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/select.ll

1157 lines
32 KiB
LLVM
Raw Normal View History

[X86][SSE] Regenerate select tests llvm-svn: 283674
2016-10-09 05:17:44 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; RUN: llc < %s -mtriple=x86_64-apple-darwin10 -mcpu=generic | FileCheck %s --check-prefix=CHECK --check-prefix=GENERIC
; RUN: llc < %s -mtriple=x86_64-apple-darwin10 -mcpu=atom | FileCheck %s --check-prefix=CHECK --check-prefix=ATOM
[X86][MCU] replace select with bit manipulation instead of branches Differential Revision: https://reviews.llvm.org/D28354 llvm-svn: 293469
2017-01-30 16:16:59 +08:00
; RUN: llc < %s -mtriple=i386-intel-elfiamcu | FileCheck %s --check-prefix=MCU
Fix the result type of SELECT nodes lowered from Select instructions with aggregate return values. This fixes PR5754. llvm-svn: 91145
2009-12-12 03:50:50 +08:00
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; PR5757
Fix the result type of SELECT nodes lowered from Select instructions with aggregate return values. This fixes PR5754. llvm-svn: 91145
2009-12-12 03:50:50 +08:00
%0 = type { i64, i32 }
merge some tests into select.ll and make them more specific. llvm-svn: 120928
2010-12-05 09:13:58 +08:00
define i32 @test1(%0* %p, %0* %q, i1 %r) nounwind {
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; CHECK-LABEL: test1:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: ## %bb.0:
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; CHECK-NEXT: addq $8, %rdi
; CHECK-NEXT: addq $8, %rsi
; CHECK-NEXT: testb $1, %dl
; CHECK-NEXT: cmovneq %rdi, %rsi
; CHECK-NEXT: movl (%rsi), %eax
; CHECK-NEXT: retq
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
;
; MCU-LABEL: test1:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: testb $1, %cl
; MCU-NEXT: jne .LBB0_1
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU-NEXT: # %bb.2:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: addl $8, %edx
Revert "[MachineCopyPropagation] Extend pass to do COPY source forwarding" This reverts commit r323991. This commit breaks target that don't model all the register constraints in TableGen. So far the workaround was to set the hasExtraXXXRegAllocReq, but it proves that it doesn't cover all the cases. For instance, when mutating an instruction (like in the lowering of COPYs) the isRenamable flag is not properly updated. The same problem will happen when attaching machine operand from one instruction to another. Geoff Berry is working on a fix in https://reviews.llvm.org/D43042. llvm-svn: 325421
2018-02-17 11:05:33 +08:00
; MCU-NEXT: movl %edx, %eax
; MCU-NEXT: movl (%eax), %eax
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: retl
; MCU-NEXT: .LBB0_1:
; MCU-NEXT: addl $8, %eax
; MCU-NEXT: movl (%eax), %eax
; MCU-NEXT: retl
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%t0 = load %0, %0* %p
%t1 = load %0, %0* %q
Fix the result type of SELECT nodes lowered from Select instructions with aggregate return values. This fixes PR5754. llvm-svn: 91145
2009-12-12 03:50:50 +08:00
%t4 = select i1 %r, %0 %t0, %0 %t1
%t5 = extractvalue %0 %t4, 1
ret i32 %t5
merge some tests into select.ll and make them more specific. llvm-svn: 120928
2010-12-05 09:13:58 +08:00
}
; PR2139
define i32 @test2() nounwind {
[X86] Combining CMOVs with [ANY,SIGN,ZERO]_EXTEND for cases where CMOV has constant arguments Combine CMOV[i16]<-[SIGN,ZERO,ANY]_EXTEND to [i32,i64] into CMOV[i32,i64]. One example of where it is useful is: before (20 bytes) <foo>: test $0x1,%dil mov $0x307e,%ax mov $0xffff,%cx cmovne %ax,%cx movzwl %cx,%eax retq after (18 bytes) <foo>: test $0x1,%dil mov $0x307e,%ecx mov $0xffff,%eax cmovne %ecx,%eax retq Reviewers: craig.topper, aaboud, spatel, RKSimon, zvi Reviewed By: spatel Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D36711 llvm-svn: 313982
2017-09-22 21:21:39 +08:00
; GENERIC-LABEL: test2:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; GENERIC: ## %bb.0: ## %entry
[X86] Combining CMOVs with [ANY,SIGN,ZERO]_EXTEND for cases where CMOV has constant arguments Combine CMOV[i16]<-[SIGN,ZERO,ANY]_EXTEND to [i32,i64] into CMOV[i32,i64]. One example of where it is useful is: before (20 bytes) <foo>: test $0x1,%dil mov $0x307e,%ax mov $0xffff,%cx cmovne %ax,%cx movzwl %cx,%eax retq after (18 bytes) <foo>: test $0x1,%dil mov $0x307e,%ecx mov $0xffff,%eax cmovne %ecx,%eax retq Reviewers: craig.topper, aaboud, spatel, RKSimon, zvi Reviewed By: spatel Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D36711 llvm-svn: 313982
2017-09-22 21:21:39 +08:00
; GENERIC-NEXT: pushq %rax
; GENERIC-NEXT: callq _return_false
; GENERIC-NEXT: xorl %ecx, %ecx
; GENERIC-NEXT: testb $1, %al
[X86] Regenerate select tests llvm-svn: 317571
2017-11-07 21:21:02 +08:00
; GENERIC-NEXT: movl $-480, %eax ## imm = 0xFE20
[X86] Combining CMOVs with [ANY,SIGN,ZERO]_EXTEND for cases where CMOV has constant arguments Combine CMOV[i16]<-[SIGN,ZERO,ANY]_EXTEND to [i32,i64] into CMOV[i32,i64]. One example of where it is useful is: before (20 bytes) <foo>: test $0x1,%dil mov $0x307e,%ax mov $0xffff,%cx cmovne %ax,%cx movzwl %cx,%eax retq after (18 bytes) <foo>: test $0x1,%dil mov $0x307e,%ecx mov $0xffff,%eax cmovne %ecx,%eax retq Reviewers: craig.topper, aaboud, spatel, RKSimon, zvi Reviewed By: spatel Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D36711 llvm-svn: 313982
2017-09-22 21:21:39 +08:00
; GENERIC-NEXT: cmovnel %ecx, %eax
; GENERIC-NEXT: shll $3, %eax
; GENERIC-NEXT: cmpl $32768, %eax ## imm = 0x8000
; GENERIC-NEXT: jge LBB1_1
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; GENERIC-NEXT: ## %bb.2: ## %bb91
[X86] Combining CMOVs with [ANY,SIGN,ZERO]_EXTEND for cases where CMOV has constant arguments Combine CMOV[i16]<-[SIGN,ZERO,ANY]_EXTEND to [i32,i64] into CMOV[i32,i64]. One example of where it is useful is: before (20 bytes) <foo>: test $0x1,%dil mov $0x307e,%ax mov $0xffff,%cx cmovne %ax,%cx movzwl %cx,%eax retq after (18 bytes) <foo>: test $0x1,%dil mov $0x307e,%ecx mov $0xffff,%eax cmovne %ecx,%eax retq Reviewers: craig.topper, aaboud, spatel, RKSimon, zvi Reviewed By: spatel Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D36711 llvm-svn: 313982
2017-09-22 21:21:39 +08:00
; GENERIC-NEXT: xorl %eax, %eax
; GENERIC-NEXT: popq %rcx
; GENERIC-NEXT: retq
; GENERIC-NEXT: LBB1_1: ## %bb90
;
; ATOM-LABEL: test2:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; ATOM: ## %bb.0: ## %entry
[X86] Combining CMOVs with [ANY,SIGN,ZERO]_EXTEND for cases where CMOV has constant arguments Combine CMOV[i16]<-[SIGN,ZERO,ANY]_EXTEND to [i32,i64] into CMOV[i32,i64]. One example of where it is useful is: before (20 bytes) <foo>: test $0x1,%dil mov $0x307e,%ax mov $0xffff,%cx cmovne %ax,%cx movzwl %cx,%eax retq after (18 bytes) <foo>: test $0x1,%dil mov $0x307e,%ecx mov $0xffff,%eax cmovne %ecx,%eax retq Reviewers: craig.topper, aaboud, spatel, RKSimon, zvi Reviewed By: spatel Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D36711 llvm-svn: 313982
2017-09-22 21:21:39 +08:00
; ATOM-NEXT: pushq %rax
; ATOM-NEXT: callq _return_false
; ATOM-NEXT: xorl %ecx, %ecx
[X86] Regenerate select tests llvm-svn: 317571
2017-11-07 21:21:02 +08:00
; ATOM-NEXT: movl $-480, %edx ## imm = 0xFE20
[X86] Combining CMOVs with [ANY,SIGN,ZERO]_EXTEND for cases where CMOV has constant arguments Combine CMOV[i16]<-[SIGN,ZERO,ANY]_EXTEND to [i32,i64] into CMOV[i32,i64]. One example of where it is useful is: before (20 bytes) <foo>: test $0x1,%dil mov $0x307e,%ax mov $0xffff,%cx cmovne %ax,%cx movzwl %cx,%eax retq after (18 bytes) <foo>: test $0x1,%dil mov $0x307e,%ecx mov $0xffff,%eax cmovne %ecx,%eax retq Reviewers: craig.topper, aaboud, spatel, RKSimon, zvi Reviewed By: spatel Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D36711 llvm-svn: 313982
2017-09-22 21:21:39 +08:00
; ATOM-NEXT: testb $1, %al
; ATOM-NEXT: cmovnel %ecx, %edx
; ATOM-NEXT: shll $3, %edx
; ATOM-NEXT: cmpl $32768, %edx ## imm = 0x8000
; ATOM-NEXT: jge LBB1_1
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; ATOM-NEXT: ## %bb.2: ## %bb91
[X86] Combining CMOVs with [ANY,SIGN,ZERO]_EXTEND for cases where CMOV has constant arguments Combine CMOV[i16]<-[SIGN,ZERO,ANY]_EXTEND to [i32,i64] into CMOV[i32,i64]. One example of where it is useful is: before (20 bytes) <foo>: test $0x1,%dil mov $0x307e,%ax mov $0xffff,%cx cmovne %ax,%cx movzwl %cx,%eax retq after (18 bytes) <foo>: test $0x1,%dil mov $0x307e,%ecx mov $0xffff,%eax cmovne %ecx,%eax retq Reviewers: craig.topper, aaboud, spatel, RKSimon, zvi Reviewed By: spatel Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D36711 llvm-svn: 313982
2017-09-22 21:21:39 +08:00
; ATOM-NEXT: xorl %eax, %eax
; ATOM-NEXT: popq %rcx
; ATOM-NEXT: retq
; ATOM-NEXT: LBB1_1: ## %bb90
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
;
; MCU-LABEL: test2:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0: # %entry
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: calll return_false
[X86] Regenerate select tests llvm-svn: 317571
2017-11-07 21:21:02 +08:00
; MCU-NEXT: xorl %ecx, %ecx
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: testb $1, %al
[X86] Combining CMOVs with [ANY,SIGN,ZERO]_EXTEND for cases where CMOV has constant arguments Combine CMOV[i16]<-[SIGN,ZERO,ANY]_EXTEND to [i32,i64] into CMOV[i32,i64]. One example of where it is useful is: before (20 bytes) <foo>: test $0x1,%dil mov $0x307e,%ax mov $0xffff,%cx cmovne %ax,%cx movzwl %cx,%eax retq after (18 bytes) <foo>: test $0x1,%dil mov $0x307e,%ecx mov $0xffff,%eax cmovne %ecx,%eax retq Reviewers: craig.topper, aaboud, spatel, RKSimon, zvi Reviewed By: spatel Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D36711 llvm-svn: 313982
2017-09-22 21:21:39 +08:00
; MCU-NEXT: jne .LBB1_2
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU-NEXT: # %bb.1: # %entry
[X86] Combining CMOVs with [ANY,SIGN,ZERO]_EXTEND for cases where CMOV has constant arguments Combine CMOV[i16]<-[SIGN,ZERO,ANY]_EXTEND to [i32,i64] into CMOV[i32,i64]. One example of where it is useful is: before (20 bytes) <foo>: test $0x1,%dil mov $0x307e,%ax mov $0xffff,%cx cmovne %ax,%cx movzwl %cx,%eax retq after (18 bytes) <foo>: test $0x1,%dil mov $0x307e,%ecx mov $0xffff,%eax cmovne %ecx,%eax retq Reviewers: craig.topper, aaboud, spatel, RKSimon, zvi Reviewed By: spatel Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D36711 llvm-svn: 313982
2017-09-22 21:21:39 +08:00
; MCU-NEXT: movl $-480, %ecx # imm = 0xFE20
[X86] Regenerate select tests llvm-svn: 317571
2017-11-07 21:21:02 +08:00
; MCU-NEXT: .LBB1_2: # %entry
[X86] Combining CMOVs with [ANY,SIGN,ZERO]_EXTEND for cases where CMOV has constant arguments Combine CMOV[i16]<-[SIGN,ZERO,ANY]_EXTEND to [i32,i64] into CMOV[i32,i64]. One example of where it is useful is: before (20 bytes) <foo>: test $0x1,%dil mov $0x307e,%ax mov $0xffff,%cx cmovne %ax,%cx movzwl %cx,%eax retq after (18 bytes) <foo>: test $0x1,%dil mov $0x307e,%ecx mov $0xffff,%eax cmovne %ecx,%eax retq Reviewers: craig.topper, aaboud, spatel, RKSimon, zvi Reviewed By: spatel Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D36711 llvm-svn: 313982
2017-09-22 21:21:39 +08:00
; MCU-NEXT: shll $3, %ecx
; MCU-NEXT: cmpl $32768, %ecx # imm = 0x8000
; MCU-NEXT: jge .LBB1_3
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU-NEXT: # %bb.4: # %bb91
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: xorl %eax, %eax
; MCU-NEXT: retl
[X86] Combining CMOVs with [ANY,SIGN,ZERO]_EXTEND for cases where CMOV has constant arguments Combine CMOV[i16]<-[SIGN,ZERO,ANY]_EXTEND to [i32,i64] into CMOV[i32,i64]. One example of where it is useful is: before (20 bytes) <foo>: test $0x1,%dil mov $0x307e,%ax mov $0xffff,%cx cmovne %ax,%cx movzwl %cx,%eax retq after (18 bytes) <foo>: test $0x1,%dil mov $0x307e,%ecx mov $0xffff,%eax cmovne %ecx,%eax retq Reviewers: craig.topper, aaboud, spatel, RKSimon, zvi Reviewed By: spatel Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D36711 llvm-svn: 313982
2017-09-22 21:21:39 +08:00
; MCU-NEXT: .LBB1_3: # %bb90
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
entry:
%tmp73 = tail call i1 @return_false()
%g.0 = select i1 %tmp73, i16 0, i16 -480
%tmp7778 = sext i16 %g.0 to i32
%tmp80 = shl i32 %tmp7778, 3
%tmp87 = icmp sgt i32 %tmp80, 32767
br i1 %tmp87, label %bb90, label %bb91
bb90:
unreachable
bb91:
ret i32 0
merge some tests into select.ll and make them more specific. llvm-svn: 120928
2010-12-05 09:13:58 +08:00
}
declare i1 @return_false()
;; Select between two floating point constants.
