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/sbb.ll

243 lines
6.1 KiB
LLVM
Raw Normal View History

[x86] add tests for select --> sbb transform; NFC llvm-svn: 306032
2017-06-23 01:01:14 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s
; Vary the operand sizes for extra coverage, but the transform should be identical in all cases.
; (X == 0) ? 0 : -1 --> (X == 0) - 1
define i8 @i8_select_0_or_neg1(i8 %x) {
; CHECK-LABEL: i8_select_0_or_neg1:
[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] add/sub (X==0) --> sbb(neg X) Our handling of select-of-constants is lumpy in IR (https://reviews.llvm.org/D24480), lumpy in DAGCombiner, and lumpy in X86ISelLowering. That's why we only had the 'sbb' codegen in 1 out of the 4 tests. This is a step towards smoothing that out. First, show that all of these IR forms are equivalent: http://rise4fun.com/Alive/mx Second, show that the 'sbb' version is faster/smaller. IACA output for SandyBridge (later Intel and AMD chips are similar based on Agner's tables): This is the "obvious" x86 codegen (what gcc appears to produce currently): | Num Of | Ports pressure in cycles | | | Uops | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | | --------------------------------------------------------------------- | 1* | | | | | | | | xor eax, eax | 1 | 1.0 | | | | | | CP | test edi, edi | 1 | | | | | | 1.0 | CP | setnz al | 1 | | 1.0 | | | | | CP | neg eax This is the adc version: | 1* | | | | | | | | xor eax, eax | 1 | 1.0 | | | | | | CP | cmp edi, 0x1 | 2 | | 1.0 | | | | 1.0 | CP | adc eax, 0xffffffff And this is sbb: | 1 | 1.0 | | | | | | | neg edi | 2 | | 1.0 | | | | 1.0 | CP | sbb eax, eax If IACA is trustworthy, then sbb became a single uop in Broadwell, so this will be clearly better than the alternatives going forward. llvm-svn: 306040
2017-06-23 02:11:19 +08:00
; CHECK-NEXT: negb %dil
; CHECK-NEXT: sbbb %al, %al
[x86] add tests for select --> sbb transform; NFC llvm-svn: 306032
2017-06-23 01:01:14 +08:00
; CHECK-NEXT: retq
%cmp = icmp eq i8 %x, 0
%sel = select i1 %cmp, i8 0, i8 -1
ret i8 %sel
}
; (X == 0) ? 0 : -1 --> (X == 0) - 1
define i16 @i16_select_0_or_neg1_as_math(i16 %x) {
; CHECK-LABEL: i16_select_0_or_neg1_as_math:
[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] add/sub (X==0) --> sbb(neg X) Our handling of select-of-constants is lumpy in IR (https://reviews.llvm.org/D24480), lumpy in DAGCombiner, and lumpy in X86ISelLowering. That's why we only had the 'sbb' codegen in 1 out of the 4 tests. This is a step towards smoothing that out. First, show that all of these IR forms are equivalent: http://rise4fun.com/Alive/mx Second, show that the 'sbb' version is faster/smaller. IACA output for SandyBridge (later Intel and AMD chips are similar based on Agner's tables): This is the "obvious" x86 codegen (what gcc appears to produce currently): | Num Of | Ports pressure in cycles | | | Uops | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | | --------------------------------------------------------------------- | 1* | | | | | | | | xor eax, eax | 1 | 1.0 | | | | | | CP | test edi, edi | 1 | | | | | | 1.0 | CP | setnz al | 1 | | 1.0 | | | | | CP | neg eax This is the adc version: | 1* | | | | | | | | xor eax, eax | 1 | 1.0 | | | | | | CP | cmp edi, 0x1 | 2 | | 1.0 | | | | 1.0 | CP | adc eax, 0xffffffff And this is sbb: | 1 | 1.0 | | | | | | | neg edi | 2 | | 1.0 | | | | 1.0 | CP | sbb eax, eax If IACA is trustworthy, then sbb became a single uop in Broadwell, so this will be clearly better than the alternatives going forward. llvm-svn: 306040
2017-06-23 02:11:19 +08:00
; CHECK-NEXT: negw %di
; CHECK-NEXT: sbbw %ax, %ax
[x86] add tests for select --> sbb transform; NFC llvm-svn: 306032
2017-06-23 01:01:14 +08:00
; CHECK-NEXT: retq
%cmp = icmp eq i16 %x, 0
%ext = zext i1 %cmp to i16
