maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/PowerPC/memCmpUsedInZeroEqualityCom...

205 lines
7.7 KiB
LLVM
Raw Normal View History

[PowerPC] auto-generate full checks and increase test coverage 3 of the tests were testing exactly the same thing: memcmp(x, y, 16) != 0. I changed that to test 4, 7, and 16 bytes, so we can see how those differ. llvm-svn: 304838
2017-06-07 06:06:07 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
[PPC] Inline expansion of memcmp This patch does an inline expansion of memcmp. It changes the memcmp library call into an inline expansion when the size is known at compile time and is under a target specified threshold. This expansion is implemented in CodeGenPrepare and expands into straight line code. The target specifies a maximum load size and the expansion works by using this size to load the two sources, compare, and exit early if a difference is found. It also has a special case when the memcmp result is used in a compare to zero equality. Differential Revision: https://reviews.llvm.org/D28637 llvm-svn: 304313
2017-06-01 01:12:38 +08:00
; RUN: llc -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
[PowerPC] auto-generate full checks and increase test coverage 3 of the tests were testing exactly the same thing: memcmp(x, y, 16) != 0. I changed that to test 4, 7, and 16 bytes, so we can see how those differ. llvm-svn: 304838
2017-06-07 06:06:07 +08:00
; Check 4 bytes - requires 1 load for each param.
define signext i32 @zeroEqualityTest02(i8* %x, i8* %y) {
; CHECK-LABEL: zeroEqualityTest02:
; CHECK: # BB#0: # %loadbb
; CHECK-NEXT: lwz 3, 0(3)
; CHECK-NEXT: lwz 4, 0(4)
; CHECK-NEXT: li 5, 1
; CHECK-NEXT: xor 3, 3, 4
; CHECK-NEXT: cmplwi 3, 0
; CHECK-NEXT: isel 3, 0, 5, 2
; CHECK-NEXT: clrldi 3, 3, 32
; 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
[PPC] Inline expansion of memcmp This patch does an inline expansion of memcmp. It changes the memcmp library call into an inline expansion when the size is known at compile time and is under a target specified threshold. This expansion is implemented in CodeGenPrepare and expands into straight line code. The target specifies a maximum load size and the expansion works by using this size to load the two sources, compare, and exit early if a difference is found. It also has a special case when the memcmp result is used in a compare to zero equality. Differential Revision: https://reviews.llvm.org/D28637 llvm-svn: 304313
2017-06-01 01:12:38 +08:00
ret i32 %.
}
[PowerPC] auto-generate full checks and increase test coverage 3 of the tests were testing exactly the same thing: memcmp(x, y, 16) != 0. I changed that to test 4, 7, and 16 bytes, so we can see how those differ. llvm-svn: 304838
2017-06-07 06:06:07 +08:00
; 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: # %loadbb
; CHECK-NEXT: ld 5, 0(3)
; CHECK-NEXT: ld 6, 0(4)
; CHECK-NEXT: xor. 5, 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: xor. 3, 3, 4
; CHECK-NEXT: beq 0, .LBB1_3
; CHECK-NEXT: .LBB1_2: # %res_block
; CHECK-NEXT: li 3, 1
; CHECK-NEXT: clrldi 3, 3, 32
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB1_3:
; CHECK-NEXT: li 3, 0
; 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
[PPC] Inline expansion of memcmp This patch does an inline expansion of memcmp. It changes the memcmp library call into an inline expansion when the size is known at compile time and is under a target specified threshold. This expansion is implemented in CodeGenPrepare and expands into straight line code. The target specifies a maximum load size and the expansion works by using this size to load the two sources, compare, and exit early if a difference is found. It also has a special case when the memcmp result is used in a compare to zero equality. Differential Revision: https://reviews.llvm.org/D28637 llvm-svn: 304313
2017-06-01 01:12:38 +08:00
ret i32 %.