define float @test3(i32 %x) nounwind readnone {
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
; CHECK-LABEL: test3:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: ## %bb.0: ## %entry
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: testl %edi, %edi
; CHECK-NEXT: sete %al
; CHECK-NEXT: leaq {{.*}}(%rip), %rcx
; CHECK-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT: retq
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
;
; MCU-LABEL: test3:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0: # %entry
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: xorl %ecx, %ecx
; MCU-NEXT: testl %eax, %eax
; MCU-NEXT: sete %cl
; MCU-NEXT: flds {{\.LCPI.*}}(,%ecx,4)
; MCU-NEXT: retl
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
entry:
%0 = icmp eq i32 %x, 0
%iftmp.0.0 = select i1 %0, float 4.200000e+01, float 2.300000e+01
ret float %iftmp.0.0
merge some tests into select.ll and make them more specific. llvm-svn: 120928
2010-12-05 09:13:58 +08:00
}
define signext i8 @test4(i8* nocapture %P, double %F) nounwind readonly {
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
; CHECK-LABEL: test4:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: ## %bb.0: ## %entry
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; CHECK-NEXT: movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: ucomisd %xmm0, %xmm1
; CHECK-NEXT: seta %al
; CHECK-NEXT: movsbl (%rdi,%rax,4), %eax
; CHECK-NEXT: retq
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
;
; MCU-LABEL: test4:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0: # %entry
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: movl %eax, %ecx
; MCU-NEXT: fldl {{[0-9]+}}(%esp)
; MCU-NEXT: flds {{\.LCPI.*}}
; MCU-NEXT: fucompp
; MCU-NEXT: fnstsw %ax
; MCU-NEXT: xorl %edx, %edx
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; MCU-NEXT: # kill: def $ah killed $ah killed $ax
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: sahf
; MCU-NEXT: seta %dl
; MCU-NEXT: movb (%ecx,%edx,4), %al
; MCU-NEXT: retl
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
entry:
%0 = fcmp olt double %F, 4.200000e+01
%iftmp.0.0 = select i1 %0, i32 4, i32 0
%1 = getelementptr i8, i8* %P, i32 %iftmp.0.0
%2 = load i8, i8* %1, align 1
ret i8 %2
merge some tests into select.ll and make them more specific. llvm-svn: 120928
2010-12-05 09:13:58 +08:00
}
define void @test5(i1 %c, <2 x i16> %a, <2 x i16> %b, <2 x i16>* %p) nounwind {
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; CHECK-LABEL: test5:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: ## %bb.0:
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; CHECK-NEXT: testb $1, %dil
; CHECK-NEXT: jne LBB4_2
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK-NEXT: ## %bb.1:
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; CHECK-NEXT: movdqa %xmm1, %xmm0
; CHECK-NEXT: LBB4_2:
; CHECK-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; CHECK-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
; CHECK-NEXT: movd %xmm0, (%rsi)
; CHECK-NEXT: retq
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
;
; MCU-LABEL: test5:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: pushl %esi
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; MCU-NEXT: movl {{[0-9]+}}(%esp), %esi
; MCU-NEXT: testb $1, %al
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: jne .LBB4_2
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU-NEXT: # %bb.1:
[X86FixupBWInsts] More precise register liveness if no <imp-use> on MOVs. Summary: Subregister liveness tracking is not implemented for X86 backend, so sometimes the whole super register is said to be live, when only a subregister is really live. That might happen if the def and the use are located in different MBBs, see added fixup-bw-isnt.mir test. However, using knowledge of the specific instructions handled by the bw-fixup-pass we can get more precise liveness information which this change does. Reviewers: MatzeB, DavidKreitzer, ab, andrew.w.kaylor, craig.topper Reviewed By: craig.topper Subscribers: n.bozhenov, myatsina, llvm-commits, hiraditya Patch by Andrei Elovikov <andrei.elovikov@intel.com> Differential Revision: https://reviews.llvm.org/D37559 llvm-svn: 313524
2017-09-18 18:17:59 +08:00
; MCU-NEXT: movzwl {{[0-9]+}}(%esp), %ecx
; MCU-NEXT: movzwl {{[0-9]+}}(%esp), %edx
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: .LBB4_2:
; MCU-NEXT: movw %cx, 2(%esi)
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; MCU-NEXT: movw %dx, (%esi)
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: popl %esi
; MCU-NEXT: retl
merge some tests into select.ll and make them more specific. llvm-svn: 120928
2010-12-05 09:13:58 +08:00
%x = select i1 %c, <2 x i16> %a, <2 x i16> %b
store <2 x i16> %x, <2 x i16>* %p
ret void
}
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; Verify that the fmul gets sunk into the one part of the diamond where it is needed.
merge some tests into select.ll and make them more specific. llvm-svn: 120928
2010-12-05 09:13:58 +08:00
define void @test6(i32 %C, <4 x float>* %A, <4 x float>* %B) nounwind {
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
; CHECK-LABEL: test6:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: ## %bb.0:
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; CHECK-NEXT: testl %edi, %edi
; CHECK-NEXT: je LBB5_1
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK-NEXT: ## %bb.2:
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; CHECK-NEXT: movaps (%rsi), %xmm0
; CHECK-NEXT: movaps %xmm0, (%rsi)
; CHECK-NEXT: retq
; CHECK-NEXT: LBB5_1:
; CHECK-NEXT: movaps (%rdx), %xmm0
; CHECK-NEXT: mulps %xmm0, %xmm0
; CHECK-NEXT: movaps %xmm0, (%rsi)
; CHECK-NEXT: retq
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
;
; MCU-LABEL: test6:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: pushl %eax
; MCU-NEXT: flds 12(%edx)
; MCU-NEXT: fstps (%esp) # 4-byte Folded Spill
; MCU-NEXT: flds 8(%edx)
; MCU-NEXT: flds 4(%edx)
; MCU-NEXT: flds (%ecx)
; MCU-NEXT: flds 4(%ecx)
; MCU-NEXT: flds 8(%ecx)
; MCU-NEXT: flds 12(%ecx)
; MCU-NEXT: fmul %st(0), %st(0)
; MCU-NEXT: fxch %st(1)
; MCU-NEXT: fmul %st(0), %st(0)
; MCU-NEXT: fxch %st(2)
; MCU-NEXT: fmul %st(0), %st(0)
; MCU-NEXT: fxch %st(3)
; MCU-NEXT: fmul %st(0), %st(0)
; MCU-NEXT: testl %eax, %eax
; MCU-NEXT: flds (%edx)
; MCU-NEXT: je .LBB5_2
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU-NEXT: # %bb.1:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: fstp %st(1)
; MCU-NEXT: fstp %st(3)
; MCU-NEXT: fstp %st(1)
; MCU-NEXT: fstp %st(0)
; MCU-NEXT: flds (%esp) # 4-byte Folded Reload
; MCU-NEXT: fldz
; MCU-NEXT: fldz
; MCU-NEXT: fldz
; MCU-NEXT: fxch %st(1)
; MCU-NEXT: fxch %st(6)
; MCU-NEXT: fxch %st(1)
; MCU-NEXT: fxch %st(5)
; MCU-NEXT: fxch %st(4)
; MCU-NEXT: fxch %st(1)
; MCU-NEXT: fxch %st(3)
; MCU-NEXT: fxch %st(2)
; MCU-NEXT: .LBB5_2:
; MCU-NEXT: fstp %st(0)
; MCU-NEXT: fstp %st(5)
; MCU-NEXT: fstp %st(3)
; MCU-NEXT: fxch %st(2)
; MCU-NEXT: fstps 12(%edx)
; MCU-NEXT: fxch %st(1)
; MCU-NEXT: fstps 8(%edx)
; MCU-NEXT: fstps 4(%edx)
; MCU-NEXT: fstps (%edx)
; MCU-NEXT: popl %eax
; MCU-NEXT: retl
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
%tmp = load <4 x float>, <4 x float>* %A
%tmp3 = load <4 x float>, <4 x float>* %B
%tmp9 = fmul <4 x float> %tmp3, %tmp3
%tmp.upgrd.1 = icmp eq i32 %C, 0
%iftmp.38.0 = select i1 %tmp.upgrd.1, <4 x float> %tmp9, <4 x float> %tmp
store <4 x float> %iftmp.38.0, <4 x float>* %A
ret void
merge some tests into select.ll and make them more specific. llvm-svn: 120928
2010-12-05 09:13:58 +08:00
}
; Select with fp80's
define x86_fp80 @test7(i32 %tmp8) nounwind {
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
; CHECK-LABEL: test7:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: ## %bb.0:
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: testl %edi, %edi
; CHECK-NEXT: setns %al
; CHECK-NEXT: shlq $4, %rax
; CHECK-NEXT: leaq {{.*}}(%rip), %rcx
; CHECK-NEXT: fldt (%rax,%rcx)
; CHECK-NEXT: retq
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
;
; MCU-LABEL: test7:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: xorl %ecx, %ecx
; MCU-NEXT: testl %eax, %eax
; MCU-NEXT: setns %cl
; MCU-NEXT: shll $4, %ecx
; MCU-NEXT: fldt {{\.LCPI.*}}(%ecx)
; MCU-NEXT: retl
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
%tmp9 = icmp sgt i32 %tmp8, -1
%retval = select i1 %tmp9, x86_fp80 0xK4005B400000000000000, x86_fp80 0xK40078700000000000000
ret x86_fp80 %retval
merge some tests into select.ll and make them more specific. llvm-svn: 120928
2010-12-05 09:13:58 +08:00
}
; widening select v6i32 and then a sub
define void @test8(i1 %c, <6 x i32>* %dst.addr, <6 x i32> %src1,<6 x i32> %src2) nounwind {
[X86][SSE] Regenerate select tests llvm-svn: 283674
2016-10-09 05:17:44 +08:00
; GENERIC-LABEL: test8:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; GENERIC: ## %bb.0:
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; GENERIC-NEXT: testb $1, %dil
[X86][SSE] Regenerate select tests llvm-svn: 283674
2016-10-09 05:17:44 +08:00
; GENERIC-NEXT: jne LBB7_1
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; GENERIC-NEXT: ## %bb.2:
[X86][SSE] Regenerate select tests llvm-svn: 283674
2016-10-09 05:17:44 +08:00
; GENERIC-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; GENERIC-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; GENERIC-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; GENERIC-NEXT: movd {{.*#+}} xmm2 = mem[0],zero,zero,zero
[X86][SSE] Regenerate select tests llvm-svn: 283674
2016-10-09 05:17:44 +08:00
; GENERIC-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; GENERIC-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; GENERIC-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; GENERIC-NEXT: movd {{.*#+}} xmm2 = mem[0],zero,zero,zero
Add LiveRangeShrink pass to shrink live range within BB. Summary: LiveRangeShrink pass moves instruction right after the definition with the same BB if the instruction and its operands all have more than one use. This pass is inexpensive and guarantees optimal live-range within BB. Reviewers: davidxl, wmi, hfinkel, MatzeB, andreadb Reviewed By: MatzeB, andreadb Subscribers: hiraditya, jyknight, sanjoy, skatkov, gberry, jholewinski, qcolombet, javed.absar, krytarowski, atrick, spatel, RKSimon, andreadb, MatzeB, mehdi_amini, mgorny, efriedma, davide, dberlin, llvm-commits Differential Revision: https://reviews.llvm.org/D32563 llvm-svn: 304371
2017-06-01 07:25:25 +08:00
; GENERIC-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; GENERIC-NEXT: jmp LBB7_3
; GENERIC-NEXT: LBB7_1:
; GENERIC-NEXT: movd %r9d, %xmm0
; GENERIC-NEXT: movd %r8d, %xmm1
; GENERIC-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; GENERIC-NEXT: movd %ecx, %xmm2
; GENERIC-NEXT: movd %edx, %xmm0
; GENERIC-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; GENERIC-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
[X86][SSE] Regenerate select tests llvm-svn: 283674
2016-10-09 05:17:44 +08:00
; GENERIC-NEXT: movd {{.*#+}} xmm2 = mem[0],zero,zero,zero
; GENERIC-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; GENERIC-NEXT: LBB7_3:
; GENERIC-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
[x86] transform vector inc/dec to use -1 constant (PR33483) Convert vector increment or decrement to sub/add with an all-ones constant: add X, <1, 1...> --> sub X, <-1, -1...> sub X, <1, 1...> --> add X, <-1, -1...> The all-ones vector constant can be materialized using a pcmpeq instruction that is commonly recognized as an idiom (has no register dependency), so that's better than loading a splat 1 constant. AVX512 uses 'vpternlogd' for 512-bit vectors because there is apparently no better way to produce 512 one-bits. The general advantages of this lowering are: 1. pcmpeq has lower latency than a memop on every uarch I looked at in Agner's tables, so in theory, this could be better for perf, but... 2. That seems unlikely to affect any OOO implementation, and I can't measure any real perf difference from this transform on Haswell or Jaguar, but... 3. It doesn't look like it from the diffs, but this is an overall size win because we eliminate 16 - 64 constant bytes in the case of a vector load. If we're broadcasting a scalar load (which might itself be a bug), then we're replacing a scalar constant load + broadcast with a single cheap op, so that should always be smaller/better too. 4. This makes the DAG/isel output more consistent - we use pcmpeq already for padd x, -1 and psub x, -1, so we should use that form for +1 too because we can. If there's some reason to favor a constant load on some CPU, let's make the reverse transform for all of these cases (either here in the DAG or in a later machine pass). This should fix: https://bugs.llvm.org/show_bug.cgi?id=33483 Differential Revision: https://reviews.llvm.org/D34336 llvm-svn: 306289
2017-06-26 22:19:26 +08:00
; GENERIC-NEXT: pcmpeqd %xmm2, %xmm2
; GENERIC-NEXT: paddd %xmm2, %xmm0
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; GENERIC-NEXT: paddd %xmm2, %xmm1
; GENERIC-NEXT: movq %xmm1, 16(%rsi)
; GENERIC-NEXT: movdqa %xmm0, (%rsi)
[X86][SSE] Regenerate select tests llvm-svn: 283674
2016-10-09 05:17:44 +08:00
; GENERIC-NEXT: retq
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
;
[X86][SSE] Regenerate select tests llvm-svn: 283674
2016-10-09 05:17:44 +08:00
; ATOM-LABEL: test8:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; ATOM: ## %bb.0:
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; ATOM-NEXT: testb $1, %dil
[X86][SSE] Regenerate select tests llvm-svn: 283674
2016-10-09 05:17:44 +08:00
; ATOM-NEXT: jne LBB7_1
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; ATOM-NEXT: ## %bb.2:
