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/inline-asm-fpstack.ll

509 lines
17 KiB
LLVM
Raw Normal View History

[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
Updated test with -verify-machineinstrs to check for PR21931 llvm-svn: 288242
2016-11-30 21:21:12 +08:00
; RUN: llc < %s -mcpu=generic -mtriple=i386-apple-darwin -verify-machineinstrs -no-integrated-as | FileCheck %s
Add ScheduleDAG support for copytoreg where the src/dst register are in different register classes, e.g. copy of ST(0) to RFP*. This gets some really trivial inline asm working that plops things on the top of stack (PR879) llvm-svn: 48105
2008-03-09 16:49:15 +08:00
FileCheckize inline asm FP stack tests llvm-svn: 108046
2010-07-11 00:30:25 +08:00
; There should be no stack manipulations between the inline asm and ret.
Add ScheduleDAG support for copytoreg where the src/dst register are in different register classes, e.g. copy of ST(0) to RFP*. This gets some really trivial inline asm working that plops things on the top of stack (PR879) llvm-svn: 48105
2008-03-09 16:49:15 +08:00
define x86_fp80 @test1() {
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-LABEL: test1:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: ## %bb.0:
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: ## InlineAsm Start
; CHECK-NEXT: fld0
; CHECK-NEXT: ## InlineAsm End
; CHECK-NEXT: retl
%tmp85 = call x86_fp80 asm sideeffect "fld0", "={st(0)}"()
ret x86_fp80 %tmp85
Add ScheduleDAG support for copytoreg where the src/dst register are in different register classes, e.g. copy of ST(0) to RFP*. This gets some really trivial inline asm working that plops things on the top of stack (PR879) llvm-svn: 48105
2008-03-09 16:49:15 +08:00
}
define double @test2() {
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +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:
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: ## InlineAsm Start
; CHECK-NEXT: fld0
; CHECK-NEXT: ## InlineAsm End
; CHECK-NEXT: retl
%tmp85 = call double asm sideeffect "fld0", "={st(0)}"()
ret double %tmp85
Add ScheduleDAG support for copytoreg where the src/dst register are in different register classes, e.g. copy of ST(0) to RFP*. This gets some really trivial inline asm working that plops things on the top of stack (PR879) llvm-svn: 48105
2008-03-09 16:49:15 +08:00
}
FileCheckize inline asm FP stack tests llvm-svn: 108046
2010-07-11 00:30:25 +08:00
; Setting up argument in st(0) should be a single fld.
; Asm consumes stack, nothing should be popped.
teach X86InstrInfo::copyRegToReg how to copy into ST(0) from an RFP register class. Teach ScheduleDAG how to handle CopyToReg with different src/dst reg classes. This allows us to compile trivial inline asms that expect stuff on the top of x87-fp stack. llvm-svn: 48107
2008-03-09 17:15:31 +08:00
define void @test3(x86_fp80 %X) {
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +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][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: fldt {{[0-9]+}}(%esp)
; CHECK-NEXT: ## InlineAsm Start
; CHECK-NEXT: frob
; CHECK-NEXT: ## InlineAsm End
; CHECK-NEXT: retl
call void asm sideeffect "frob ", "{st(0)},~{st},~{dirflag},~{fpsr},~{flags}"( x86_fp80 %X)
ret void
teach X86InstrInfo::copyRegToReg how to copy into ST(0) from an RFP register class. Teach ScheduleDAG how to handle CopyToReg with different src/dst reg classes. This allows us to compile trivial inline asms that expect stuff on the top of x87-fp stack. llvm-svn: 48107
2008-03-09 17:15:31 +08:00
}
define void @test4(double %X) {
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-LABEL: test4:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: ## %bb.0:
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: fldl {{[0-9]+}}(%esp)
; CHECK-NEXT: ## InlineAsm Start
; CHECK-NEXT: frob
; CHECK-NEXT: ## InlineAsm End
; CHECK-NEXT: retl
call void asm sideeffect "frob ", "{st(0)},~{st},~{dirflag},~{fpsr},~{flags}"( double %X)
ret void
teach X86InstrInfo::copyRegToReg how to copy into ST(0) from an RFP register class. Teach ScheduleDAG how to handle CopyToReg with different src/dst reg classes. This allows us to compile trivial inline asms that expect stuff on the top of x87-fp stack. llvm-svn: 48107
2008-03-09 17:15:31 +08:00
}
FileCheckize inline asm FP stack tests llvm-svn: 108046
2010-07-11 00:30:25 +08:00
; Same as test3/4, but using value from fadd.
; The fadd can be done in xmm or x87 regs - we don't test that.
teach X86InstrInfo::copyRegToReg how to copy into ST(0) from an RFP register class. Teach ScheduleDAG how to handle CopyToReg with different src/dst reg classes. This allows us to compile trivial inline asms that expect stuff on the top of x87-fp stack. llvm-svn: 48107
2008-03-09 17:15:31 +08:00
define void @test5(double %X) {
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-LABEL: test5:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: ## %bb.0:
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: fldl {{[0-9]+}}(%esp)
; CHECK-NEXT: fadds LCPI4_0
; CHECK-NEXT: ## InlineAsm Start
; CHECK-NEXT: frob
; CHECK-NEXT: ## InlineAsm End
; CHECK-NEXT: retl
%Y = fadd double %X, 123.0
call void asm sideeffect "frob ", "{st(0)},~{st},~{dirflag},~{fpsr},~{flags}"( double %Y)
ret void
teach X86InstrInfo::copyRegToReg how to copy into ST(0) from an RFP register class. Teach ScheduleDAG how to handle CopyToReg with different src/dst reg classes. This allows us to compile trivial inline asms that expect stuff on the top of x87-fp stack. llvm-svn: 48107
2008-03-09 17:15:31 +08:00
}
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
define void @test6(double %A, double %B, double %C, double %D, double %E) nounwind {
; CHECK-LABEL: test6:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: ## %bb.0: ## %entry
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: fldl {{[0-9]+}}(%esp)
; CHECK-NEXT: fldl {{[0-9]+}}(%esp)
; CHECK-NEXT: fldl {{[0-9]+}}(%esp)
; CHECK-NEXT: fldl {{[0-9]+}}(%esp)
; CHECK-NEXT: fldl {{[0-9]+}}(%esp)
; CHECK-NEXT: ## InlineAsm Start
[X86] Print %st(0) as %st when its implicit to the instruction. Continue printing it as %st(0) when its encoded in the instruction. This is a step back from the change I made in r352985. This appears to be more consistent with gcc and objdump behavior. llvm-svn: 353015
2019-02-04 12:15:10 +08:00
; CHECK-NEXT: foo %st %st
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: ## InlineAsm End
Revert r352985 "[X86] Print %st(0) as %st to match what gcc inline asm uses as the clobber name to make MS inline asm work correctly" Looking into gcc and objdump behavior more this was overly aggressive. If the register is encoded in the instruction we should print %st(0), if its implicit we should print %st. I'll be making a more directed change in a future patch. llvm-svn: 353013
2019-02-04 12:15:02 +08:00
; CHECK-NEXT: fstp %st(0)
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: ## InlineAsm Start
[X86] Print %st(0) as %st when its implicit to the instruction. Continue printing it as %st(0) when its encoded in the instruction. This is a step back from the change I made in r352985. This appears to be more consistent with gcc and objdump behavior. llvm-svn: 353015
2019-02-04 12:15:10 +08:00
; CHECK-NEXT: bar %st(1) %st
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: ## InlineAsm End
; CHECK-NEXT: fstp %st(1)
Revert r352985 "[X86] Print %st(0) as %st to match what gcc inline asm uses as the clobber name to make MS inline asm work correctly" Looking into gcc and objdump behavior more this was overly aggressive. If the register is encoded in the instruction we should print %st(0), if its implicit we should print %st. I'll be making a more directed change in a future patch. llvm-svn: 353013
