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/X86/xor.ll

196 lines
4.8 KiB
LLVM
Raw Normal View History

generalize test; nothing Nehalem-specific here llvm-svn: 228532
2015-02-09 03:38:25 +08:00
; RUN: llc < %s -march=x86 -mattr=+sse2 | FileCheck %s -check-prefix=X32
; RUN: llc < %s -mtriple=x86_64-linux -mattr=+sse2 | FileCheck %s -check-prefix=X64
; RUN: llc < %s -mtriple=x86_64-win32 -mattr=+sse2 | FileCheck %s -check-prefix=X64
convert testcases to filecheck. llvm-svn: 82759
2009-09-25 14:49:41 +08:00
; Though it is undefined, we want xor undef,undef to produce zero.
define <4 x i32> @test1() nounwind {
%tmp = xor <4 x i32> undef, undef
ret <4 x i32> %tmp
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; X32-LABEL: test1:
Expand V_SET0 to xorps by default. The xorps instruction is smaller than pxor, so prefer that encoding. The ExecutionDepsFix pass will switch the encoding to pxor and xorpd when appropriate. llvm-svn: 143996
2011-11-08 03:15:58 +08:00
; X32: xorps %xmm0, %xmm0
convert testcases to filecheck. llvm-svn: 82759
2009-09-25 14:49:41 +08:00
; X32: ret
}
; Though it is undefined, we want xor undef,undef to produce zero.
define i32 @test2() nounwind{
%tmp = xor i32 undef, undef
ret i32 %tmp
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; X32-LABEL: test2:
convert testcases to filecheck. llvm-svn: 82759
2009-09-25 14:49:41 +08:00
; X32: xorl %eax, %eax
; X32: ret
}
define i32 @test3(i32 %a, i32 %b) nounwind {
Prefer to expand mask for xor to -1, so we have a chance to turn it into a not. If it cannot be expanded, it will keep the old behaviour and try to shrink the constant. Part of enhancement for PR2191. llvm-svn: 49280
2008-04-07 05:23:02 +08:00
entry:
%tmp1not = xor i32 %b, -2
%tmp3 = and i32 %tmp1not, %a
%tmp4 = lshr i32 %tmp3, 1
ret i32 %tmp4
convert testcases to filecheck. llvm-svn: 82759
2009-09-25 14:49:41 +08:00
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; X64-LABEL: test3:
Don't depend on the physreg coalescing order. llvm-svn: 130818
2011-05-04 09:01:47 +08:00
; X64: notl
; X64: andl
Reapply r161633-161634 "Partition use lists so defs always come before uses."" No changes to these patches, MRI needed to be notified when changing uses into defs and vice versa. llvm-svn: 161644
2012-08-10 08:21:30 +08:00
; X64: shrl
convert testcases to filecheck. llvm-svn: 82759
2009-09-25 14:49:41 +08:00
; X64: ret
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; X32-LABEL: test3:
convert testcases to filecheck. llvm-svn: 82759
2009-09-25 14:49:41 +08:00
; X32: movl 8(%esp), %eax
; X32: notl %eax
; X32: andl 4(%esp), %eax
; X32: shrl %eax
; X32: ret
Prefer to expand mask for xor to -1, so we have a chance to turn it into a not. If it cannot be expanded, it will keep the old behaviour and try to shrink the constant. Part of enhancement for PR2191. llvm-svn: 49280
2008-04-07 05:23:02 +08:00
}
convert testcases to filecheck. llvm-svn: 82759
2009-09-25 14:49:41 +08:00
define i32 @test4(i32 %a, i32 %b) nounwind {
Prefer to expand mask for xor to -1, so we have a chance to turn it into a not. If it cannot be expanded, it will keep the old behaviour and try to shrink the constant. Part of enhancement for PR2191. llvm-svn: 49280
2008-04-07 05:23:02 +08:00
entry:
br label %bb
bb:
%b_addr.0 = phi i32 [ %b, %entry ], [ %tmp8, %bb ]
%a_addr.0 = phi i32 [ %a, %entry ], [ %tmp3, %bb ]
%tmp3 = xor i32 %a_addr.0, %b_addr.0
%tmp4not = xor i32 %tmp3, 2147483647
%tmp6 = and i32 %tmp4not, %b_addr.0
%tmp8 = shl i32 %tmp6, 1
%tmp10 = icmp eq i32 %tmp8, 0
br i1 %tmp10, label %bb12, label %bb
bb12:
ret i32 %tmp3
convert testcases to filecheck. llvm-svn: 82759
2009-09-25 14:49:41 +08:00