%add = add i16 %ext, -1
ret i16 %add
}
[x86] add more tests for select --> sbb transform; NFC These are siblings of the tests added with r306032. llvm-svn: 306064
2017-06-23 06:17:05 +08:00
; (X != 0) ? -1 : 0 --> 0 - (X != 0)
[x86] add tests for select --> sbb transform; NFC llvm-svn: 306032
2017-06-23 01:01:14 +08:00
define i32 @i32_select_0_or_neg1_commuted(i32 %x) {
; CHECK-LABEL: i32_select_0_or_neg1_commuted:
[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] add tests for select --> sbb transform; NFC llvm-svn: 306032
2017-06-23 01:01:14 +08:00
; CHECK-NEXT: negl %edi
; CHECK-NEXT: sbbl %eax, %eax
; CHECK-NEXT: retq
%cmp = icmp ne i32 %x, 0
%sel = select i1 %cmp, i32 -1, i32 0
ret i32 %sel
}
[x86] add more tests for select --> sbb transform; NFC These are siblings of the tests added with r306032. llvm-svn: 306064
2017-06-23 06:17:05 +08:00
; (X != 0) ? -1 : 0 --> 0 - (X != 0)
[x86] add tests for select --> sbb transform; NFC llvm-svn: 306032
2017-06-23 01:01:14 +08:00
define i64 @i64_select_0_or_neg1_commuted_as_math(i64 %x) {
; CHECK-LABEL: i64_select_0_or_neg1_commuted_as_math:
[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] add/sub (X==0) --> sbb(neg X) Our handling of select-of-constants is lumpy in IR (https://reviews.llvm.org/D24480), lumpy in DAGCombiner, and lumpy in X86ISelLowering. That's why we only had the 'sbb' codegen in 1 out of the 4 tests. This is a step towards smoothing that out. First, show that all of these IR forms are equivalent: http://rise4fun.com/Alive/mx Second, show that the 'sbb' version is faster/smaller. IACA output for SandyBridge (later Intel and AMD chips are similar based on Agner's tables): This is the "obvious" x86 codegen (what gcc appears to produce currently): | Num Of | Ports pressure in cycles | | | Uops | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | | --------------------------------------------------------------------- | 1* | | | | | | | | xor eax, eax | 1 | 1.0 | | | | | | CP | test edi, edi | 1 | | | | | | 1.0 | CP | setnz al | 1 | | 1.0 | | | | | CP | neg eax This is the adc version: | 1* | | | | | | | | xor eax, eax | 1 | 1.0 | | | | | | CP | cmp edi, 0x1 | 2 | | 1.0 | | | | 1.0 | CP | adc eax, 0xffffffff And this is sbb: | 1 | 1.0 | | | | | | | neg edi | 2 | | 1.0 | | | | 1.0 | CP | sbb eax, eax If IACA is trustworthy, then sbb became a single uop in Broadwell, so this will be clearly better than the alternatives going forward. llvm-svn: 306040
2017-06-23 02:11:19 +08:00
; CHECK-NEXT: negq %rdi
; CHECK-NEXT: sbbq %rax, %rax
[x86] add tests for select --> sbb transform; NFC llvm-svn: 306032
2017-06-23 01:01:14 +08:00
; CHECK-NEXT: retq
%cmp = icmp ne i64 %x, 0
%ext = zext i1 %cmp to i64
[x86] add more tests for select --> sbb transform; NFC These are siblings of the tests added with r306032. llvm-svn: 306064
2017-06-23 06:17:05 +08:00
%sub = sub i64 0, %ext
ret i64 %sub
}
; (X == 0) ? -1 : 0 --> 0 - (X == 0)
define i64 @i64_select_neg1_or_0(i64 %x) {
; CHECK-LABEL: i64_select_neg1_or_0:
[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] add more tests for select --> sbb transform; NFC These are siblings of the tests added with r306032. llvm-svn: 306064
2017-06-23 06:17:05 +08:00
; CHECK-NEXT: cmpq $1, %rdi
; CHECK-NEXT: sbbq %rax, %rax
; CHECK-NEXT: retq
%cmp = icmp eq i64 %x, 0
%sel = select i1 %cmp, i64 -1, i64 0
ret i64 %sel
}
; (X == 0) ? -1 : 0 --> 0 - (X == 0)
define i32 @i32_select_neg1_or_0_as_math(i32 %x) {
; CHECK-LABEL: i32_select_neg1_or_0_as_math:
[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] add more tests for select --> sbb transform; NFC These are siblings of the tests added with r306032. llvm-svn: 306064
2017-06-23 06:17:05 +08:00
; CHECK-NEXT: cmpl $1, %edi