2019-02-04 12:15:02 +08:00
; CHECK-NEXT: fstp %st(0)
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: ## InlineAsm Start
[X86] Print %st(0) as %st when its implicit to the instruction. Continue printing it as %st(0) when its encoded in the instruction. This is a step back from the change I made in r352985. This appears to be more consistent with gcc and objdump behavior. llvm-svn: 353015
2019-02-04 12:15:10 +08:00
; CHECK-NEXT: baz %st(1) %st
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: ## InlineAsm End
Revert r352985 "[X86] Print %st(0) as %st to match what gcc inline asm uses as the clobber name to make MS inline asm work correctly" Looking into gcc and objdump behavior more this was overly aggressive. If the register is encoded in the instruction we should print %st(0), if its implicit we should print %st. I'll be making a more directed change in a future patch. llvm-svn: 353013
2019-02-04 12:15:02 +08:00
; CHECK-NEXT: fstp %st(0)
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: ## InlineAsm Start
[X86] Print %st(0) as %st when its implicit to the instruction. Continue printing it as %st(0) when its encoded in the instruction. This is a step back from the change I made in r352985. This appears to be more consistent with gcc and objdump behavior. llvm-svn: 353015
2019-02-04 12:15:10 +08:00
; CHECK-NEXT: baz %st
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: ## InlineAsm End
Revert r352985 "[X86] Print %st(0) as %st to match what gcc inline asm uses as the clobber name to make MS inline asm work correctly" Looking into gcc and objdump behavior more this was overly aggressive. If the register is encoded in the instruction we should print %st(0), if its implicit we should print %st. I'll be making a more directed change in a future patch. llvm-svn: 353013
2019-02-04 12:15:02 +08:00
; CHECK-NEXT: fstp %st(0)
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: retl
Implement basic support for the 'f' register class constraint. This basically works, but probably won't if you mix it with 't' or 'u' yet. llvm-svn: 48243
2008-03-12 03:50:13 +08:00
entry:
FileCheckize inline asm FP stack tests llvm-svn: 108046
2010-07-11 00:30:25 +08:00
; Uses the same value twice, should have one fstp after the asm.
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
tail call void asm sideeffect "foo $0 $1", "f,f,~{dirflag},~{fpsr},~{flags}"( double %A, double %A ) nounwind
FileCheckize inline asm FP stack tests llvm-svn: 108046
2010-07-11 00:30:25 +08:00
; Uses two different values, should be in st(0)/st(1) and both be popped.
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
tail call void asm sideeffect "bar $0 $1", "f,f,~{dirflag},~{fpsr},~{flags}"( double %B, double %C ) nounwind
; Uses two different values, one of which isn't killed in this asm, it should not be popped after the asm.
tail call void asm sideeffect "baz $0 $1", "f,f,~{dirflag},~{fpsr},~{flags}"( double %D, double %E ) nounwind
FileCheckize inline asm FP stack tests llvm-svn: 108046
2010-07-11 00:30:25 +08:00
; This is the last use of %D, so it should be popped after.
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
tail call void asm sideeffect "baz $0", "f,~{dirflag},~{fpsr},~{flags}"( double %D ) nounwind
ret void
Implement basic support for the 'f' register class constraint. This basically works, but probably won't if you mix it with 't' or 'u' yet. llvm-svn: 48243
2008-03-12 03:50:13 +08:00
}
Add ScheduleDAG support for copytoreg where the src/dst register are in different register classes, e.g. copy of ST(0) to RFP*. This gets some really trivial inline asm working that plops things on the top of stack (PR879) llvm-svn: 48105
2008-03-09 16:49:15 +08:00
Move all inline-asm-fpstack tests to a single file. Also fix some of the tests that were actually testing wrong behavior - An input operand in {st} is only popped by the inline asm when {st} is also in the clobber list. The original bug reports all had ~{st} clobbers as they should. llvm-svn: 133916
2011-06-28 01:27:37 +08:00
; PR4185
; Passing a non-killed value to asm in {st}.
; Make sure it is duped before.
; asm kills st(0), so we shouldn't pop anything
; A valid alternative would be to remat the constant pool load before each
; inline asm.
define void @testPR4185() {
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-LABEL: testPR4185:
[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: ## %return
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: flds LCPI6_0
Revert r352985 "[X86] Print %st(0) as %st to match what gcc inline asm uses as the clobber name to make MS inline asm work correctly" Looking into gcc and objdump behavior more this was overly aggressive. If the register is encoded in the instruction we should print %st(0), if its implicit we should print %st. I'll be making a more directed change in a future patch. llvm-svn: 353013
2019-02-04 12:15:02 +08:00
; CHECK-NEXT: fld %st(0)
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: ## InlineAsm Start
[X86] Print %st(0) as %st when its implicit to the instruction. Continue printing it as %st(0) when its encoded in the instruction. This is a step back from the change I made in r352985. This appears to be more consistent with gcc and objdump behavior. llvm-svn: 353015
2019-02-04 12:15:10 +08:00
; CHECK-NEXT: fistpl %st
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: ## InlineAsm End
; CHECK-NEXT: ## InlineAsm Start
[X86] Print %st(0) as %st when its implicit to the instruction. Continue printing it as %st(0) when its encoded in the instruction. This is a step back from the change I made in r352985. This appears to be more consistent with gcc and objdump behavior. llvm-svn: 353015
2019-02-04 12:15:10 +08:00
; CHECK-NEXT: fistpl %st
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: ## InlineAsm End
; CHECK-NEXT: retl
Move all inline-asm-fpstack tests to a single file. Also fix some of the tests that were actually testing wrong behavior - An input operand in {st} is only popped by the inline asm when {st} is also in the clobber list. The original bug reports all had ~{st} clobbers as they should. llvm-svn: 133916
2011-06-28 01:27:37 +08:00
return:
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
call void asm sideeffect "fistpl $0", "{st},~{st}"(double 1.000000e+06)
call void asm sideeffect "fistpl $0", "{st},~{st}"(double 1.000000e+06)
ret void
Move all inline-asm-fpstack tests to a single file. Also fix some of the tests that were actually testing wrong behavior - An input operand in {st} is only popped by the inline asm when {st} is also in the clobber list. The original bug reports all had ~{st} clobbers as they should. llvm-svn: 133916
2011-06-28 01:27:37 +08:00
}
Clean up the handling of the x87 fp stack to make it more robust. Drop the FpMov instructions, use plain COPY instead. Drop the FpSET/GET instruction for accessing fixed stack positions. Instead use normal COPY to/from ST registers around inline assembly, and provide a single new FpPOP_RETVAL instruction that can access the return value(s) from a call. This is still necessary since you cannot tell from the CALL instruction alone if it returns anything on the FP stack. Teach fast isel to use this. This provides a much more robust way of handling fixed stack registers - we can tolerate arbitrary FP stack instructions inserted around calls and inline assembly. Live range splitting could sometimes break x87 code by inserting spill code in unfortunate places. As a bonus we handle floating point inline assembly correctly now. llvm-svn: 134018
2011-06-29 02:32:28 +08:00
; Passing a non-killed value through asm in {st}.