[X86][SSE] Regenerate select tests llvm-svn: 283674
2016-10-09 05:17:44 +08:00
; ATOM-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; ATOM-NEXT: movd {{.*#+}} xmm2 = mem[0],zero,zero,zero
; ATOM-NEXT: movd {{.*#+}} xmm3 = mem[0],zero,zero,zero
; ATOM-NEXT: movd {{.*#+}} xmm4 = mem[0],zero,zero,zero
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; ATOM-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1]
; ATOM-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
[X86][SSE] Regenerate select tests llvm-svn: 283674
2016-10-09 05:17:44 +08:00
; ATOM-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; ATOM-NEXT: jmp LBB7_3
; ATOM-NEXT: LBB7_1:
; ATOM-NEXT: movd %r9d, %xmm0
[X86][SSE] Change BUILD_VECTOR interleaving ordering to improve coalescing/combine opportunities We currently generate BUILD_VECTOR as a tree of UNPCKL shuffles of the same type: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 2, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 1> Step 2: unpcklps X, Y ==> <3, 2, 1, 0> The issue is because we are not placing sequential vector elements together early enough, we fail to recognise many combinable patterns - consecutive scalar loads, extractions etc. Instead, this patch unpacks progressively larger sequential vector elements together: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 1, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 2> Step 2: unpcklpd X, Y ==> <3, 2, 1, 0> This does mean that we are creating UNPCKL shuffle of different value types, but the relevant combines that benefit from this are quite capable of handling the additional BITCASTs that are now included in the shuffle tree. Differential Revision: https://reviews.llvm.org/D33864 llvm-svn: 304688
2017-06-05 04:12:04 +08:00
; ATOM-NEXT: movd %r8d, %xmm2
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; ATOM-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1]
[X86][SSE] Change BUILD_VECTOR interleaving ordering to improve coalescing/combine opportunities We currently generate BUILD_VECTOR as a tree of UNPCKL shuffles of the same type: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 2, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 1> Step 2: unpcklps X, Y ==> <3, 2, 1, 0> The issue is because we are not placing sequential vector elements together early enough, we fail to recognise many combinable patterns - consecutive scalar loads, extractions etc. Instead, this patch unpacks progressively larger sequential vector elements together: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 1, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 2> Step 2: unpcklpd X, Y ==> <3, 2, 1, 0> This does mean that we are creating UNPCKL shuffle of different value types, but the relevant combines that benefit from this are quite capable of handling the additional BITCASTs that are now included in the shuffle tree. Differential Revision: https://reviews.llvm.org/D33864 llvm-svn: 304688
2017-06-05 04:12:04 +08:00
; ATOM-NEXT: movd %ecx, %xmm3
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; ATOM-NEXT: movd %edx, %xmm0
; ATOM-NEXT: movd {{.*#+}} xmm4 = mem[0],zero,zero,zero
; ATOM-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; ATOM-NEXT: LBB7_3:
; ATOM-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1]
; ATOM-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
[x86] transform vector inc/dec to use -1 constant (PR33483) Convert vector increment or decrement to sub/add with an all-ones constant: add X, <1, 1...> --> sub X, <-1, -1...> sub X, <1, 1...> --> add X, <-1, -1...> The all-ones vector constant can be materialized using a pcmpeq instruction that is commonly recognized as an idiom (has no register dependency), so that's better than loading a splat 1 constant. AVX512 uses 'vpternlogd' for 512-bit vectors because there is apparently no better way to produce 512 one-bits. The general advantages of this lowering are: 1. pcmpeq has lower latency than a memop on every uarch I looked at in Agner's tables, so in theory, this could be better for perf, but... 2. That seems unlikely to affect any OOO implementation, and I can't measure any real perf difference from this transform on Haswell or Jaguar, but... 3. It doesn't look like it from the diffs, but this is an overall size win because we eliminate 16 - 64 constant bytes in the case of a vector load. If we're broadcasting a scalar load (which might itself be a bug), then we're replacing a scalar constant load + broadcast with a single cheap op, so that should always be smaller/better too. 4. This makes the DAG/isel output more consistent - we use pcmpeq already for padd x, -1 and psub x, -1, so we should use that form for +1 too because we can. If there's some reason to favor a constant load on some CPU, let's make the reverse transform for all of these cases (either here in the DAG or in a later machine pass). This should fix: https://bugs.llvm.org/show_bug.cgi?id=33483 Differential Revision: https://reviews.llvm.org/D34336 llvm-svn: 306289
2017-06-26 22:19:26 +08:00
; ATOM-NEXT: pcmpeqd %xmm2, %xmm2
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; ATOM-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1]
[x86] transform vector inc/dec to use -1 constant (PR33483) Convert vector increment or decrement to sub/add with an all-ones constant: add X, <1, 1...> --> sub X, <-1, -1...> sub X, <1, 1...> --> add X, <-1, -1...> The all-ones vector constant can be materialized using a pcmpeq instruction that is commonly recognized as an idiom (has no register dependency), so that's better than loading a splat 1 constant. AVX512 uses 'vpternlogd' for 512-bit vectors because there is apparently no better way to produce 512 one-bits. The general advantages of this lowering are: 1. pcmpeq has lower latency than a memop on every uarch I looked at in Agner's tables, so in theory, this could be better for perf, but... 2. That seems unlikely to affect any OOO implementation, and I can't measure any real perf difference from this transform on Haswell or Jaguar, but... 3. It doesn't look like it from the diffs, but this is an overall size win because we eliminate 16 - 64 constant bytes in the case of a vector load. If we're broadcasting a scalar load (which might itself be a bug), then we're replacing a scalar constant load + broadcast with a single cheap op, so that should always be smaller/better too. 4. This makes the DAG/isel output more consistent - we use pcmpeq already for padd x, -1 and psub x, -1, so we should use that form for +1 too because we can. If there's some reason to favor a constant load on some CPU, let's make the reverse transform for all of these cases (either here in the DAG or in a later machine pass). This should fix: https://bugs.llvm.org/show_bug.cgi?id=33483 Differential Revision: https://reviews.llvm.org/D34336 llvm-svn: 306289
2017-06-26 22:19:26 +08:00
; ATOM-NEXT: paddd %xmm2, %xmm0
; ATOM-NEXT: paddd %xmm2, %xmm1
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; ATOM-NEXT: movdqa %xmm0, (%rsi)
Re-land MachineInstr: Reason locally about some memory objects before going to AA. Summary: Reverts r311008 to reinstate r310825 with a fix. Refine alias checking for pseudo vs value to be conservative. This fixes the original failure in builtbot unittest SingleSource/UnitTests/2003-07-09-SignedArgs. Reviewers: hfinkel, nemanjai, efriedma Reviewed By: efriedma Subscribers: bjope, mcrosier, nhaehnle, javed.absar, llvm-commits Differential Revision: https://reviews.llvm.org/D36900 llvm-svn: 312126
2017-08-30 22:57:12 +08:00
; ATOM-NEXT: movq %xmm1, 16(%rsi)
[X86][SSE] Regenerate select tests llvm-svn: 283674
2016-10-09 05:17:44 +08:00
; ATOM-NEXT: retq
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
;
; MCU-LABEL: test8:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: pushl %ebp
; MCU-NEXT: pushl %ebx
; MCU-NEXT: pushl %edi
; MCU-NEXT: pushl %esi
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; MCU-NEXT: testb $1, %al
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: jne .LBB7_1
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU-NEXT: # %bb.2:
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; MCU-NEXT: leal {{[0-9]+}}(%esp), %eax
; MCU-NEXT: movl (%eax), %eax
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: je .LBB7_5
; MCU-NEXT: .LBB7_4:
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; MCU-NEXT: leal {{[0-9]+}}(%esp), %ecx
; MCU-NEXT: movl (%ecx), %ecx
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: je .LBB7_8
; MCU-NEXT: .LBB7_7:
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; MCU-NEXT: leal {{[0-9]+}}(%esp), %esi
; MCU-NEXT: movl (%esi), %esi
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: je .LBB7_11
; MCU-NEXT: .LBB7_10:
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; MCU-NEXT: leal {{[0-9]+}}(%esp), %edi
; MCU-NEXT: movl (%edi), %edi
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: je .LBB7_14
; MCU-NEXT: .LBB7_13:
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; MCU-NEXT: leal {{[0-9]+}}(%esp), %ebx
; MCU-NEXT: movl (%ebx), %ebx
; MCU-NEXT: je .LBB7_17
; MCU-NEXT: .LBB7_16:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: leal {{[0-9]+}}(%esp), %ebp
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; MCU-NEXT: jmp .LBB7_18
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: .LBB7_1:
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; MCU-NEXT: leal {{[0-9]+}}(%esp), %eax
; MCU-NEXT: movl (%eax), %eax
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: jne .LBB7_4
; MCU-NEXT: .LBB7_5:
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; MCU-NEXT: leal {{[0-9]+}}(%esp), %ecx
; MCU-NEXT: movl (%ecx), %ecx
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: jne .LBB7_7
; MCU-NEXT: .LBB7_8:
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; MCU-NEXT: leal {{[0-9]+}}(%esp), %esi
; MCU-NEXT: movl (%esi), %esi
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: jne .LBB7_10
; MCU-NEXT: .LBB7_11:
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; MCU-NEXT: leal {{[0-9]+}}(%esp), %edi
; MCU-NEXT: movl (%edi), %edi
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: jne .LBB7_13
; MCU-NEXT: .LBB7_14:
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; MCU-NEXT: leal {{[0-9]+}}(%esp), %ebx
; MCU-NEXT: movl (%ebx), %ebx
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: jne .LBB7_16
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; MCU-NEXT: .LBB7_17:
; MCU-NEXT: leal {{[0-9]+}}(%esp), %ebp
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: .LBB7_18:
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; MCU-NEXT: movl (%ebp), %ebp
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: decl %ebp
; MCU-NEXT: decl %ebx
; MCU-NEXT: decl %edi
; MCU-NEXT: decl %esi
; MCU-NEXT: decl %ecx
[x86] Fix an amazing goof in the handling of sub, or, and xor lowering. The comment for this code indicated that it should work similar to our handling of add lowering above: if we see uses of an instruction other than flag usage and store usage, it tries to avoid the specialized X86ISD::* nodes that are designed for flag+op modeling and emits an explicit test. Problem is, only the add case actually did this. In all the other cases, the logic was incomplete and inverted. Any time the value was used by a store, we bailed on the specialized X86ISD node. All of this appears to have been historical where we had different logic here. =/ Turns out, we have quite a few patterns designed around these nodes. We should actually form them. I fixed the code to match what we do for add, and it has quite a positive effect just within some of our test cases. The only thing close to a regression I see is using: notl %r testl %r, %r instead of: xorl -1, %r But we can add a pattern or something to fold that back out. The improvements seem more than worth this. I've also worked with Craig to update the comments to no longer be actively contradicted by the code. =[ Some of this still remains a mystery to both Craig and myself, but this seems like a large step in the direction of consistency and slightly more accurate comments. Many thanks to Craig for help figuring out this nasty stuff. Differential Revision: https://reviews.llvm.org/D37096 llvm-svn: 311737
2017-08-25 08:34:07 +08:00
; MCU-NEXT: decl %eax
; MCU-NEXT: movl %eax, 20(%edx)
; MCU-NEXT: movl %ecx, 16(%edx)
; MCU-NEXT: movl %esi, 12(%edx)
; MCU-NEXT: movl %edi, 8(%edx)
; MCU-NEXT: movl %ebx, 4(%edx)
; MCU-NEXT: movl %ebp, (%edx)
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: popl %esi
; MCU-NEXT: popl %edi
; MCU-NEXT: popl %ebx
; MCU-NEXT: popl %ebp
; MCU-NEXT: retl
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
%x = select i1 %c, <6 x i32> %src1, <6 x i32> %src2
%val = sub <6 x i32> %x, < i32 1, i32 1, i32 1, i32 1, i32 1, i32 1 >
store <6 x i32> %val, <6 x i32>* %dst.addr
ret void
Fix the result type of SELECT nodes lowered from Select instructions with aggregate return values. This fixes PR5754. llvm-svn: 91145
2009-12-12 03:50:50 +08:00
}
Improve an integer select optimization in two ways: 1. generalize (select (x == 0), -1, 0) -> (sign_bit (x - 1)) to: (select (x == 0), -1, y) -> (sign_bit (x - 1)) | y 2. Handle the identical pattern that happens with !=: (select (x != 0), y, -1) -> (sign_bit (x - 1)) | y cmov is often high latency and can't fold immediates or memory operands. For example for (x == 0) ? -1 : 1, before we got: < testb %sil, %sil < movl $-1, %ecx < movl $1, %eax < cmovel %ecx, %eax now we get: > cmpb $1, %sil > sbbl %eax, %eax > orl $1, %eax llvm-svn: 120929
2010-12-05 09:23:24 +08:00
;; Test integer select between values and constants.
