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/peephole-na-phys-copy-foldi...

413 lines
12 KiB
LLVM
Raw Normal View History

[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
[X86] Update a regexp in a test case to resist register allocation changes. llvm-svn: 268954
2016-05-10 03:01:42 +08:00
; RUN: llc -mtriple=i386-linux-gnu %s -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK32
; RUN: llc -mtriple=x86_64-linux-gnu -mattr=+sahf %s -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK64
MachineInstrBundle: Fix reversed isSuperRegisterEq() call Unfortunately this fix had the effect of exposing the -verify-machineinstrs FIXME of X86InstrInfo.cpp in two testcases for which I disabled it for now. Two testcases also have additional pushq/popq where the corrected code cannot prove that %rax is dead any longer. Looking at the examples, this could potentially be fixed by improving computeRegisterLiveness() to check the live-in lists of the successors blocks when reaching the end of a block. This fixes http://llvm.org/PR25951. llvm-svn: 256799
2016-01-05 08:45:35 +08:00
; TODO: Reenable verify-machineinstrs once the if (!AXDead) // FIXME in
; X86InstrInfo::copyPhysReg() is resolved.
CodeGen peephole: fold redundant phys reg copies Code generation often exposes redundant physical register copies through virtual registers such as: %vreg = COPY %PHYSREG ... %PHYSREG = COPY %vreg There are cases where no intervening clobber of %PHYSREG occurs, and the later copy could therefore be removed. In some cases this further allows us to remove the initial copy. This patch contains a motivating example which comes from the x86 build of Chrome, specifically cc::ResourceProvider::UnlockForRead uses libstdc++'s implementation of hash_map. That example has two tests live at the same time, and after machine sinking LLVM has confused itself enough and things spilling EFLAGS is a great idea even though it's never restored and the comparison results are both live. Before this patch we have: DEC32m %RIP, 1, %noreg, <ga:@L>, %noreg, %EFLAGS<imp-def> %vreg1<def> = COPY %EFLAGS; GR64:%vreg1 %EFLAGS<def> = COPY %vreg1; GR64:%vreg1 JNE_1 <BB#1>, %EFLAGS<imp-use> Both copies are useless. This patch tries to eliminate the later copy in a generic manner. dec is especially confusing to LLVM when compared with sub. I wrote this patch to treat all physical registers generically, but only remove redundant copies of non-allocatable physical registers because the allocatable ones caused issues (e.g. when calling conventions weren't properly modeled) and should be handled later by the register allocator anyways. The following tests used to failed when the patch also replaced allocatable registers: CodeGen/X86/StackColoring.ll CodeGen/X86/avx512-calling-conv.ll CodeGen/X86/copy-propagation.ll CodeGen/X86/inline-asm-fpstack.ll CodeGen/X86/musttail-varargs.ll CodeGen/X86/pop-stack-cleanup.ll CodeGen/X86/preserve_mostcc64.ll CodeGen/X86/tailcallstack64.ll CodeGen/X86/this-return-64.ll This happens because COPY has other special meaning for e.g. dependency breakage and x87 FP stack. Note that all other backends' tests pass. Reviewers: qcolombet Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D15157 llvm-svn: 254665
2015-12-04 07:43:56 +08:00
; The peephole optimizer can elide some physical register copies such as
; EFLAGS. Make sure the flags are used directly, instead of needlessly using
; lahf, when possible.
@L = external global i32
@M = external global i8
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
CodeGen peephole: fold redundant phys reg copies Code generation often exposes redundant physical register copies through virtual registers such as: %vreg = COPY %PHYSREG ... %PHYSREG = COPY %vreg There are cases where no intervening clobber of %PHYSREG occurs, and the later copy could therefore be removed. In some cases this further allows us to remove the initial copy. This patch contains a motivating example which comes from the x86 build of Chrome, specifically cc::ResourceProvider::UnlockForRead uses libstdc++'s implementation of hash_map. That example has two tests live at the same time, and after machine sinking LLVM has confused itself enough and things spilling EFLAGS is a great idea even though it's never restored and the comparison results are both live. Before this patch we have: DEC32m %RIP, 1, %noreg, <ga:@L>, %noreg, %EFLAGS<imp-def> %vreg1<def> = COPY %EFLAGS; GR64:%vreg1 %EFLAGS<def> = COPY %vreg1; GR64:%vreg1 JNE_1 <BB#1>, %EFLAGS<imp-use> Both copies are useless. This patch tries to eliminate the later copy in a generic manner. dec is especially confusing