[x86] add/sub (X==0) --> sbb(cmp X, 1) This is very similar to the transform in: https://reviews.llvm.org/rL306040 ...but in this case, we use cmp X, 1 to set the carry bit as needed. Again, we can show that all of these are logically equivalent (although InstCombine currently canonicalizes to a form not seen here), and if we believe IACA, then this is the smallest/fastest code. Eg, with SNB: | Num Of | Ports pressure in cycles | | | Uops | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | | --------------------------------------------------------------------- | 1 | 1.0 | | | | | | | cmp edi, 0x1 | 2 | | 1.0 | | | | 1.0 | CP | sbb eax, eax The larger motivation is to clean up all select-of-constants combining/lowering because we're missing some common cases. llvm-svn: 306072
2017-06-23 07:47:15 +08:00
; CHECK-NEXT: sbbl %eax, %eax
[x86] add more tests for select --> sbb transform; NFC These are siblings of the tests added with r306032. llvm-svn: 306064
2017-06-23 06:17:05 +08:00
; CHECK-NEXT: retq
%cmp = icmp eq i32 %x, 0
%ext = zext i1 %cmp to i32
%sub = sub i32 0, %ext
ret i32 %sub
}
; (X != 0) ? 0 : -1 --> (X != 0) - 1
define i16 @i16_select_neg1_or_0_commuted(i16 %x) {
; CHECK-LABEL: i16_select_neg1_or_0_commuted:
[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] add more tests for select --> sbb transform; NFC These are siblings of the tests added with r306032. llvm-svn: 306064
2017-06-23 06:17:05 +08:00
; CHECK-NEXT: cmpw $1, %di
[x86] add/sub (X==0) --> sbb(cmp X, 1) This is very similar to the transform in: https://reviews.llvm.org/rL306040 ...but in this case, we use cmp X, 1 to set the carry bit as needed. Again, we can show that all of these are logically equivalent (although InstCombine currently canonicalizes to a form not seen here), and if we believe IACA, then this is the smallest/fastest code. Eg, with SNB: | Num Of | Ports pressure in cycles | | | Uops | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | | --------------------------------------------------------------------- | 1 | 1.0 | | | | | | | cmp edi, 0x1 | 2 | | 1.0 | | | | 1.0 | CP | sbb eax, eax The larger motivation is to clean up all select-of-constants combining/lowering because we're missing some common cases. llvm-svn: 306072
2017-06-23 07:47:15 +08:00
; CHECK-NEXT: sbbw %ax, %ax
[x86] add more tests for select --> sbb transform; NFC These are siblings of the tests added with r306032. llvm-svn: 306064
2017-06-23 06:17:05 +08:00
; CHECK-NEXT: retq
%cmp = icmp ne i16 %x, 0
%sel = select i1 %cmp, i16 0, i16 -1
ret i16 %sel
}
; (X != 0) ? 0 : -1 --> (X != 0) - 1
define i8 @i8_select_neg1_or_0_commuted_as_math(i8 %x) {
; CHECK-LABEL: i8_select_neg1_or_0_commuted_as_math:
[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] add more tests for select --> sbb transform; NFC These are siblings of the tests added with r306032. llvm-svn: 306064
2017-06-23 06:17:05 +08:00
; CHECK-NEXT: cmpb $1, %dil
[x86] add/sub (X==0) --> sbb(cmp X, 1) This is very similar to the transform in: https://reviews.llvm.org/rL306040 ...but in this case, we use cmp X, 1 to set the carry bit as needed. Again, we can show that all of these are logically equivalent (although InstCombine currently canonicalizes to a form not seen here), and if we believe IACA, then this is the smallest/fastest code. Eg, with SNB: | Num Of | Ports pressure in cycles | | | Uops | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | | --------------------------------------------------------------------- | 1 | 1.0 | | | | | | | cmp edi, 0x1 | 2 | | 1.0 | | | | 1.0 | CP | sbb eax, eax The larger motivation is to clean up all select-of-constants combining/lowering because we're missing some common cases. llvm-svn: 306072
2017-06-23 07:47:15 +08:00
; CHECK-NEXT: sbbb %al, %al
[x86] add more tests for select --> sbb transform; NFC These are siblings of the tests added with r306032. llvm-svn: 306064