define i64 @test9(i64 %x, i64 %y) nounwind readnone ssp noredzone {
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; GENERIC-LABEL: test9:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; GENERIC: ## %bb.0:
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; GENERIC-NEXT: cmpq $1, %rdi
; GENERIC-NEXT: sbbq %rax, %rax
; GENERIC-NEXT: orq %rsi, %rax
; GENERIC-NEXT: retq
;
; ATOM-LABEL: test9:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; ATOM: ## %bb.0:
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; ATOM-NEXT: cmpq $1, %rdi
; ATOM-NEXT: sbbq %rax, %rax
; ATOM-NEXT: orq %rsi, %rax
; ATOM-NEXT: nop
; ATOM-NEXT: nop
; ATOM-NEXT: retq
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
;
; MCU-LABEL: test9:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: orl %edx, %eax
; MCU-NEXT: jne .LBB8_1
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU-NEXT: # %bb.2:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: movl $-1, %eax
; MCU-NEXT: movl $-1, %edx
; MCU-NEXT: retl
; MCU-NEXT: .LBB8_1:
; MCU-NEXT: movl {{[0-9]+}}(%esp), %eax
; MCU-NEXT: movl {{[0-9]+}}(%esp), %edx
; MCU-NEXT: retl
Improve an integer select optimization in two ways: 1. generalize (select (x == 0), -1, 0) -> (sign_bit (x - 1)) to: (select (x == 0), -1, y) -> (sign_bit (x - 1)) | y 2. Handle the identical pattern that happens with !=: (select (x != 0), y, -1) -> (sign_bit (x - 1)) | y cmov is often high latency and can't fold immediates or memory operands. For example for (x == 0) ? -1 : 1, before we got: < testb %sil, %sil < movl $-1, %ecx < movl $1, %eax < cmovel %ecx, %eax now we get: > cmpb $1, %sil > sbbl %eax, %eax > orl $1, %eax llvm-svn: 120929
2010-12-05 09:23:24 +08:00
%cmp = icmp ne i64 %x, 0
%cond = select i1 %cmp, i64 %y, i64 -1
ret i64 %cond
}
;; Same as test9
define i64 @test9a(i64 %x, i64 %y) nounwind readnone ssp noredzone {
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; GENERIC-LABEL: test9a:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; GENERIC: ## %bb.0:
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; GENERIC-NEXT: cmpq $1, %rdi
; GENERIC-NEXT: sbbq %rax, %rax
; GENERIC-NEXT: orq %rsi, %rax
; GENERIC-NEXT: retq
;
; ATOM-LABEL: test9a:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; ATOM: ## %bb.0:
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; ATOM-NEXT: cmpq $1, %rdi
; ATOM-NEXT: sbbq %rax, %rax
; ATOM-NEXT: orq %rsi, %rax
; ATOM-NEXT: nop
; ATOM-NEXT: nop
; ATOM-NEXT: retq
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
;
; MCU-LABEL: test9a:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: orl %edx, %eax
; MCU-NEXT: movl $-1, %eax
; MCU-NEXT: movl $-1, %edx
; MCU-NEXT: je .LBB9_2
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU-NEXT: # %bb.1:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: movl {{[0-9]+}}(%esp), %eax
; MCU-NEXT: movl {{[0-9]+}}(%esp), %edx
; MCU-NEXT: .LBB9_2:
; MCU-NEXT: retl
Improve an integer select optimization in two ways: 1. generalize (select (x == 0), -1, 0) -> (sign_bit (x - 1)) to: (select (x == 0), -1, y) -> (sign_bit (x - 1)) | y 2. Handle the identical pattern that happens with !=: (select (x != 0), y, -1) -> (sign_bit (x - 1)) | y cmov is often high latency and can't fold immediates or memory operands. For example for (x == 0) ? -1 : 1, before we got: < testb %sil, %sil < movl $-1, %ecx < movl $1, %eax < cmovel %ecx, %eax now we get: > cmpb $1, %sil > sbbl %eax, %eax > orl $1, %eax llvm-svn: 120929
2010-12-05 09:23:24 +08:00
%cmp = icmp eq i64 %x, 0
%cond = select i1 %cmp, i64 -1, i64 %y
ret i64 %cond
}
define i64 @test9b(i64 %x, i64 %y) nounwind readnone ssp noredzone {
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; GENERIC-LABEL: test9b:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; GENERIC: ## %bb.0:
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; GENERIC-NEXT: cmpq $1, %rdi
; GENERIC-NEXT: sbbq %rax, %rax
; GENERIC-NEXT: orq %rsi, %rax
; GENERIC-NEXT: retq
;
; ATOM-LABEL: test9b:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; ATOM: ## %bb.0:
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; ATOM-NEXT: cmpq $1, %rdi
; ATOM-NEXT: sbbq %rax, %rax
; ATOM-NEXT: orq %rsi, %rax
; ATOM-NEXT: nop
; ATOM-NEXT: nop
; ATOM-NEXT: retq
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
;
; MCU-LABEL: test9b:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0:
[x86] use more shift or LEA for select-of-constants (2nd try) The previous rev (r310208) failed to account for overflow when subtracting the constants to see if they're suitable for shift/lea. This version add a check for that and more test were added in r310490. We can convert any select-of-constants to math ops: http://rise4fun.com/Alive/d7d For this patch, I'm enhancing an existing x86 transform that uses fake multiplies (they always become shl/lea) to avoid cmov or branching. The current code misses cases where we have a negative constant and a positive constant, so this is just trying to plug that hole. The DAGCombiner diff prevents us from hitting a terrible inefficiency: we can start with a select in IR, create a select DAG node, convert it into a sext, convert it back into a select, and then lower it to sext machine code. Some notes about the test diffs: 1. 2010-08-04-MaskedSignedCompare.ll - We were creating control flow that didn't exist in the IR. 2. memcmp.ll - Choose -1 or 1 is the case that got me looking at this again. We could avoid the push/pop in some cases if we used 'movzbl %al' instead of an xor on a different reg? That's a post-DAG problem though. 3. mul-constant-result.ll - The trade-off between sbb+not vs. setne+neg could be addressed if that's a regression, but those would always be nearly equivalent. 4. pr22338.ll and sext-i1.ll - These tests have undef operands, so we don't actually care about these diffs. 5. sbb.ll - This shows a win for what is likely a common case: choose -1 or 0. 6. select.ll - There's another borderline case here: cmp+sbb+or vs. test+set+lea? Also, sbb+not vs. setae+neg shows up again. 7. select_const.ll - These are motivating cases for the enhancement; replace cmov with cheaper ops. Assembly differences between movzbl and xor to avoid a partial reg stall are caused later by the X86 Fixup SetCC pass. Differential Revision: https://reviews.llvm.org/D35340 llvm-svn: 310717
2017-08-11 23:44:14 +08:00
; MCU-NEXT: movl %edx, %ecx
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: xorl %edx, %edx
[x86] use more shift or LEA for select-of-constants (2nd try) The previous rev (r310208) failed to account for overflow when subtracting the constants to see if they're suitable for shift/lea. This version add a check for that and more test were added in r310490. We can convert any select-of-constants to math ops: http://rise4fun.com/Alive/d7d For this patch, I'm enhancing an existing x86 transform that uses fake multiplies (they always become shl/lea) to avoid cmov or branching. The current code misses cases where we have a negative constant and a positive constant, so this is just trying to plug that hole. The DAGCombiner diff prevents us from hitting a terrible inefficiency: we can start with a select in IR, create a select DAG node, convert it into a sext, convert it back into a select, and then lower it to sext machine code. Some notes about the test diffs: 1. 2010-08-04-MaskedSignedCompare.ll - We were creating control flow that didn't exist in the IR. 2. memcmp.ll - Choose -1 or 1 is the case that got me looking at this again. We could avoid the push/pop in some cases if we used 'movzbl %al' instead of an xor on a different reg? That's a post-DAG problem though. 3. mul-constant-result.ll - The trade-off between sbb+not vs. setne+neg could be addressed if that's a regression, but those would always be nearly equivalent. 4. pr22338.ll and sext-i1.ll - These tests have undef operands, so we don't actually care about these diffs. 5. sbb.ll - This shows a win for what is likely a common case: choose -1 or 0. 6. select.ll - There's another borderline case here: cmp+sbb+or vs. test+set+lea? Also, sbb+not vs. setae+neg shows up again. 7. select_const.ll - These are motivating cases for the enhancement; replace cmov with cheaper ops. Assembly differences between movzbl and xor to avoid a partial reg stall are caused later by the X86 Fixup SetCC pass. Differential Revision: https://reviews.llvm.org/D35340 llvm-svn: 310717
2017-08-11 23:44:14 +08:00
; MCU-NEXT: orl %ecx, %eax
; MCU-NEXT: sete %dl
; MCU-NEXT: negl %edx
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: movl {{[0-9]+}}(%esp), %eax
; MCU-NEXT: orl %edx, %eax
; MCU-NEXT: orl {{[0-9]+}}(%esp), %edx
; MCU-NEXT: retl
Improve an integer select optimization in two ways: 1. generalize (select (x == 0), -1, 0) -> (sign_bit (x - 1)) to: (select (x == 0), -1, y) -> (sign_bit (x - 1)) | y 2. Handle the identical pattern that happens with !=: (select (x != 0), y, -1) -> (sign_bit (x - 1)) | y cmov is often high latency and can't fold immediates or memory operands. For example for (x == 0) ? -1 : 1, before we got: < testb %sil, %sil < movl $-1, %ecx < movl $1, %eax < cmovel %ecx, %eax now we get: > cmpb $1, %sil > sbbl %eax, %eax > orl $1, %eax llvm-svn: 120929
2010-12-05 09:23:24 +08:00
%cmp = icmp eq i64 %x, 0
%A = sext i1 %cmp to i64
%cond = or i64 %y, %A
ret i64 %cond
}
;; Select between -1 and 1.
define i64 @test10(i64 %x, i64 %y) nounwind readnone ssp noredzone {
[x86] use more shift or LEA for select-of-constants (2nd try) The previous rev (r310208) failed to account for overflow when subtracting the constants to see if they're suitable for shift/lea. This version add a check for that and more test were added in r310490. We can convert any select-of-constants to math ops: http://rise4fun.com/Alive/d7d For this patch, I'm enhancing an existing x86 transform that uses fake multiplies (they always become shl/lea) to avoid cmov or branching. The current code misses cases where we have a negative constant and a positive constant, so this is just trying to plug that hole. The DAGCombiner diff prevents us from hitting a terrible inefficiency: we can start with a select in IR, create a select DAG node, convert it into a sext, convert it back into a select, and then lower it to sext machine code. Some notes about the test diffs: 1. 2010-08-04-MaskedSignedCompare.ll - We were creating control flow that didn't exist in the IR. 2. memcmp.ll - Choose -1 or 1 is the case that got me looking at this again. We could avoid the push/pop in some cases if we used 'movzbl %al' instead of an xor on a different reg? That's a post-DAG problem though. 3. mul-constant-result.ll - The trade-off between sbb+not vs. setne+neg could be addressed if that's a regression, but those would always be nearly equivalent. 4. pr22338.ll and sext-i1.ll - These tests have undef operands, so we don't actually care about these diffs. 5. sbb.ll - This shows a win for what is likely a common case: choose -1 or 0. 6. select.ll - There's another borderline case here: cmp+sbb+or vs. test+set+lea? Also, sbb+not vs. setae+neg shows up again. 7. select_const.ll - These are motivating cases for the enhancement; replace cmov with cheaper ops. Assembly differences between movzbl and xor to avoid a partial reg stall are caused later by the X86 Fixup SetCC pass. Differential Revision: https://reviews.llvm.org/D35340 llvm-svn: 310717
2017-08-11 23:44:14 +08:00
; CHECK-LABEL: test10:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: ## %bb.0:
[x86] use more shift or LEA for select-of-constants (2nd try) The previous rev (r310208) failed to account for overflow when subtracting the constants to see if they're suitable for shift/lea. This version add a check for that and more test were added in r310490. We can convert any select-of-constants to math ops: http://rise4fun.com/Alive/d7d For this patch, I'm enhancing an existing x86 transform that uses fake multiplies (they always become shl/lea) to avoid cmov or branching. The current code misses cases where we have a negative constant and a positive constant, so this is just trying to plug that hole. The DAGCombiner diff prevents us from hitting a terrible inefficiency: we can start with a select in IR, create a select DAG node, convert it into a sext, convert it back into a select, and then lower it to sext machine code. Some notes about the test diffs: 1. 2010-08-04-MaskedSignedCompare.ll - We were creating control flow that didn't exist in the IR. 2. memcmp.ll - Choose -1 or 1 is the case that got me looking at this again. We could avoid the push/pop in some cases if we used 'movzbl %al' instead of an xor on a different reg? That's a post-DAG problem though. 3. mul-constant-result.ll - The trade-off between sbb+not vs. setne+neg could be addressed if that's a regression, but those would always be nearly equivalent. 4. pr22338.ll and sext-i1.ll - These tests have undef operands, so we don't actually care about these diffs. 5. sbb.ll - This shows a win for what is likely a common case: choose -1 or 0. 6. select.ll - There's another borderline case here: cmp+sbb+or vs. test+set+lea? Also, sbb+not vs. setae+neg shows up again. 7. select_const.ll - These are motivating cases for the enhancement; replace cmov with cheaper ops. Assembly differences between movzbl and xor to avoid a partial reg stall are caused later by the X86 Fixup SetCC pass. Differential Revision: https://reviews.llvm.org/D35340 llvm-svn: 310717
2017-08-11 23:44:14 +08:00
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: testq %rdi, %rdi
; CHECK-NEXT: setne %al
; CHECK-NEXT: leaq -1(%rax,%rax), %rax
; CHECK-NEXT: retq
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
;
; MCU-LABEL: test10:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: orl %edx, %eax
; MCU-NEXT: movl $-1, %eax
; MCU-NEXT: movl $-1, %edx
; MCU-NEXT: je .LBB11_2
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU-NEXT: # %bb.1:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: xorl %edx, %edx
; MCU-NEXT: movl $1, %eax
; MCU-NEXT: .LBB11_2:
; MCU-NEXT: retl
Improve an integer select optimization in two ways: 1. generalize (select (x == 0), -1, 0) -> (sign_bit (x - 1)) to: (select (x == 0), -1, y) -> (sign_bit (x - 1)) | y 2. Handle the identical pattern that happens with !=: (select (x != 0), y, -1) -> (sign_bit (x - 1)) | y cmov is often high latency and can't fold immediates or memory operands. For example for (x == 0) ? -1 : 1, before we got: < testb %sil, %sil < movl $-1, %ecx < movl $1, %eax < cmovel %ecx, %eax now we get: > cmpb $1, %sil > sbbl %eax, %eax > orl $1, %eax llvm-svn: 120929
2010-12-05 09:23:24 +08:00
%cmp = icmp eq i64 %x, 0
%cond = select i1 %cmp, i64 -1, i64 1
ret i64 %cond
}