to LLVM when compared with sub. I wrote this patch to treat all physical registers generically, but only remove redundant copies of non-allocatable physical registers because the allocatable ones caused issues (e.g. when calling conventions weren't properly modeled) and should be handled later by the register allocator anyways. The following tests used to failed when the patch also replaced allocatable registers: CodeGen/X86/StackColoring.ll CodeGen/X86/avx512-calling-conv.ll CodeGen/X86/copy-propagation.ll CodeGen/X86/inline-asm-fpstack.ll CodeGen/X86/musttail-varargs.ll CodeGen/X86/pop-stack-cleanup.ll CodeGen/X86/preserve_mostcc64.ll CodeGen/X86/tailcallstack64.ll CodeGen/X86/this-return-64.ll This happens because COPY has other special meaning for e.g. dependency breakage and x87 FP stack. Note that all other backends' tests pass. Reviewers: qcolombet Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D15157 llvm-svn: 254665
2015-12-04 07:43:56 +08:00
declare i32 @bar(i64)
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
define i1 @plus_one() nounwind {
; CHECK32-LABEL: plus_one:
[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
; CHECK32: # %bb.0: # %entry
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK32-NEXT: movb M, %al
; CHECK32-NEXT: incl L
; CHECK32-NEXT: jne .LBB0_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
; CHECK32-NEXT: # %bb.1: # %entry
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK32-NEXT: andb $8, %al
; CHECK32-NEXT: je .LBB0_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
; CHECK32-NEXT: # %bb.3: # %exit2
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK32-NEXT: xorl %eax, %eax
; CHECK32-NEXT: retl
; CHECK32-NEXT: .LBB0_2: # %exit
; CHECK32-NEXT: movb $1, %al
; CHECK32-NEXT: retl
;
; CHECK64-LABEL: plus_one:
[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
; CHECK64: # %bb.0: # %entry
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK64-NEXT: movb {{.*}}(%rip), %al
; CHECK64-NEXT: incl {{.*}}(%rip)
; CHECK64-NEXT: jne .LBB0_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
; CHECK64-NEXT: # %bb.1: # %entry
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK64-NEXT: andb $8, %al
; CHECK64-NEXT: je .LBB0_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
; CHECK64-NEXT: # %bb.3: # %exit2
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK64-NEXT: xorl %eax, %eax
; CHECK64-NEXT: retq
; CHECK64-NEXT: .LBB0_2: # %exit
; CHECK64-NEXT: movb $1, %al
; CHECK64-NEXT: retq
CodeGen peephole: fold redundant phys reg copies Code generation often exposes redundant physical register copies through virtual registers such as: %vreg = COPY %PHYSREG ... %PHYSREG = COPY %vreg There are cases where no intervening clobber of %PHYSREG occurs, and the later copy could therefore be removed. In some cases this further allows us to remove the initial copy. This patch contains a motivating example which comes from the x86 build of Chrome, specifically cc::ResourceProvider::UnlockForRead uses libstdc++'s implementation of hash_map. That example has two tests live at the same time, and after machine sinking LLVM has confused itself enough and things spilling EFLAGS is a great idea even though it's never restored and the comparison results are both live. Before this patch we have: DEC32m %RIP, 1, %noreg, <ga:@L>, %noreg, %EFLAGS<imp-def> %vreg1<def> = COPY %EFLAGS; GR64:%vreg1 %EFLAGS<def> = COPY %vreg1; GR64:%vreg1 JNE_1 <BB#1>, %EFLAGS<imp-use> Both copies are useless. This patch tries to eliminate the later copy in a generic manner. dec is especially confusing to LLVM when compared with sub. I wrote this patch to treat all physical registers generically, but only remove redundant copies of non-allocatable physical registers because the allocatable ones caused issues (e.g. when calling conventions weren't properly modeled) and should be handled later by the register allocator anyways. The following tests used to failed when the patch also replaced allocatable registers: CodeGen/X86/StackColoring.ll CodeGen/X86/avx512-calling-conv.ll CodeGen/X86/copy-propagation.ll CodeGen/X86/inline-asm-fpstack.ll CodeGen/X86/musttail-varargs.ll CodeGen/X86/pop-stack-cleanup.ll CodeGen/X86/preserve_mostcc64.ll CodeGen/X86/tailcallstack64.ll CodeGen/X86/this-return-64.ll This happens because COPY has other special meaning for e.g. dependency breakage and x87 FP stack. Note that all other backends' tests pass. Reviewers: qcolombet Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D15157 llvm-svn: 254665
2015-12-04 07:43:56 +08:00
entry:
%loaded_L = load i32, i32* @L
%val = add nsw i32 %loaded_L, 1 ; N.B. will emit inc.
