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/ctpop-combine.ll

65 lines
1.8 KiB
LLVM
Raw Normal View History

[X86] Regenerated popcnt combine tests llvm-svn: 274124
2016-06-29 21:54:03 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown -mcpu=corei7 | FileCheck %s
Add a DAGCombine to turn (ctpop x) u< 2 into (x & x-1) == 0. This shaves off 4 popcounts from the hacked 186.crafty source. This is enabled even when a native popcount instruction is available. The combined code is one operation longer but it should be faster nevertheless. llvm-svn: 123621
2011-01-17 20:04:57 +08:00
[SelectionDAG] Improve known bits support for CTPOP. This is based on the same concept from ValueTracking's version of computeKnownBits. llvm-svn: 302110
2017-05-04 12:33:27 +08:00
declare i8 @llvm.ctpop.i8(i8) nounwind readnone
Add a DAGCombine to turn (ctpop x) u< 2 into (x & x-1) == 0. This shaves off 4 popcounts from the hacked 186.crafty source. This is enabled even when a native popcount instruction is available. The combined code is one operation longer but it should be faster nevertheless. llvm-svn: 123621
2011-01-17 20:04:57 +08:00
declare i64 @llvm.ctpop.i64(i64) nounwind readnone
define i32 @test1(i64 %x) nounwind readnone {
[X86] Regenerated popcnt combine tests llvm-svn: 274124
2016-06-29 21:54:03 +08:00
; CHECK-LABEL: test1:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: # %bb.0:
Recommit r274692 - [X86] Transform setcc + movzbl into xorl + setcc xorl + setcc is generally the preferred sequence due to the partial register stall setcc + movzbl suffers from. As a bonus, it also encodes one byte smaller. This fixes PR28146. The original commit tried inserting an 8bit-subreg into a GR32 (not GR32_ABCD) which was not appreciated by fast regalloc on 32-bit. llvm-svn: 274802
2016-07-08 06:50:23 +08:00
; CHECK-NEXT: leaq -1(%rdi), %rcx
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: testq %rcx, %rdi
[X86] Regenerated popcnt combine tests llvm-svn: 274124
2016-06-29 21:54:03 +08:00
; CHECK-NEXT: setne %al
; CHECK-NEXT: retq
Add a DAGCombine to turn (ctpop x) u< 2 into (x & x-1) == 0. This shaves off 4 popcounts from the hacked 186.crafty source. This is enabled even when a native popcount instruction is available. The combined code is one operation longer but it should be faster nevertheless. llvm-svn: 123621
2011-01-17 20:04:57 +08:00
%count = tail call i64 @llvm.ctpop.i64(i64 %x)
%cast = trunc i64 %count to i32
%cmp = icmp ugt i32 %cast, 1
%conv = zext i1 %cmp to i32
ret i32 %conv
}
define i32 @test2(i64 %x) nounwind readnone {
[X86] Regenerated popcnt combine tests llvm-svn: 274124
2016-06-29 21:54:03 +08:00
; CHECK-LABEL: test2:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: # %bb.0:
Recommit r274692 - [X86] Transform setcc + movzbl into xorl + setcc xorl + setcc is generally the preferred sequence due to the partial register stall setcc + movzbl suffers from. As a bonus, it also encodes one byte smaller. This fixes PR28146. The original commit tried inserting an 8bit-subreg into a GR32 (not GR32_ABCD) which was not appreciated by fast regalloc on 32-bit. llvm-svn: 274802
2016-07-08 06:50:23 +08:00
; CHECK-NEXT: leaq -1(%rdi), %rcx
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: testq %rcx, %rdi
[X86] Regenerated popcnt combine tests llvm-svn: 274124
2016-06-29 21:54:03 +08:00
; CHECK-NEXT: sete %al
; CHECK-NEXT: retq
Add a DAGCombine to turn (ctpop x) u< 2 into (x & x-1) == 0. This shaves off 4 popcounts from the hacked 186.crafty source. This is enabled even when a native popcount instruction is available. The combined code is one operation longer but it should be faster nevertheless. llvm-svn: 123621
2011-01-17 20:04:57 +08:00
%count = tail call i64 @llvm.ctpop.i64(i64 %x)
Fix an off-by-one error in ctpop combining. llvm-svn: 123664
2011-01-18 02:00:28 +08:00
%cmp = icmp ult i64 %count, 2
Add a DAGCombine to turn (ctpop x) u< 2 into (x & x-1) == 0. This shaves off 4 popcounts from the hacked 186.crafty source. This is enabled even when a native popcount instruction is available. The combined code is one operation longer but it should be faster nevertheless. llvm-svn: 123621
2011-01-17 20:04:57 +08:00
%conv = zext i1 %cmp to i32
ret i32 %conv
}
Fix an off-by-one error in ctpop combining. llvm-svn: 123664
2011-01-18 02:00:28 +08:00