; Make sure it is not duped before.
; Second asm kills st(0), so we shouldn't pop anything
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; A valid alternative would be to remat the constant pool load before each inline asm.
Clean up the handling of the x87 fp stack to make it more robust. Drop the FpMov instructions, use plain COPY instead. Drop the FpSET/GET instruction for accessing fixed stack positions. Instead use normal COPY to/from ST registers around inline assembly, and provide a single new FpPOP_RETVAL instruction that can access the return value(s) from a call. This is still necessary since you cannot tell from the CALL instruction alone if it returns anything on the FP stack. Teach fast isel to use this. This provides a much more robust way of handling fixed stack registers - we can tolerate arbitrary FP stack instructions inserted around calls and inline assembly. Live range splitting could sometimes break x87 code by inserting spill code in unfortunate places. As a bonus we handle floating point inline assembly correctly now. llvm-svn: 134018
2011-06-29 02:32:28 +08:00
define void @testPR4185b() {
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-LABEL: testPR4185b:
[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: ## %return
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: flds LCPI7_0
; CHECK-NEXT: ## InlineAsm Start
[X86] Print %st(0) as %st when its implicit to the instruction. Continue printing it as %st(0) when its encoded in the instruction. This is a step back from the change I made in r352985. This appears to be more consistent with gcc and objdump behavior. llvm-svn: 353015
2019-02-04 12:15:10 +08:00
; CHECK-NEXT: fistl %st
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: ## InlineAsm End
; CHECK-NEXT: ## InlineAsm Start
[X86] Print %st(0) as %st when its implicit to the instruction. Continue printing it as %st(0) when its encoded in the instruction. This is a step back from the change I made in r352985. This appears to be more consistent with gcc and objdump behavior. llvm-svn: 353015
2019-02-04 12:15:10 +08:00
; CHECK-NEXT: fistpl %st
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: ## InlineAsm End
; CHECK-NEXT: retl
Clean up the handling of the x87 fp stack to make it more robust. Drop the FpMov instructions, use plain COPY instead. Drop the FpSET/GET instruction for accessing fixed stack positions. Instead use normal COPY to/from ST registers around inline assembly, and provide a single new FpPOP_RETVAL instruction that can access the return value(s) from a call. This is still necessary since you cannot tell from the CALL instruction alone if it returns anything on the FP stack. Teach fast isel to use this. This provides a much more robust way of handling fixed stack registers - we can tolerate arbitrary FP stack instructions inserted around calls and inline assembly. Live range splitting could sometimes break x87 code by inserting spill code in unfortunate places. As a bonus we handle floating point inline assembly correctly now. llvm-svn: 134018
2011-06-29 02:32:28 +08:00
return:
call void asm sideeffect "fistl $0", "{st}"(double 1.000000e+06)
call void asm sideeffect "fistpl $0", "{st},~{st}"(double 1.000000e+06)
ret void
}
Move all inline-asm-fpstack tests to a single file. Also fix some of the tests that were actually testing wrong behavior - An input operand in {st} is only popped by the inline asm when {st} is also in the clobber list. The original bug reports all had ~{st} clobbers as they should. llvm-svn: 133916
2011-06-28 01:27:37 +08:00
; PR4459
; The return value from ceil must be duped before being consumed by asm.
define void @testPR4459(x86_fp80 %a) {
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-LABEL: testPR4459:
[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][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: subl $28, %esp
; CHECK-NEXT: .cfi_def_cfa_offset 32
; CHECK-NEXT: fldt {{[0-9]+}}(%esp)
; CHECK-NEXT: fstpt (%esp)
; CHECK-NEXT: calll _ceil
Revert r352985 "[X86] Print %st(0) as %st to match what gcc inline asm uses as the clobber name to make MS inline asm work correctly" Looking into gcc and objdump behavior more this was overly aggressive. If the register is encoded in the instruction we should print %st(0), if its implicit we should print %st. I'll be making a more directed change in a future patch. llvm-svn: 353013
2019-02-04 12:15:02 +08:00
; CHECK-NEXT: fld %st(0)
Re-enable "[MachineCopyPropagation] Extend pass to do COPY source forwarding" Re-enable commit r323991 now that r325931 has been committed to make MachineOperand::isRenamable() check more conservative w.r.t. code changes and opt-in on a per-target basis. llvm-svn: 326208
2018-02-28 00:59:10 +08:00
; CHECK-NEXT: fxch %st(1)
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: ## InlineAsm Start
[X86] Print %st(0) as %st when its implicit to the instruction. Continue printing it as %st(0) when its encoded in the instruction. This is a step back from the change I made in r352985. This appears to be more consistent with gcc and objdump behavior. llvm-svn: 353015
2019-02-04 12:15:10 +08:00
; CHECK-NEXT: fistpl %st
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: ## InlineAsm End
; CHECK-NEXT: fstpt (%esp)
; CHECK-NEXT: calll _test3
; CHECK-NEXT: addl $28, %esp
; CHECK-NEXT: retl
Move all inline-asm-fpstack tests to a single file. Also fix some of the tests that were actually testing wrong behavior - An input operand in {st} is only popped by the inline asm when {st} is also in the clobber list. The original bug reports all had ~{st} clobbers as they should. llvm-svn: 133916
2011-06-28 01:27:37 +08:00
entry:
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
%0 = call x86_fp80 @ceil(x86_fp80 %a)
call void asm sideeffect "fistpl $0", "{st},~{st}"( x86_fp80 %0)
call void @test3(x86_fp80 %0 )
ret void
Move all inline-asm-fpstack tests to a single file. Also fix some of the tests that were actually testing wrong behavior - An input operand in {st} is only popped by the inline asm when {st} is also in the clobber list. The original bug reports all had ~{st} clobbers as they should. llvm-svn: 133916
2011-06-28 01:27:37 +08:00
}
declare x86_fp80 @ceil(x86_fp80)
; PR4484
; test1 leaves a value on the stack that is needed after the asm.
; Load %a from stack after ceil
; Set up call to test.
