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/machine-combiner-int.ll

200 lines
5.8 KiB
LLVM
Raw Normal View History

[MachineCombiner] Add check for optimal pattern order. In D41587, @mssimpso discovered that the order of some patterns for AArch64 was sub-optimal. I thought a bit about how we could avoid that case in the future. I do not think there is a need for evaluating all patterns for now. But this patch adds an extra (expensive) check, that evaluates the latencies of all patterns, and ensures that the latency saved decreases for subsequent patterns. This catches the sub-optimal order fixed in D41587, but I am not entirely happy with the check, as it only applies to sub-optimal patterns seen while building with EXPENSIVE_CHECKS on. It did not discover any other sub-optimal pattern ordering. Reviewers: Gerolf, spatel, mssimpso Reviewed By: Gerolf, mssimpso Differential Revision: https://reviews.llvm.org/D41766 llvm-svn: 323873
2018-01-31 21:54:30 +08:00
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -machine-combiner-verify-pattern-order=true | FileCheck %s
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -stop-after machine-combiner -machine-combiner-verify-pattern-order=true -o - | FileCheck %s --check-prefix=DEAD
[x86] reassociate integer multiplies using machine combiner pass Add i16, i32, i64 imul machine instructions to the list of reassociation candidates. A new bit of logic is needed to handle integer instructions: they have an implicit EFLAGS operand, so we have to make sure it's dead in order to do any reassociation with integer ops. Differential Revision: http://reviews.llvm.org/D11660 llvm-svn: 243756
2015-08-01 00:21:55 +08:00
; Verify that integer multiplies are reassociated. The first multiply in
; each test should be independent of the result of the preceding add (lea).
[x86] enable machine combiner reassociations for scalar 'and' insts llvm-svn: 246300
2015-08-28 22:09:48 +08:00
; TODO: This test does not actually test i16 machine instruction reassociation
; because the operands are being promoted to i32 types.
[x86] reassociate integer multiplies using machine combiner pass Add i16, i32, i64 imul machine instructions to the list of reassociation candidates. A new bit of logic is needed to handle integer instructions: they have an implicit EFLAGS operand, so we have to make sure it's dead in order to do any reassociation with integer ops. Differential Revision: http://reviews.llvm.org/D11660 llvm-svn: 243756
2015-08-01 00:21:55 +08:00
define i16 @reassociate_muls_i16(i16 %x0, i16 %x1, i16 %x2, i16 %x3) {
; CHECK-LABEL: reassociate_muls_i16:
[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:
VirtRegMap: Replace some identity copies with KILL instructions. An identity COPY like this: %AL = COPY %AL, %EAX<imp-def> has no semantic effect, but encodes liveness information: Further users of %EAX only depend on this instruction even though it does not define the full register. Replace the COPY with a KILL instruction in those cases to maintain this liveness information. (This reverts a small part of r238588 but this time adds a comment explaining why a KILL instruction is useful). llvm-svn: 274952
2016-07-09 08:19:07 +08:00
; CHECK-NEXT: # kill
; CHECK-NEXT: # kill
[x86] reassociate integer multiplies using machine combiner pass Add i16, i32, i64 imul machine instructions to the list of reassociation candidates. A new bit of logic is needed to handle integer instructions: they have an implicit EFLAGS operand, so we have to make sure it's dead in order to do any reassociation with integer ops. Differential Revision: http://reviews.llvm.org/D11660 llvm-svn: 243756
2015-08-01 00:21:55 +08:00
; CHECK-NEXT: leal (%rdi,%rsi), %eax
; CHECK-NEXT: imull %ecx, %edx
; CHECK-NEXT: imull %edx, %eax
VirtRegMap: Replace some identity copies with KILL instructions. An identity COPY like this: %AL = COPY %AL, %EAX<imp-def> has no semantic effect, but encodes liveness information: Further users of %EAX only depend on this instruction even though it does not define the full register. Replace the COPY with a KILL instruction in those cases to maintain this liveness information. (This reverts a small part of r238588 but this time adds a comment explaining why a KILL instruction is useful). llvm-svn: 274952
2016-07-09 08:19:07 +08:00
; CHECK-NEXT: # kill
[x86] reassociate integer multiplies using machine combiner pass Add i16, i32, i64 imul machine instructions to the list of reassociation candidates. A new bit of logic is needed to handle integer instructions: they have an implicit EFLAGS operand, so we have to make sure it's dead in order to do any reassociation with integer ops. Differential Revision: http://reviews.llvm.org/D11660 llvm-svn: 243756