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; X64-LABEL: test4:
implement and document support for filecheck variables. This allows matching and remembering a string and then matching and verifying that the string occurs later in the file. Change X86/xor.ll to use this in some cases where the test was checking for an arbitrary register allocation decision. llvm-svn: 82891
2009-09-27 15:56:52 +08:00
; X64: notl [[REG:%[a-z]+]]
; X64: andl {{.*}}[[REG]]
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; X32-LABEL: test4:
implement and document support for filecheck variables. This allows matching and remembering a string and then matching and verifying that the string occurs later in the file. Change X86/xor.ll to use this in some cases where the test was checking for an arbitrary register allocation decision. llvm-svn: 82891
2009-09-27 15:56:52 +08:00
; X32: notl [[REG:%[a-z]+]]
; X32: andl {{.*}}[[REG]]
Prefer to expand mask for xor to -1, so we have a chance to turn it into a not. If it cannot be expanded, it will keep the old behaviour and try to shrink the constant. Part of enhancement for PR2191. llvm-svn: 49280
2008-04-07 05:23:02 +08:00
}
convert testcases to filecheck. llvm-svn: 82759
2009-09-25 14:49:41 +08:00
define i16 @test5(i16 %a, i16 %b) nounwind {
Prefer to expand mask for xor to -1, so we have a chance to turn it into a not. If it cannot be expanded, it will keep the old behaviour and try to shrink the constant. Part of enhancement for PR2191. llvm-svn: 49280
2008-04-07 05:23:02 +08:00
entry:
br label %bb
bb:
%b_addr.0 = phi i16 [ %b, %entry ], [ %tmp8, %bb ]
%a_addr.0 = phi i16 [ %a, %entry ], [ %tmp3, %bb ]
%tmp3 = xor i16 %a_addr.0, %b_addr.0
%tmp4not = xor i16 %tmp3, 32767
%tmp6 = and i16 %tmp4not, %b_addr.0
%tmp8 = shl i16 %tmp6, 1
%tmp10 = icmp eq i16 %tmp8, 0
br i1 %tmp10, label %bb12, label %bb
bb12:
ret i16 %tmp3
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; X64-LABEL: test5:
Enable i16 to i32 promotion by default. llvm-svn: 102493
2010-04-28 16:30:49 +08:00
; X64: notl [[REG:%[a-z]+]]
; X64: andl {{.*}}[[REG]]
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; X32-LABEL: test5:
Enable i16 to i32 promotion by default. llvm-svn: 102493
2010-04-28 16:30:49 +08:00
; X32: notl [[REG:%[a-z]+]]
; X32: andl {{.*}}[[REG]]
Prefer to expand mask for xor to -1, so we have a chance to turn it into a not. If it cannot be expanded, it will keep the old behaviour and try to shrink the constant. Part of enhancement for PR2191. llvm-svn: 49280
2008-04-07 05:23:02 +08:00
}
convert testcases to filecheck. llvm-svn: 82759
2009-09-25 14:49:41 +08:00
define i8 @test6(i8 %a, i8 %b) nounwind {
Prefer to expand mask for xor to -1, so we have a chance to turn it into a not. If it cannot be expanded, it will keep the old behaviour and try to shrink the constant. Part of enhancement for PR2191. llvm-svn: 49280
2008-04-07 05:23:02 +08:00
entry:
br label %bb
bb:
%b_addr.0 = phi i8 [ %b, %entry ], [ %tmp8, %bb ]
%a_addr.0 = phi i8 [ %a, %entry ], [ %tmp3, %bb ]
%tmp3 = xor i8 %a_addr.0, %b_addr.0
%tmp4not = xor i8 %tmp3, 127
%tmp6 = and i8 %tmp4not, %b_addr.0
%tmp8 = shl i8 %tmp6, 1
%tmp10 = icmp eq i8 %tmp8, 0
br i1 %tmp10, label %bb12, label %bb
bb12:
ret i8 %tmp3
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; X64-LABEL: test6:
implement and document support for filecheck variables. This allows matching and remembering a string and then matching and verifying that the string occurs later in the file. Change X86/xor.ll to use this in some cases where the test was checking for an arbitrary register allocation decision. llvm-svn: 82891
2009-09-27 15:56:52 +08:00
; X64: notb [[REG:%[a-z]+]]
; X64: andb {{.*}}[[REG]]