define void @testPR4484(x86_fp80 %a) {
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-LABEL: testPR4484:
[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][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: subl $28, %esp
; CHECK-NEXT: .cfi_def_cfa_offset 32
; CHECK-NEXT: fldt {{[0-9]+}}(%esp)
[X86] Regenerate test to drop 'End function' comments some other other regex updates. llvm-svn: 353014
2019-02-04 12:15:04 +08:00
; CHECK-NEXT: fstpt {{[-0-9]+}}(%e{{[sb]}}p) ## 10-byte Folded Spill
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: calll _test1
[X86] Regenerate test to drop 'End function' comments some other other regex updates. llvm-svn: 353014
2019-02-04 12:15:04 +08:00
; CHECK-NEXT: fldt {{[-0-9]+}}(%e{{[sb]}}p) ## 10-byte Folded Reload
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: ## InlineAsm Start
[X86] Print %st(0) as %st when its implicit to the instruction. Continue printing it as %st(0) when its encoded in the instruction. This is a step back from the change I made in r352985. This appears to be more consistent with gcc and objdump behavior. llvm-svn: 353015
2019-02-04 12:15:10 +08:00
; CHECK-NEXT: fistpl %st
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: ## InlineAsm End
; CHECK-NEXT: fstpt (%esp)
; CHECK-NEXT: calll _test3
; CHECK-NEXT: addl $28, %esp
; CHECK-NEXT: retl
Move all inline-asm-fpstack tests to a single file. Also fix some of the tests that were actually testing wrong behavior - An input operand in {st} is only popped by the inline asm when {st} is also in the clobber list. The original bug reports all had ~{st} clobbers as they should. llvm-svn: 133916
2011-06-28 01:27:37 +08:00
entry:
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
%0 = call x86_fp80 @test1()
call void asm sideeffect "fistpl $0", "{st},~{st}"(x86_fp80 %a)
call void @test3(x86_fp80 %0)
ret void
Move all inline-asm-fpstack tests to a single file. Also fix some of the tests that were actually testing wrong behavior - An input operand in {st} is only popped by the inline asm when {st} is also in the clobber list. The original bug reports all had ~{st} clobbers as they should. llvm-svn: 133916
2011-06-28 01:27:37 +08:00
}
; PR4485
define void @testPR4485(x86_fp80* %a) {
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-LABEL: testPR4485:
[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][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %eax
; CHECK-NEXT: fldt (%eax)
; CHECK-NEXT: flds LCPI10_0
[X86] Print %st(0) as %st when its implicit to the instruction. Continue printing it as %st(0) when its encoded in the instruction. This is a step back from the change I made in r352985. This appears to be more consistent with gcc and objdump behavior. llvm-svn: 353015
2019-02-04 12:15:10 +08:00
; CHECK-NEXT: fmul %st, %st(1)
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: flds LCPI10_1
[X86] Print %st(0) as %st when its implicit to the instruction. Continue printing it as %st(0) when its encoded in the instruction. This is a step back from the change I made in r352985. This appears to be more consistent with gcc and objdump behavior. llvm-svn: 353015
2019-02-04 12:15:10 +08:00
; CHECK-NEXT: fmul %st, %st(2)
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: fxch %st(2)
; CHECK-NEXT: ## InlineAsm Start
[X86] Print %st(0) as %st when its implicit to the instruction. Continue printing it as %st(0) when its encoded in the instruction. This is a step back from the change I made in r352985. This appears to be more consistent with gcc and objdump behavior. llvm-svn: 353015
2019-02-04 12:15:10 +08:00
; CHECK-NEXT: fistpl %st
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: ## InlineAsm End
; CHECK-NEXT: fldt (%eax)
[X86] Print all register forms of x87 fadd/fsub/fdiv/fmul as having two arguments where on is %st. All of these instructions consume one encoded register and the other register is %st. They either write the result to %st or the encoded register. Previously we printed both arguments when the encoded register was written. And we printed one argument when the result was written to %st. For the stack popping forms the encoded register is always the destination and we didn't print both operands. This was inconsistent with gcc and objdump and just makes the output assembly code harder to read. This patch changes things to always print both operands making us consistent with gcc and objdump. The parser should still be able to handle the single register forms just as it did before. This also matches the GNU assembler behavior. llvm-svn: 353061
2019-02-05 01:28:18 +08:00
; CHECK-NEXT: fmulp %st, %st(1)
; CHECK-NEXT: fmulp %st, %st(1)
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: ## InlineAsm Start
[X86] Print %st(0) as %st when its implicit to the instruction. Continue printing it as %st(0) when its encoded in the instruction. This is a step back from the change I made in r352985. This appears to be more consistent with gcc and objdump behavior. llvm-svn: 353015
2019-02-04 12:15:10 +08:00
; CHECK-NEXT: fistpl %st
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: ## InlineAsm End
; CHECK-NEXT: retl
Move all inline-asm-fpstack tests to a single file. Also fix some of the tests that were actually testing wrong behavior - An input operand in {st} is only popped by the inline asm when {st} is also in the clobber list. The original bug reports all had ~{st} clobbers as they should. llvm-svn: 133916
2011-06-28 01:27:37 +08:00
entry:
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
%0 = load x86_fp80, x86_fp80* %a, align 16
%1 = fmul x86_fp80 %0, 0xK4006B400000000000000
%2 = fmul x86_fp80 %1, 0xK4012F424000000000000
tail call void asm sideeffect "fistpl $0", "{st},~{st}"(x86_fp80 %2)
%3 = load x86_fp80, x86_fp80* %a, align 16
%4 = fmul x86_fp80 %3, 0xK4006B400000000000000
%5 = fmul x86_fp80 %4, 0xK4012F424000000000000
tail call void asm sideeffect "fistpl $0", "{st},~{st}"(x86_fp80 %5)
ret void
Move all inline-asm-fpstack tests to a single file. Also fix some of the tests that were actually testing wrong behavior - An input operand in {st} is only popped by the inline asm when {st} is also in the clobber list. The original bug reports all had ~{st} clobbers as they should. llvm-svn: 133916
2011-06-28 01:27:37 +08:00
}
Clean up the handling of the x87 fp stack to make it more robust. Drop the FpMov instructions, use plain COPY instead. Drop the FpSET/GET instruction for accessing fixed stack positions. Instead use normal COPY to/from ST registers around inline assembly, and provide a single new FpPOP_RETVAL instruction that can access the return value(s) from a call. This is still necessary since you cannot tell from the CALL instruction alone if it returns anything on the FP stack. Teach fast isel to use this. This provides a much more robust way of handling fixed stack registers - we can tolerate arbitrary FP stack instructions inserted around calls and inline assembly. Live range splitting could sometimes break x87 code by inserting spill code in unfortunate places. As a bonus we handle floating point inline assembly correctly now. llvm-svn: 134018
2011-06-29 02:32:28 +08:00
; An input argument in a fixed position is implicitly popped by the asm only if
; the input argument is tied to an output register, or it is in the clobber list.
; The clobber list case is tested above.
;
; This doesn't implicitly pop the stack:
;
; void fist1(long double x, int *p) {
; asm volatile ("fistl %1" : : "t"(x), "m"(*p));
; }
define void @fist1(x86_fp80 %x, i32* %p) nounwind ssp {
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-LABEL: fist1:
[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][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: fldt {{[0-9]+}}(%esp)
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %eax
; CHECK-NEXT: ## InlineAsm Start
; CHECK-NEXT: fistl (%eax)
; CHECK-NEXT: ## InlineAsm End
Revert r352985 "[X86] Print %st(0) as %st to match what gcc inline asm uses as the clobber name to make MS inline asm work correctly" Looking into gcc and objdump behavior more this was overly aggressive. If the register is encoded in the instruction we should print %st(0), if its implicit we should print %st. I'll be making a more directed change in a future patch. llvm-svn: 353013
2019-02-04 12:15:02 +08:00
; CHECK-NEXT: fstp %st(0)
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: retl
Clean up the handling of the x87 fp stack to make it more robust. Drop the FpMov instructions, use plain COPY instead. Drop the FpSET/GET instruction for accessing fixed stack positions. Instead use normal COPY to/from ST registers around inline assembly, and provide a single new FpPOP_RETVAL instruction that can access the return value(s) from a call. This is still necessary since you cannot tell from the CALL instruction alone if it returns anything on the FP stack. Teach fast isel to use this. This provides a much more robust way of handling fixed stack registers - we can tolerate arbitrary FP stack instructions inserted around calls and inline assembly. Live range splitting could sometimes break x87 code by inserting spill code in unfortunate places. As a bonus we handle floating point inline assembly correctly now. llvm-svn: 134018
2011-06-29 02:32:28 +08:00
entry:
tail call void asm sideeffect "fistl $1", "{st},*m,~{memory},~{dirflag},~{fpsr},~{flags}"(x86_fp80 %x, i32* %p) nounwind
ret void
}
; Here, the input operand is tied to an output which means that is is
; implicitly popped (and then the output is implicitly pushed).