2015-08-01 00:21:55 +08:00
; CHECK-NEXT: retq
%t0 = add i16 %x0, %x1
%t1 = mul i16 %x2, %t0
%t2 = mul i16 %x3, %t1
ret i16 %t2
}
define i32 @reassociate_muls_i32(i32 %x0, i32 %x1, i32 %x2, i32 %x3) {
; CHECK-LABEL: reassociate_muls_i32:
[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:
VirtRegMap: Replace some identity copies with KILL instructions. An identity COPY like this: %AL = COPY %AL, %EAX<imp-def> has no semantic effect, but encodes liveness information: Further users of %EAX only depend on this instruction even though it does not define the full register. Replace the COPY with a KILL instruction in those cases to maintain this liveness information. (This reverts a small part of r238588 but this time adds a comment explaining why a KILL instruction is useful). llvm-svn: 274952
2016-07-09 08:19:07 +08:00
; CHECK-NEXT: # kill
; CHECK-NEXT: # kill
[x86] reassociate integer multiplies using machine combiner pass Add i16, i32, i64 imul machine instructions to the list of reassociation candidates. A new bit of logic is needed to handle integer instructions: they have an implicit EFLAGS operand, so we have to make sure it's dead in order to do any reassociation with integer ops. Differential Revision: http://reviews.llvm.org/D11660 llvm-svn: 243756
2015-08-01 00:21:55 +08:00
; CHECK-NEXT: leal (%rdi,%rsi), %eax
; CHECK-NEXT: imull %ecx, %edx
; CHECK-NEXT: imull %edx, %eax
; CHECK-NEXT: retq
[x86] machine combiner reassociation: mark EFLAGS operand as 'dead' In the commentary for D11660, I wasn't sure if it was alright to create new integer machine instructions without also creating the implicit EFLAGS operand. From what I can see, the implicit operand is always created by the MachineInstrBuilder based on the instruction type, so we don't have to do that explicitly. However, in reviewing the debug output, I noticed that the operand was not marked as 'dead'. The machine combiner should do that to preserve future optimization opportunities that may be checking for that dead EFLAGS operand themselves. Differential Revision: http://reviews.llvm.org/D11696 llvm-svn: 243990
2015-08-04 23:21:56 +08:00
; DEAD: ADD32rr
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
; DEAD-NEXT: IMUL32rr{{.*}}implicit-def dead $eflags
; DEAD-NEXT: IMUL32rr{{.*}}implicit-def dead $eflags
[x86] machine combiner reassociation: mark EFLAGS operand as 'dead' In the commentary for D11660, I wasn't sure if it was alright to create new integer machine instructions without also creating the implicit EFLAGS operand. From what I can see, the implicit operand is always created by the MachineInstrBuilder based on the instruction type, so we don't have to do that explicitly. However, in reviewing the debug output, I noticed that the operand was not marked as 'dead'. The machine combiner should do that to preserve future optimization opportunities that may be checking for that dead EFLAGS operand themselves. Differential Revision: http://reviews.llvm.org/D11696 llvm-svn: 243990
2015-08-04 23:21:56 +08:00
[x86] reassociate integer multiplies using machine combiner pass Add i16, i32, i64 imul machine instructions to the list of reassociation candidates. A new bit of logic is needed to handle integer instructions: they have an implicit EFLAGS operand, so we have to make sure it's dead in order to do any reassociation with integer ops. Differential Revision: http://reviews.llvm.org/D11660 llvm-svn: 243756
2015-08-01 00:21:55 +08:00
%t0 = add i32 %x0, %x1
%t1 = mul i32 %x2, %t0
%t2 = mul i32 %x3, %t1
ret i32 %t2
}
define i64 @reassociate_muls_i64(i64 %x0, i64 %x1, i64 %x2, i64 %x3) {
; CHECK-LABEL: reassociate_muls_i64:
[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] reassociate integer multiplies using machine combiner pass Add i16, i32, i64 imul machine instructions to the list of reassociation candidates. A new bit of logic is needed to handle integer instructions: they have an implicit EFLAGS operand, so we have to make sure it's dead in order to do any reassociation with integer ops. Differential Revision: http://reviews.llvm.org/D11660 llvm-svn: 243756
2015-08-01 00:21:55 +08:00
; CHECK-NEXT: leaq (%rdi,%rsi), %rax
; CHECK-NEXT: imulq %rcx, %rdx
; CHECK-NEXT: imulq %rdx, %rax
; CHECK-NEXT: retq
%t0 = add i64 %x0, %x1
%t1 = mul i64 %x2, %t0
%t2 = mul i64 %x3, %t1
ret i64 %t2
}
[x86] enable machine combiner reassociations for scalar 'and' insts llvm-svn: 246300
2015-08-28 22:09:48 +08:00
; Verify that integer 'ands' are reassociated. The first 'and' in
; each test should be independent of the result of the preceding sub.