[PowerPC] auto-generate full checks and increase test coverage 3 of the tests were testing exactly the same thing: memcmp(x, y, 16) != 0. I changed that to test 4, 7, and 16 bytes, so we can see how those differ. llvm-svn: 304838
2017-06-07 06:06:07 +08:00
}
[PPC] Inline expansion of memcmp This patch does an inline expansion of memcmp. It changes the memcmp library call into an inline expansion when the size is known at compile time and is under a target specified threshold. This expansion is implemented in CodeGenPrepare and expands into straight line code. The target specifies a maximum load size and the expansion works by using this size to load the two sources, compare, and exit early if a difference is found. It also has a special case when the memcmp result is used in a compare to zero equality. Differential Revision: https://reviews.llvm.org/D28637 llvm-svn: 304313
2017-06-01 01:12:38 +08:00
[PowerPC] auto-generate full checks and increase test coverage 3 of the tests were testing exactly the same thing: memcmp(x, y, 16) != 0. I changed that to test 4, 7, and 16 bytes, so we can see how those differ. llvm-svn: 304838
2017-06-07 06:06:07 +08:00
; Check 7 bytes - requires 3 loads for each param.
define signext i32 @zeroEqualityTest03(i8* %x, i8* %y) {
; CHECK-LABEL: zeroEqualityTest03:
; CHECK: # BB#0: # %loadbb
; CHECK-NEXT: lwz 5, 0(3)
; CHECK-NEXT: lwz 6, 0(4)
; CHECK-NEXT: xor 5, 5, 6
; CHECK-NEXT: cmplwi 5, 0
; 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: xor 5, 5, 6
; CHECK-NEXT: rlwinm. 5, 5, 0, 16, 31
; 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: xor 3, 3, 4
; CHECK-NEXT: rlwinm. 3, 3, 0, 24, 31
; CHECK-NEXT: beq 0, .LBB2_4
; CHECK-NEXT: .LBB2_3: # %res_block
; CHECK-NEXT: li 3, 1
; CHECK-NEXT: clrldi 3, 3, 32
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB2_4:
; CHECK-NEXT: li 3, 0
; 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
[PPC] Inline expansion of memcmp This patch does an inline expansion of memcmp. It changes the memcmp library call into an inline expansion when the size is known at compile time and is under a target specified threshold. This expansion is implemented in CodeGenPrepare and expands into straight line code. The target specifies a maximum load size and the expansion works by using this size to load the two sources, compare, and exit early if a difference is found. It also has a special case when the memcmp result is used in a compare to zero equality. Differential Revision: https://reviews.llvm.org/D28637 llvm-svn: 304313
2017-06-01 01:12:38 +08:00
}
; Validate with > 0
[PowerPC] auto-generate full checks and increase test coverage 3 of the tests were testing exactly the same thing: memcmp(x, y, 16) != 0. I changed that to test 4, 7, and 16 bytes, so we can see how those differ. llvm-svn: 304838
2017-06-07 06:06:07 +08:00
define signext i32 @zeroEqualityTest04() {
; CHECK-LABEL: zeroEqualityTest04:
; CHECK: # BB#0: # %loadbb
; 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: subf. 7, 4, 3
; 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: subf. 5, 4, 3
; CHECK-NEXT: beq 0, .LBB3_4
; CHECK-NEXT: .LBB3_2: # %res_block
; CHECK-NEXT: cmpld 3, 4
; CHECK-NEXT: li 3, 1
; CHECK-NEXT: li 12, -1
; CHECK-NEXT: isel 3, 12, 3, 0
; CHECK-NEXT: .LBB3_3: # %endblock
; CHECK-NEXT: cmpwi 3, 1
; CHECK-NEXT: li 3, 0
; CHECK-NEXT: li 4, 1
; CHECK-NEXT: isel 3, 4, 3, 0
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB3_4:
; CHECK-NEXT: li 3, 0
; CHECK-NEXT: b .LBB3_3
[PPC] Inline expansion of memcmp This patch does an inline expansion of memcmp. It changes the memcmp library call into an inline expansion when the size is known at compile time and is under a target specified threshold. This expansion is implemented in CodeGenPrepare and expands into straight line code. The target specifies a maximum load size and the expansion works by using this size to load the two sources, compare, and exit early if a difference is found. It also has a special case when the memcmp result is used in a compare to zero equality. Differential Revision: https://reviews.llvm.org/D28637 llvm-svn: 304313