;
; long double fist2(long double x, int *p) {
; long double y;
; asm ("fistl %1" : "=&t"(y) : "0"(x), "m"(*p) : "memory");
; return y;
; }
define x86_fp80 @fist2(x86_fp80 %x, i32* %p) nounwind ssp {
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-LABEL: fist2:
[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][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: fldt {{[0-9]+}}(%esp)
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %eax
; CHECK-NEXT: ## InlineAsm Start
; CHECK-NEXT: fistl (%eax)
; CHECK-NEXT: ## InlineAsm End
; CHECK-NEXT: retl
Clean up the handling of the x87 fp stack to make it more robust. Drop the FpMov instructions, use plain COPY instead. Drop the FpSET/GET instruction for accessing fixed stack positions. Instead use normal COPY to/from ST registers around inline assembly, and provide a single new FpPOP_RETVAL instruction that can access the return value(s) from a call. This is still necessary since you cannot tell from the CALL instruction alone if it returns anything on the FP stack. Teach fast isel to use this. This provides a much more robust way of handling fixed stack registers - we can tolerate arbitrary FP stack instructions inserted around calls and inline assembly. Live range splitting could sometimes break x87 code by inserting spill code in unfortunate places. As a bonus we handle floating point inline assembly correctly now. llvm-svn: 134018
2011-06-29 02:32:28 +08:00
entry:
%0 = tail call x86_fp80 asm "fistl $2", "=&{st},0,*m,~{memory},~{dirflag},~{fpsr},~{flags}"(x86_fp80 %x, i32* %p) nounwind
ret x86_fp80 %0
}
; An 'f' constraint is never implicitly popped:
;
; void fucomp1(long double x, long double y) {
; asm volatile ("fucomp %1" : : "t"(x), "f"(y) : "st");
; }
define void @fucomp1(x86_fp80 %x, x86_fp80 %y) nounwind ssp {
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-LABEL: fucomp1:
[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][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: fldt {{[0-9]+}}(%esp)
; CHECK-NEXT: fldt {{[0-9]+}}(%esp)
; CHECK-NEXT: fxch %st(1)
; CHECK-NEXT: ## InlineAsm Start
; CHECK-NEXT: fucomp %st(1)
; CHECK-NEXT: ## InlineAsm End
Revert r352985 "[X86] Print %st(0) as %st to match what gcc inline asm uses as the clobber name to make MS inline asm work correctly" Looking into gcc and objdump behavior more this was overly aggressive. If the register is encoded in the instruction we should print %st(0), if its implicit we should print %st. I'll be making a more directed change in a future patch. llvm-svn: 353013
2019-02-04 12:15:02 +08:00
; CHECK-NEXT: fstp %st(0)
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: retl
Clean up the handling of the x87 fp stack to make it more robust. Drop the FpMov instructions, use plain COPY instead. Drop the FpSET/GET instruction for accessing fixed stack positions. Instead use normal COPY to/from ST registers around inline assembly, and provide a single new FpPOP_RETVAL instruction that can access the return value(s) from a call. This is still necessary since you cannot tell from the CALL instruction alone if it returns anything on the FP stack. Teach fast isel to use this. This provides a much more robust way of handling fixed stack registers - we can tolerate arbitrary FP stack instructions inserted around calls and inline assembly. Live range splitting could sometimes break x87 code by inserting spill code in unfortunate places. As a bonus we handle floating point inline assembly correctly now. llvm-svn: 134018
2011-06-29 02:32:28 +08:00
entry:
tail call void asm sideeffect "fucomp $1", "{st},f,~{st},~{dirflag},~{fpsr},~{flags}"(x86_fp80 %x, x86_fp80 %y) nounwind
ret void
}
; The 'u' constraint is only popped implicitly when clobbered:
;
; void fucomp2(long double x, long double y) {
; asm volatile ("fucomp %1" : : "t"(x), "u"(y) : "st");
; }
;
; void fucomp3(long double x, long double y) {
; asm volatile ("fucompp %1" : : "t"(x), "u"(y) : "st", "st(1)");
; }
;
define void @fucomp2(x86_fp80 %x, x86_fp80 %y) nounwind ssp {
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-LABEL: fucomp2:
[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][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: fldt {{[0-9]+}}(%esp)
; CHECK-NEXT: fldt {{[0-9]+}}(%esp)
; CHECK-NEXT: fxch %st(1)
; CHECK-NEXT: ## InlineAsm Start
; CHECK-NEXT: fucomp %st(1)
; CHECK-NEXT: ## InlineAsm End
Revert r352985 "[X86] Print %st(0) as %st to match what gcc inline asm uses as the clobber name to make MS inline asm work correctly" Looking into gcc and objdump behavior more this was overly aggressive. If the register is encoded in the instruction we should print %st(0), if its implicit we should print %st. I'll be making a more directed change in a future patch. llvm-svn: 353013
2019-02-04 12:15:02 +08:00
; CHECK-NEXT: fstp %st(0)
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: retl
Clean up the handling of the x87 fp stack to make it more robust. Drop the FpMov instructions, use plain COPY instead. Drop the FpSET/GET instruction for accessing fixed stack positions. Instead use normal COPY to/from ST registers around inline assembly, and provide a single new FpPOP_RETVAL instruction that can access the return value(s) from a call. This is still necessary since you cannot tell from the CALL instruction alone if it returns anything on the FP stack. Teach fast isel to use this. This provides a much more robust way of handling fixed stack registers - we can tolerate arbitrary FP stack instructions inserted around calls and inline assembly. Live range splitting could sometimes break x87 code by inserting spill code in unfortunate places. As a bonus we handle floating point inline assembly correctly now. llvm-svn: 134018
2011-06-29 02:32:28 +08:00
entry:
tail call void asm sideeffect "fucomp $1", "{st},{st(1)},~{st},~{dirflag},~{fpsr},~{flags}"(x86_fp80 %x, x86_fp80 %y) nounwind
ret void
}
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
Clean up the handling of the x87 fp stack to make it more robust. Drop the FpMov instructions, use plain COPY instead. Drop the FpSET/GET instruction for accessing fixed stack positions. Instead use normal COPY to/from ST registers around inline assembly, and provide a single new FpPOP_RETVAL instruction that can access the return value(s) from a call. This is still necessary since you cannot tell from the CALL instruction alone if it returns anything on the FP stack. Teach fast isel to use this. This provides a much more robust way of handling fixed stack registers - we can tolerate arbitrary FP stack instructions inserted around calls and inline assembly. Live range splitting could sometimes break x87 code by inserting spill code in unfortunate places. As a bonus we handle floating point inline assembly correctly now. llvm-svn: 134018
2011-06-29 02:32:28 +08:00
define void @fucomp3(x86_fp80 %x, x86_fp80 %y) nounwind ssp {
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-LABEL: fucomp3:
[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][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: fldt {{[0-9]+}}(%esp)
; CHECK-NEXT: fldt {{[0-9]+}}(%esp)
; CHECK-NEXT: fxch %st(1)
; CHECK-NEXT: ## InlineAsm Start
; CHECK-NEXT: fucompp %st(1)
; CHECK-NEXT: ## InlineAsm End
; CHECK-NEXT: retl
Clean up the handling of the x87 fp stack to make it more robust. Drop the FpMov instructions, use plain COPY instead. Drop the FpSET/GET instruction for accessing fixed stack positions. Instead use normal COPY to/from ST registers around inline assembly, and provide a single new FpPOP_RETVAL instruction that can access the return value(s) from a call. This is still necessary since you cannot tell from the CALL instruction alone if it returns anything on the FP stack. Teach fast isel to use this. This provides a much more robust way of handling fixed stack registers - we can tolerate arbitrary FP stack instructions inserted around calls and inline assembly. Live range splitting could sometimes break x87 code by inserting spill code in unfortunate places. As a bonus we handle floating point inline assembly correctly now. llvm-svn: 134018
2011-06-29 02:32:28 +08:00
entry:
tail call void asm sideeffect "fucompp $1", "{st},{st(1)},~{st},~{st(1)},~{dirflag},~{fpsr},~{flags}"(x86_fp80 %x, x86_fp80 %y) nounwind
ret void
}
; One input, two outputs, one dead output.
