movdqu 8(%eax), %xmm1 -; X86-SSE2-NEXT: pcmpeqb {{\.LCPI.*}}, %xmm1 -; X86-SSE2-NEXT: pcmpeqb {{\.LCPI.*}}, %xmm0 -; X86-SSE2-NEXT: pand %xmm1, %xmm0 -; X86-SSE2-NEXT: pmovmskb %xmm0, %eax -; X86-SSE2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X86-SSE2-NEXT: setne %al -; X86-SSE2-NEXT: retl -; -; X64-SSE2-LABEL: length24_eq_const: -; X64-SSE2: # %bb.0: -; X64-SSE2-NEXT: movdqu (%rdi), %xmm0 -; X64-SSE2-NEXT: movq {{.*#+}} xmm1 = mem[0],zero -; X64-SSE2-NEXT: pcmpeqb {{.*}}(%rip), %xmm1 -; X64-SSE2-NEXT: pcmpeqb {{.*}}(%rip), %xmm0 -; X64-SSE2-NEXT: pand %xmm1, %xmm0 -; X64-SSE2-NEXT: pmovmskb %xmm0, %eax -; X64-SSE2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X64-SSE2-NEXT: setne %al -; X64-SSE2-NEXT: retq -; -; X64-AVX-LABEL: length24_eq_const: -; X64-AVX: # %bb.0: -; X64-AVX-NEXT: vmovdqu (%rdi), %xmm0 -; X64-AVX-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero -; X64-AVX-NEXT: vpcmpeqb {{.*}}(%rip), %xmm1, %xmm1 -; X64-AVX-NEXT: vpcmpeqb {{.*}}(%rip), %xmm0, %xmm0 -; X64-AVX-NEXT: vpand %xmm1, %xmm0, %xmm0 -; X64-AVX-NEXT: vpmovmskb %xmm0, %eax -; X64-AVX-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X64-AVX-NEXT: setne %al -; X64-AVX-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* getelementptr inbounds ([65 x i8], [65 x i8]* @.str, i32 0, i32 0), i64 24) nounwind - %c = icmp ne i32 %m, 0 - ret i1 %c -} - -define i32 @length32(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length32: -; X86: # %bb.0: -; X86-NEXT: pushl $0 -; X86-NEXT: pushl $32 -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: retl -; -; X64-LABEL: length32: -; X64: # %bb.0: -; X64-NEXT: movl $32, %edx -; X64-NEXT: jmp memcmp # TAILCALL - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 32) nounwind - ret i32 %m -} - -; PR33325 - https://bugs.llvm.org/show_bug.cgi?id=33325 - -define i1 @length32_eq(i8* %x, i8* %y) nounwind { -; X86-NOSSE-LABEL: length32_eq: -; X86-NOSSE: # %bb.0: -; X86-NOSSE-NEXT: pushl $0 -; X86-NOSSE-NEXT: pushl $32 -; X86-NOSSE-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NOSSE-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NOSSE-NEXT: calll memcmp -; X86-NOSSE-NEXT: addl $16, %esp -; X86-NOSSE-NEXT: testl %eax, %eax -; X86-NOSSE-NEXT: sete %al -; X86-NOSSE-NEXT: retl -; -; X86-SSE1-LABEL: length32_eq: -; X86-SSE1: # %bb.0: -; X86-SSE1-NEXT: pushl $0 -; X86-SSE1-NEXT: pushl $32 -; X86-SSE1-NEXT: pushl {{[0-9]+}}(%esp) -; X86-SSE1-NEXT: pushl {{[0-9]+}}(%esp) -; X86-SSE1-NEXT: calll memcmp -; X86-SSE1-NEXT: addl $16, %esp -; X86-SSE1-NEXT: testl %eax, %eax -; X86-SSE1-NEXT: sete %al -; X86-SSE1-NEXT: retl -; -; X86-SSE2-LABEL: length32_eq: -; X86-SSE2: # %bb.0: -; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-SSE2-NEXT: movdqu (%ecx), %xmm0 -; X86-SSE2-NEXT: movdqu 16(%ecx), %xmm1 -; X86-SSE2-NEXT: movdqu (%eax), %xmm2 -; X86-SSE2-NEXT: pcmpeqb %xmm0, %xmm2 -; X86-SSE2-NEXT: movdqu 16(%eax), %xmm0 -; X86-SSE2-NEXT: pcmpeqb %xmm1, %xmm0 -; X86-SSE2-NEXT: pand %xmm2, %xmm0 -; X86-SSE2-NEXT: pmovmskb %xmm0, %eax -; X86-SSE2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X86-SSE2-NEXT: sete %al -; X86-SSE2-NEXT: retl -; -; X64-SSE2-LABEL: length32_eq: -; X64-SSE2: # %bb.0: -; X64-SSE2-NEXT: movdqu (%rdi), %xmm0 -; X64-SSE2-NEXT: movdqu 16(%rdi), %xmm1 -; X64-SSE2-NEXT: movdqu (%rsi), %xmm2 -; X64-SSE2-NEXT: pcmpeqb %xmm0, %xmm2 -; X64-SSE2-NEXT: movdqu 16(%rsi), %xmm0 -; X64-SSE2-NEXT: pcmpeqb %xmm1, %xmm0 -; X64-SSE2-NEXT: pand %xmm2, %xmm0 -; X64-SSE2-NEXT: pmovmskb %xmm0, %eax -; X64-SSE2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X64-SSE2-NEXT: sete %al -; X64-SSE2-NEXT: retq -; -; X64-AVX1-LABEL: length32_eq: -; X64-AVX1: # %bb.0: -; X64-AVX1-NEXT: vmovdqu (%rdi), %xmm0 -; X64-AVX1-NEXT: vmovdqu 16(%rdi), %xmm1 -; X64-AVX1-NEXT: vpcmpeqb 16(%rsi), %xmm1, %xmm1 -; X64-AVX1-NEXT: vpcmpeqb (%rsi), %xmm0, %xmm0 -; X64-AVX1-NEXT: vpand %xmm1, %xmm0, %xmm0 -; X64-AVX1-NEXT: vpmovmskb %xmm0, %eax -; X64-AVX1-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X64-AVX1-NEXT: sete %al -; X64-AVX1-NEXT: retq -; -; X64-AVX2-LABEL: length32_eq: -; X64-AVX2: # %bb.0: -; X64-AVX2-NEXT: vmovdqu (%rdi), %ymm0 -; X64-AVX2-NEXT: vpcmpeqb (%rsi), %ymm0, %ymm0 -; X64-AVX2-NEXT: vpmovmskb %ymm0, %eax -; X64-AVX2-NEXT: cmpl $-1, %eax -; X64-AVX2-NEXT: sete %al -; X64-AVX2-NEXT: vzeroupper -; X64-AVX2-NEXT: retq - %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 32) nounwind - %cmp = icmp eq i32 %call, 0 - ret i1 %cmp -} - -define i1 @length32_eq_prefer128(i8* %x, i8* %y) nounwind "prefer-vector-width"="128" { -; X86-NOSSE-LABEL: length32_eq_prefer128: -; X86-NOSSE: # %bb.0: -; X86-NOSSE-NEXT: pushl $0 -; X86-NOSSE-NEXT: pushl $32 -; X86-NOSSE-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NOSSE-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NOSSE-NEXT: calll memcmp -; X86-NOSSE-NEXT: addl $16, %esp -; X86-NOSSE-NEXT: testl %eax, %eax -; X86-NOSSE-NEXT: sete %al -; X86-NOSSE-NEXT: retl -; -; X86-SSE1-LABEL: length32_eq_prefer128: -; X86-SSE1: # %bb.0: -; X86-SSE1-NEXT: pushl $0 -; X86-SSE1-NEXT: pushl $32 -; X86-SSE1-NEXT: pushl {{[0-9]+}}(%esp) -; X86-SSE1-NEXT: pushl {{[0-9]+}}(%esp) -; X86-SSE1-NEXT: calll memcmp -; X86-SSE1-NEXT: addl $16, %esp -; X86-SSE1-NEXT: testl %eax, %eax -; X86-SSE1-NEXT: sete %al -; X86-SSE1-NEXT: retl -; -; X86-SSE2-LABEL: length32_eq_prefer128: -; X86-SSE2: # %bb.0: -; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %ecx -; X86-SSE2-NEXT: movdqu (%ecx), %xmm0 -; X86-SSE2-NEXT: movdqu 16(%ecx), %xmm1 -; X86-SSE2-NEXT: movdqu (%eax), %xmm2 -; X86-SSE2-NEXT: pcmpeqb %xmm0, %xmm2 -; X86-SSE2-NEXT: movdqu 16(%eax), %xmm0 -; X86-SSE2-NEXT: pcmpeqb %xmm1, %xmm0 -; X86-SSE2-NEXT: pand %xmm2, %xmm0 -; X86-SSE2-NEXT: pmovmskb %xmm0, %eax -; X86-SSE2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X86-SSE2-NEXT: sete %al -; X86-SSE2-NEXT: retl -; -; X64-SSE2-LABEL: length32_eq_prefer128: -; X64-SSE2: # %bb.0: -; X64-SSE2-NEXT: movdqu (%rdi), %xmm0 -; X64-SSE2-NEXT: movdqu 