define i8 @reassociate_ands_i8(i8 %x0, i8 %x1, i8 %x2, i8 %x3) {
; CHECK-LABEL: reassociate_ands_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
; CHECK: # %bb.0:
[x86] enable machine combiner reassociations for scalar 'and' insts llvm-svn: 246300
2015-08-28 22:09:48 +08:00
; CHECK-NEXT: subb %sil, %dil
; CHECK-NEXT: andb %cl, %dl
; CHECK-NEXT: andb %dil, %dl
[X86] Teach X86FixupBWInsts to promote MOV8rr/MOV16rr to MOV32rr. This re-applies r268760, reverted in r268794. Fixes http://llvm.org/PR27670 The original imp-defs assertion was way overzealous: forward all implicit operands, except imp-defs of the new super-reg def (r268787 for GR64, but also possible for GR16->GR32), or imp-uses of the new super-reg use. While there, mark the source use as Undef, and add an imp-use of the old source reg: that should cover any case of dead super-regs. At the stage the pass runs, flags are unlikely to matter anyway; still, let's be as correct as possible. Also add MIR tests for the various interesting cases. Original commit message: Codesize is less (16) or equal (8), and we avoid partial dependencies. Differential Revision: http://reviews.llvm.org/D19999 llvm-svn: 268831
2016-05-07 09:11:17 +08:00
; CHECK-NEXT: movl %edx, %eax
fix CHECK_NEXT -> CHECK-NEXT llvm-svn: 264661
2016-03-29 05:14:24 +08:00
; CHECK-NEXT: retq
[x86] enable machine combiner reassociations for scalar 'and' insts llvm-svn: 246300
2015-08-28 22:09:48 +08:00
%t0 = sub i8 %x0, %x1
%t1 = and i8 %x2, %t0
%t2 = and i8 %x3, %t1
ret i8 %t2
}
; TODO: No way to test i16? These appear to always get promoted to i32.
define i32 @reassociate_ands_i32(i32 %x0, i32 %x1, i32 %x2, i32 %x3) {
; CHECK-LABEL: reassociate_ands_i32:
[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] enable machine combiner reassociations for scalar 'and' insts llvm-svn: 246300
2015-08-28 22:09:48 +08:00
; CHECK-NEXT: subl %esi, %edi
; CHECK-NEXT: andl %ecx, %edx
; CHECK-NEXT: andl %edi, %edx
fix CHECK_NEXT -> CHECK-NEXT llvm-svn: 264661
2016-03-29 05:14:24 +08:00
; CHECK-NEXT: movl %edx, %eax
; CHECK-NEXT: retq
[x86] enable machine combiner reassociations for scalar 'and' insts llvm-svn: 246300
2015-08-28 22:09:48 +08:00
%t0 = sub i32 %x0, %x1
%t1 = and i32 %x2, %t0
%t2 = and i32 %x3, %t1
ret i32 %t2
}
define i64 @reassociate_ands_i64(i64 %x0, i64 %x1, i64 %x2, i64 %x3) {
; CHECK-LABEL: reassociate_ands_i64:
[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] enable machine combiner reassociations for scalar 'and' insts llvm-svn: 246300
2015-08-28 22:09:48 +08:00
; CHECK-NEXT: subq %rsi, %rdi
; CHECK-NEXT: andq %rcx, %rdx
; CHECK-NEXT: andq %rdi, %rdx
; CHECK-NEXT: movq %rdx, %rax
fix CHECK_NEXT -> CHECK-NEXT llvm-svn: 264661
2016-03-29 05:14:24 +08:00
; CHECK-NEXT: retq
[x86] enable machine combiner reassociations for scalar 'and' insts llvm-svn: 246300
2015-08-28 22:09:48 +08:00
%t0 = sub i64 %x0, %x1
%t1 = and i64 %x2, %t0
%t2 = and i64 %x3, %t1
ret i64 %t2
}
[x86] enable machine combiner reassociations for scalar 'or' insts llvm-svn: 246481
2015-09-01 04:27:03 +08:00
; Verify that integer 'ors' are reassociated. The first 'or' in
; each test should be independent of the result of the preceding sub.