%complex = type { float, float }
define float @sincos1(float %x) nounwind ssp {
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-LABEL: sincos1:
[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][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: flds {{[0-9]+}}(%esp)
; CHECK-NEXT: ## InlineAsm Start
; CHECK-NEXT: sincos
; CHECK-NEXT: ## InlineAsm End
; CHECK-NEXT: fstp %st(1)
; CHECK-NEXT: retl
Clean up the handling of the x87 fp stack to make it more robust. Drop the FpMov instructions, use plain COPY instead. Drop the FpSET/GET instruction for accessing fixed stack positions. Instead use normal COPY to/from ST registers around inline assembly, and provide a single new FpPOP_RETVAL instruction that can access the return value(s) from a call. This is still necessary since you cannot tell from the CALL instruction alone if it returns anything on the FP stack. Teach fast isel to use this. This provides a much more robust way of handling fixed stack registers - we can tolerate arbitrary FP stack instructions inserted around calls and inline assembly. Live range splitting could sometimes break x87 code by inserting spill code in unfortunate places. As a bonus we handle floating point inline assembly correctly now. llvm-svn: 134018
2011-06-29 02:32:28 +08:00
entry:
%0 = tail call %complex asm "sincos", "={st},={st(1)},0,~{dirflag},~{fpsr},~{flags}"(float %x) nounwind
%asmresult = extractvalue %complex %0, 0
ret float %asmresult
}
; Same thing, swapped output operands.
define float @sincos2(float %x) nounwind ssp {
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-LABEL: sincos2:
[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][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: flds {{[0-9]+}}(%esp)
; CHECK-NEXT: ## InlineAsm Start
; CHECK-NEXT: sincos
; CHECK-NEXT: ## InlineAsm End
; CHECK-NEXT: fstp %st(1)
; CHECK-NEXT: retl
Clean up the handling of the x87 fp stack to make it more robust. Drop the FpMov instructions, use plain COPY instead. Drop the FpSET/GET instruction for accessing fixed stack positions. Instead use normal COPY to/from ST registers around inline assembly, and provide a single new FpPOP_RETVAL instruction that can access the return value(s) from a call. This is still necessary since you cannot tell from the CALL instruction alone if it returns anything on the FP stack. Teach fast isel to use this. This provides a much more robust way of handling fixed stack registers - we can tolerate arbitrary FP stack instructions inserted around calls and inline assembly. Live range splitting could sometimes break x87 code by inserting spill code in unfortunate places. As a bonus we handle floating point inline assembly correctly now. llvm-svn: 134018
2011-06-29 02:32:28 +08:00
entry:
%0 = tail call %complex asm "sincos", "={st(1)},={st},1,~{dirflag},~{fpsr},~{flags}"(float %x) nounwind
%asmresult = extractvalue %complex %0, 1
ret float %asmresult
}
; Clobber st(0) after it was live-out/dead from the previous asm.
; Load x, make a copy for the second asm.
; Discard dead result in st(0), bring x to the top.
; x is now in st(0) for the second asm
; Discard both results.
define float @sincos3(float %x) nounwind ssp {
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-LABEL: sincos3:
[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][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: flds {{[0-9]+}}(%esp)
Revert r352985 "[X86] Print %st(0) as %st to match what gcc inline asm uses as the clobber name to make MS inline asm work correctly" Looking into gcc and objdump behavior more this was overly aggressive. If the register is encoded in the instruction we should print %st(0), if its implicit we should print %st. I'll be making a more directed change in a future patch. llvm-svn: 353013
2019-02-04 12:15:02 +08:00
; CHECK-NEXT: fld %st(0)
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: ## InlineAsm Start
; CHECK-NEXT: sincos
; CHECK-NEXT: ## InlineAsm End
Revert r352985 "[X86] Print %st(0) as %st to match what gcc inline asm uses as the clobber name to make MS inline asm work correctly" Looking into gcc and objdump behavior more this was overly aggressive. If the register is encoded in the instruction we should print %st(0), if its implicit we should print %st. I'll be making a more directed change in a future patch. llvm-svn: 353013
2019-02-04 12:15:02 +08:00
; CHECK-NEXT: fstp %st(0)
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: fxch %st(1)
; CHECK-NEXT: ## InlineAsm Start
; CHECK-NEXT: sincos
; CHECK-NEXT: ## InlineAsm End
; CHECK-NEXT: fstp %st(1)
Revert r352985 "[X86] Print %st(0) as %st to match what gcc inline asm uses as the clobber name to make MS inline asm work correctly" Looking into gcc and objdump behavior more this was overly aggressive. If the register is encoded in the instruction we should print %st(0), if its implicit we should print %st. I'll be making a more directed change in a future patch. llvm-svn: 353013
2019-02-04 12:15:02 +08:00
; CHECK-NEXT: fstp %st(0)
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: retl
Clean up the handling of the x87 fp stack to make it more robust. Drop the FpMov instructions, use plain COPY instead. Drop the FpSET/GET instruction for accessing fixed stack positions. Instead use normal COPY to/from ST registers around inline assembly, and provide a single new FpPOP_RETVAL instruction that can access the return value(s) from a call. This is still necessary since you cannot tell from the CALL instruction alone if it returns anything on the FP stack. Teach fast isel to use this. This provides a much more robust way of handling fixed stack registers - we can tolerate arbitrary FP stack instructions inserted around calls and inline assembly. Live range splitting could sometimes break x87 code by inserting spill code in unfortunate places. As a bonus we handle floating point inline assembly correctly now. llvm-svn: 134018
2011-06-29 02:32:28 +08:00
entry:
%0 = tail call %complex asm sideeffect "sincos", "={st(1)},={st},1,~{dirflag},~{fpsr},~{flags}"(float %x) nounwind
%1 = tail call %complex asm sideeffect "sincos", "={st(1)},={st},1,~{dirflag},~{fpsr},~{flags}"(float %x) nounwind
%asmresult = extractvalue %complex %0, 0
ret float %asmresult
}
Don't clobber pending ST regs when FP regs are killed. X86FloatingPoint keeps track of pending ST registers for an upcoming inline asm instruction with fixed stack register constraints. It does this by remembering which FP register holds the value that should appear at a fixed stack position for the inline asm. When that FP register is killed before the inline asm, make sure to duplicate it to a scratch register, so the ST register still has a live FP reference. This could happen when the same FP register was copied to two ST registers, or when a spill instruction is inserted between the ST copy and the inline asm. This fixes PR10602. llvm-svn: 137050
2011-08-09 01:15:43 +08:00
; Pass the same value in two fixed stack slots.