2017-06-23 06:17:05 +08:00
; CHECK-NEXT: retq
%cmp = icmp ne i8 %x, 0
%ext = zext i1 %cmp to i8
%add = add i8 %ext, -1
ret i8 %add
[x86] add tests for select --> sbb transform; NFC llvm-svn: 306032
2017-06-23 01:01:14 +08:00
}
[x86] add tests for missing sbb transforms; NFC llvm-svn: 306337
2017-06-27 06:20:07 +08:00
; (X <u Y) ? -1 : 0 --> cmp, sbb
define i32 @ult_select_neg1_or_0(i32 %x, i32 %y) nounwind {
; CHECK-LABEL: ult_select_neg1_or_0:
[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] add tests for missing sbb transforms; NFC llvm-svn: 306337
2017-06-27 06:20:07 +08:00
; CHECK-NEXT: cmpl %esi, %edi
; CHECK-NEXT: sbbl %eax, %eax
; CHECK-NEXT: retq
%cmp = icmp ult i32 %x, %y
%ext = sext i1 %cmp to i32
ret i32 %ext
}
; Swap the predicate and compare operands:
; (Y >u X) ? -1 : 0 --> cmp, sbb
define i32 @ugt_select_neg1_or_0(i32 %x, i32 %y) nounwind {
; CHECK-LABEL: ugt_select_neg1_or_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: # %bb.0:
[x86] use more shift or LEA for select-of-constants (2nd try) The previous rev (r310208) failed to account for overflow when subtracting the constants to see if they're suitable for shift/lea. This version add a check for that and more test were added in r310490. We can convert any select-of-constants to math ops: http://rise4fun.com/Alive/d7d For this patch, I'm enhancing an existing x86 transform that uses fake multiplies (they always become shl/lea) to avoid cmov or branching. The current code misses cases where we have a negative constant and a positive constant, so this is just trying to plug that hole. The DAGCombiner diff prevents us from hitting a terrible inefficiency: we can start with a select in IR, create a select DAG node, convert it into a sext, convert it back into a select, and then lower it to sext machine code. Some notes about the test diffs: 1. 2010-08-04-MaskedSignedCompare.ll - We were creating control flow that didn't exist in the IR. 2. memcmp.ll - Choose -1 or 1 is the case that got me looking at this again. We could avoid the push/pop in some cases if we used 'movzbl %al' instead of an xor on a different reg? That's a post-DAG problem though. 3. mul-constant-result.ll - The trade-off between sbb+not vs. setne+neg could be addressed if that's a regression, but those would always be nearly equivalent. 4. pr22338.ll and sext-i1.ll - These tests have undef operands, so we don't actually care about these diffs. 5. sbb.ll - This shows a win for what is likely a common case: choose -1 or 0. 6. select.ll - There's another borderline case here: cmp+sbb+or vs. test+set+lea? Also, sbb+not vs. setae+neg shows up again. 7. select_const.ll - These are motivating cases for the enhancement; replace cmov with cheaper ops. Assembly differences between movzbl and xor to avoid a partial reg stall are caused later by the X86 Fixup SetCC pass. Differential Revision: https://reviews.llvm.org/D35340 llvm-svn: 310717
2017-08-11 23:44:14 +08:00
; CHECK-NEXT: cmpl %esi, %edi
; CHECK-NEXT: sbbl %eax, %eax
[x86] add tests for missing sbb transforms; NFC llvm-svn: 306337
2017-06-27 06:20:07 +08:00
; CHECK-NEXT: retq
%cmp = icmp ugt i32 %y, %x
%ext = sext i1 %cmp to i32
ret i32 %ext
}
; Invert the predicate and effectively swap the select operands:
; (X >=u Y) ? 0 : -1 --> (X <u Y) ? -1 : 0 --> cmp, sbb
define i32 @uge_select_0_or_neg1(i32 %x, i32 %y) nounwind {
; CHECK-LABEL: uge_select_0_or_neg1:
[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] add tests for missing sbb transforms; NFC llvm-svn: 306337
2017-06-27 06:20:07 +08:00
; CHECK-NEXT: cmpl %esi, %edi