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; X32-LABEL: test6:
implement and document support for filecheck variables. This allows matching and remembering a string and then matching and verifying that the string occurs later in the file. Change X86/xor.ll to use this in some cases where the test was checking for an arbitrary register allocation decision. llvm-svn: 82891
2009-09-27 15:56:52 +08:00
; X32: notb [[REG:%[a-z]+]]
; X32: andb {{.*}}[[REG]]
Prefer to expand mask for xor to -1, so we have a chance to turn it into a not. If it cannot be expanded, it will keep the old behaviour and try to shrink the constant. Part of enhancement for PR2191. llvm-svn: 49280
2008-04-07 05:23:02 +08:00
}
convert testcases to filecheck. llvm-svn: 82759
2009-09-25 14:49:41 +08:00
define i32 @test7(i32 %a, i32 %b) nounwind {
Prefer to expand mask for xor to -1, so we have a chance to turn it into a not. If it cannot be expanded, it will keep the old behaviour and try to shrink the constant. Part of enhancement for PR2191. llvm-svn: 49280
2008-04-07 05:23:02 +08:00
entry:
br label %bb
bb:
%b_addr.0 = phi i32 [ %b, %entry ], [ %tmp8, %bb ]
%a_addr.0 = phi i32 [ %a, %entry ], [ %tmp3, %bb ]
%tmp3 = xor i32 %a_addr.0, %b_addr.0
%tmp4not = xor i32 %tmp3, 2147483646
%tmp6 = and i32 %tmp4not, %b_addr.0
%tmp8 = shl i32 %tmp6, 1
%tmp10 = icmp eq i32 %tmp8, 0
br i1 %tmp10, label %bb12, label %bb
bb12:
ret i32 %tmp3
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; X64-LABEL: test7:
implement and document support for filecheck variables. This allows matching and remembering a string and then matching and verifying that the string occurs later in the file. Change X86/xor.ll to use this in some cases where the test was checking for an arbitrary register allocation decision. llvm-svn: 82891
2009-09-27 15:56:52 +08:00
; X64: xorl $2147483646, [[REG:%[a-z]+]]
; X64: andl {{.*}}[[REG]]
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; X32-LABEL: test7:
implement and document support for filecheck variables. This allows matching and remembering a string and then matching and verifying that the string occurs later in the file. Change X86/xor.ll to use this in some cases where the test was checking for an arbitrary register allocation decision. llvm-svn: 82891
2009-09-27 15:56:52 +08:00
; X32: xorl $2147483646, [[REG:%[a-z]+]]
; X32: andl {{.*}}[[REG]]
Prefer to expand mask for xor to -1, so we have a chance to turn it into a not. If it cannot be expanded, it will keep the old behaviour and try to shrink the constant. Part of enhancement for PR2191. llvm-svn: 49280
2008-04-07 05:23:02 +08:00
}
Canonicalize -1 - x to ~x. Instcombine does this but apparently there are situations where this pattern will escape the optimizer and / or created by isel. Here is a case that's seen in JavaScriptCore: %t1 = sub i32 0, %a %t2 = add i32 %t1, -1 The dag combiner pattern: ((c1-A)+c2) -> (c1+c2)-A will fold it to -1 - %a. llvm-svn: 93773
2010-01-19 05:38:44 +08:00
define i32 @test8(i32 %a) nounwind {
; rdar://7553032
entry:
%t1 = sub i32 0, %a
%t2 = add i32 %t1, -1
ret i32 %t2
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; X64-LABEL: test8:
Don't depend on the physreg coalescing order. llvm-svn: 130818
2011-05-04 09:01:47 +08:00
; X64: notl {{%eax|%edi|%ecx}}
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; X32-LABEL: test8:
Canonicalize -1 - x to ~x. Instcombine does this but apparently there are situations where this pattern will escape the optimizer and / or created by isel. Here is a case that's seen in JavaScriptCore: %t1 = sub i32 0, %a %t2 = add i32 %t1, -1 The dag combiner pattern: ((c1-A)+c2) -> (c1+c2)-A will fold it to -1 - %a. llvm-svn: 93773