store i32 %val, i32* @L
%loaded_M = load i8, i8* @M
%masked = and i8 %loaded_M, 8
%M_is_true = icmp ne i8 %masked, 0
%L_is_false = icmp eq i32 %val, 0
%cond = and i1 %L_is_false, %M_is_true
br i1 %cond, label %exit2, label %exit
exit:
ret i1 true
exit2:
ret i1 false
}
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
define i1 @plus_forty_two() nounwind {
; CHECK32-LABEL: plus_forty_two:
[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
; CHECK32: # %bb.0: # %entry
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK32-NEXT: movb M, %al
[x86] Extend the manual ISel of `add` and `sub` with both RMW memory operands and used flags to support matching immediate operands. This is a bit trickier than register operands, and we still want to fall back on a register operands even for things that appear to be "immediates" when they won't actually select into the operation's immediate operand. This also requires us to handle things like selecting `sub` vs. `add` to minimize the number of bits needed to represent the immediate, and picking the shortest immediate encoding. In order to that, we in turn need to scan to make sure that CF isn't used as it will get inverted. The end result seems very nice though, and we're now generating optimal instruction sequences for these patterns IMO. A follow-up patch will further expand this to other operations with RMW memory operands. But handing `add` and `sub` are useful starting points to flesh out the machinery and make sure interesting and complex cases can be handled. Thanks to Craig Topper who provided a few fixes and improvements to this patch in addition to the review! Differential Revision: https://reviews.llvm.org/D37139 llvm-svn: 312764
2017-09-08 07:54:24 +08:00
; CHECK32-NEXT: addl $42, L
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK32-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
; CHECK32-NEXT: # %bb.1: # %entry
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK32-NEXT: andb $8, %al
; CHECK32-NEXT: je .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
; CHECK32-NEXT: # %bb.3: # %exit2
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK32-NEXT: xorl %eax, %eax
; CHECK32-NEXT: retl
; CHECK32-NEXT: .LBB1_2: # %exit
; CHECK32-NEXT: movb $1, %al
; CHECK32-NEXT: retl
;
; CHECK64-LABEL: plus_forty_two:
[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
; CHECK64: # %bb.0: # %entry
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK64-NEXT: movb {{.*}}(%rip), %al
[x86] Extend the manual ISel of `add` and `sub` with both RMW memory operands and used flags to support matching immediate operands. This is a bit trickier than register operands, and we still want to fall back on a register operands even for things that appear to be "immediates" when they won't actually select into the operation's immediate operand. This also requires us to handle things like selecting `sub` vs. `add` to minimize the number of bits needed to represent the immediate, and picking the shortest immediate encoding. In order to that, we in turn need to scan to make sure that CF isn't used as it will get inverted. The end result seems very nice though, and we're now generating optimal instruction sequences for these patterns IMO. A follow-up patch will further expand this to other operations with RMW memory operands. But handing `add` and `sub` are useful starting points to flesh out the machinery and make sure interesting and complex cases can be handled. Thanks to Craig Topper who provided a few fixes and improvements to this patch in addition to the review! Differential Revision: https://reviews.llvm.org/D37139 llvm-svn: 312764
2017-09-08 07:54:24 +08:00
; CHECK64-NEXT: addl $42, {{.*}}(%rip)
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK64-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
; CHECK64-NEXT: # %bb.1: # %entry
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK64-NEXT: andb $8, %al
; CHECK64-NEXT: je .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
; CHECK64-NEXT: # %bb.3: # %exit2
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK64-NEXT: xorl %eax, %eax
; CHECK64-NEXT: retq
; CHECK64-NEXT: .LBB1_2: # %exit
; CHECK64-NEXT: movb $1, %al
; CHECK64-NEXT: retq
CodeGen peephole: fold redundant phys reg copies Code generation often exposes redundant physical register copies through virtual registers such as: %vreg = COPY %PHYSREG ... %PHYSREG = COPY %vreg There are cases where no intervening clobber of %PHYSREG occurs, and the later copy could therefore be removed. In some cases this further allows us to remove the initial copy. This patch contains a motivating example which comes from the x86 build of Chrome, specifically cc::ResourceProvider::UnlockForRead uses libstdc++'s implementation of hash_map. That example has two tests live at the same time, and after machine sinking LLVM has confused itself enough and things spilling EFLAGS is a great idea even though it's never restored and the comparison results are both live. Before this patch we have: DEC32m %RIP, 1, %noreg, <ga:@L>, %noreg, %EFLAGS<imp-def> %vreg1<def> = COPY %EFLAGS; GR64:%vreg1 %EFLAGS<def> = COPY %vreg1; GR64:%vreg1 JNE_1 <BB#1>, %EFLAGS<imp-use> Both copies are useless. This patch tries to eliminate the later copy in a generic manner. dec is especially confusing to LLVM when compared with sub. I wrote this patch to treat all physical registers generically, but only remove redundant copies of non-allocatable physical registers because the allocatable ones caused issues (e.g. when calling conventions weren't properly modeled) and should be handled later by the register allocator anyways. The following tests used to failed when the patch also replaced allocatable registers: CodeGen/X86/StackColoring.ll CodeGen/X86/avx512-calling-conv.ll CodeGen/X86/copy-propagation.ll CodeGen/X86/inline-asm-fpstack.ll CodeGen/X86/musttail-varargs.ll CodeGen/X86/pop-stack-cleanup.ll CodeGen/X86/preserve_mostcc64.ll CodeGen/X86/tailcallstack64.ll CodeGen/X86/this-return-64.ll This happens because COPY has other special meaning for e.g. dependency breakage and x87 FP stack. Note that all other backends' tests pass. Reviewers: qcolombet Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D15157 llvm-svn: 254665
2015-12-04 07:43:56 +08:00
entry:
%loaded_L = load i32, i32* @L
%val = add nsw i32 %loaded_L, 42 ; N.B. won't emit inc.