16(%rdi), %xmm1 -; X64-SSE2-NEXT: movdqu (%rsi), %xmm2 -; X64-SSE2-NEXT: pcmpeqb %xmm0, %xmm2 -; X64-SSE2-NEXT: movdqu 16(%rsi), %xmm0 -; X64-SSE2-NEXT: pcmpeqb %xmm1, %xmm0 -; X64-SSE2-NEXT: pand %xmm2, %xmm0 -; X64-SSE2-NEXT: pmovmskb %xmm0, %eax -; X64-SSE2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X64-SSE2-NEXT: sete %al -; X64-SSE2-NEXT: retq -; -; X64-AVX-LABEL: length32_eq_prefer128: -; X64-AVX: # %bb.0: -; X64-AVX-NEXT: vmovdqu (%rdi), %xmm0 -; X64-AVX-NEXT: vmovdqu 16(%rdi), %xmm1 -; X64-AVX-NEXT: vpcmpeqb 16(%rsi), %xmm1, %xmm1 -; X64-AVX-NEXT: vpcmpeqb (%rsi), %xmm0, %xmm0 -; X64-AVX-NEXT: vpand %xmm1, %xmm0, %xmm0 -; X64-AVX-NEXT: vpmovmskb %xmm0, %eax -; X64-AVX-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X64-AVX-NEXT: sete %al -; X64-AVX-NEXT: retq - %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 32) nounwind - %cmp = icmp eq i32 %call, 0 - ret i1 %cmp -} - -define i1 @length32_eq_const(i8* %X) nounwind { -; X86-NOSSE-LABEL: length32_eq_const: -; X86-NOSSE: # %bb.0: -; X86-NOSSE-NEXT: pushl $0 -; X86-NOSSE-NEXT: pushl $32 -; X86-NOSSE-NEXT: pushl $.L.str -; X86-NOSSE-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NOSSE-NEXT: calll memcmp -; X86-NOSSE-NEXT: addl $16, %esp -; X86-NOSSE-NEXT: testl %eax, %eax -; X86-NOSSE-NEXT: setne %al -; X86-NOSSE-NEXT: retl -; -; X86-SSE1-LABEL: length32_eq_const: -; X86-SSE1: # %bb.0: -; X86-SSE1-NEXT: pushl $0 -; X86-SSE1-NEXT: pushl $32 -; X86-SSE1-NEXT: pushl $.L.str -; X86-SSE1-NEXT: pushl {{[0-9]+}}(%esp) -; X86-SSE1-NEXT: calll memcmp -; X86-SSE1-NEXT: addl $16, %esp -; X86-SSE1-NEXT: testl %eax, %eax -; X86-SSE1-NEXT: setne %al -; X86-SSE1-NEXT: retl -; -; X86-SSE2-LABEL: length32_eq_const: -; X86-SSE2: # %bb.0: -; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-SSE2-NEXT: movdqu (%eax), %xmm0 -; X86-SSE2-NEXT: movdqu 16(%eax), %xmm1 -; X86-SSE2-NEXT: pcmpeqb {{\.LCPI.*}}, %xmm1 -; X86-SSE2-NEXT: pcmpeqb {{\.LCPI.*}}, %xmm0 -; X86-SSE2-NEXT: pand %xmm1, %xmm0 -; X86-SSE2-NEXT: pmovmskb %xmm0, %eax -; X86-SSE2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X86-SSE2-NEXT: setne %al -; X86-SSE2-NEXT: retl -; -; X64-SSE2-LABEL: length32_eq_const: -; X64-SSE2: # %bb.0: -; X64-SSE2-NEXT: movdqu (%rdi), %xmm0 -; X64-SSE2-NEXT: movdqu 16(%rdi), %xmm1 -; X64-SSE2-NEXT: pcmpeqb {{.*}}(%rip), %xmm1 -; X64-SSE2-NEXT: pcmpeqb {{.*}}(%rip), %xmm0 -; X64-SSE2-NEXT: pand %xmm1, %xmm0 -; X64-SSE2-NEXT: pmovmskb %xmm0, %eax -; X64-SSE2-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X64-SSE2-NEXT: setne %al -; X64-SSE2-NEXT: retq -; -; X64-AVX1-LABEL: length32_eq_const: -; X64-AVX1: # %bb.0: -; X64-AVX1-NEXT: vmovdqu (%rdi), %xmm0 -; X64-AVX1-NEXT: vmovdqu 16(%rdi), %xmm1 -; X64-AVX1-NEXT: vpcmpeqb {{.*}}(%rip), %xmm1, %xmm1 -; X64-AVX1-NEXT: vpcmpeqb {{.*}}(%rip), %xmm0, %xmm0 -; X64-AVX1-NEXT: vpand %xmm1, %xmm0, %xmm0 -; X64-AVX1-NEXT: vpmovmskb %xmm0, %eax -; X64-AVX1-NEXT: cmpl $65535, %eax # imm = 0xFFFF -; X64-AVX1-NEXT: setne %al -; X64-AVX1-NEXT: retq -; -; X64-AVX2-LABEL: length32_eq_const: -; X64-AVX2: # %bb.0: -; X64-AVX2-NEXT: vmovdqu (%rdi), %ymm0 -; X64-AVX2-NEXT: vpcmpeqb {{.