generalize the previous check to handle -1 on either side of the select, inserting a not to compensate. Add a missing isZero check that I lost somehow. This improves codegen of: void *func(long count) { return new int[count]; } from: __Z4funcl: ## @_Z4funcl movl $4, %ecx ## encoding: [0xb9,0x04,0x00,0x00,0x00] movq %rdi, %rax ## encoding: [0x48,0x89,0xf8] mulq %rcx ## encoding: [0x48,0xf7,0xe1] testq %rdx, %rdx ## encoding: [0x48,0x85,0xd2] movq $-1, %rdi ## encoding: [0x48,0xc7,0xc7,0xff,0xff,0xff,0xff] cmoveq %rax, %rdi ## encoding: [0x48,0x0f,0x44,0xf8] jmp __Znam ## TAILCALL ## encoding: [0xeb,A] to: __Z4funcl: ## @_Z4funcl movl $4, %ecx ## encoding: [0xb9,0x04,0x00,0x00,0x00] movq %rdi, %rax ## encoding: [0x48,0x89,0xf8] mulq %rcx ## encoding: [0x48,0xf7,0xe1] cmpq $1, %rdx ## encoding: [0x48,0x83,0xfa,0x01] sbbq %rdi, %rdi ## encoding: [0x48,0x19,0xff] notq %rdi ## encoding: [0x48,0xf7,0xd7] orq %rax, %rdi ## encoding: [0x48,0x09,0xc7] jmp __Znam ## TAILCALL ## encoding: [0xeb,A] llvm-svn: 120932
2010-12-05 10:00:51 +08:00
define i64 @test11(i64 %x, i64 %y) nounwind readnone ssp noredzone {
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; CHECK-LABEL: test11:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: ## %bb.0:
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; CHECK-NEXT: cmpq $1, %rdi
; CHECK-NEXT: sbbq %rax, %rax
; CHECK-NEXT: notq %rax
; CHECK-NEXT: orq %rsi, %rax
; CHECK-NEXT: retq
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
;
; MCU-LABEL: test11:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: orl %edx, %eax
; MCU-NEXT: je .LBB12_1
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU-NEXT: # %bb.2:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: movl $-1, %eax
; MCU-NEXT: movl $-1, %edx
; MCU-NEXT: retl
; MCU-NEXT: .LBB12_1:
; MCU-NEXT: movl {{[0-9]+}}(%esp), %eax
; MCU-NEXT: movl {{[0-9]+}}(%esp), %edx
; MCU-NEXT: retl
generalize the previous check to handle -1 on either side of the select, inserting a not to compensate. Add a missing isZero check that I lost somehow. This improves codegen of: void *func(long count) { return new int[count]; } from: __Z4funcl: ## @_Z4funcl movl $4, %ecx ## encoding: [0xb9,0x04,0x00,0x00,0x00] movq %rdi, %rax ## encoding: [0x48,0x89,0xf8] mulq %rcx ## encoding: [0x48,0xf7,0xe1] testq %rdx, %rdx ## encoding: [0x48,0x85,0xd2] movq $-1, %rdi ## encoding: [0x48,0xc7,0xc7,0xff,0xff,0xff,0xff] cmoveq %rax, %rdi ## encoding: [0x48,0x0f,0x44,0xf8] jmp __Znam ## TAILCALL ## encoding: [0xeb,A] to: __Z4funcl: ## @_Z4funcl movl $4, %ecx ## encoding: [0xb9,0x04,0x00,0x00,0x00] movq %rdi, %rax ## encoding: [0x48,0x89,0xf8] mulq %rcx ## encoding: [0x48,0xf7,0xe1] cmpq $1, %rdx ## encoding: [0x48,0x83,0xfa,0x01] sbbq %rdi, %rdi ## encoding: [0x48,0x19,0xff] notq %rdi ## encoding: [0x48,0xf7,0xd7] orq %rax, %rdi ## encoding: [0x48,0x09,0xc7] jmp __Znam ## TAILCALL ## encoding: [0xeb,A] llvm-svn: 120932
2010-12-05 10:00:51 +08:00
%cmp = icmp eq i64 %x, 0
%cond = select i1 %cmp, i64 %y, i64 -1
ret i64 %cond
}
define i64 @test11a(i64 %x, i64 %y) nounwind readnone ssp noredzone {
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; CHECK-LABEL: test11a:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: ## %bb.0:
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; CHECK-NEXT: cmpq $1, %rdi
; CHECK-NEXT: sbbq %rax, %rax
; CHECK-NEXT: notq %rax
; CHECK-NEXT: orq %rsi, %rax
; CHECK-NEXT: retq
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
;
; MCU-LABEL: test11a:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: orl %edx, %eax
; MCU-NEXT: movl $-1, %eax
; MCU-NEXT: movl $-1, %edx
; MCU-NEXT: jne .LBB13_2
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU-NEXT: # %bb.1:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: movl {{[0-9]+}}(%esp), %eax
; MCU-NEXT: movl {{[0-9]+}}(%esp), %edx
; MCU-NEXT: .LBB13_2:
; MCU-NEXT: retl
generalize the previous check to handle -1 on either side of the select, inserting a not to compensate. Add a missing isZero check that I lost somehow. This improves codegen of: void *func(long count) { return new int[count]; } from: __Z4funcl: ## @_Z4funcl movl $4, %ecx ## encoding: [0xb9,0x04,0x00,0x00,0x00] movq %rdi, %rax ## encoding: [0x48,0x89,0xf8] mulq %rcx ## encoding: [0x48,0xf7,0xe1] testq %rdx, %rdx ## encoding: [0x48,0x85,0xd2] movq $-1, %rdi ## encoding: [0x48,0xc7,0xc7,0xff,0xff,0xff,0xff] cmoveq %rax, %rdi ## encoding: [0x48,0x0f,0x44,0xf8] jmp __Znam ## TAILCALL ## encoding: [0xeb,A] to: __Z4funcl: ## @_Z4funcl movl $4, %ecx ## encoding: [0xb9,0x04,0x00,0x00,0x00] movq %rdi, %rax ## encoding: [0x48,0x89,0xf8] mulq %rcx ## encoding: [0x48,0xf7,0xe1] cmpq $1, %rdx ## encoding: [0x48,0x83,0xfa,0x01] sbbq %rdi, %rdi ## encoding: [0x48,0x19,0xff] notq %rdi ## encoding: [0x48,0xf7,0xd7] orq %rax, %rdi ## encoding: [0x48,0x09,0xc7] jmp __Znam ## TAILCALL ## encoding: [0xeb,A] llvm-svn: 120932
2010-12-05 10:00:51 +08:00
%cmp = icmp ne i64 %x, 0
%cond = select i1 %cmp, i64 -1, i64 %y
ret i64 %cond
}
Improve an integer select optimization in two ways: 1. generalize (select (x == 0), -1, 0) -> (sign_bit (x - 1)) to: (select (x == 0), -1, y) -> (sign_bit (x - 1)) | y 2. Handle the identical pattern that happens with !=: (select (x != 0), y, -1) -> (sign_bit (x - 1)) | y cmov is often high latency and can't fold immediates or memory operands. For example for (x == 0) ? -1 : 1, before we got: < testb %sil, %sil < movl $-1, %ecx < movl $1, %eax < cmovel %ecx, %eax now we get: > cmpb $1, %sil > sbbl %eax, %eax > orl $1, %eax llvm-svn: 120929
2010-12-05 09:23:24 +08:00
Teach X86ISelLowering that the second result of X86ISD::UMUL is a flags result. This allows us to compile: void *test12(long count) { return new int[count]; } into: test12: movl $4, %ecx movq %rdi, %rax mulq %rcx movq $-1, %rdi cmovnoq %rax, %rdi jmp __Znam ## TAILCALL instead of: test12: movl $4, %ecx movq %rdi, %rax mulq %rcx seto %cl testb %cl, %cl movq $-1, %rdi cmoveq %rax, %rdi jmp __Znam Of course it would be even better if the regalloc inverted the cmov to 'cmovoq', which would eliminate the need for the 'movq %rdi, %rax'. llvm-svn: 120936
2010-12-05 15:49:54 +08:00
declare noalias i8* @_Znam(i64) noredzone
define noalias i8* @test12(i64 %count) nounwind ssp noredzone {
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; GENERIC-LABEL: test12:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; GENERIC: ## %bb.0: ## %entry
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; GENERIC-NEXT: movl $4, %ecx
; GENERIC-NEXT: movq %rdi, %rax
; GENERIC-NEXT: mulq %rcx
; GENERIC-NEXT: movq $-1, %rdi
; GENERIC-NEXT: cmovnoq %rax, %rdi
; GENERIC-NEXT: jmp __Znam ## TAILCALL
;
; ATOM-LABEL: test12:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; ATOM: ## %bb.0: ## %entry
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; ATOM-NEXT: movq %rdi, %rax
; ATOM-NEXT: movl $4, %ecx
; ATOM-NEXT: mulq %rcx
; ATOM-NEXT: movq $-1, %rdi
; ATOM-NEXT: cmovnoq %rax, %rdi
; ATOM-NEXT: jmp __Znam ## TAILCALL
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
;
; MCU-LABEL: test12:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0: # %entry
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: pushl %ebp
; MCU-NEXT: pushl %ebx
; MCU-NEXT: pushl %edi
; MCU-NEXT: pushl %esi
; MCU-NEXT: movl %edx, %ebx
; MCU-NEXT: movl %eax, %ebp
; MCU-NEXT: movl $4, %ecx
; MCU-NEXT: mull %ecx
; MCU-NEXT: movl %eax, %esi
; MCU-NEXT: leal (%edx,%ebx,4), %edi
; MCU-NEXT: movl %edi, %edx
; MCU-NEXT: pushl $0
; MCU-NEXT: pushl $4
; MCU-NEXT: calll __udivdi3
; MCU-NEXT: addl $8, %esp
; MCU-NEXT: xorl %ebx, %edx
; MCU-NEXT: xorl %ebp, %eax
; MCU-NEXT: orl %edx, %eax
; MCU-NEXT: movl $-1, %eax
; MCU-NEXT: movl $-1, %edx
; MCU-NEXT: jne .LBB14_2
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU-NEXT: # %bb.1: # %entry
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: movl %esi, %eax
; MCU-NEXT: movl %edi, %edx
; MCU-NEXT: .LBB14_2: # %entry
; MCU-NEXT: popl %esi
; MCU-NEXT: popl %edi
; MCU-NEXT: popl %ebx
; MCU-NEXT: popl %ebp
; MCU-NEXT: jmp _Znam # TAILCALL
Teach X86ISelLowering that the second result of X86ISD::UMUL is a flags result. This allows us to compile: void *test12(long count) { return new int[count]; } into: test12: movl $4, %ecx movq %rdi, %rax mulq %rcx movq $-1, %rdi cmovnoq %rax, %rdi jmp __Znam ## TAILCALL instead of: test12: movl $4, %ecx movq %rdi, %rax mulq %rcx seto %cl testb %cl, %cl movq $-1, %rdi cmoveq %rax, %rdi jmp __Znam Of course it would be even better if the regalloc inverted the cmov to 'cmovoq', which would eliminate the need for the 'movq %rdi, %rax'. llvm-svn: 120936
2010-12-05 15:49:54 +08:00
entry:
%A = tail call { i64, i1 } @llvm.umul.with.overflow.i64(i64 %count, i64 4)
%B = extractvalue { i64, i1 } %A, 1
%C = extractvalue { i64, i1 } %A, 0
%D = select i1 %B, i64 -1, i64 %C
%call = tail call noalias i8* @_Znam(i64 %D) nounwind noredzone
ret i8* %call
}
declare { i64, i1 } @llvm.umul.with.overflow.i64(i64, i64) nounwind readnone
X86: Lower a select directly to a setcc_carry if possible. int test(unsigned long a, unsigned long b) { return -(a < b); } compiles to _test: ## @test cmpq %rsi, %rdi ## encoding: [0x48,0x39,0xf7] sbbl %eax, %eax ## encoding: [0x19,0xc0] ret ## encoding: [0xc3] instead of _test: ## @test xorl %ecx, %ecx ## encoding: [0x31,0xc9] cmpq %rsi, %rdi ## encoding: [0x48,0x39,0xf7] movl $-1, %eax ## encoding: [0xb8,0xff,0xff,0xff,0xff] cmovael %ecx, %eax ## encoding: [0x0f,0x43,0xc1] ret ## encoding: [0xc3] llvm-svn: 122451
2010-12-23 07:09:28 +08:00
define i32 @test13(i32 %a, i32 %b) nounwind {
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; GENERIC-LABEL: test13:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; GENERIC: ## %bb.0:
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; GENERIC-NEXT: cmpl %esi, %edi
; GENERIC-NEXT: sbbl %eax, %eax
; GENERIC-NEXT: retq
;
; ATOM-LABEL: test13:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; ATOM: ## %bb.0:
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; ATOM-NEXT: cmpl %esi, %edi
; ATOM-NEXT: sbbl %eax, %eax
; ATOM-NEXT: nop
; ATOM-NEXT: nop
; ATOM-NEXT: nop
; ATOM-NEXT: nop
; ATOM-NEXT: retq
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
;
; MCU-LABEL: test13:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: cmpl %edx, %eax
; MCU-NEXT: sbbl %eax, %eax
; MCU-NEXT: retl
X86: Lower a select directly to a setcc_carry if possible. int test(unsigned long a, unsigned long b) { return -(a < b); } compiles to _test: ## @test cmpq %rsi, %rdi ## encoding: [0x48,0x39,0xf7] sbbl %eax, %eax ## encoding: [0x19,0xc0] ret ## encoding: [0xc3] instead of _test: ## @test xorl %ecx, %ecx ## encoding: [0x31,0xc9] cmpq %rsi, %rdi ## encoding: [0x48,0x39,0xf7] movl $-1, %eax ## encoding: [0xb8,0xff,0xff,0xff,0xff] cmovael %ecx, %eax ## encoding: [0x0f,0x43,0xc1] ret ## encoding: [0xc3] llvm-svn: 122451
2010-12-23 07:09:28 +08:00
%c = icmp ult i32 %a, %b
%d = sext i1 %c to i32
ret i32 %d
}
Teach X86ISelLowering that the second result of X86ISD::UMUL is a flags result. This allows us to compile: void *test12(long count) { return new int[count]; } into: test12: movl $4, %ecx movq %rdi, %rax mulq %rcx movq $-1, %rdi cmovnoq %rax, %rdi jmp __Znam ## TAILCALL instead of: test12: movl $4, %ecx movq %rdi, %rax mulq %rcx seto %cl testb %cl, %cl movq $-1, %rdi cmoveq %rax, %rdi jmp __Znam Of course it would be even better if the regalloc inverted the cmov to 'cmovoq', which would eliminate the need for the 'movq %rdi, %rax'. llvm-svn: 120936
2010-12-05 15:49:54 +08:00
X86: Lower a select directly to a setcc_carry if possible. int test(unsigned long a, unsigned long b) { return -(a < b); } compiles to _test: ## @test cmpq %rsi, %rdi ## encoding: [0x48,0x39,0xf7] sbbl %eax, %eax ## encoding: [0x19,0xc0] ret ## encoding: [0xc3] instead of _test: ## @test xorl %ecx, %ecx ## encoding: [0x31,0xc9] cmpq %rsi, %rdi ## encoding: [0x48,0x39,0xf7] movl $-1, %eax ## encoding: [0xb8,0xff,0xff,0xff,0xff] cmovael %ecx, %eax ## encoding: [0x0f,0x43,0xc1] ret ## encoding: [0xc3] llvm-svn: 122451
2010-12-23 07:09:28 +08:00
define i32 @test14(i32 %a, i32 %b) nounwind {
[x86] use more shift or LEA for select-of-constants (2nd try) The previous rev (r310208) failed to account for overflow when subtracting the constants to see if they're suitable for shift/lea. This version add a check for that and more test were added in r310490. We can convert any select-of-constants to math ops: http://rise4fun.com/Alive/d7d For this patch, I'm enhancing an existing x86 transform that uses fake multiplies (they always become shl/lea) to avoid cmov or branching. The current code misses cases where we have a negative constant and a positive constant, so this is just trying to plug that hole. The DAGCombiner diff prevents us from hitting a terrible inefficiency: we can start with a select in IR, create a select DAG node, convert it into a sext, convert it back into a select, and then lower it to sext machine code. Some notes about the test diffs: 1. 2010-08-04-MaskedSignedCompare.ll - We were creating control flow that didn't exist in the IR. 2. memcmp.ll - Choose -1 or 1 is the case that got me looking at this again. We could avoid the push/pop in some cases if we used 'movzbl %al' instead of an xor on a different reg? That's a post-DAG problem though. 3. mul-constant-result.ll - The trade-off between sbb+not vs. setne+neg could be addressed if that's a regression, but those would always be nearly equivalent. 4. pr22338.ll and sext-i1.ll - These tests have undef operands, so we don't actually care about these diffs. 5. sbb.ll - This shows a win for what is likely a common case: choose -1 or 0. 6. select.ll - There's another borderline case here: cmp+sbb+or vs. test+set+lea? Also, sbb+not vs. setae+neg shows up again. 7. select_const.ll - These are motivating cases for the enhancement; replace cmov with cheaper ops. Assembly differences between movzbl and xor to avoid a partial reg stall are caused later by the X86 Fixup SetCC pass. Differential Revision: https://reviews.llvm.org/D35340 llvm-svn: 310717
2017-08-11 23:44:14 +08:00
; CHECK-LABEL: test14:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: ## %bb.0:
[x86] use more shift or LEA for select-of-constants (2nd try) The previous rev (r310208) failed to account for overflow when subtracting the constants to see if they're suitable for shift/lea. This version add a check for that and more test were added in r310490. We can convert any select-of-constants to math ops: http://rise4fun.com/Alive/d7d For this patch, I'm enhancing an existing x86 transform that uses fake multiplies (they always become shl/lea) to avoid cmov or branching. The current code misses cases where we have a negative constant and a positive constant, so this is just trying to plug that hole. The DAGCombiner diff prevents us from hitting a terrible inefficiency: we can start with a select in IR, create a select DAG node, convert it into a sext, convert it back into a select, and then lower it to sext machine code. Some notes about the test diffs: 1. 2010-08-04-MaskedSignedCompare.ll - We were creating control flow that didn't exist in the IR. 2. memcmp.ll - Choose -1 or 1 is the case that got me looking at this again. We could avoid the push/pop in some cases if we used 'movzbl %al' instead of an xor on a different reg? That's a post-DAG problem though. 3. mul-constant-result.ll - The trade-off between sbb+not vs. setne+neg could be addressed if that's a regression, but those would always be nearly equivalent. 4. pr22338.ll and sext-i1.ll - These tests have undef operands, so we don't actually care about these diffs. 5. sbb.ll - This shows a win for what is likely a common case: choose -1 or 0. 6. select.ll - There's another borderline case here: cmp+sbb+or vs. test+set+lea? Also, sbb+not vs. setae+neg shows up again. 7. select_const.ll - These are motivating cases for the enhancement; replace cmov with cheaper ops. Assembly differences between movzbl and xor to avoid a partial reg stall are caused later by the X86 Fixup SetCC pass. Differential Revision: https://reviews.llvm.org/D35340 llvm-svn: 310717
2017-08-11 23:44:14 +08:00
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: cmpl %esi, %edi
; CHECK-NEXT: setae %al
; CHECK-NEXT: negl %eax
; CHECK-NEXT: retq
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
;
; MCU-LABEL: test14:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0:
[x86] use more shift or LEA for select-of-constants (2nd try) The previous rev (r310208) failed to account for overflow when subtracting the constants to see if they're suitable for shift/lea. This version add a check for that and more test were added in r310490. We can convert any select-of-constants to math ops: http://rise4fun.com/Alive/d7d For this patch, I'm enhancing an existing x86 transform that uses fake multiplies (they always become shl/lea) to avoid cmov or branching. The current code misses cases where we have a negative constant and a positive constant, so this is just trying to plug that hole. The DAGCombiner diff prevents us from hitting a terrible inefficiency: we can start with a select in IR, create a select DAG node, convert it into a sext, convert it back into a select, and then lower it to sext machine code. Some notes about the test diffs: 1. 2010-08-04-MaskedSignedCompare.ll - We were creating control flow that didn't exist in the IR. 2. memcmp.ll - Choose -1 or 1 is the case that got me looking at this again. We could avoid the push/pop in some cases if we used 'movzbl %al' instead of an xor on a different reg? That's a post-DAG problem though. 3. mul-constant-result.ll - The trade-off between sbb+not vs. setne+neg could be addressed if that's a regression, but those would always be nearly equivalent. 4. pr22338.ll and sext-i1.ll - These tests have undef operands, so we don't actually care about these diffs. 5. sbb.ll - This shows a win for what is likely a common case: choose -1 or 0. 6. select.ll - There's another borderline case here: cmp+sbb+or vs. test+set+lea? Also, sbb+not vs. setae+neg shows up again. 7. select_const.ll - These are motivating cases for the enhancement; replace cmov with cheaper ops. Assembly differences between movzbl and xor to avoid a partial reg stall are caused later by the X86 Fixup SetCC pass. Differential Revision: https://reviews.llvm.org/D35340 llvm-svn: 310717
2017-08-11 23:44:14 +08:00
; MCU-NEXT: xorl %ecx, %ecx
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: cmpl %edx, %eax
[x86] use more shift or LEA for select-of-constants (2nd try) The previous rev (r310208) failed to account for overflow when subtracting the constants to see if they're suitable for shift/lea. This version add a check for that and more test were added in r310490. We can convert any select-of-constants to math ops: http://rise4fun.com/Alive/d7d For this patch, I'm enhancing an existing x86 transform that uses fake multiplies (they always become shl/lea) to avoid cmov or branching. The current code misses cases where we have a negative constant and a positive constant, so this is just trying to plug that hole. The DAGCombiner diff prevents us from hitting a terrible inefficiency: we can start with a select in IR, create a select DAG node, convert it into a sext, convert it back into a select, and then lower it to sext machine code. Some notes about the test diffs: 1. 2010-08-04-MaskedSignedCompare.ll - We were creating control flow that didn't exist in the IR. 2. memcmp.ll - Choose -1 or 1 is the case that got me looking at this again. We could avoid the push/pop in some cases if we used 'movzbl %al' instead of an xor on a different reg? That's a post-DAG problem though. 3. mul-constant-result.ll - The trade-off between sbb+not vs. setne+neg could be addressed if that's a regression, but those would always be nearly equivalent. 4. pr22338.ll and sext-i1.ll - These tests have undef operands, so we don't actually care about these diffs. 5. sbb.ll - This shows a win for what is likely a common case: choose -1 or 0. 6. select.ll - There's another borderline case here: cmp+sbb+or vs. test+set+lea? Also, sbb+not vs. setae+neg shows up again. 7. select_const.ll - These are motivating cases for the enhancement; replace cmov with cheaper ops. Assembly differences between movzbl and xor to avoid a partial reg stall are caused later by the X86 Fixup SetCC pass. Differential Revision: https://reviews.llvm.org/D35340 llvm-svn: 310717
2017-08-11 23:44:14 +08:00
; MCU-NEXT: setae %cl
; MCU-NEXT: negl %ecx
; MCU-NEXT: movl %ecx, %eax
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: retl
X86: Lower a select directly to a setcc_carry if possible. int test(unsigned long a, unsigned long b) { return -(a < b); } compiles to _test: ## @test cmpq %rsi, %rdi ## encoding: [0x48,0x39,0xf7] sbbl %eax, %eax ## encoding: [0x19,0xc0] ret ## encoding: [0xc3] instead of _test: ## @test xorl %ecx, %ecx ## encoding: [0x31,0xc9] cmpq %rsi, %rdi ## encoding: [0x48,0x39,0xf7] movl $-1, %eax ## encoding: [0xb8,0xff,0xff,0xff,0xff] cmovael %ecx, %eax ## encoding: [0x0f,0x43,0xc1] ret ## encoding: [0xc3] llvm-svn: 122451
2010-12-23 07:09:28 +08:00
%c = icmp uge i32 %a, %b
%d = sext i1 %c to i32
ret i32 %d
}
Improve an integer select optimization in two ways: 1. generalize (select (x == 0), -1, 0) -> (sign_bit (x - 1)) to: (select (x == 0), -1, y) -> (sign_bit (x - 1)) | y 2. Handle the identical pattern that happens with !=: (select (x != 0), y, -1) -> (sign_bit (x - 1)) | y cmov is often high latency and can't fold immediates or memory operands. For example for (x == 0) ? -1 : 1, before we got: < testb %sil, %sil < movl $-1, %ecx < movl $1, %eax < cmovel %ecx, %eax now we get: > cmpb $1, %sil > sbbl %eax, %eax > orl $1, %eax llvm-svn: 120929
2010-12-05 09:23:24 +08:00
X86: optimization for -(x != 0) This patch will optimize -(x != 0) on X86 FROM cmpl $0x01,%edi sbbl %eax,%eax notl %eax TO negl %edi sbbl %eax %eax In order to generate negl, I added patterns in Target/X86/X86InstrCompiler.td: def : Pat<(X86sub_flag 0, GR32:$src), (NEG32r GR32:$src)>; rdar: 10961709 llvm-svn: 156312
2012-05-08 02:06:23 +08:00
; rdar://10961709
define i32 @test15(i32 %x) nounwind {
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; GENERIC-LABEL: test15:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; GENERIC: ## %bb.0: ## %entry
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; GENERIC-NEXT: negl %edi
; GENERIC-NEXT: sbbl %eax, %eax
; GENERIC-NEXT: retq
;
; ATOM-LABEL: test15:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; ATOM: ## %bb.0: ## %entry
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; ATOM-NEXT: negl %edi
; ATOM-NEXT: sbbl %eax, %eax
; ATOM-NEXT: nop
; ATOM-NEXT: nop
; ATOM-NEXT: nop
; ATOM-NEXT: nop
; ATOM-NEXT: retq
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
;
; MCU-LABEL: test15:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0: # %entry
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: negl %eax
; MCU-NEXT: sbbl %eax, %eax
; MCU-NEXT: retl
X86: optimization for -(x != 0) This patch will optimize -(x != 0) on X86 FROM cmpl $0x01,%edi sbbl %eax,%eax notl %eax TO negl %edi sbbl %eax %eax In order to generate negl, I added patterns in Target/X86/X86InstrCompiler.td: def : Pat<(X86sub_flag 0, GR32:$src), (NEG32r GR32:$src)>; rdar: 10961709 llvm-svn: 156312
2012-05-08 02:06:23 +08:00
entry:
%cmp = icmp ne i32 %x, 0
%sub = sext i1 %cmp to i32
ret i32 %sub
}
define i64 @test16(i64 %x) nounwind uwtable readnone ssp {
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; GENERIC-LABEL: test16:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; GENERIC: ## %bb.0: ## %entry
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; GENERIC-NEXT: negq %rdi
; GENERIC-NEXT: sbbq %rax, %rax
; GENERIC-NEXT: retq
;
; ATOM-LABEL: test16:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; ATOM: ## %bb.0: ## %entry
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; ATOM-NEXT: negq %rdi
; ATOM-NEXT: sbbq %rax, %rax
; ATOM-NEXT: nop
; ATOM-NEXT: nop
; ATOM-NEXT: nop
; ATOM-NEXT: nop
; ATOM-NEXT: retq
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
;
; MCU-LABEL: test16:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0: # %entry
[x86] use more shift or LEA for select-of-constants (2nd try) The previous rev (r310208) failed to account for overflow when subtracting the constants to see if they're suitable for shift/lea. This version add a check for that and more test were added in r310490. We can convert any select-of-constants to math ops: http://rise4fun.com/Alive/d7d For this patch, I'm enhancing an existing x86 transform that uses fake multiplies (they always become shl/lea) to avoid cmov or branching. The current code misses cases where we have a negative constant and a positive constant, so this is just trying to plug that hole. The DAGCombiner diff prevents us from hitting a terrible inefficiency: we can start with a select in IR, create a select DAG node, convert it into a sext, convert it back into a select, and then lower it to sext machine code. Some notes about the test diffs: 1. 2010-08-04-MaskedSignedCompare.ll - We were creating control flow that didn't exist in the IR. 2. memcmp.ll - Choose -1 or 1 is the case that got me looking at this again. We could avoid the push/pop in some cases if we used 'movzbl %al' instead of an xor on a different reg? That's a post-DAG problem though. 3. mul-constant-result.ll - The trade-off between sbb+not vs. setne+neg could be addressed if that's a regression, but those would always be nearly equivalent. 4. pr22338.ll and sext-i1.ll - These tests have undef operands, so we don't actually care about these diffs. 5. sbb.ll - This shows a win for what is likely a common case: choose -1 or 0. 6. select.ll - There's another borderline case here: cmp+sbb+or vs. test+set+lea? Also, sbb+not vs. setae+neg shows up again. 7. select_const.ll - These are motivating cases for the enhancement; replace cmov with cheaper ops. Assembly differences between movzbl and xor to avoid a partial reg stall are caused later by the X86 Fixup SetCC pass. Differential Revision: https://reviews.llvm.org/D35340 llvm-svn: 310717
2017-08-11 23:44:14 +08:00
; MCU-NEXT: movl %eax, %ecx
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: xorl %eax, %eax
[x86] use more shift or LEA for select-of-constants (2nd try) The previous rev (r310208) failed to account for overflow when subtracting the constants to see if they're suitable for shift/lea. This version add a check for that and more test were added in r310490. We can convert any select-of-constants to math ops: http://rise4fun.com/Alive/d7d For this patch, I'm enhancing an existing x86 transform that uses fake multiplies (they always become shl/lea) to avoid cmov or branching. The current code misses cases where we have a negative constant and a positive constant, so this is just trying to plug that hole. The DAGCombiner diff prevents us from hitting a terrible inefficiency: we can start with a select in IR, create a select DAG node, convert it into a sext, convert it back into a select, and then lower it to sext machine code. Some notes about the test diffs: 1. 2010-08-04-MaskedSignedCompare.ll - We were creating control flow that didn't exist in the IR. 2. memcmp.ll - Choose -1 or 1 is the case that got me looking at this again. We could avoid the push/pop in some cases if we used 'movzbl %al' instead of an xor on a different reg? That's a post-DAG problem though. 3. mul-constant-result.ll - The trade-off between sbb+not vs. setne+neg could be addressed if that's a regression, but those would always be nearly equivalent. 4. pr22338.ll and sext-i1.ll - These tests have undef operands, so we don't actually care about these diffs. 5. sbb.ll - This shows a win for what is likely a common case: choose -1 or 0. 6. select.ll - There's another borderline case here: cmp+sbb+or vs. test+set+lea? Also, sbb+not vs. setae+neg shows up again. 7. select_const.ll - These are motivating cases for the enhancement; replace cmov with cheaper ops. Assembly differences between movzbl and xor to avoid a partial reg stall are caused later by the X86 Fixup SetCC pass. Differential Revision: https://reviews.llvm.org/D35340 llvm-svn: 310717
2017-08-11 23:44:14 +08:00
; MCU-NEXT: orl %edx, %ecx
; MCU-NEXT: setne %al
; MCU-NEXT: negl %eax
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: movl %eax, %edx
; MCU-NEXT: retl
X86: optimization for -(x != 0) This patch will optimize -(x != 0) on X86 FROM cmpl $0x01,%edi sbbl %eax,%eax notl %eax TO negl %edi sbbl %eax %eax In order to generate negl, I added patterns in Target/X86/X86InstrCompiler.td: def : Pat<(X86sub_flag 0, GR32:$src), (NEG32r GR32:$src)>; rdar: 10961709 llvm-svn: 156312
2012-05-08 02:06:23 +08:00
entry:
%cmp = icmp ne i64 %x, 0
%conv1 = sext i1 %cmp to i64
ret i64 %conv1
}
define i16 @test17(i16 %x) nounwind {
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; GENERIC-LABEL: test17:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; GENERIC: ## %bb.0: ## %entry
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; GENERIC-NEXT: negw %di