store i32 %val, i32* @L
%loaded_M = load i8, i8* @M
%masked = and i8 %loaded_M, 8
%M_is_true = icmp ne i8 %masked, 0
%L_is_false = icmp eq i32 %val, 0
%cond = and i1 %L_is_false, %M_is_true
br i1 %cond, label %exit2, label %exit
exit:
ret i1 true
exit2:
ret i1 false
}
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
define i1 @minus_one() nounwind {
; CHECK32-LABEL: minus_one:
[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
; CHECK32: # %bb.0: # %entry
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK32-NEXT: movb M, %al
; CHECK32-NEXT: decl L
; CHECK32-NEXT: jne .LBB2_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
; CHECK32-NEXT: # %bb.1: # %entry
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK32-NEXT: andb $8, %al
; CHECK32-NEXT: je .LBB2_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
; CHECK32-NEXT: # %bb.3: # %exit2
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK32-NEXT: xorl %eax, %eax
; CHECK32-NEXT: retl
; CHECK32-NEXT: .LBB2_2: # %exit
; CHECK32-NEXT: movb $1, %al
; CHECK32-NEXT: retl
;
; CHECK64-LABEL: minus_one:
[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
; CHECK64: # %bb.0: # %entry
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK64-NEXT: movb {{.*}}(%rip), %al
; CHECK64-NEXT: decl {{.*}}(%rip)
; CHECK64-NEXT: jne .LBB2_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
; CHECK64-NEXT: # %bb.1: # %entry
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK64-NEXT: andb $8, %al
; CHECK64-NEXT: je .LBB2_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
; CHECK64-NEXT: # %bb.3: # %exit2
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK64-NEXT: xorl %eax, %eax
; CHECK64-NEXT: retq
; CHECK64-NEXT: .LBB2_2: # %exit
; CHECK64-NEXT: movb $1, %al
; CHECK64-NEXT: retq
CodeGen peephole: fold redundant phys reg copies Code generation often exposes redundant physical register copies through virtual registers such as: %vreg = COPY %PHYSREG ... %PHYSREG = COPY %vreg There are cases where no intervening clobber of %PHYSREG occurs, and the later copy could therefore be removed. In some cases this further allows us to remove the initial copy. This patch contains a motivating example which comes from the x86 build of Chrome, specifically cc::ResourceProvider::UnlockForRead uses libstdc++'s implementation of hash_map. That example has two tests live at the same time, and after machine sinking LLVM has confused itself enough and things spilling EFLAGS is a great idea even though it's never restored and the comparison results are both live. Before this patch we have: DEC32m %RIP, 1, %noreg, <ga:@L>, %noreg, %EFLAGS<imp-def> %vreg1<def> = COPY %EFLAGS; GR64:%vreg1 %EFLAGS<def> = COPY %vreg1; GR64:%vreg1 JNE_1 <BB#1>, %EFLAGS<imp-use> Both copies are useless. This patch tries to eliminate the later copy in a generic manner. dec is especially confusing to LLVM when compared with sub. I wrote this patch to treat all physical registers generically, but only remove redundant copies of non-allocatable physical registers because the allocatable ones caused issues (e.g. when calling conventions weren't properly modeled) and should be handled later by the register allocator anyways. The following tests used to failed when the patch also replaced allocatable registers: CodeGen/X86/StackColoring.ll CodeGen/X86/avx512-calling-conv.ll CodeGen/X86/copy-propagation.ll CodeGen/X86/inline-asm-fpstack.ll CodeGen/X86/musttail-varargs.ll CodeGen/X86/pop-stack-cleanup.ll CodeGen/X86/preserve_mostcc64.ll CodeGen/X86/tailcallstack64.ll CodeGen/X86/this-return-64.ll This happens because COPY has other special meaning for e.g. dependency breakage and x87 FP stack. Note that all other backends' tests pass. Reviewers: qcolombet Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D15157 llvm-svn: 254665
2015-12-04 07:43:56 +08:00
entry:
%loaded_L = load i32, i32* @L
%val = add nsw i32 %loaded_L, -1 ; N.B. will emit dec.
store i32 %val, i32* @L
%loaded_M = load i8, i8* @M
%masked = and i8 %loaded_M, 8
%M_is_true = icmp ne i8 %masked, 0
%L_is_false = icmp eq i32 %val, 0
%cond = and i1 %L_is_false, %M_is_true
br i1 %cond, label %exit2, label %exit
exit:
ret i1 true
exit2:
ret i1 false
}
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
define i1 @minus_forty_two() nounwind {
; CHECK32-LABEL: minus_forty_two:
[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
; CHECK32: # %bb.0: # %entry
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK32-NEXT: movb M, %al
[x86] Extend the manual ISel of `add` and `sub` with both RMW memory operands and used flags to support matching immediate operands. This is a bit trickier than register operands, and we still want to fall back on a register operands even for things that appear to be "immediates" when they won't actually select into the operation's immediate operand. This also requires us to handle things like selecting `sub` vs. `add` to minimize the number of bits needed to represent the immediate, and picking the shortest immediate encoding. In order to that, we in turn need to scan to make sure that CF isn't used as it will get inverted. The end result seems very nice though, and we're now generating optimal instruction sequences for these patterns IMO. A follow-up patch will further expand this to other operations with RMW memory operands. But handing `add` and `sub` are useful starting points to flesh out the machinery and make sure interesting and complex cases can be handled. Thanks to Craig Topper who provided a few fixes and improvements to this patch in addition to the review! Differential Revision: https://reviews.llvm.org/D37139 llvm-svn: 312764