define i32 @test3(i64 %x) nounwind readnone {
[X86] Regenerated popcnt combine tests llvm-svn: 274124
2016-06-29 21:54:03 +08:00
; CHECK-LABEL: test3:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: # %bb.0:
[x86] don't blindly transform SETB into SBB I noticed unnecessary 'sbb' instructions in D30472 and while looking at 'ptest' codegen recently. This happens because we were transforming any 'setb' - even when we only wanted a single-bit result. This patch moves those transforms under visitAdd/visitSub, so we we're only creating sbb/adc when it is a win. I don't know why we need a SETCC_CARRY node type, but I'm not proposing to change that existing behavior in this patch. Also, I'm skeptical that sbb/adc are a win for all micro-arches, so I added comments to the test files where this transform still fires. The test changes here are all cases where we no longer produce sbb/adc. Avoiding partial register stalls (generating an xor to clear a register) is not handled in some cases, but that's a separate issue. Differential Revision: https://reviews.llvm.org/D30611 llvm-svn: 297586
2017-03-13 02:28:48 +08:00
; CHECK-NEXT: popcntq %rdi, %rcx
; CHECK-NEXT: andb $63, %cl
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: cmpb $2, %cl
; CHECK-NEXT: setb %al
[X86] Regenerated popcnt combine tests llvm-svn: 274124
2016-06-29 21:54:03 +08:00
; CHECK-NEXT: retq
Fix an off-by-one error in ctpop combining. llvm-svn: 123664
2011-01-18 02:00:28 +08:00
%count = tail call i64 @llvm.ctpop.i64(i64 %x)
%cast = trunc i64 %count to i6 ; Too small for 0-64
%cmp = icmp ult i6 %cast, 2
%conv = zext i1 %cmp to i32
ret i32 %conv
}
[SelectionDAG] Improve known bits support for CTPOP. This is based on the same concept from ValueTracking's version of computeKnownBits. llvm-svn: 302110
2017-05-04 12:33:27 +08:00
define i8 @test4(i8 %x) nounwind readnone {
; CHECK-LABEL: test4:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: # %bb.0:
[SelectionDAG] Improve known bits support for CTPOP. This is based on the same concept from ValueTracking's version of computeKnownBits. llvm-svn: 302110
2017-05-04 12:33:27 +08:00
; CHECK-NEXT: andl $127, %edi
[X86] Promote i8 CTPOP to i32 instead of i16 when we have the POPCNT instruction. The 32-bit version is shorter to encode and the zext we emit for the promotion is likely going to be a 32-bit zero extend anyway. llvm-svn: 319468
2017-12-01 04:15:31 +08:00
; CHECK-NEXT: popcntl %edi, %eax
[CodeGen] Use MachineOperand::print in the MIRPrinter for MO_Register. Work towards the unification of MIR and debug output by refactoring the interfaces. For MachineOperand::print, keep a simple version that can be easily called from `dump()`, and a more complex one which will be called from both the MIRPrinter and MachineInstr::print. Add extra checks inside MachineOperand for detached operands (operands with getParent() == nullptr). https://reviews.llvm.org/D40836 * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: ([^ ]+) ([^ ]+)<def> ([^ ]+)/kill: \1 def \2 \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: ([^ ]+) ([^ ]+) ([^ ]+)<def>/kill: \1 \2 def \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: def ([^ ]+) ([^ ]+) ([^ ]+)<def>/kill: def \1 \2 def \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/<def>//g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<kill>/killed \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-use,kill>/implicit killed \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<dead>/dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<def[ ]*,[ ]*dead>/dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-def[ ]*,[ ]*dead>/implicit-def dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-def>/implicit-def \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-use>/implicit \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<internal>/internal \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<undef>/undef \1/g' llvm-svn: 320022
2017-12-07 18:40:31 +08:00
; CHECK-NEXT: # kill: def %al killed %al killed %eax
[SelectionDAG] Improve known bits support for CTPOP. This is based on the same concept from ValueTracking's version of computeKnownBits. llvm-svn: 302110
2017-05-04 12:33:27 +08:00
; CHECK-NEXT: retq
%x2 = and i8 %x, 127
%count = tail call i8 @llvm.ctpop.i8(i8 %x2)
%and = and i8 %count, 7
ret i8 %and
}