2017-06-01 01:12:38 +08:00
%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
[PowerPC] auto-generate full checks and increase test coverage 3 of the tests were testing exactly the same thing: memcmp(x, y, 16) != 0. I changed that to test 4, 7, and 16 bytes, so we can see how those differ. llvm-svn: 304838
2017-06-07 06:06:07 +08:00
define signext i32 @zeroEqualityTest05() {
; CHECK-LABEL: zeroEqualityTest05:
; CHECK: # BB#0: # %loadbb
; 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: subf. 7, 4, 3
; 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: subf. 5, 4, 3
; CHECK-NEXT: beq 0, .LBB4_4
; CHECK-NEXT: .LBB4_2: # %res_block
; CHECK-NEXT: cmpld 3, 4
; CHECK-NEXT: li 3, 1
; CHECK-NEXT: li 12, -1
; CHECK-NEXT: isel 3, 12, 3, 0
; CHECK-NEXT: .LBB4_3: # %endblock
; CHECK-NEXT: srwi 3, 3, 31
; CHECK-NEXT: xori 3, 3, 1
; CHECK-NEXT: clrldi 3, 3, 32
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB4_4:
; CHECK-NEXT: li 3, 0
; CHECK-NEXT: b .LBB4_3
[PPC] Inline expansion of memcmp This patch does an inline expansion of memcmp. It changes the memcmp library call into an inline expansion when the size is known at compile time and is under a target specified threshold. This expansion is implemented in CodeGenPrepare and expands into straight line code. The target specifies a maximum load size and the expansion works by using this size to load the two sources, compare, and exit early if a difference is found. It also has a special case when the memcmp result is used in a compare to zero equality. Differential Revision: https://reviews.llvm.org/D28637 llvm-svn: 304313
2017-06-01 01:12:38 +08:00
%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()?:
; Function Attrs: nounwind readonly
[PowerPC] auto-generate full checks and increase test coverage 3 of the tests were testing exactly the same thing: memcmp(x, y, 16) != 0. I changed that to test 4, 7, and 16 bytes, so we can see how those differ. llvm-svn: 304838
2017-06-07 06:06:07 +08:00
define signext i32 @zeroEqualityTest06() {
; CHECK-LABEL: zeroEqualityTest06:
; CHECK: # BB#0: # %loadbb
; CHECK-NEXT: addis 3, 2, .LzeroEqualityTest04.buffer1@toc@ha
; CHECK-NEXT: addis 4, 2, .LzeroEqualityTest04.buffer2@toc@ha
; CHECK-NEXT: ld 3, .LzeroEqualityTest04.buffer1@toc@l(3)
; CHECK-NEXT: ld 4, .LzeroEqualityTest04.buffer2@toc@l(4)
; CHECK-NEXT: xor. 3, 3, 4
; CHECK-NEXT: bne 0, .LBB5_2
; CHECK-NEXT: # BB#1: # %loadbb1
; CHECK-NEXT: addis 3, 2, .LzeroEqualityTest04.buffer1@toc@ha+8
; CHECK-NEXT: addis 4, 2, .LzeroEqualityTest04.buffer2@toc@ha+8
; CHECK-NEXT: ld 3, .LzeroEqualityTest04.buffer1@toc@l+8(3)
; CHECK-NEXT: ld 4, .LzeroEqualityTest04.buffer2@toc@l+8(4)
; CHECK-NEXT: xor. 3, 3, 4
; CHECK-NEXT: beq 0, .LBB5_4
; CHECK-NEXT: .LBB5_2: # %res_block
; CHECK-NEXT: li 3, 1
; CHECK-NEXT: .LBB5_3: # %endblock
; CHECK-NEXT: cntlzw 3, 3
; CHECK-NEXT: srwi 3, 3, 5
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB5_4:
; CHECK-NEXT: li 3, 0
; CHECK-NEXT: b .LBB5_3
[PPC] Inline expansion of memcmp This patch does an inline expansion of memcmp. It changes the memcmp library call into an inline expansion when the size is known at compile time and is under a target specified threshold. This expansion is implemented in CodeGenPrepare and expands into straight line code. The target specifies a maximum load size and the expansion works by using this size to load the two sources, compare, and exit early if a difference is found. It also has a special case when the memcmp result is used in a compare to zero equality. Differential Revision: https://reviews.llvm.org/D28637 llvm-svn: 304313
2017-06-01 01:12:38 +08:00
%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
}