2017-09-08 07:54:24 +08:00
; CHECK32-NEXT: addl $-42, L
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK32-NEXT: jne .LBB3_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
; CHECK32-NEXT: # %bb.1: # %entry
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK32-NEXT: andb $8, %al
; CHECK32-NEXT: je .LBB3_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
; CHECK32-NEXT: # %bb.3: # %exit2
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK32-NEXT: xorl %eax, %eax
; CHECK32-NEXT: retl
; CHECK32-NEXT: .LBB3_2: # %exit
; CHECK32-NEXT: movb $1, %al
; CHECK32-NEXT: retl
;
; CHECK64-LABEL: minus_forty_two:
[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
; CHECK64: # %bb.0: # %entry
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK64-NEXT: movb {{.*}}(%rip), %al
[x86] Extend the manual ISel of `add` and `sub` with both RMW memory operands and used flags to support matching immediate operands. This is a bit trickier than register operands, and we still want to fall back on a register operands even for things that appear to be "immediates" when they won't actually select into the operation's immediate operand. This also requires us to handle things like selecting `sub` vs. `add` to minimize the number of bits needed to represent the immediate, and picking the shortest immediate encoding. In order to that, we in turn need to scan to make sure that CF isn't used as it will get inverted. The end result seems very nice though, and we're now generating optimal instruction sequences for these patterns IMO. A follow-up patch will further expand this to other operations with RMW memory operands. But handing `add` and `sub` are useful starting points to flesh out the machinery and make sure interesting and complex cases can be handled. Thanks to Craig Topper who provided a few fixes and improvements to this patch in addition to the review! Differential Revision: https://reviews.llvm.org/D37139 llvm-svn: 312764
2017-09-08 07:54:24 +08:00
; CHECK64-NEXT: addl $-42, {{.*}}(%rip)
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK64-NEXT: jne .LBB3_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
; CHECK64-NEXT: # %bb.1: # %entry
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK64-NEXT: andb $8, %al
; CHECK64-NEXT: je .LBB3_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
; CHECK64-NEXT: # %bb.3: # %exit2
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK64-NEXT: xorl %eax, %eax
; CHECK64-NEXT: retq
; CHECK64-NEXT: .LBB3_2: # %exit
; CHECK64-NEXT: movb $1, %al
; CHECK64-NEXT: retq
CodeGen peephole: fold redundant phys reg copies Code generation often exposes redundant physical register copies through virtual registers such as: %vreg = COPY %PHYSREG ... %PHYSREG = COPY %vreg There are cases where no intervening clobber of %PHYSREG occurs, and the later copy could therefore be removed. In some cases this further allows us to remove the initial copy. This patch contains a motivating example which comes from the x86 build of Chrome, specifically cc::ResourceProvider::UnlockForRead uses libstdc++'s implementation of hash_map. That example has two tests live at the same time, and after machine sinking LLVM has confused itself enough and things spilling EFLAGS is a great idea even though it's never restored and the comparison results are both live. Before this patch we have: DEC32m %RIP, 1, %noreg, <ga:@L>, %noreg, %EFLAGS<imp-def> %vreg1<def> = COPY %EFLAGS; GR64:%vreg1 %EFLAGS<def> = COPY %vreg1; GR64:%vreg1 JNE_1 <BB#1>, %EFLAGS<imp-use> Both copies are useless. This patch tries to eliminate the later copy in a generic manner. dec is especially confusing to LLVM when compared with sub. I wrote this patch to treat all physical registers generically, but only remove redundant copies of non-allocatable physical registers because the allocatable ones caused issues (e.g. when calling conventions weren't properly modeled) and should be handled later by the register allocator anyways. The following tests used to failed when the patch also replaced allocatable registers: CodeGen/X86/StackColoring.ll CodeGen/X86/avx512-calling-conv.ll CodeGen/X86/copy-propagation.ll CodeGen/X86/inline-asm-fpstack.ll CodeGen/X86/musttail-varargs.ll CodeGen/X86/pop-stack-cleanup.ll CodeGen/X86/preserve_mostcc64.ll CodeGen/X86/tailcallstack64.ll CodeGen/X86/this-return-64.ll This happens because COPY has other special meaning for e.g. dependency breakage and x87 FP stack. Note that all other backends' tests pass. Reviewers: qcolombet Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D15157 llvm-svn: 254665
2015-12-04 07:43:56 +08:00
entry:
%loaded_L = load i32, i32* @L
%val = add nsw i32 %loaded_L, -42 ; N.B. won't emit dec.