[x86] use more shift or LEA for select-of-constants (2nd try) The previous rev (r310208) failed to account for overflow when subtracting the constants to see if they're suitable for shift/lea. This version add a check for that and more test were added in r310490. We can convert any select-of-constants to math ops: http://rise4fun.com/Alive/d7d For this patch, I'm enhancing an existing x86 transform that uses fake multiplies (they always become shl/lea) to avoid cmov or branching. The current code misses cases where we have a negative constant and a positive constant, so this is just trying to plug that hole. The DAGCombiner diff prevents us from hitting a terrible inefficiency: we can start with a select in IR, create a select DAG node, convert it into a sext, convert it back into a select, and then lower it to sext machine code. Some notes about the test diffs: 1. 2010-08-04-MaskedSignedCompare.ll - We were creating control flow that didn't exist in the IR. 2. memcmp.ll - Choose -1 or 1 is the case that got me looking at this again. We could avoid the push/pop in some cases if we used 'movzbl %al' instead of an xor on a different reg? That's a post-DAG problem though. 3. mul-constant-result.ll - The trade-off between sbb+not vs. setne+neg could be addressed if that's a regression, but those would always be nearly equivalent. 4. pr22338.ll and sext-i1.ll - These tests have undef operands, so we don't actually care about these diffs. 5. sbb.ll - This shows a win for what is likely a common case: choose -1 or 0. 6. select.ll - There's another borderline case here: cmp+sbb+or vs. test+set+lea? Also, sbb+not vs. setae+neg shows up again. 7. select_const.ll - These are motivating cases for the enhancement; replace cmov with cheaper ops. Assembly differences between movzbl and xor to avoid a partial reg stall are caused later by the X86 Fixup SetCC pass. Differential Revision: https://reviews.llvm.org/D35340 llvm-svn: 310717
2017-08-11 23:44:14 +08:00
; GENERIC-NEXT: sbbl %eax, %eax
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; GENERIC-NEXT: ## kill: def $ax killed $ax killed $eax
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; GENERIC-NEXT: retq
;
; ATOM-LABEL: test17:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; ATOM: ## %bb.0: ## %entry
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; ATOM-NEXT: negw %di
[x86] use more shift or LEA for select-of-constants (2nd try) The previous rev (r310208) failed to account for overflow when subtracting the constants to see if they're suitable for shift/lea. This version add a check for that and more test were added in r310490. We can convert any select-of-constants to math ops: http://rise4fun.com/Alive/d7d For this patch, I'm enhancing an existing x86 transform that uses fake multiplies (they always become shl/lea) to avoid cmov or branching. The current code misses cases where we have a negative constant and a positive constant, so this is just trying to plug that hole. The DAGCombiner diff prevents us from hitting a terrible inefficiency: we can start with a select in IR, create a select DAG node, convert it into a sext, convert it back into a select, and then lower it to sext machine code. Some notes about the test diffs: 1. 2010-08-04-MaskedSignedCompare.ll - We were creating control flow that didn't exist in the IR. 2. memcmp.ll - Choose -1 or 1 is the case that got me looking at this again. We could avoid the push/pop in some cases if we used 'movzbl %al' instead of an xor on a different reg? That's a post-DAG problem though. 3. mul-constant-result.ll - The trade-off between sbb+not vs. setne+neg could be addressed if that's a regression, but those would always be nearly equivalent. 4. pr22338.ll and sext-i1.ll - These tests have undef operands, so we don't actually care about these diffs. 5. sbb.ll - This shows a win for what is likely a common case: choose -1 or 0. 6. select.ll - There's another borderline case here: cmp+sbb+or vs. test+set+lea? Also, sbb+not vs. setae+neg shows up again. 7. select_const.ll - These are motivating cases for the enhancement; replace cmov with cheaper ops. Assembly differences between movzbl and xor to avoid a partial reg stall are caused later by the X86 Fixup SetCC pass. Differential Revision: https://reviews.llvm.org/D35340 llvm-svn: 310717
2017-08-11 23:44:14 +08:00
; ATOM-NEXT: sbbl %eax, %eax
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; ATOM-NEXT: ## kill: def $ax killed $ax killed $eax
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; ATOM-NEXT: nop
; ATOM-NEXT: nop
; ATOM-NEXT: nop
; ATOM-NEXT: nop
; ATOM-NEXT: retq
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
;
; MCU-LABEL: test17:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0: # %entry
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: negw %ax
[x86] use more shift or LEA for select-of-constants (2nd try) The previous rev (r310208) failed to account for overflow when subtracting the constants to see if they're suitable for shift/lea. This version add a check for that and more test were added in r310490. We can convert any select-of-constants to math ops: http://rise4fun.com/Alive/d7d For this patch, I'm enhancing an existing x86 transform that uses fake multiplies (they always become shl/lea) to avoid cmov or branching. The current code misses cases where we have a negative constant and a positive constant, so this is just trying to plug that hole. The DAGCombiner diff prevents us from hitting a terrible inefficiency: we can start with a select in IR, create a select DAG node, convert it into a sext, convert it back into a select, and then lower it to sext machine code. Some notes about the test diffs: 1. 2010-08-04-MaskedSignedCompare.ll - We were creating control flow that didn't exist in the IR. 2. memcmp.ll - Choose -1 or 1 is the case that got me looking at this again. We could avoid the push/pop in some cases if we used 'movzbl %al' instead of an xor on a different reg? That's a post-DAG problem though. 3. mul-constant-result.ll - The trade-off between sbb+not vs. setne+neg could be addressed if that's a regression, but those would always be nearly equivalent. 4. pr22338.ll and sext-i1.ll - These tests have undef operands, so we don't actually care about these diffs. 5. sbb.ll - This shows a win for what is likely a common case: choose -1 or 0. 6. select.ll - There's another borderline case here: cmp+sbb+or vs. test+set+lea? Also, sbb+not vs. setae+neg shows up again. 7. select_const.ll - These are motivating cases for the enhancement; replace cmov with cheaper ops. Assembly differences between movzbl and xor to avoid a partial reg stall are caused later by the X86 Fixup SetCC pass. Differential Revision: https://reviews.llvm.org/D35340 llvm-svn: 310717
2017-08-11 23:44:14 +08:00
; MCU-NEXT: sbbl %eax, %eax
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; MCU-NEXT: # kill: def $ax killed $ax killed $eax
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: retl
X86: optimization for -(x != 0) This patch will optimize -(x != 0) on X86 FROM cmpl $0x01,%edi sbbl %eax,%eax notl %eax TO negl %edi sbbl %eax %eax In order to generate negl, I added patterns in Target/X86/X86InstrCompiler.td: def : Pat<(X86sub_flag 0, GR32:$src), (NEG32r GR32:$src)>; rdar: 10961709 llvm-svn: 156312
2012-05-08 02:06:23 +08:00
entry:
%cmp = icmp ne i16 %x, 0
%sub = sext i1 %cmp to i16
ret i16 %sub
}
X86: Promote i8 cmov when both operands are coming from truncates of the same width. X86 doesn't have i8 cmovs so isel would emit a branch. Emitting branches at this level is often not a good idea because it's too late for many optimizations to kick in. This solution doesn't add any extensions (truncs are free) and tries to avoid introducing partial register stalls by filtering direct copyfromregs. I'm seeing a ~10% speedup on reading a random .png file with libpng15 via graphicsmagick on x86_64/westmere, but YMMV depending on the microarchitecture. llvm-svn: 165868
2012-10-13 18:39:49 +08:00
define i8 @test18(i32 %x, i8 zeroext %a, i8 zeroext %b) nounwind {
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; GENERIC-LABEL: test18:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; GENERIC: ## %bb.0:
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; GENERIC-NEXT: cmpl $15, %edi
; GENERIC-NEXT: cmovgel %edx, %esi
; GENERIC-NEXT: movl %esi, %eax
; GENERIC-NEXT: retq
;
; ATOM-LABEL: test18:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; ATOM: ## %bb.0:
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; ATOM-NEXT: cmpl $15, %edi
; ATOM-NEXT: cmovgel %edx, %esi
; ATOM-NEXT: movl %esi, %eax
; ATOM-NEXT: nop
; ATOM-NEXT: nop
; ATOM-NEXT: retq
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
;
; MCU-LABEL: test18:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: cmpl $15, %eax
; MCU-NEXT: jl .LBB20_2
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU-NEXT: # %bb.1:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: movl %ecx, %edx
; MCU-NEXT: .LBB20_2:
; MCU-NEXT: movl %edx, %eax
; MCU-NEXT: retl
X86: Promote i8 cmov when both operands are coming from truncates of the same width. X86 doesn't have i8 cmovs so isel would emit a branch. Emitting branches at this level is often not a good idea because it's too late for many optimizations to kick in. This solution doesn't add any extensions (truncs are free) and tries to avoid introducing partial register stalls by filtering direct copyfromregs. I'm seeing a ~10% speedup on reading a random .png file with libpng15 via graphicsmagick on x86_64/westmere, but YMMV depending on the microarchitecture. llvm-svn: 165868
2012-10-13 18:39:49 +08:00
%cmp = icmp slt i32 %x, 15
%sel = select i1 %cmp, i8 %a, i8 %b
ret i8 %sel
}
Revert "Revert r212640, "Add trunc (select c, a, b) -> select c (trunc a), (trunc b) combine."" Don't try to convert the select condition type. llvm-svn: 212750
2014-07-11 02:21:04 +08:00
define i32 @trunc_select_miscompile(i32 %a, i1 zeroext %cc) {
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; CHECK-LABEL: trunc_select_miscompile:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: ## %bb.0:
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; CHECK-NEXT: orb $2, %sil
; CHECK-NEXT: movl %esi, %ecx
; CHECK-NEXT: shll %cl, %edi
; CHECK-NEXT: movl %edi, %eax
; CHECK-NEXT: retq
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
;
; MCU-LABEL: trunc_select_miscompile:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: orb $2, %dl
; MCU-NEXT: movl %edx, %ecx
; MCU-NEXT: shll %cl, %eax
; MCU-NEXT: retl
Revert "Revert r212640, "Add trunc (select c, a, b) -> select c (trunc a), (trunc b) combine."" Don't try to convert the select condition type. llvm-svn: 212750
2014-07-11 02:21:04 +08:00
%tmp1 = select i1 %cc, i32 3, i32 2
%tmp2 = shl i32 %a, %tmp1
ret i32 %tmp2
[SDAG] Fix a really, really terrible bug in the DAG combiner. This code is completely wrong. It is also dead, as if it were to *ever* run, it would crash. Fortunately, after my work to the combiner, it is at least *possible* to reach the code, and llvm-stress has found a test case. Thanks to Patrick for reporting. It would be really good if anyone who remembers how this code works and what it was intended to do could add some more obvious test coverage instead of my completely contrived and reduced test case. My test case was so brittle I left a bread crumb comment in it to help the next person to stumble on it and not know what it was actually testing for. llvm-svn: 214785
2014-08-05 05:29:59 +08:00
}
reproducer for pr29002 https://reviews.llvm.org/D26449 llvm-svn: 286470
2016-11-11 00:27:27 +08:00
; reproducer for pr29002
define void @clamp_i8(i32 %src, i8* %dst) {
DAGCombiner: fix combine of trunc and select bugzilla: https://llvm.org/bugs/show_bug.cgi?id=29002 pr29002 Differential Revision: https://reviews.llvm.org/D26449 llvm-svn: 286938
2016-11-15 15:55:22 +08:00
; GENERIC-LABEL: clamp_i8:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; GENERIC: ## %bb.0:
DAGCombiner: fix combine of trunc and select bugzilla: https://llvm.org/bugs/show_bug.cgi?id=29002 pr29002 Differential Revision: https://reviews.llvm.org/D26449 llvm-svn: 286938
2016-11-15 15:55:22 +08:00
; GENERIC-NEXT: cmpl $127, %edi
; GENERIC-NEXT: movl $127, %eax
; GENERIC-NEXT: cmovlel %edi, %eax
; GENERIC-NEXT: cmpl $-128, %eax
; GENERIC-NEXT: movb $-128, %cl
; GENERIC-NEXT: jl LBB22_2
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; GENERIC-NEXT: ## %bb.1:
DAGCombiner: fix combine of trunc and select bugzilla: https://llvm.org/bugs/show_bug.cgi?id=29002 pr29002 Differential Revision: https://reviews.llvm.org/D26449 llvm-svn: 286938
2016-11-15 15:55:22 +08:00
; GENERIC-NEXT: movl %eax, %ecx
; GENERIC-NEXT: LBB22_2:
; GENERIC-NEXT: movb %cl, (%rsi)
; GENERIC-NEXT: retq
;
; ATOM-LABEL: clamp_i8:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; ATOM: ## %bb.0:
DAGCombiner: fix combine of trunc and select bugzilla: https://llvm.org/bugs/show_bug.cgi?id=29002 pr29002 Differential Revision: https://reviews.llvm.org/D26449 llvm-svn: 286938
2016-11-15 15:55:22 +08:00
; ATOM-NEXT: cmpl $127, %edi
; ATOM-NEXT: movl $127, %eax
; ATOM-NEXT: cmovlel %edi, %eax
; ATOM-NEXT: movb $-128, %cl
; ATOM-NEXT: cmpl $-128, %eax
; ATOM-NEXT: jl LBB22_2
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; ATOM-NEXT: ## %bb.1:
DAGCombiner: fix combine of trunc and select bugzilla: https://llvm.org/bugs/show_bug.cgi?id=29002 pr29002 Differential Revision: https://reviews.llvm.org/D26449 llvm-svn: 286938
2016-11-15 15:55:22 +08:00
; ATOM-NEXT: movl %eax, %ecx
; ATOM-NEXT: LBB22_2:
; ATOM-NEXT: movb %cl, (%rsi)
; ATOM-NEXT: retq
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
;
; MCU-LABEL: clamp_i8:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: cmpl $127, %eax
; MCU-NEXT: movl $127, %ecx
; MCU-NEXT: jg .LBB22_2
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU-NEXT: # %bb.1:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: movl %eax, %ecx
; MCU-NEXT: .LBB22_2:
; MCU-NEXT: cmpl $-128, %ecx
; MCU-NEXT: movb $-128, %al
; MCU-NEXT: jl .LBB22_4
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU-NEXT: # %bb.3:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: movl %ecx, %eax
; MCU-NEXT: .LBB22_4:
; MCU-NEXT: movb %al, (%edx)
; MCU-NEXT: retl
reproducer for pr29002 https://reviews.llvm.org/D26449 llvm-svn: 286470
2016-11-11 00:27:27 +08:00
%cmp = icmp sgt i32 %src, 127
%sel1 = select i1 %cmp, i32 127, i32 %src
%cmp1 = icmp slt i32 %sel1, -128
%sel2 = select i1 %cmp1, i32 -128, i32 %sel1
%conv = trunc i32 %sel2 to i8
store i8 %conv, i8* %dst, align 2
ret void
}
; reproducer for pr29002
define void @clamp(i32 %src, i16* %dst) {
; GENERIC-LABEL: clamp:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; GENERIC: ## %bb.0:
reproducer for pr29002 https://reviews.llvm.org/D26449 llvm-svn: 286470
2016-11-11 00:27:27 +08:00
; GENERIC-NEXT: cmpl $32767, %edi ## imm = 0x7FFF