define i8 @reassociate_ors_i8(i8 %x0, i8 %x1, i8 %x2, i8 %x3) {
; CHECK-LABEL: reassociate_ors_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
; CHECK: # %bb.0:
[x86] enable machine combiner reassociations for scalar 'or' insts llvm-svn: 246481
2015-09-01 04:27:03 +08:00
; CHECK-NEXT: subb %sil, %dil
; CHECK-NEXT: orb %cl, %dl
; CHECK-NEXT: orb %dil, %dl
[X86] Teach X86FixupBWInsts to promote MOV8rr/MOV16rr to MOV32rr. This re-applies r268760, reverted in r268794. Fixes http://llvm.org/PR27670 The original imp-defs assertion was way overzealous: forward all implicit operands, except imp-defs of the new super-reg def (r268787 for GR64, but also possible for GR16->GR32), or imp-uses of the new super-reg use. While there, mark the source use as Undef, and add an imp-use of the old source reg: that should cover any case of dead super-regs. At the stage the pass runs, flags are unlikely to matter anyway; still, let's be as correct as possible. Also add MIR tests for the various interesting cases. Original commit message: Codesize is less (16) or equal (8), and we avoid partial dependencies. Differential Revision: http://reviews.llvm.org/D19999 llvm-svn: 268831
2016-05-07 09:11:17 +08:00
; CHECK-NEXT: movl %edx, %eax
fix CHECK_NEXT -> CHECK-NEXT llvm-svn: 264661
2016-03-29 05:14:24 +08:00
; CHECK-NEXT: retq
[x86] enable machine combiner reassociations for scalar 'or' insts llvm-svn: 246481
2015-09-01 04:27:03 +08:00
%t0 = sub i8 %x0, %x1
%t1 = or i8 %x2, %t0
%t2 = or i8 %x3, %t1
ret i8 %t2
}
; TODO: No way to test i16? These appear to always get promoted to i32.
define i32 @reassociate_ors_i32(i32 %x0, i32 %x1, i32 %x2, i32 %x3) {
; CHECK-LABEL: reassociate_ors_i32:
[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] enable machine combiner reassociations for scalar 'or' insts llvm-svn: 246481
2015-09-01 04:27:03 +08:00
; CHECK-NEXT: subl %esi, %edi
; CHECK-NEXT: orl %ecx, %edx
; CHECK-NEXT: orl %edi, %edx
fix CHECK_NEXT -> CHECK-NEXT llvm-svn: 264661
2016-03-29 05:14:24 +08:00
; CHECK-NEXT: movl %edx, %eax
; CHECK-NEXT: retq
[x86] enable machine combiner reassociations for scalar 'or' insts llvm-svn: 246481
2015-09-01 04:27:03 +08:00
%t0 = sub i32 %x0, %x1
%t1 = or i32 %x2, %t0
%t2 = or i32 %x3, %t1
ret i32 %t2
}
define i64 @reassociate_ors_i64(i64 %x0, i64 %x1, i64 %x2, i64 %x3) {
; CHECK-LABEL: reassociate_ors_i64:
[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] enable machine combiner reassociations for scalar 'or' insts llvm-svn: 246481
2015-09-01 04:27:03 +08:00
; CHECK-NEXT: subq %rsi, %rdi
; CHECK-NEXT: orq %rcx, %rdx
; CHECK-NEXT: orq %rdi, %rdx
; CHECK-NEXT: movq %rdx, %rax
fix CHECK_NEXT -> CHECK-NEXT llvm-svn: 264661
2016-03-29 05:14:24 +08:00
; CHECK-NEXT: retq
[x86] enable machine combiner reassociations for scalar 'or' insts llvm-svn: 246481
2015-09-01 04:27:03 +08:00
%t0 = sub i64 %x0, %x1
%t1 = or i64 %x2, %t0
%t2 = or i64 %x3, %t1
ret i64 %t2
}
[x86] enable machine combiner reassociations for scalar 'xor' insts llvm-svn: 246781
2015-09-04 00:36:16 +08:00
; Verify that integer 'xors' are reassociated. The first 'xor' in
; each test should be independent of the result of the preceding sub.