store i32 %val, i32* @L
%loaded_M = load i8, i8* @M
%masked = and i8 %loaded_M, 8
%M_is_true = icmp ne i8 %masked, 0
%L_is_false = icmp eq i32 %val, 0
%cond = and i1 %L_is_false, %M_is_true
br i1 %cond, label %exit2, label %exit
exit:
ret i1 true
exit2:
ret i1 false
}
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
define i64 @test_intervening_call(i64* %foo, i64 %bar, i64 %baz) nounwind {
; CHECK32-LABEL: test_intervening_call:
[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
; CHECK32: # %bb.0: # %entry
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK32-NEXT: pushl %ebp
; CHECK32-NEXT: movl %esp, %ebp
; CHECK32-NEXT: pushl %ebx
; CHECK32-NEXT: pushl %esi
; CHECK32-NEXT: movl 12(%ebp), %eax
; CHECK32-NEXT: movl 16(%ebp), %edx
; CHECK32-NEXT: movl 20(%ebp), %ebx
; CHECK32-NEXT: movl 24(%ebp), %ecx
; CHECK32-NEXT: movl 8(%ebp), %esi
; CHECK32-NEXT: lock cmpxchg8b (%esi)
; CHECK32-NEXT: pushl %eax
; CHECK32-NEXT: seto %al
; CHECK32-NEXT: lahf
; CHECK32-NEXT: movl %eax, %esi
; CHECK32-NEXT: popl %eax
; CHECK32-NEXT: subl $8, %esp
; CHECK32-NEXT: pushl %edx
; CHECK32-NEXT: pushl %eax
; CHECK32-NEXT: calll bar
; CHECK32-NEXT: addl $16, %esp
; CHECK32-NEXT: movl %esi, %eax
; CHECK32-NEXT: addb $127, %al
; CHECK32-NEXT: sahf
; CHECK32-NEXT: jne .LBB4_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
; CHECK32-NEXT: # %bb.1: # %t
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK32-NEXT: movl $42, %eax
; CHECK32-NEXT: jmp .LBB4_2
; CHECK32-NEXT: .LBB4_3: # %f
; CHECK32-NEXT: xorl %eax, %eax
; CHECK32-NEXT: .LBB4_2: # %t
; CHECK32-NEXT: xorl %edx, %edx
; CHECK32-NEXT: popl %esi
; CHECK32-NEXT: popl %ebx
; CHECK32-NEXT: popl %ebp
; CHECK32-NEXT: retl
;
; CHECK64-LABEL: test_intervening_call:
[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
; CHECK64: # %bb.0: # %entry
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK64-NEXT: pushq %rbp
; CHECK64-NEXT: movq %rsp, %rbp
; CHECK64-NEXT: pushq %rbx
; CHECK64-NEXT: pushq %rax
; CHECK64-NEXT: movq %rsi, %rax
; CHECK64-NEXT: lock cmpxchgq %rdx, (%rdi)
; CHECK64-NEXT: pushq %rax
; CHECK64-NEXT: seto %al
; CHECK64-NEXT: lahf
; CHECK64-NEXT: movq %rax, %rbx
; CHECK64-NEXT: popq %rax
; CHECK64-NEXT: movq %rax, %rdi
; CHECK64-NEXT: callq bar
; CHECK64-NEXT: movq %rbx, %rax
; CHECK64-NEXT: addb $127, %al
; CHECK64-NEXT: sahf
; CHECK64-NEXT: jne .LBB4_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
; CHECK64-NEXT: # %bb.1: # %t
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK64-NEXT: movl $42, %eax
; CHECK64-NEXT: jmp .LBB4_2
; CHECK64-NEXT: .LBB4_3: # %f
; CHECK64-NEXT: xorl %eax, %eax
; CHECK64-NEXT: .LBB4_2: # %t
; CHECK64-NEXT: addq $8, %rsp
; CHECK64-NEXT: popq %rbx
; CHECK64-NEXT: popq %rbp
; CHECK64-NEXT: retq
entry:
CodeGen peephole: fold redundant phys reg copies Code generation often exposes redundant physical register copies through virtual registers such as: %vreg = COPY %PHYSREG ... %PHYSREG = COPY %vreg There are cases where no intervening clobber of %PHYSREG occurs, and the later copy could therefore be removed. In some cases this further allows us to remove the initial copy. This patch contains a motivating example which comes from the x86 build of Chrome, specifically cc::ResourceProvider::UnlockForRead uses libstdc++'s implementation of hash_map. That example has two tests live at the same time, and after machine sinking LLVM has confused itself enough and things spilling EFLAGS is a great idea even though it's never restored and the comparison results are both live. Before this patch we have: DEC32m %RIP, 1, %noreg, <ga:@L>, %noreg, %EFLAGS<imp-def> %vreg1<def> = COPY %EFLAGS; GR64:%vreg1 %EFLAGS<def> = COPY %vreg1; GR64:%vreg1 JNE_1 <BB#1>, %EFLAGS<imp-use> Both copies are useless. This patch tries to eliminate the later copy in a generic manner. dec is especially confusing to LLVM when compared with sub. I wrote this patch to treat all physical registers generically, but only remove redundant copies of non-allocatable physical registers because the allocatable ones caused issues (e.g. when calling conventions weren't properly modeled) and should be handled later by the register allocator anyways. The following tests used to failed when the patch also replaced allocatable registers: CodeGen/X86/StackColoring.ll CodeGen/X86/avx512-calling-conv.ll CodeGen/X86/copy-propagation.ll CodeGen/X86/inline-asm-fpstack.ll CodeGen/X86/musttail-varargs.ll CodeGen/X86/pop-stack-cleanup.ll CodeGen/X86/preserve_mostcc64.ll CodeGen/X86/tailcallstack64.ll CodeGen/X86/this-return-64.ll This happens because COPY has other special meaning for e.g. dependency breakage and x87 FP stack. Note that all other backends' tests pass. Reviewers: qcolombet Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D15157 llvm-svn: 254665
2015-12-04 07:43:56 +08:00
; cmpxchg sets EFLAGS, call clobbers it, then br uses EFLAGS.
