summaryrefslogtreecommitdiffstats
path: root/llvm/test/CodeGen/PowerPC
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/test/CodeGen/PowerPC')
-rw-r--r--llvm/test/CodeGen/PowerPC/memCmpUsedInZeroEqualityComparison.ll218
-rw-r--r--llvm/test/CodeGen/PowerPC/memcmp-mergeexpand.ll40
-rw-r--r--llvm/test/CodeGen/PowerPC/memcmp.ll70
-rw-r--r--llvm/test/CodeGen/PowerPC/memcmpIR.ll192
4 files changed, 0 insertions, 520 deletions
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
-}
OpenPOWER on IntegriCloud