define i32 @PR10602() nounwind ssp {
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-LABEL: PR10602:
[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][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: flds LCPI19_0
Revert r352985 "[X86] Print %st(0) as %st to match what gcc inline asm uses as the clobber name to make MS inline asm work correctly" Looking into gcc and objdump behavior more this was overly aggressive. If the register is encoded in the instruction we should print %st(0), if its implicit we should print %st. I'll be making a more directed change in a future patch. llvm-svn: 353013
2019-02-04 12:15:02 +08:00
; CHECK-NEXT: fld %st(0)
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: fxch %st(1)
; CHECK-NEXT: ## InlineAsm Start
[X86] Print %st(0) as %st when its implicit to the instruction. Continue printing it as %st(0) when its encoded in the instruction. This is a step back from the change I made in r352985. This appears to be more consistent with gcc and objdump behavior. llvm-svn: 353015
2019-02-04 12:15:10 +08:00
; CHECK-NEXT: fcomi %st(1), %st; pushf; pop %eax
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: ## InlineAsm End
Revert r352985 "[X86] Print %st(0) as %st to match what gcc inline asm uses as the clobber name to make MS inline asm work correctly" Looking into gcc and objdump behavior more this was overly aggressive. If the register is encoded in the instruction we should print %st(0), if its implicit we should print %st. I'll be making a more directed change in a future patch. llvm-svn: 353013
2019-02-04 12:15:02 +08:00
; CHECK-NEXT: fstp %st(0)
; CHECK-NEXT: fstp %st(0)
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: retl
Don't clobber pending ST regs when FP regs are killed. X86FloatingPoint keeps track of pending ST registers for an upcoming inline asm instruction with fixed stack register constraints. It does this by remembering which FP register holds the value that should appear at a fixed stack position for the inline asm. When that FP register is killed before the inline asm, make sure to duplicate it to a scratch register, so the ST register still has a live FP reference. This could happen when the same FP register was copied to two ST registers, or when a spill instruction is inserted between the ST copy and the inline asm. This fixes PR10602. llvm-svn: 137050
2011-08-09 01:15:43 +08:00
entry:
%0 = tail call i32 asm "fcomi $2, $1; pushf; pop $0", "=r,{st},{st(1)},~{dirflag},~{fpsr},~{flags}"(double 2.000000e+00, double 2.000000e+00) nounwind
ret i32 %0
}
[X86] Simplify X87 stackifier pass. Stop using ST registers for function returns and inline-asm instructions and use FP registers instead. This allows removing a large amount of code in the stackifier pass that was needed to track register liveness and handle copies between ST and FP registers and function calls returning floating point values. It also fixes a bug which manifests when an ST register defined by an inline-asm instruction was live across another inline-asm instruction, as shown in the following sequence of machine instructions: 1. INLINEASM <es:frndint> $0:[regdef], %ST0<imp-def,tied5> 2. INLINEASM <es:fldcw $0> 3. %FP0<def> = COPY %ST0 <rdar://problem/16952634> llvm-svn: 214580
2014-08-02 06:19:41 +08:00
; <rdar://problem/16952634>
; X87 stackifier asserted when there was an ST register defined by an
; inline-asm instruction and the ST register was live across another
; inline-asm instruction.
;
[CodeGen] Print external symbols as $symbol in both MIR and debug output Work towards the unification of MIR and debug output by printing `$symbol` instead of `<es:symbol>`. Only debug syntax is affected. llvm-svn: 320681
2017-12-14 18:02:58 +08:00
; INLINEASM $frndint [sideeffect] [attdialect], $0:[regdef], %st0<imp-def,tied5>, $1:[reguse tiedto:$0], %st0<tied3>, $2:[clobber], early-clobber implicit dead %eflags
; INLINEASM $fldcw $0 [sideeffect] [mayload] [attdialect], $0:[mem], undef %eax, 1, %noreg, 0, %noreg, $1:[clobber], early-clobber implicit dead %eflags
[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
; %fp0 = COPY %st0
[X86] Simplify X87 stackifier pass. Stop using ST registers for function returns and inline-asm instructions and use FP registers instead. This allows removing a large amount of code in the stackifier pass that was needed to track register liveness and handle copies between ST and FP registers and function calls returning floating point values. It also fixes a bug which manifests when an ST register defined by an inline-asm instruction was live across another inline-asm instruction, as shown in the following sequence of machine instructions: 1. INLINEASM <es:frndint> $0:[regdef], %ST0<imp-def,tied5> 2. INLINEASM <es:fldcw $0> 3. %FP0<def> = COPY %ST0 <rdar://problem/16952634> llvm-svn: 214580
2014-08-02 06:19:41 +08:00
%struct.fpu_t = type { [8 x x86_fp80], x86_fp80, %struct.anon1, %struct.anon2, i32, i8, [15 x i8] }
%struct.anon1 = type { i32, i32, i32 }
%struct.anon2 = type { i32, i32, i32, i32 }
@fpu = external global %struct.fpu_t, align 16
; Function Attrs: ssp
define void @test_live_st(i32 %a1) {
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-LABEL: test_live_st:
[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][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: subl $12, %esp
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: fldt (%eax)
; CHECK-NEXT: cmpl $1, {{[0-9]+}}(%esp)
; CHECK-NEXT: jne LBB20_2
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK-NEXT: ## %bb.1: ## %sw.bb4.i
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: ## InlineAsm Start
; CHECK-NEXT: frndint
; CHECK-NEXT: ## InlineAsm End
; CHECK-NEXT: ## InlineAsm Start
; CHECK-NEXT: fldcw (%eax)
; CHECK-NEXT: ## InlineAsm End
; CHECK-NEXT: LBB20_2: ## %_Z5tointRKe.exit
[X86] Don't set exception mask bits when modifying FPCW to change rounding mode for fp->int conversion When we need to do an fp->int conversion using x87 instructions, we need to temporarily change the rounding mode to 0b11 and perform a store. To do this we save the old value of the fpcw to the stack, then set the fpcw to 0xc7f, do the store, then restore fpcw. But the 0xc7f value forces the exception mask bits 1. While this is what they would be in the default FP environment, as we move to support changing the FP environments, we shouldn't make this assumption. This patch changes the code to explicitly OR 0xc00 with the old value so that only the rounding mode is changed. Unfortunately, this requires two stack temporaries instead of one. One to hold the old value and one to hold the new value. Without two stack temporaries we would need an additional GPR. We already need one to do the OR operation in. This is similar to what gcc and icc do for this operation. Though they are both better at reusing the stack temporaries when there are multiple truncates in a function(or at least in a basic block) Differential Revision: https://reviews.llvm.org/D57788 llvm-svn: 354178
2019-02-16 05:59:33 +08:00
; CHECK-NEXT: fnstcw (%esp)
; CHECK-NEXT: movzwl (%esp), %eax
; CHECK-NEXT: orl $3072, %eax ## imm = 0xC00
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: movw %ax, {{[0-9]+}}(%esp)
; CHECK-NEXT: fldcw {{[0-9]+}}(%esp)
