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/cmpxchg-clobber-flags.ll

189 lines
5.1 KiB
LLVM
Raw Normal View History

MachineInstrBundle: Fix reversed isSuperRegisterEq() call Unfortunately this fix had the effect of exposing the -verify-machineinstrs FIXME of X86InstrInfo.cpp in two testcases for which I disabled it for now. Two testcases also have additional pushq/popq where the corrected code cannot prove that %rax is dead any longer. Looking at the examples, this could potentially be fixed by improving computeRegisterLiveness() to check the live-in lists of the successors blocks when reaching the end of a block. This fixes http://llvm.org/PR25951. llvm-svn: 256799
2016-01-05 08:45:35 +08:00
; RUN: llc -mtriple=i386-linux-gnu %s -o - | FileCheck %s -check-prefix=i386
; RUN: llc -mtriple=i386-linux-gnu -pre-RA-sched=fast %s -o - | FileCheck %s -check-prefix=i386f
CodeGen: Redo analyzePhysRegs() and computeRegisterLiveness() computeRegisterLiveness() was broken in that it reported dead for a register even if a subregister was alive. I assume this was because the results of analayzePhysRegs() are hard to understand with respect to subregisters. This commit: Changes the results of analyzePhysRegs (=struct PhysRegInfo) to be clearly understandable, also renames the fields to avoid silent breakage of third-party code (and improve the grammar). Fix all (two) users of computeRegisterLiveness() in llvm: By reenabling it and removing workarounds for the bug. This fixes http://llvm.org/PR24535 and http://llvm.org/PR25033 Differential Revision: http://reviews.llvm.org/D15320 llvm-svn: 255362
2015-12-12 03:42:09 +08:00
MachineInstrBundle: Fix reversed isSuperRegisterEq() call Unfortunately this fix had the effect of exposing the -verify-machineinstrs FIXME of X86InstrInfo.cpp in two testcases for which I disabled it for now. Two testcases also have additional pushq/popq where the corrected code cannot prove that %rax is dead any longer. Looking at the examples, this could potentially be fixed by improving computeRegisterLiveness() to check the live-in lists of the successors blocks when reaching the end of a block. This fixes http://llvm.org/PR25951. llvm-svn: 256799
2016-01-05 08:45:35 +08:00
; RUN: llc -mtriple=x86_64-linux-gnu %s -o - | FileCheck %s -check-prefix=x8664
; RUN: llc -mtriple=x86_64-linux-gnu -pre-RA-sched=fast %s -o - | FileCheck %s -check-prefix=x8664
; RUN: llc -mtriple=x86_64-linux-gnu -mattr=+sahf %s -o - | FileCheck %s -check-prefix=x8664-sahf
; RUN: llc -mtriple=x86_64-linux-gnu -mattr=+sahf -pre-RA-sched=fast %s -o - | FileCheck %s -check-prefix=x8664-sahf
; RUN: llc -mtriple=x86_64-linux-gnu -mcpu=corei7 %s -o - | FileCheck %s -check-prefix=x8664-sahf
; TODO: Reenable verify-machineinstr once the if (!AXDead) // FIXME
; in X86InstrInfo::copyPhysReg() is resolved.