[x86] add SBB optimization for SETAE (uge) condition code x86 scalar select-of-constants (Cond ? C1 : C2) combining/lowering is a mess with missing optimizations. We handle some patterns, but miss logical variants. To clean that up, we should convert all select-of-constants to logic/math and enhance the combining for the expected patterns from that. DAGCombiner already has the foundation to allow the transforms, so we just need to fill in the holes for x86 math op lowering. Selecting 0 or -1 needs extra attention to produce the optimal code as shown here. Attempt to verify that all of these IR forms are logically equivalent: http://rise4fun.com/Alive/plxs Earlier steps in this series: rL306040 rL306072 Differential Revision: https://reviews.llvm.org/D34652 llvm-svn: 307404
2017-07-07 22:56:20 +08:00
; CHECK-NEXT: sbbl %eax, %eax
[x86] add tests for missing sbb transforms; NFC llvm-svn: 306337
2017-06-27 06:20:07 +08:00
; CHECK-NEXT: retq
%cmp = icmp uge i32 %x, %y
%ext = zext i1 %cmp to i32
%add = add i32 %ext, -1
ret i32 %add
}
; Swap the predicate and compare operands:
; (Y <=u X) ? 0 : -1 --> (X <u Y) ? -1 : 0 --> cmp, sbb
define i32 @ule_select_0_or_neg1(i32 %x, i32 %y) nounwind {
; CHECK-LABEL: ule_select_0_or_neg1:
[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] add SBB optimization for SETBE (ule) condition code x86 scalar select-of-constants (Cond ? C1 : C2) combining/lowering is a mess with missing optimizations. We handle some patterns, but miss logical variants. To clean that up, we should convert all select-of-constants to logic/math and enhance the combining for the expected patterns from that. Selecting 0 or -1 needs extra attention to produce the optimal code as shown here. Attempt to verify that all of these IR forms are logically equivalent: http://rise4fun.com/Alive/plxs Earlier steps in this series: rL306040 rL306072 rL307404 (D34652) As acknowledged in the earlier review, there's a possibility that some Intel uarch would prefer to produce an xor to clear the fake register operand with sbb %eax, %eax. This will likely need to be addressed in a separate pass. llvm-svn: 307471
2017-07-08 22:04:48 +08:00
; CHECK-NEXT: cmpl %esi, %edi
; CHECK-NEXT: sbbl %eax, %eax
[x86] add tests for missing sbb transforms; NFC llvm-svn: 306337
2017-06-27 06:20:07 +08:00
; CHECK-NEXT: retq
%cmp = icmp ule i32 %y, %x
%ext = zext i1 %cmp to i32
%add = add i32 %ext, -1
ret i32 %add
}
; Verify that subtract with constant is the same thing.
; (X >=u Y) ? 0 : -1 --> (X <u Y) ? -1 : 0 --> cmp, sbb
define i32 @uge_select_0_or_neg1_sub(i32 %x, i32 %y) nounwind {
; CHECK-LABEL: uge_select_0_or_neg1_sub:
[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] add tests for missing sbb transforms; NFC llvm-svn: 306337
2017-06-27 06:20:07 +08:00
; CHECK-NEXT: cmpl %esi, %edi
[x86] add SBB optimization for SETAE (uge) condition code x86 scalar select-of-constants (Cond ? C1 : C2) combining/lowering is a mess with missing optimizations. We handle some patterns, but miss logical variants. To clean that up, we should convert all select-of-constants to logic/math and enhance the combining for the expected patterns from that. DAGCombiner already has the foundation to allow the transforms, so we just need to fill in the holes for x86 math op lowering. Selecting 0 or -1 needs extra attention to produce the optimal code as shown here. Attempt to verify that all of these IR forms are logically equivalent: http://rise4fun.com/Alive/plxs Earlier steps in this series: rL306040 rL306072 Differential Revision: https://reviews.llvm.org/D34652 llvm-svn: 307404
2017-07-07 22:56:20 +08:00
; CHECK-NEXT: sbbl %eax, %eax
[x86] add tests for missing sbb transforms; NFC llvm-svn: 306337
2017-06-27 06:20:07 +08:00
; CHECK-NEXT: retq
%cmp = icmp uge i32 %x, %y
%ext = zext i1 %cmp to i32
%sub = sub i32 %ext, 1
ret i32 %sub
}
[x86] add tests for improving sbb transforms; NFC We're subtracting X from X the hard way... llvm-svn: 307819
2017-07-13 01:44:50 +08:00
; Check more sub-from-zero patterns.