*}}(%rip), %ymm0, %ymm0 -; X64-AVX2-NEXT: vpmovmskb %ymm0, %eax -; X64-AVX2-NEXT: cmpl $-1, %eax -; X64-AVX2-NEXT: setne %al -; X64-AVX2-NEXT: vzeroupper -; X64-AVX2-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* getelementptr inbounds ([65 x i8], [65 x i8]* @.str, i32 0, i32 0), i64 32) nounwind - %c = icmp ne i32 %m, 0 - ret i1 %c -} - -define i32 @length64(i8* %X, i8* %Y) nounwind { -; X86-LABEL: length64: -; X86: # %bb.0: -; X86-NEXT: pushl $0 -; X86-NEXT: pushl $64 -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: retl -; -; X64-LABEL: length64: -; X64: # %bb.0: -; X64-NEXT: movl $64, %edx -; X64-NEXT: jmp memcmp # TAILCALL - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 64) nounwind - ret i32 %m -} - -define i1 @length64_eq(i8* %x, i8* %y) nounwind { -; X86-LABEL: length64_eq: -; X86: # %bb.0: -; X86-NEXT: pushl $0 -; X86-NEXT: pushl $64 -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: testl %eax, %eax -; X86-NEXT: setne %al -; X86-NEXT: retl -; -; X64-SSE2-LABEL: length64_eq: -; X64-SSE2: # %bb.0: -; X64-SSE2-NEXT: pushq %rax -; X64-SSE2-NEXT: movl $64, %edx -; X64-SSE2-NEXT: callq memcmp -; X64-SSE2-NEXT: testl %eax, %eax -; X64-SSE2-NEXT: setne %al -; X64-SSE2-NEXT: popq %rcx -; X64-SSE2-NEXT: retq -; -; X64-AVX1-LABEL: length64_eq: -; X64-AVX1: # %bb.0: -; X64-AVX1-NEXT: pushq %rax -; X64-AVX1-NEXT: movl $64, %edx -; X64-AVX1-NEXT: callq memcmp -; X64-AVX1-NEXT: testl %eax, %eax -; X64-AVX1-NEXT: setne %al -; X64-AVX1-NEXT: popq %rcx -; X64-AVX1-NEXT: retq -; -; X64-AVX2-LABEL: length64_eq: -; X64-AVX2: # %bb.0: -; X64-AVX2-NEXT: vmovdqu (%rdi), %ymm0 -; X64-AVX2-NEXT: vmovdqu 32(%rdi), %ymm1 -; X64-AVX2-NEXT: vpcmpeqb 32(%rsi), %ymm1, %ymm1 -; X64-AVX2-NEXT: vpcmpeqb (%rsi), %ymm0, %ymm0 -; X64-AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0 -; X64-AVX2-NEXT: vpmovmskb %ymm0, %eax -; X64-AVX2-NEXT: cmpl $-1, %eax -; X64-AVX2-NEXT: setne %al -; X64-AVX2-NEXT: vzeroupper -; X64-AVX2-NEXT: retq - %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 64) nounwind - %cmp = icmp ne i32 %call, 0 - ret i1 %cmp -} - -define i1 @length64_eq_const(i8* %X) nounwind { -; X86-LABEL: length64_eq_const: -; X86: # %bb.0: -; X86-NEXT: pushl $0 -; X86-NEXT: pushl $64 -; X86-NEXT: pushl $.L.str -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: testl %eax, %eax -; X86-NEXT: sete %al -; X86-NEXT: retl -; -; X64-SSE2-LABEL: length64_eq_const: -; X64-SSE2: # %bb.0: -; X64-SSE2-NEXT: pushq %rax -; X64-SSE2-NEXT: movl $.L.str, %esi -; X64-SSE2-NEXT: movl $64, %edx -; X64-SSE2-NEXT: callq memcmp -; X64-SSE2-NEXT: testl %eax, %eax -; X64-SSE2-NEXT: sete %al -; X64-SSE2-NEXT: popq %rcx -; X64-SSE2-NEXT: retq -; -; X64-AVX1-LABEL: length64_eq_const: -; X64-AVX1: # %bb.0: -; X64-AVX1-NEXT: pushq %rax -; X64-AVX1-NEXT: movl $.L.str, %esi -; X64-AVX1-NEXT: movl $64, %edx -; X64-AVX1-NEXT: callq memcmp -; X64-AVX1-NEXT: testl %eax, %eax -; X64-AVX1-NEXT: sete %al -; X64-AVX1-NEXT: popq %rcx -; X64-AVX1-NEXT: retq -; -; X64-AVX2-LABEL: length64_eq_const: -; X64-AVX2: # %bb.0: -; X64-AVX2-NEXT: vmovdqu (%rdi), %ymm0 -; X64-AVX2-NEXT: vmovdqu 32(%rdi), %ymm1 -; X64-AVX2-NEXT: vpcmpeqb {{.