ScheduleDAG: record PhysReg dependencies represented by CopyFromReg nodes x86's CMPXCHG -> EFLAGS consumer wasn't being recorded as a real EFLAGS dependency because it was represented by a pair of CopyFromReg(EFLAGS) -> CopyToReg(EFLAGS) nodes. ScheduleDAG was expecting the source to be an implicit-def on the instruction, where the result numbers in the DAG and the Uses list in TableGen matched up precisely. The Copy notation seems much more robust, so this patch extends ScheduleDAG rather than refactoring x86. Should fix PR20376. llvm-svn: 220529
2014-10-24 06:31:48 +08:00
x86: Emit LAHF/SAHF instead of PUSHF/POPF NaCl's sandbox doesn't allow PUSHF/POPF out of security concerns (priviledged emulators have forgotten to mask system bits in the past, and EFLAGS's DF bit is a constant source of hilarity). Commit r220529 fixed PR20376 by saving cmpxchg's flags result using EFLAGS, this commit now generated LAHF/SAHF instead, for all of x86 (not just NaCl) because it leads to an overall performance gain over PUSHF/POPF. As with the previous patch this code generation is pretty bad because it occurs very later, after register allocation, and in many cases it rematerializes flags which were already available (e.g. already in a register through SETE). Fortunately it's somewhat rare that this code needs to fire. I did [[ https://github.com/jfbastien/benchmark-x86-flags | a bit of benchmarking ]], the results on an Intel Haswell E5-2690 CPU at 2.9GHz are: | Time per call (ms) | Runtime (ms) | Benchmark | | 0.000012514 | 6257 | sete.i386 | | 0.000012810 | 6405 | sete.i386-fast | | 0.000010456 | 5228 | sete.x86-64 | | 0.000010496 | 5248 | sete.x86-64-fast | | 0.000012906 | 6453 | lahf-sahf.i386 | | 0.000013236 | 6618 | lahf-sahf.i386-fast | | 0.000010580 | 5290 | lahf-sahf.x86-64 | | 0.000010304 | 5152 | lahf-sahf.x86-64-fast | | 0.000028056 | 14028 | pushf-popf.i386 | | 0.000027160 | 13580 | pushf-popf.i386-fast | | 0.000023810 | 11905 | pushf-popf.x86-64 | | 0.000026468 | 13234 | pushf-popf.x86-64-fast | Clearly `PUSHF`/`POPF` are suboptimal. It doesn't really seems to be worth teaching LLVM about individual flags, at least not for this purpose. Reviewers: rnk, jvoung, t.p.northover Subscribers: llvm-commits Differential revision: http://reviews.llvm.org/D6629 llvm-svn: 244503
2015-08-11 04:59:36 +08:00
declare i32 @foo()
declare i32 @bar(i64)
ScheduleDAG: record PhysReg dependencies represented by CopyFromReg nodes x86's CMPXCHG -> EFLAGS consumer wasn't being recorded as a real EFLAGS dependency because it was represented by a pair of CopyFromReg(EFLAGS) -> CopyToReg(EFLAGS) nodes. ScheduleDAG was expecting the source to be an implicit-def on the instruction, where the result numbers in the DAG and the Uses list in TableGen matched up precisely. The Copy notation seems much more robust, so this patch extends ScheduleDAG rather than refactoring x86. Should fix PR20376. llvm-svn: 220529
2014-10-24 06:31:48 +08:00
define i64 @test_intervening_call(i64* %foo, i64 %bar, i64 %baz) {
x86: Emit LAHF/SAHF instead of PUSHF/POPF NaCl's sandbox doesn't allow PUSHF/POPF out of security concerns (priviledged emulators have forgotten to mask system bits in the past, and EFLAGS's DF bit is a constant source of hilarity). Commit r220529 fixed PR20376 by saving cmpxchg's flags result using EFLAGS, this commit now generated LAHF/SAHF instead, for all of x86 (not just NaCl) because it leads to an overall performance gain over PUSHF/POPF. As with the previous patch this code generation is pretty bad because it occurs very later, after register allocation, and in many cases it rematerializes flags which were already available (e.g. already in a register through SETE). Fortunately it's somewhat rare that this code needs to fire. I did [[ https://github.com/jfbastien/benchmark-x86-flags | a bit of benchmarking ]], the results on an Intel Haswell E5-2690 CPU at 2.9GHz are: | Time per call (ms) | Runtime (ms) | Benchmark | | 0.000012514 | 6257 | sete.i386 | | 0.000012810 | 6405 | sete.i386-fast | | 0.000010456 | 5228 | sete.x86-64 | | 0.000010496 | 5248 | sete.x86-64-fast | | 0.000012906 | 6453 | lahf-sahf.i386 | | 0.000013236 | 6618 | lahf-sahf.i386-fast | | 0.000010580 | 5290 | lahf-sahf.x86-64 | | 0.000010304 | 5152 | lahf-sahf.x86-64-fast | | 0.000028056 | 14028 | pushf-popf.i386 | | 0.000027160 | 13580 | pushf-popf.i386-fast | | 0.000023810 | 11905 | pushf-popf.x86-64 | | 0.000026468 | 13234 | pushf-popf.x86-64-fast | Clearly `PUSHF`/`POPF` are suboptimal. It doesn't really seems to be worth teaching LLVM about individual flags, at least not for this purpose. Reviewers: rnk, jvoung, t.p.northover Subscribers: llvm-commits Differential revision: http://reviews.llvm.org/D6629 llvm-svn: 244503