; GENERIC-NEXT: movl $32767, %eax ## imm = 0x7FFF
; GENERIC-NEXT: cmovlel %edi, %eax
; GENERIC-NEXT: cmpl $-32768, %eax ## imm = 0x8000
[X86] Promote 16-bit cmovs to 32-bits This allows us to avoid an opsize prefix. And forcing some move immediates to i32 avoids a length changing prefix on those instructions. This mostly replaces the existing combine we had for zext/sext+cmov of constants. I left in a case for sign extending a 32 bit cmov of constants to 64 bits. Differential Revision: https://reviews.llvm.org/D43327 llvm-svn: 325601
2018-02-21 01:41:00 +08:00
; GENERIC-NEXT: movl $32768, %ecx ## imm = 0x8000
; GENERIC-NEXT: cmovgel %eax, %ecx
DAGCombiner: fix combine of trunc and select bugzilla: https://llvm.org/bugs/show_bug.cgi?id=29002 pr29002 Differential Revision: https://reviews.llvm.org/D26449 llvm-svn: 286938
2016-11-15 15:55:22 +08:00
; GENERIC-NEXT: movw %cx, (%rsi)
reproducer for pr29002 https://reviews.llvm.org/D26449 llvm-svn: 286470
2016-11-11 00:27:27 +08:00
; GENERIC-NEXT: retq
;
; ATOM-LABEL: clamp:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; ATOM: ## %bb.0:
reproducer for pr29002 https://reviews.llvm.org/D26449 llvm-svn: 286470
2016-11-11 00:27:27 +08:00
; ATOM-NEXT: cmpl $32767, %edi ## imm = 0x7FFF
; ATOM-NEXT: movl $32767, %eax ## imm = 0x7FFF
; ATOM-NEXT: cmovlel %edi, %eax
[X86] Promote 16-bit cmovs to 32-bits This allows us to avoid an opsize prefix. And forcing some move immediates to i32 avoids a length changing prefix on those instructions. This mostly replaces the existing combine we had for zext/sext+cmov of constants. I left in a case for sign extending a 32 bit cmov of constants to 64 bits. Differential Revision: https://reviews.llvm.org/D43327 llvm-svn: 325601
2018-02-21 01:41:00 +08:00
; ATOM-NEXT: movl $32768, %ecx ## imm = 0x8000
reproducer for pr29002 https://reviews.llvm.org/D26449 llvm-svn: 286470
2016-11-11 00:27:27 +08:00
; ATOM-NEXT: cmpl $-32768, %eax ## imm = 0x8000
[X86] Promote 16-bit cmovs to 32-bits This allows us to avoid an opsize prefix. And forcing some move immediates to i32 avoids a length changing prefix on those instructions. This mostly replaces the existing combine we had for zext/sext+cmov of constants. I left in a case for sign extending a 32 bit cmov of constants to 64 bits. Differential Revision: https://reviews.llvm.org/D43327 llvm-svn: 325601
2018-02-21 01:41:00 +08:00
; ATOM-NEXT: cmovgel %eax, %ecx
DAGCombiner: fix combine of trunc and select bugzilla: https://llvm.org/bugs/show_bug.cgi?id=29002 pr29002 Differential Revision: https://reviews.llvm.org/D26449 llvm-svn: 286938
2016-11-15 15:55:22 +08:00
; ATOM-NEXT: movw %cx, (%rsi)
reproducer for pr29002 https://reviews.llvm.org/D26449 llvm-svn: 286470
2016-11-11 00:27:27 +08:00
; ATOM-NEXT: retq
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
;
; MCU-LABEL: clamp:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: cmpl $32767, %eax # imm = 0x7FFF
; MCU-NEXT: movl $32767, %ecx # imm = 0x7FFF
; MCU-NEXT: jg .LBB23_2
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU-NEXT: # %bb.1:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: movl %eax, %ecx
; MCU-NEXT: .LBB23_2:
; MCU-NEXT: cmpl $-32768, %ecx # imm = 0x8000
[X86] Promote 16-bit cmovs to 32-bits This allows us to avoid an opsize prefix. And forcing some move immediates to i32 avoids a length changing prefix on those instructions. This mostly replaces the existing combine we had for zext/sext+cmov of constants. I left in a case for sign extending a 32 bit cmov of constants to 64 bits. Differential Revision: https://reviews.llvm.org/D43327 llvm-svn: 325601
2018-02-21 01:41:00 +08:00
; MCU-NEXT: movl $32768, %eax # imm = 0x8000
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: jl .LBB23_4
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU-NEXT: # %bb.3:
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: movl %ecx, %eax
; MCU-NEXT: .LBB23_4:
; MCU-NEXT: movw %ax, (%edx)
; MCU-NEXT: retl
reproducer for pr29002 https://reviews.llvm.org/D26449 llvm-svn: 286470
2016-11-11 00:27:27 +08:00
%cmp = icmp sgt i32 %src, 32767
%sel1 = select i1 %cmp, i32 32767, i32 %src
%cmp1 = icmp slt i32 %sel1, -32768
%sel2 = select i1 %cmp1, i32 -32768, i32 %sel1
%conv = trunc i32 %sel2 to i16
store i16 %conv, i16* %dst, align 2
ret void
}
[SDAG] Fix a really, really terrible bug in the DAG combiner. This code is completely wrong. It is also dead, as if it were to *ever* run, it would crash. Fortunately, after my work to the combiner, it is at least *possible* to reach the code, and llvm-stress has found a test case. Thanks to Patrick for reporting. It would be really good if anyone who remembers how this code works and what it was intended to do could add some more obvious test coverage instead of my completely contrived and reduced test case. My test case was so brittle I left a bread crumb comment in it to help the next person to stumble on it and not know what it was actually testing for. llvm-svn: 214785
2014-08-05 05:29:59 +08:00
define void @test19() {
; This is a massive reduction of an llvm-stress test case that generates
; interesting chains feeding setcc and eventually a f32 select operation. This
; is intended to exercise the SELECT formation in the DAG combine simplifying
; a simplified select_cc node. If it it regresses and is no longer triggering
; that code path, it can be deleted.
;
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; CHECK-LABEL: test19:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: ## %bb.0: ## %BB
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; CHECK-NEXT: movl $-1, %eax
; CHECK-NEXT: movb $1, %cl
; CHECK-NEXT: .p2align 4, 0x90
reproducer for pr29002 https://reviews.llvm.org/D26449 llvm-svn: 286470
2016-11-11 00:27:27 +08:00
; CHECK-NEXT: LBB24_1: ## %CF
[X86][SSE] Regenerate select tests llvm-svn: 283674
2016-10-09 05:17:44 +08:00
; CHECK-NEXT: ## =>This Inner Loop Header: Depth=1
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; CHECK-NEXT: testb %cl, %cl
reproducer for pr29002 https://reviews.llvm.org/D26449 llvm-svn: 286470
2016-11-11 00:27:27 +08:00
; CHECK-NEXT: jne LBB24_1
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK-NEXT: ## %bb.2: ## %CF250
reproducer for pr29002 https://reviews.llvm.org/D26449 llvm-svn: 286470
2016-11-11 00:27:27 +08:00
; CHECK-NEXT: ## in Loop: Header=BB24_1 Depth=1
; CHECK-NEXT: jne LBB24_1
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; CHECK-NEXT: .p2align 4, 0x90
reproducer for pr29002 https://reviews.llvm.org/D26449 llvm-svn: 286470
2016-11-11 00:27:27 +08:00
; CHECK-NEXT: LBB24_3: ## %CF242
[X86][SSE] Regenerate select tests llvm-svn: 283674
2016-10-09 05:17:44 +08:00
; CHECK-NEXT: ## =>This Inner Loop Header: Depth=1
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; CHECK-NEXT: cmpl %eax, %eax
; CHECK-NEXT: ucomiss %xmm0, %xmm0
reproducer for pr29002 https://reviews.llvm.org/D26449 llvm-svn: 286470
2016-11-11 00:27:27 +08:00
; CHECK-NEXT: jp LBB24_3
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK-NEXT: ## %bb.4: ## %CF244
[x86] regenerate checks llvm-svn: 281529
2016-09-15 04:16:24 +08:00
; CHECK-NEXT: retq
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
;
; MCU-LABEL: test19:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0: # %BB
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: movl $-1, %ecx
; MCU-NEXT: movb $1, %al
; MCU-NEXT: .p2align 4, 0x90
; MCU-NEXT: .LBB24_1: # %CF
; MCU-NEXT: # =>This Inner Loop Header: Depth=1
; MCU-NEXT: testb %al, %al
; MCU-NEXT: jne .LBB24_1
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU-NEXT: # %bb.2: # %CF250
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: # in Loop: Header=BB24_1 Depth=1
; MCU-NEXT: jne .LBB24_1
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU-NEXT: # %bb.3: # %CF242.preheader
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: fldz
; MCU-NEXT: .p2align 4, 0x90
; MCU-NEXT: .LBB24_4: # %CF242
; MCU-NEXT: # =>This Inner Loop Header: Depth=1
; MCU-NEXT: cmpl %eax, %ecx
; MCU-NEXT: fucom %st(0)
; MCU-NEXT: fnstsw %ax
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; MCU-NEXT: # kill: def $ah killed $ah killed $ax
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: sahf
; MCU-NEXT: jp .LBB24_4
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU-NEXT: # %bb.5: # %CF244
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: fstp %st(0)
; MCU-NEXT: retl
[SDAG] Fix a really, really terrible bug in the DAG combiner. This code is completely wrong. It is also dead, as if it were to *ever* run, it would crash. Fortunately, after my work to the combiner, it is at least *possible* to reach the code, and llvm-stress has found a test case. Thanks to Patrick for reporting. It would be really good if anyone who remembers how this code works and what it was intended to do could add some more obvious test coverage instead of my completely contrived and reduced test case. My test case was so brittle I left a bread crumb comment in it to help the next person to stumble on it and not know what it was actually testing for. llvm-svn: 214785
2014-08-05 05:29:59 +08:00
BB:
br label %CF
CF:
%Cmp10 = icmp ule i8 undef, undef
br i1 %Cmp10, label %CF, label %CF250
CF250:
%E12 = extractelement <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, i32 2
%Cmp32 = icmp ugt i1 %Cmp10, false
br i1 %Cmp32, label %CF, label %CF242
CF242:
%Cmp38 = icmp uge i32 %E12, undef
%FC = uitofp i1 %Cmp38 to float
%Sl59 = select i1 %Cmp32, float %FC, float undef
%Cmp60 = fcmp ugt float undef, undef
br i1 %Cmp60, label %CF242, label %CF244
CF244:
%B122 = fadd float %Sl59, undef
ret void
}
[X86][MCU] replace select with bit manipulation instead of branches Differential Revision: https://reviews.llvm.org/D28354 llvm-svn: 293469
2017-01-30 16:16:59 +08:00
define i16 @select_xor_1(i16 %A, i8 %cond) {
; CHECK-LABEL: select_xor_1:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: ## %bb.0: ## %entry
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; CHECK-NEXT: movl %edi, %eax
; CHECK-NEXT: xorl $43, %eax
; CHECK-NEXT: testb $1, %sil
[X86] Promote 16-bit cmovs to 32-bits This allows us to avoid an opsize prefix. And forcing some move immediates to i32 avoids a length changing prefix on those instructions. This mostly replaces the existing combine we had for zext/sext+cmov of constants. I left in a case for sign extending a 32 bit cmov of constants to 64 bits. Differential Revision: https://reviews.llvm.org/D43327 llvm-svn: 325601
2018-02-21 01:41:00 +08:00
; CHECK-NEXT: cmovel %edi, %eax
; CHECK-NEXT: ## kill: def $ax killed $ax killed $eax
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; CHECK-NEXT: retq
;
; MCU-LABEL: select_xor_1:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0: # %entry
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: andl $1, %edx
; MCU-NEXT: negl %edx
; MCU-NEXT: andl $43, %edx
; MCU-NEXT: xorl %edx, %eax
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; MCU-NEXT: # kill: def $ax killed $ax killed $eax
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: retl
[X86][MCU] replace select with bit manipulation instead of branches Differential Revision: https://reviews.llvm.org/D28354 llvm-svn: 293469
2017-01-30 16:16:59 +08:00
entry:
%and = and i8 %cond, 1
%cmp10 = icmp eq i8 %and, 0
%0 = xor i16 %A, 43
%1 = select i1 %cmp10, i16 %A, i16 %0
ret i16 %1
}
define i32 @select_xor_2(i32 %A, i32 %B, i8 %cond) {
; CHECK-LABEL: select_xor_2:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: ## %bb.0: ## %entry
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; CHECK-NEXT: xorl %edi, %esi
; CHECK-NEXT: testb $1, %dl
; CHECK-NEXT: cmovel %edi, %esi
; CHECK-NEXT: movl %esi, %eax
; CHECK-NEXT: retq
;
; MCU-LABEL: select_xor_2:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0: # %entry
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: andl $1, %ecx
[X86][MCU] replace select with bit manipulation instead of branches Differential Revision: https://reviews.llvm.org/D28354 llvm-svn: 293469
2017-01-30 16:16:59 +08:00
; MCU-NEXT: negl %ecx
; MCU-NEXT: andl %edx, %ecx
; MCU-NEXT: xorl %ecx, %eax
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: retl
[X86][MCU] replace select with bit manipulation instead of branches Differential Revision: https://reviews.llvm.org/D28354 llvm-svn: 293469
2017-01-30 16:16:59 +08:00
entry:
%and = and i8 %cond, 1
%cmp10 = icmp eq i8 %and, 0
%0 = xor i32 %B, %A
%1 = select i1 %cmp10, i32 %A, i32 %0
ret i32 %1
}
define i32 @select_or(i32 %A, i32 %B, i8 %cond) {
; CHECK-LABEL: select_or:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: ## %bb.0: ## %entry
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; CHECK-NEXT: orl %edi, %esi
; CHECK-NEXT: testb $1, %dl
; CHECK-NEXT: cmovel %edi, %esi
; CHECK-NEXT: movl %esi, %eax
; CHECK-NEXT: retq
;
; MCU-LABEL: select_or:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0: # %entry
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: andl $1, %ecx
[X86][MCU] replace select with bit manipulation instead of branches Differential Revision: https://reviews.llvm.org/D28354 llvm-svn: 293469
2017-01-30 16:16:59 +08:00
; MCU-NEXT: negl %ecx
; MCU-NEXT: andl %edx, %ecx
; MCU-NEXT: orl %ecx, %eax
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: retl
[X86][MCU] replace select with bit manipulation instead of branches Differential Revision: https://reviews.llvm.org/D28354 llvm-svn: 293469
2017-01-30 16:16:59 +08:00
entry:
%and = and i8 %cond, 1
%cmp10 = icmp eq i8 %and, 0
%0 = or i32 %B, %A
%1 = select i1 %cmp10, i32 %A, i32 %0
ret i32 %1
}
[X86][MCU] Minor bug fix for r293469 + test case llvm-svn: 293478
2017-01-30 21:14:37 +08:00
define i32 @select_or_1(i32 %A, i32 %B, i32 %cond) {
; CHECK-LABEL: select_or_1:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: ## %bb.0: ## %entry
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; CHECK-NEXT: orl %edi, %esi
; CHECK-NEXT: testb $1, %dl
; CHECK-NEXT: cmovel %edi, %esi
; CHECK-NEXT: movl %esi, %eax
; CHECK-NEXT: retq
;
; MCU-LABEL: select_or_1:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; MCU: # %bb.0: # %entry
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: andl $1, %ecx
[X86][MCU] Minor bug fix for r293469 + test case llvm-svn: 293478
2017-01-30 21:14:37 +08:00
; MCU-NEXT: negl %ecx
; MCU-NEXT: andl %edx, %ecx
; MCU-NEXT: orl %ecx, %eax
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
; MCU-NEXT: retl
[X86][MCU] Minor bug fix for r293469 + test case llvm-svn: 293478
2017-01-30 21:14:37 +08:00
entry:
%and = and i32 %cond, 1
%cmp10 = icmp eq i32 %and, 0
%0 = or i32 %B, %A
%1 = select i1 %cmp10, i32 %A, i32 %0
ret i32 %1
Update various test's codegen. NFC llvm-svn: 296257
2017-02-26 00:46:47 +08:00
}