*}}(%rip), %ymm1, %ymm1 -; X64-AVX2-NEXT: vpcmpeqb {{.*}}(%rip), %ymm0, %ymm0 -; X64-AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0 -; X64-AVX2-NEXT: vpmovmskb %ymm0, %eax -; X64-AVX2-NEXT: cmpl $-1, %eax -; X64-AVX2-NEXT: sete %al -; X64-AVX2-NEXT: vzeroupper -; X64-AVX2-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* getelementptr inbounds ([65 x i8], [65 x i8]* @.str, i32 0, i32 0), i64 64) nounwind - %c = icmp eq i32 %m, 0 - ret i1 %c -} - -; This checks that we do not do stupid things with huge sizes. -define i32 @huge_length(i8* %X, i8* %Y) nounwind { -; X86-LABEL: huge_length: -; X86: # %bb.0: -; X86-NEXT: pushl $2147483647 # imm = 0x7FFFFFFF -; X86-NEXT: pushl $-1 -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: retl -; -; X64-LABEL: huge_length: -; X64: # %bb.0: -; X64-NEXT: movabsq $9223372036854775807, %rdx # imm = 0x7FFFFFFFFFFFFFFF -; X64-NEXT: jmp memcmp # TAILCALL - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 9223372036854775807) nounwind - ret i32 %m -} - -define i1 @huge_length_eq(i8* %X, i8* %Y) nounwind { -; X86-LABEL: huge_length_eq: -; X86: # %bb.0: -; X86-NEXT: pushl $2147483647 # imm = 0x7FFFFFFF -; X86-NEXT: pushl $-1 -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: testl %eax, %eax -; X86-NEXT: sete %al -; X86-NEXT: retl -; -; X64-LABEL: huge_length_eq: -; X64: # %bb.0: -; X64-NEXT: pushq %rax -; X64-NEXT: movabsq $9223372036854775807, %rdx # imm = 0x7FFFFFFFFFFFFFFF -; X64-NEXT: callq memcmp -; X64-NEXT: testl %eax, %eax -; X64-NEXT: sete %al -; X64-NEXT: popq %rcx -; X64-NEXT: retq - - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 9223372036854775807) nounwind - %c = icmp eq i32 %m, 0 - ret i1 %c -} - -; This checks non-constant sizes. -define i32 @nonconst_length(i8* %X, i8* %Y, i64 %size) nounwind { -; X86-LABEL: nonconst_length: -; X86: # %bb.0: -; X86-NEXT: jmp memcmp # TAILCALL -; -; X64-LABEL: nonconst_length: -; X64: # %bb.0: -; X64-NEXT: jmp memcmp # TAILCALL - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 %size) nounwind - ret i32 %m -} - -define i1 @nonconst_length_eq(i8* %X, i8* %Y, i64 %size) nounwind { -; X86-LABEL: nonconst_length_eq: -; X86: # %bb.0: -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: pushl {{[0-9]+}}(%esp) -; X86-NEXT: calll memcmp -; X86-NEXT: addl $16, %esp -; X86-NEXT: testl %eax, %eax -; X86-NEXT: sete %al -; X86-NEXT: retl -; -; X64-LABEL: nonconst_length_eq: -; X64: # %bb.0: -; X64-NEXT: pushq %rax -; X64-NEXT: callq memcmp -; X64-NEXT: testl %eax, %eax -; X64-NEXT: sete %al -; X64-NEXT: popq %rcx -; X64-NEXT: retq - %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 %size) nounwind - %c = icmp eq i32 %m, 0 - ret i1 %c -} |