2015-08-11 04:59:36 +08:00
; i386-LABEL: test_intervening_call:
; i386: cmpxchg8b
; i386-NEXT: pushl %eax
; i386-NEXT: seto %al
; i386-NEXT: lahf
; i386-NEXT: movl %eax, [[FLAGS:%.*]]
; i386-NEXT: popl %eax
[X86] Enable call frame optimization ("mov to push") not only for optsize (PR26325) The size savings are significant, and from what I can tell, both ICC and GCC do this. Differential Revision: http://reviews.llvm.org/D18573 llvm-svn: 264966
2016-03-31 07:38:01 +08:00
; i386-NEXT: subl $8, %esp
; i386-NEXT: pushl %edx
; i386-NEXT: pushl %eax
x86: Emit LAHF/SAHF instead of PUSHF/POPF NaCl's sandbox doesn't allow PUSHF/POPF out of security concerns (priviledged emulators have forgotten to mask system bits in the past, and EFLAGS's DF bit is a constant source of hilarity). Commit r220529 fixed PR20376 by saving cmpxchg's flags result using EFLAGS, this commit now generated LAHF/SAHF instead, for all of x86 (not just NaCl) because it leads to an overall performance gain over PUSHF/POPF. As with the previous patch this code generation is pretty bad because it occurs very later, after register allocation, and in many cases it rematerializes flags which were already available (e.g. already in a register through SETE). Fortunately it's somewhat rare that this code needs to fire. I did [[ https://github.com/jfbastien/benchmark-x86-flags | a bit of benchmarking ]], the results on an Intel Haswell E5-2690 CPU at 2.9GHz are: | Time per call (ms) | Runtime (ms) | Benchmark | | 0.000012514 | 6257 | sete.i386 | | 0.000012810 | 6405 | sete.i386-fast | | 0.000010456 | 5228 | sete.x86-64 | | 0.000010496 | 5248 | sete.x86-64-fast | | 0.000012906 | 6453 | lahf-sahf.i386 | | 0.000013236 | 6618 | lahf-sahf.i386-fast | | 0.000010580 | 5290 | lahf-sahf.x86-64 | | 0.000010304 | 5152 | lahf-sahf.x86-64-fast | | 0.000028056 | 14028 | pushf-popf.i386 | | 0.000027160 | 13580 | pushf-popf.i386-fast | | 0.000023810 | 11905 | pushf-popf.x86-64 | | 0.000026468 | 13234 | pushf-popf.x86-64-fast | Clearly `PUSHF`/`POPF` are suboptimal. It doesn't really seems to be worth teaching LLVM about individual flags, at least not for this purpose. Reviewers: rnk, jvoung, t.p.northover Subscribers: llvm-commits Differential revision: http://reviews.llvm.org/D6629 llvm-svn: 244503
2015-08-11 04:59:36 +08:00
; i386-NEXT: calll bar
[X86] Enable call frame optimization ("mov to push") not only for optsize (PR26325) The size savings are significant, and from what I can tell, both ICC and GCC do this. Differential Revision: http://reviews.llvm.org/D18573 llvm-svn: 264966
2016-03-31 07:38:01 +08:00
; i386-NEXT: addl $16, %esp
x86: Emit LAHF/SAHF instead of PUSHF/POPF NaCl's sandbox doesn't allow PUSHF/POPF out of security concerns (priviledged emulators have forgotten to mask system bits in the past, and EFLAGS's DF bit is a constant source of hilarity). Commit r220529 fixed PR20376 by saving cmpxchg's flags result using EFLAGS, this commit now generated LAHF/SAHF instead, for all of x86 (not just NaCl) because it leads to an overall performance gain over PUSHF/POPF. As with the previous patch this code generation is pretty bad because it occurs very later, after register allocation, and in many cases it rematerializes flags which were already available (e.g. already in a register through SETE). Fortunately it's somewhat rare that this code needs to fire. I did [[ https://github.com/jfbastien/benchmark-x86-flags | a bit of benchmarking ]], the results on an Intel Haswell E5-2690 CPU at 2.9GHz are: | Time per call (ms) | Runtime (ms) | Benchmark | | 0.000012514 | 6257 | sete.i386 | | 0.000012810 | 6405 | sete.i386-fast | | 0.000010456 | 5228 | sete.x86-64 | | 0.000010496 | 5248 | sete.x86-64-fast | | 0.000012906 | 6453 | lahf-sahf.i386 | | 0.000013236 | 6618 | lahf-sahf.i386-fast | | 0.000010580 | 5290 | lahf-sahf.x86-64 | | 0.000010304 | 5152 | lahf-sahf.x86-64-fast | | 0.000028056 | 14028 | pushf-popf.i386 | | 0.000027160 | 13580 | pushf-popf.i386-fast | | 0.000023810 | 11905 | pushf-popf.x86-64 | | 0.000026468 | 13234 | pushf-popf.x86-64-fast | Clearly `PUSHF`/`POPF` are suboptimal. It doesn't really seems to be worth teaching LLVM about individual flags, at least not for this purpose. Reviewers: rnk, jvoung, t.p.northover Subscribers: llvm-commits Differential revision: http://reviews.llvm.org/D6629 llvm-svn: 244503