%cx = cmpxchg i64* %foo, i64 %bar, i64 %baz seq_cst seq_cst
%v = extractvalue { i64, i1 } %cx, 0
%p = extractvalue { i64, i1 } %cx, 1
call i32 @bar(i64 %v)
br i1 %p, label %t, label %f
t:
ret i64 42
f:
ret i64 0
}
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
define i64 @test_two_live_flags(i64* %foo0, i64 %bar0, i64 %baz0, i64* %foo1, i64 %bar1, i64 %baz1) nounwind {
; CHECK32-LABEL: test_two_live_flags:
[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
; CHECK32: # %bb.0: # %entry
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK32-NEXT: pushl %ebp
; CHECK32-NEXT: movl %esp, %ebp
; CHECK32-NEXT: pushl %ebx
; CHECK32-NEXT: pushl %edi
; CHECK32-NEXT: pushl %esi
; CHECK32-NEXT: movl 44(%ebp), %edi
; CHECK32-NEXT: movl 12(%ebp), %eax
; CHECK32-NEXT: movl 16(%ebp), %edx
; CHECK32-NEXT: movl 20(%ebp), %ebx
; CHECK32-NEXT: movl 24(%ebp), %ecx
; CHECK32-NEXT: movl 8(%ebp), %esi
; CHECK32-NEXT: lock cmpxchg8b (%esi)
; CHECK32-NEXT: seto %al
; CHECK32-NEXT: lahf
; CHECK32-NEXT: movl %eax, %esi
; CHECK32-NEXT: movl 32(%ebp), %eax
; CHECK32-NEXT: movl 36(%ebp), %edx
; CHECK32-NEXT: movl %edi, %ecx
; CHECK32-NEXT: movl 40(%ebp), %ebx
; CHECK32-NEXT: movl 28(%ebp), %edi
; CHECK32-NEXT: lock cmpxchg8b (%edi)
; CHECK32-NEXT: sete %al
; CHECK32-NEXT: pushl %eax
; CHECK32-NEXT: movl %esi, %eax
; CHECK32-NEXT: addb $127, %al
; CHECK32-NEXT: sahf
; CHECK32-NEXT: popl %eax
; CHECK32-NEXT: jne .LBB5_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
; CHECK32-NEXT: # %bb.1: # %entry
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK32-NEXT: testb %al, %al
; CHECK32-NEXT: je .LBB5_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
; CHECK32-NEXT: # %bb.2: # %t
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK32-NEXT: movl $42, %eax
; CHECK32-NEXT: jmp .LBB5_3
; CHECK32-NEXT: .LBB5_4: # %f
; CHECK32-NEXT: xorl %eax, %eax
; CHECK32-NEXT: .LBB5_3: # %t
; CHECK32-NEXT: xorl %edx, %edx
; CHECK32-NEXT: popl %esi
; CHECK32-NEXT: popl %edi
; CHECK32-NEXT: popl %ebx
; CHECK32-NEXT: popl %ebp
; CHECK32-NEXT: retl
;
; CHECK64-LABEL: test_two_live_flags:
[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
; CHECK64: # %bb.0: # %entry
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK64-NEXT: pushq %rbp
; CHECK64-NEXT: movq %rsp, %rbp
; CHECK64-NEXT: movq %rsi, %rax
; CHECK64-NEXT: lock cmpxchgq %rdx, (%rdi)
; CHECK64-NEXT: seto %al
; CHECK64-NEXT: lahf
; CHECK64-NEXT: movq %rax, %rdx
; CHECK64-NEXT: movq %r8, %rax
; CHECK64-NEXT: lock cmpxchgq %r9, (%rcx)
; CHECK64-NEXT: sete %al
; CHECK64-NEXT: pushq %rax
; CHECK64-NEXT: movq %rdx, %rax
; CHECK64-NEXT: addb $127, %al
; CHECK64-NEXT: sahf
; CHECK64-NEXT: popq %rax
; CHECK64-NEXT: jne .LBB5_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
; CHECK64-NEXT: # %bb.1: # %entry
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK64-NEXT: testb %al, %al
; CHECK64-NEXT: je .LBB5_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
; CHECK64-NEXT: # %bb.2: # %t
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK64-NEXT: movl $42, %eax
; CHECK64-NEXT: popq %rbp
; CHECK64-NEXT: retq
; CHECK64-NEXT: .LBB5_3: # %f
; CHECK64-NEXT: xorl %eax, %eax
; CHECK64-NEXT: popq %rbp
; CHECK64-NEXT: retq
entry:
CodeGen peephole: fold redundant phys reg copies Code generation often exposes redundant physical register copies through virtual registers such as: %vreg = COPY %PHYSREG ... %PHYSREG = COPY %vreg There are cases where no intervening clobber of %PHYSREG occurs, and the later copy could therefore be removed. In some cases this further allows us to remove the initial copy. This patch contains a motivating example which comes from the x86 build of Chrome, specifically cc::ResourceProvider::UnlockForRead uses libstdc++'s implementation of hash_map. That example has two tests live at the same time, and after machine sinking LLVM has confused itself enough and things spilling EFLAGS is a great idea even though it's never restored and the comparison results are both live. Before this patch we have: DEC32m %RIP, 1, %noreg, <ga:@L>, %noreg, %EFLAGS<imp-def> %vreg1<def> = COPY %EFLAGS; GR64:%vreg1 %EFLAGS<def> = COPY %vreg1; GR64:%vreg1 JNE_1 <BB#1>, %EFLAGS<imp-use> Both copies are useless. This patch tries to eliminate the later copy in a generic manner. dec is especially confusing to LLVM when compared with sub. I wrote this patch to treat all physical registers generically, but only remove redundant copies of