; (X >u Y) ? -1 : 0 --> cmp, sbb
define i64 @ugt_select_neg1_or_0_sub(i64 %x, i64 %y) nounwind {
; CHECK-LABEL: ugt_select_neg1_or_0_sub:
[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] add tests for improving sbb transforms; NFC We're subtracting X from X the hard way... llvm-svn: 307819
2017-07-13 01:44:50 +08:00
; CHECK-NEXT: cmpq %rdi, %rsi
[x86] improve SBB optimizations for SETB/SETA with subtract This is another step towards removing a combine that turns sext into select of constants and preparing the backend for an IR future where select is the canonical form. Earlier commits in this area: https://reviews.llvm.org/rL306040 https://reviews.llvm.org/rL306072 https://reviews.llvm.org/rL307404 (https://reviews.llvm.org/D34652) https://reviews.llvm.org/rL307471 llvm-svn: 307821
2017-07-13 01:56:46 +08:00
; CHECK-NEXT: sbbq %rax, %rax
[x86] add tests for improving sbb transforms; NFC We're subtracting X from X the hard way... llvm-svn: 307819
2017-07-13 01:44:50 +08:00
; CHECK-NEXT: retq
%cmp = icmp ugt i64 %x, %y
%zext = zext i1 %cmp to i64
%sub = sub i64 0, %zext
ret i64 %sub
}
; Swap the predicate and compare operands:
; (Y <u X) ? -1 : 0 --> cmp, sbb
define i16 @ult_select_neg1_or_0_sub(i16 %x, i16 %y) nounwind {
; CHECK-LABEL: ult_select_neg1_or_0_sub:
[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] add tests for improving sbb transforms; NFC We're subtracting X from X the hard way... llvm-svn: 307819
2017-07-13 01:44:50 +08:00
; CHECK-NEXT: cmpw %di, %si
[x86] improve SBB optimizations for SETB/SETA with subtract This is another step towards removing a combine that turns sext into select of constants and preparing the backend for an IR future where select is the canonical form. Earlier commits in this area: https://reviews.llvm.org/rL306040 https://reviews.llvm.org/rL306072 https://reviews.llvm.org/rL307404 (https://reviews.llvm.org/D34652) https://reviews.llvm.org/rL307471 llvm-svn: 307821
2017-07-13 01:56:46 +08:00
; CHECK-NEXT: sbbw %ax, %ax
[x86] add tests for improving sbb transforms; NFC We're subtracting X from X the hard way... llvm-svn: 307819
2017-07-13 01:44:50 +08:00
; CHECK-NEXT: retq
%cmp = icmp ult i16 %y, %x
%zext = zext i1 %cmp to i16
%sub = sub i16 0, %zext
ret i16 %sub
}
[x86] fix value types for SBB transform (PR33560) I'm not sure yet why this wouldn't fail in the simple case, but clearly I used the wrong value type with: https://reviews.llvm.org/rL306040 ...and the bug manifests with: https://bugs.llvm.org/show_bug.cgi?id=33560 llvm-svn: 306139
2017-06-24 02:42:15 +08:00
; Make sure we're creating nodes with the right value types. This would crash.
; https://bugs.llvm.org/show_bug.cgi?id=33560
define void @PR33560(i8 %x, i64 %y) {
; CHECK-LABEL: PR33560:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: # %bb.0: # %entry
[x86] fix value types for SBB transform (PR33560) I'm not sure yet why this wouldn't fail in the simple case, but clearly I used the wrong value type with: https://reviews.llvm.org/rL306040 ...and the bug manifests with: https://bugs.llvm.org/show_bug.cgi?id=33560 llvm-svn: 306139
2017-06-24 02:42:15 +08:00
; CHECK-NEXT: negb %dil
; CHECK-NEXT: sbbq %rax, %rax
; CHECK-NEXT: cmpq %rsi, %rax
; CHECK-NEXT: retq
entry:
%cmp1 = icmp eq i8 %x, 0
%ext = zext i1 %cmp1 to i64
%add = add i64 %ext, -1
%cmp2 = icmp eq i64 %add, %y
br i1 %cmp2, label %end, label %else
else:
%tmp7 = zext i1 %cmp1 to i8
br label %end
end:
ret void
}