2015-08-11 04:59:36 +08:00
; i386-NEXT: movl [[FLAGS]], %eax
; i386-NEXT: addb $127, %al
; i386-NEXT: sahf
; i386-NEXT: jne
; i386f-LABEL: test_intervening_call:
; i386f: cmpxchg8b
; i386f-NEXT: movl %eax, (%esp)
; i386f-NEXT: movl %edx, 4(%esp)
; i386f-NEXT: seto %al
; i386f-NEXT: lahf
; i386f-NEXT: movl %eax, [[FLAGS:%.*]]
; i386f-NEXT: calll bar
; i386f-NEXT: movl [[FLAGS]], %eax
; i386f-NEXT: addb $127, %al
; i386f-NEXT: sahf
; i386f-NEXT: jne
; x8664-LABEL: test_intervening_call:
; x8664: cmpxchgq
X86: Don't emit SAHF/LAHF for 64-bit targets unless explicitly supported These instructions are not supported by all CPUs in 64-bit mode. Emitting them causes Chromium to crash on start-up for users with such chips. (GCC puts these instructions behind -msahf on 64-bit for the same reason.) This patch adds FeatureLAHFSAHF, enables it by default for 32-bit targets and modern CPUs, and changes X86InstrInfo::copyPhysReg back to the lowering from before r244503 when the instructions are not available. Differential Revision: http://reviews.llvm.org/D15240 llvm-svn: 254793
2015-12-05 07:00:33 +08:00
; x8664: pushfq
; x8664-NEXT: popq [[FLAGS:%.*]]
x86: Emit LAHF/SAHF instead of PUSHF/POPF NaCl's sandbox doesn't allow PUSHF/POPF out of security concerns (priviledged emulators have forgotten to mask system bits in the past, and EFLAGS's DF bit is a constant source of hilarity). Commit r220529 fixed PR20376 by saving cmpxchg's flags result using EFLAGS, this commit now generated LAHF/SAHF instead, for all of x86 (not just NaCl) because it leads to an overall performance gain over PUSHF/POPF. As with the previous patch this code generation is pretty bad because it occurs very later, after register allocation, and in many cases it rematerializes flags which were already available (e.g. already in a register through SETE). Fortunately it's somewhat rare that this code needs to fire. I did [[ https://github.com/jfbastien/benchmark-x86-flags | a bit of benchmarking ]], the results on an Intel Haswell E5-2690 CPU at 2.9GHz are: | Time per call (ms) | Runtime (ms) | Benchmark | | 0.000012514 | 6257 | sete.i386 | | 0.000012810 | 6405 | sete.i386-fast | | 0.000010456 | 5228 | sete.x86-64 | | 0.000010496 | 5248 | sete.x86-64-fast | | 0.000012906 | 6453 | lahf-sahf.i386 | | 0.000013236 | 6618 | lahf-sahf.i386-fast | | 0.000010580 | 5290 | lahf-sahf.x86-64 | | 0.000010304 | 5152 | lahf-sahf.x86-64-fast | | 0.000028056 | 14028 | pushf-popf.i386 | | 0.000027160 | 13580 | pushf-popf.i386-fast | | 0.000023810 | 11905 | pushf-popf.x86-64 | | 0.000026468 | 13234 | pushf-popf.x86-64-fast | Clearly `PUSHF`/`POPF` are suboptimal. It doesn't really seems to be worth teaching LLVM about individual flags, at least not for this purpose. Reviewers: rnk, jvoung, t.p.northover Subscribers: llvm-commits Differential revision: http://reviews.llvm.org/D6629 llvm-svn: 244503
2015-08-11 04:59:36 +08:00
; x8664-NEXT: movq %rax, %rdi
; x8664-NEXT: callq bar
X86: Don't emit SAHF/LAHF for 64-bit targets unless explicitly supported These instructions are not supported by all CPUs in 64-bit mode. Emitting them causes Chromium to crash on start-up for users with such chips. (GCC puts these instructions behind -msahf on 64-bit for the same reason.) This patch adds FeatureLAHFSAHF, enables it by default for 32-bit targets and modern CPUs, and changes X86InstrInfo::copyPhysReg back to the lowering from before r244503 when the instructions are not available. Differential Revision: http://reviews.llvm.org/D15240 llvm-svn: 254793
2015-12-05 07:00:33 +08:00
; x8664-NEXT: pushq [[FLAGS]]
; x8664-NEXT: popfq
; x8664-NEXT: jne
; x8664-sahf-LABEL: test_intervening_call:
; x8664-sahf: cmpxchgq
; x8664-sahf: pushq %rax
; x8664-sahf-NEXT: seto %al
; x8664-sahf-NEXT: lahf
; x8664-sahf-NEXT: movq %rax, [[FLAGS:%.*]]
; x8664-sahf-NEXT: popq %rax
; x8664-sahf-NEXT: movq %rax, %rdi
; x8664-sahf-NEXT: callq bar
[MachineInstrBundle] Improvement the recognition of dead definitions. Now, it is possible to know that partial definitions are dead definitions and recognize that clobbered registers are also dead. llvm-svn: 267621
2016-04-27 07:14:24 +08:00
; RAX is dead, no need to push and pop it.