non-allocatable physical registers because the allocatable ones caused issues (e.g. when calling conventions weren't properly modeled) and should be handled later by the register allocator anyways. The following tests used to failed when the patch also replaced allocatable registers: CodeGen/X86/StackColoring.ll CodeGen/X86/avx512-calling-conv.ll CodeGen/X86/copy-propagation.ll CodeGen/X86/inline-asm-fpstack.ll CodeGen/X86/musttail-varargs.ll CodeGen/X86/pop-stack-cleanup.ll CodeGen/X86/preserve_mostcc64.ll CodeGen/X86/tailcallstack64.ll CodeGen/X86/this-return-64.ll This happens because COPY has other special meaning for e.g. dependency breakage and x87 FP stack. Note that all other backends' tests pass. Reviewers: qcolombet Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D15157 llvm-svn: 254665
2015-12-04 07:43:56 +08:00
%cx0 = cmpxchg i64* %foo0, i64 %bar0, i64 %baz0 seq_cst seq_cst
%p0 = extractvalue { i64, i1 } %cx0, 1
%cx1 = cmpxchg i64* %foo1, i64 %bar1, i64 %baz1 seq_cst seq_cst
%p1 = extractvalue { i64, i1 } %cx1, 1
%flag = and i1 %p0, %p1
br i1 %flag, label %t, label %f
t:
ret i64 42
f:
ret i64 0
}
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
define i1 @asm_clobbering_flags(i32* %mem) nounwind {
; CHECK32-LABEL: asm_clobbering_flags:
[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
; CHECK32: # %bb.0: # %entry
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; CHECK32-NEXT: movl (%ecx), %edx
; CHECK32-NEXT: testl %edx, %edx
; CHECK32-NEXT: setg %al
; CHECK32-NEXT: #APP
; CHECK32-NEXT: bsfl %edx, %edx
; CHECK32-NEXT: #NO_APP
; CHECK32-NEXT: movl %edx, (%ecx)
; CHECK32-NEXT: retl
;
; CHECK64-LABEL: asm_clobbering_flags:
[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
; CHECK64: # %bb.0: # %entry
[x86] NFC - normalize test case formatting of IR and generate CHECK lines with the script rather than using manually written checks. llvm-svn: 311753
2017-08-25 10:32:51 +08:00
; CHECK64-NEXT: movl (%rdi), %ecx
; CHECK64-NEXT: testl %ecx, %ecx
; CHECK64-NEXT: setg %al
; CHECK64-NEXT: #APP
; CHECK64-NEXT: bsfl %ecx, %ecx
; CHECK64-NEXT: #NO_APP
; CHECK64-NEXT: movl %ecx, (%rdi)
; CHECK64-NEXT: retq
entry:
CodeGen peephole: fold redundant phys reg copies Code generation often exposes redundant physical register copies through virtual registers such as: %vreg = COPY %PHYSREG ... %PHYSREG = COPY %vreg There are cases where no intervening clobber of %PHYSREG occurs, and the later copy could therefore be removed. In some cases this further allows us to remove the initial copy. This patch contains a motivating example which comes from the x86 build of Chrome, specifically cc::ResourceProvider::UnlockForRead uses libstdc++'s implementation of hash_map. That example has two tests live at the same time, and after machine sinking LLVM has confused itself enough and things spilling EFLAGS is a great idea even though it's never restored and the comparison results are both live. Before this patch we have: DEC32m %RIP, 1, %noreg, <ga:@L>, %noreg, %EFLAGS<imp-def> %vreg1<def> = COPY %EFLAGS; GR64:%vreg1 %EFLAGS<def> = COPY %vreg1; GR64:%vreg1 JNE_1 <BB#1>, %EFLAGS<imp-use> Both copies are useless. This patch tries to eliminate the later copy in a generic manner. dec is especially confusing to LLVM when compared with sub. I wrote this patch to treat all physical registers generically, but only remove redundant copies of non-allocatable physical registers because the allocatable ones caused issues (e.g. when calling conventions weren't properly modeled) and should be handled later by the register allocator anyways. The following tests used to failed when the patch also replaced allocatable registers: CodeGen/X86/StackColoring.ll CodeGen/X86/avx512-calling-conv.ll CodeGen/X86/copy-propagation.ll CodeGen/X86/inline-asm-fpstack.ll CodeGen/X86/musttail-varargs.ll CodeGen/X86/pop-stack-cleanup.ll CodeGen/X86/preserve_mostcc64.ll CodeGen/X86/tailcallstack64.ll CodeGen/X86/this-return-64.ll This happens because COPY has other special meaning for e.g. dependency breakage and x87 FP stack. Note that all other backends' tests pass. Reviewers: qcolombet Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D15157 llvm-svn: 254665
2015-12-04 07:43:56 +08:00
%val = load i32, i32* %mem, align 4
%cmp = icmp sgt i32 %val, 0
%res = tail call i32 asm "bsfl $1,$0", "=r,r,~{cc},~{dirflag},~{fpsr},~{flags}"(i32 %val)
store i32 %res, i32* %mem, align 4
ret i1 %cmp
}