define i8 @reassociate_xors_i8(i8 %x0, i8 %x1, i8 %x2, i8 %x3) {
; CHECK-LABEL: reassociate_xors_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
; CHECK: # %bb.0:
[x86] enable machine combiner reassociations for scalar 'xor' insts llvm-svn: 246781
2015-09-04 00:36:16 +08:00
; CHECK-NEXT: subb %sil, %dil
; CHECK-NEXT: xorb %cl, %dl
; CHECK-NEXT: xorb %dil, %dl
[X86] Teach X86FixupBWInsts to promote MOV8rr/MOV16rr to MOV32rr. This re-applies r268760, reverted in r268794. Fixes http://llvm.org/PR27670 The original imp-defs assertion was way overzealous: forward all implicit operands, except imp-defs of the new super-reg def (r268787 for GR64, but also possible for GR16->GR32), or imp-uses of the new super-reg use. While there, mark the source use as Undef, and add an imp-use of the old source reg: that should cover any case of dead super-regs. At the stage the pass runs, flags are unlikely to matter anyway; still, let's be as correct as possible. Also add MIR tests for the various interesting cases. Original commit message: Codesize is less (16) or equal (8), and we avoid partial dependencies. Differential Revision: http://reviews.llvm.org/D19999 llvm-svn: 268831
2016-05-07 09:11:17 +08:00
; CHECK-NEXT: movl %edx, %eax
fix CHECK_NEXT -> CHECK-NEXT llvm-svn: 264661
2016-03-29 05:14:24 +08:00
; CHECK-NEXT: retq
[x86] enable machine combiner reassociations for scalar 'xor' insts llvm-svn: 246781
2015-09-04 00:36:16 +08:00
%t0 = sub i8 %x0, %x1
%t1 = xor i8 %x2, %t0
%t2 = xor i8 %x3, %t1
ret i8 %t2
}
; TODO: No way to test i16? These appear to always get promoted to i32.
define i32 @reassociate_xors_i32(i32 %x0, i32 %x1, i32 %x2, i32 %x3) {
; CHECK-LABEL: reassociate_xors_i32:
[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] enable machine combiner reassociations for scalar 'xor' insts llvm-svn: 246781
2015-09-04 00:36:16 +08:00
; CHECK-NEXT: subl %esi, %edi
; CHECK-NEXT: xorl %ecx, %edx
; CHECK-NEXT: xorl %edi, %edx
fix CHECK_NEXT -> CHECK-NEXT llvm-svn: 264661
2016-03-29 05:14:24 +08:00
; CHECK-NEXT: movl %edx, %eax
; CHECK-NEXT: retq
[x86] enable machine combiner reassociations for scalar 'xor' insts llvm-svn: 246781
2015-09-04 00:36:16 +08:00
%t0 = sub i32 %x0, %x1
%t1 = xor i32 %x2, %t0
%t2 = xor i32 %x3, %t1
ret i32 %t2
}
define i64 @reassociate_xors_i64(i64 %x0, i64 %x1, i64 %x2, i64 %x3) {
; CHECK-LABEL: reassociate_xors_i64:
[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] enable machine combiner reassociations for scalar 'xor' insts llvm-svn: 246781
2015-09-04 00:36:16 +08:00
; CHECK-NEXT: subq %rsi, %rdi
; CHECK-NEXT: xorq %rcx, %rdx
; CHECK-NEXT: xorq %rdi, %rdx
; CHECK-NEXT: movq %rdx, %rax
fix CHECK_NEXT -> CHECK-NEXT llvm-svn: 264661
2016-03-29 05:14:24 +08:00
; CHECK-NEXT: retq
[x86] enable machine combiner reassociations for scalar 'xor' insts llvm-svn: 246781
2015-09-04 00:36:16 +08:00
%t0 = sub i64 %x0, %x1
%t1 = xor i64 %x2, %t0
%t2 = xor i64 %x3, %t1
ret i64 %t2
}