[X86] Don't set exception mask bits when modifying FPCW to change rounding mode for fp->int conversion When we need to do an fp->int conversion using x87 instructions, we need to temporarily change the rounding mode to 0b11 and perform a store. To do this we save the old value of the fpcw to the stack, then set the fpcw to 0xc7f, do the store, then restore fpcw. But the 0xc7f value forces the exception mask bits 1. While this is what they would be in the default FP environment, as we move to support changing the FP environments, we shouldn't make this assumption. This patch changes the code to explicitly OR 0xc00 with the old value so that only the rounding mode is changed. Unfortunately, this requires two stack temporaries instead of one. One to hold the old value and one to hold the new value. Without two stack temporaries we would need an additional GPR. We already need one to do the OR operation in. This is similar to what gcc and icc do for this operation. Though they are both better at reusing the stack temporaries when there are multiple truncates in a function(or at least in a basic block) Differential Revision: https://reviews.llvm.org/D57788 llvm-svn: 354178
2019-02-16 05:59:33 +08:00
; CHECK-NEXT: fistpl {{[0-9]+}}(%esp)
; CHECK-NEXT: fldcw (%esp)
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %eax
; CHECK-NEXT: movl %eax, {{[0-9]+}}(%esp)
; CHECK-NEXT: fildl {{[0-9]+}}(%esp)
; CHECK-NEXT: movl L_fpu$non_lazy_ptr, %eax
; CHECK-NEXT: fstpt 128(%eax)
; CHECK-NEXT: addl $12, %esp
; CHECK-NEXT: retl
[X86] Simplify X87 stackifier pass. Stop using ST registers for function returns and inline-asm instructions and use FP registers instead. This allows removing a large amount of code in the stackifier pass that was needed to track register liveness and handle copies between ST and FP registers and function calls returning floating point values. It also fixes a bug which manifests when an ST register defined by an inline-asm instruction was live across another inline-asm instruction, as shown in the following sequence of machine instructions: 1. INLINEASM <es:frndint> $0:[regdef], %ST0<imp-def,tied5> 2. INLINEASM <es:fldcw $0> 3. %FP0<def> = COPY %ST0 <rdar://problem/16952634> llvm-svn: 214580
2014-08-02 06:19:41 +08:00
entry:
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%0 = load x86_fp80, x86_fp80* undef, align 16
[X86] Simplify X87 stackifier pass. Stop using ST registers for function returns and inline-asm instructions and use FP registers instead. This allows removing a large amount of code in the stackifier pass that was needed to track register liveness and handle copies between ST and FP registers and function calls returning floating point values. It also fixes a bug which manifests when an ST register defined by an inline-asm instruction was live across another inline-asm instruction, as shown in the following sequence of machine instructions: 1. INLINEASM <es:frndint> $0:[regdef], %ST0<imp-def,tied5> 2. INLINEASM <es:fldcw $0> 3. %FP0<def> = COPY %ST0 <rdar://problem/16952634> llvm-svn: 214580
2014-08-02 06:19:41 +08:00
%cond = icmp eq i32 %a1, 1
br i1 %cond, label %sw.bb4.i, label %_Z5tointRKe.exit
sw.bb4.i:
%1 = call x86_fp80 asm sideeffect "frndint", "={st},0,~{dirflag},~{fpsr},~{flags}"(x86_fp80 %0)
call void asm sideeffect "fldcw $0", "*m,~{dirflag},~{fpsr},~{flags}"(i32* undef)
br label %_Z5tointRKe.exit
_Z5tointRKe.exit:
%result.0.i = phi x86_fp80 [ %1, %sw.bb4.i ], [ %0, %entry ]
%conv.i1814 = fptosi x86_fp80 %result.0.i to i32
%conv626 = sitofp i32 %conv.i1814 to x86_fp80
[opaque pointer type] Add textual IR support for explicit type parameter to gep operator Similar to gep (r230786) and load (r230794) changes. Similar migration script can be used to update test cases, which successfully migrated all of LLVM and Polly, but about 4 test cases needed manually changes in Clang. (this script will read the contents of stdin and massage it into stdout - wrap it in the 'apply.sh' script shown in previous commits + xargs to apply it over a large set of test cases) import fileinput import sys import re rep = re.compile(r"(getelementptr(?:\s+inbounds)?\s*\()((<\d*\s+x\s+)?([^@]*?)(|\s*addrspace\(\d+\))\s*\*(?(3)>)\s*)(?=$|%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|zeroinitializer|<|\[\[[a-zA-Z]|\{\{)", re.MULTILINE | re.DOTALL) def conv(match): line = match.group(1) line += match.group(4) line += ", " line += match.group(2) return line line = sys.stdin.read() off = 0 for match in re.finditer(rep, line): sys.stdout.write(line[off:match.start()]) sys.stdout.write(conv(match)) off = match.end() sys.stdout.write(line[off:]) llvm-svn: 232184
2015-03-14 02:20:45 +08:00
store x86_fp80 %conv626, x86_fp80* getelementptr inbounds (%struct.fpu_t, %struct.fpu_t* @fpu, i32 0, i32 1)
[X86] Simplify X87 stackifier pass. Stop using ST registers for function returns and inline-asm instructions and use FP registers instead. This allows removing a large amount of code in the stackifier pass that was needed to track register liveness and handle copies between ST and FP registers and function calls returning floating point values. It also fixes a bug which manifests when an ST register defined by an inline-asm instruction was live across another inline-asm instruction, as shown in the following sequence of machine instructions: 1. INLINEASM <es:frndint> $0:[regdef], %ST0<imp-def,tied5> 2. INLINEASM <es:fldcw $0> 3. %FP0<def> = COPY %ST0 <rdar://problem/16952634> llvm-svn: 214580
2014-08-02 06:19:41 +08:00
br label %return
return:
ret void
}
; Check that x87 stackifier is correctly rewriting FP registers to ST registers.
define double @test_operand_rewrite() {
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-LABEL: test_operand_rewrite:
[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][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: ## InlineAsm Start
[X86] Print %st(0) as %st when its implicit to the instruction. Continue printing it as %st(0) when its encoded in the instruction. This is a step back from the change I made in r352985. This appears to be more consistent with gcc and objdump behavior. llvm-svn: 353015
2019-02-04 12:15:10 +08:00
; CHECK-NEXT: foo %st, %st(1)
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: ## InlineAsm End
[X86] Print all register forms of x87 fadd/fsub/fdiv/fmul as having two arguments where on is %st. All of these instructions consume one encoded register and the other register is %st. They either write the result to %st or the encoded register. Previously we printed both arguments when the encoded register was written. And we printed one argument when the result was written to %st. For the stack popping forms the encoded register is always the destination and we didn't print both operands. This was inconsistent with gcc and objdump and just makes the output assembly code harder to read. This patch changes things to always print both operands making us consistent with gcc and objdump. The parser should still be able to handle the single register forms just as it did before. This also matches the GNU assembler behavior. llvm-svn: 353061
2019-02-05 01:28:18 +08:00
; CHECK-NEXT: fsubp %st, %st(1)
[X86][X87] Regenerate inline-asm tests llvm-svn: 310201
2017-08-06 20:17:10 +08:00
; CHECK-NEXT: retl
[X86] Simplify X87 stackifier pass. Stop using ST registers for function returns and inline-asm instructions and use FP registers instead. This allows removing a large amount of code in the stackifier pass that was needed to track register liveness and handle copies between ST and FP registers and function calls returning floating point values. It also fixes a bug which manifests when an ST register defined by an inline-asm instruction was live across another inline-asm instruction, as shown in the following sequence of machine instructions: 1. INLINEASM <es:frndint> $0:[regdef], %ST0<imp-def,tied5> 2. INLINEASM <es:fldcw $0> 3. %FP0<def> = COPY %ST0 <rdar://problem/16952634> llvm-svn: 214580
2014-08-02 06:19:41 +08:00
entry:
%0 = tail call { double, double } asm sideeffect "foo $0, $1", "={st},={st(1)},~{dirflag},~{fpsr},~{flags}"()
%asmresult = extractvalue { double, double } %0, 0
%asmresult1 = extractvalue { double, double } %0, 1
%sub = fsub double %asmresult, %asmresult1
ret double %sub
}