2010-01-19 05:38:44 +08:00
; X32: notl %eax
}
DAGCombiner: Simplify inverted bit tests Fold (xor (and x, y), y) -> (and (not x), y) This removes an opportunity for a constant to appear twice. llvm-svn: 181395
2013-05-08 14:44:42 +08:00
define i32 @test9(i32 %a) nounwind {
%1 = and i32 %a, 4096
%2 = xor i32 %1, 4096
ret i32 %2
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; X64-LABEL: test9:
DAGCombiner: Simplify inverted bit tests Fold (xor (and x, y), y) -> (and (not x), y) This removes an opportunity for a constant to appear twice. llvm-svn: 181395
2013-05-08 14:44:42 +08:00
; X64: notl [[REG:%[a-z]+]]
; X64: andl {{.*}}[[REG:%[a-z]+]]
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; X32-LABEL: test9:
DAGCombiner: Simplify inverted bit tests Fold (xor (and x, y), y) -> (and (not x), y) This removes an opportunity for a constant to appear twice. llvm-svn: 181395
2013-05-08 14:44:42 +08:00
; X32: notl [[REG:%[a-z]+]]
; X32: andl {{.*}}[[REG:%[a-z]+]]
}
DAGCombiner: Generate a correct constant for vector types when folding (xor (and)) into (and (not)). PR15948. llvm-svn: 181597
2013-05-10 22:09:52 +08:00
; PR15948
define <4 x i32> @test10(<4 x i32> %a) nounwind {
%1 = and <4 x i32> %a, <i32 4096, i32 4096, i32 4096, i32 4096>
%2 = xor <4 x i32> %1, <i32 4096, i32 4096, i32 4096, i32 4096>
ret <4 x i32> %2
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; X64-LABEL: test10:
DAGCombiner: Generate a correct constant for vector types when folding (xor (and)) into (and (not)). PR15948. llvm-svn: 181597
2013-05-10 22:09:52 +08:00
; X64: andnps
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; X32-LABEL: test10:
DAGCombiner: Generate a correct constant for vector types when folding (xor (and)) into (and (not)). PR15948. llvm-svn: 181597
2013-05-10 22:09:52 +08:00
; X32: andnps
}
DAGCombiner: Don't fold xor into not if getNOT would introduce an illegal constant. This happens e.g. with <2 x i64> -1 on x86_32. It cannot be generated directly because i64 is illegal. It would be nice if getNOT would handle this transparently, but I don't see a way to generate a legal constant there right now. Fixes PR17487. llvm-svn: 192795
2013-10-16 22:16:19 +08:00
define i32 @PR17487(i1 %tobool) {
%tmp = insertelement <2 x i1> undef, i1 %tobool, i32 1
%tmp1 = zext <2 x i1> %tmp to <2 x i64>
%tmp2 = xor <2 x i64> %tmp1, <i64 1, i64 1>
%tmp3 = extractelement <2 x i64> %tmp2, i32 1
%add = add nsw i64 0, %tmp3
%cmp6 = icmp ne i64 %add, 1
%conv7 = zext i1 %cmp6 to i32
ret i32 %conv7
; X64-LABEL: PR17487:
; X64: andn
DAGCombiner: Partially revert r192795, getNOT was fixed not to create illegal constants. llvm-svn: 194959
2013-11-17 18:40:03 +08:00
; X32-LABEL: PR17487:
; X32: andn
DAGCombiner: Don't fold xor into not if getNOT would introduce an illegal constant. This happens e.g. with <2 x i64> -1 on x86_32. It cannot be generated directly because i64 is illegal. It would be nice if getNOT would handle this transparently, but I don't see a way to generate a legal constant there right now. Fixes PR17487. llvm-svn: 192795
2013-10-16 22:16:19 +08:00
}
DAGCombiner: fold (xor (shl 1, x), -1) -> (rotl ~1, x) Targets which provide a rotate make it possible to replace a sequence of (XOR (SHL 1, x), -1) with (ROTL ~1, x). This saves an instruction on architectures like X86 and POWER(64). Differential Revision: http://reviews.llvm.org/D8350 llvm-svn: 232572
2015-03-18 08:03:36 +08:00
define i32 @test11(i32 %b) {
%shl = shl i32 1, %b
%neg = xor i32 %shl, -1
ret i32 %neg
; X64-LABEL: test11:
; X64: movl $-2, %[[REG:.*]]
; X64: roll %{{.*}}, %[[REG]]
; X32-LABEL: test11:
; X32: movl $-2, %[[REG:.*]]
; X32: roll %{{.*}}, %[[REG]]
}