X86: Don't emit SAHF/LAHF for 64-bit targets unless explicitly supported These instructions are not supported by all CPUs in 64-bit mode. Emitting them causes Chromium to crash on start-up for users with such chips. (GCC puts these instructions behind -msahf on 64-bit for the same reason.) This patch adds FeatureLAHFSAHF, enables it by default for 32-bit targets and modern CPUs, and changes X86InstrInfo::copyPhysReg back to the lowering from before r244503 when the instructions are not available. Differential Revision: http://reviews.llvm.org/D15240 llvm-svn: 254793
2015-12-05 07:00:33 +08:00
; x8664-sahf-NEXT: movq [[FLAGS]], %rax
; x8664-sahf-NEXT: addb $127, %al
; x8664-sahf-NEXT: sahf
; x8664-sahf-NEXT: jne
ScheduleDAG: record PhysReg dependencies represented by CopyFromReg nodes x86's CMPXCHG -> EFLAGS consumer wasn't being recorded as a real EFLAGS dependency because it was represented by a pair of CopyFromReg(EFLAGS) -> CopyToReg(EFLAGS) nodes. ScheduleDAG was expecting the source to be an implicit-def on the instruction, where the result numbers in the DAG and the Uses list in TableGen matched up precisely. The Copy notation seems much more robust, so this patch extends ScheduleDAG rather than refactoring x86. Should fix PR20376. llvm-svn: 220529
2014-10-24 06:31:48 +08:00
%cx = cmpxchg i64* %foo, i64 %bar, i64 %baz seq_cst seq_cst
x86: Emit LAHF/SAHF instead of PUSHF/POPF NaCl's sandbox doesn't allow PUSHF/POPF out of security concerns (priviledged emulators have forgotten to mask system bits in the past, and EFLAGS's DF bit is a constant source of hilarity). Commit r220529 fixed PR20376 by saving cmpxchg's flags result using EFLAGS, this commit now generated LAHF/SAHF instead, for all of x86 (not just NaCl) because it leads to an overall performance gain over PUSHF/POPF. As with the previous patch this code generation is pretty bad because it occurs very later, after register allocation, and in many cases it rematerializes flags which were already available (e.g. already in a register through SETE). Fortunately it's somewhat rare that this code needs to fire. I did [[ https://github.com/jfbastien/benchmark-x86-flags | a bit of benchmarking ]], the results on an Intel Haswell E5-2690 CPU at 2.9GHz are: | Time per call (ms) | Runtime (ms) | Benchmark | | 0.000012514 | 6257 | sete.i386 | | 0.000012810 | 6405 | sete.i386-fast | | 0.000010456 | 5228 | sete.x86-64 | | 0.000010496 | 5248 | sete.x86-64-fast | | 0.000012906 | 6453 | lahf-sahf.i386 | | 0.000013236 | 6618 | lahf-sahf.i386-fast | | 0.000010580 | 5290 | lahf-sahf.x86-64 | | 0.000010304 | 5152 | lahf-sahf.x86-64-fast | | 0.000028056 | 14028 | pushf-popf.i386 | | 0.000027160 | 13580 | pushf-popf.i386-fast | | 0.000023810 | 11905 | pushf-popf.x86-64 | | 0.000026468 | 13234 | pushf-popf.x86-64-fast | Clearly `PUSHF`/`POPF` are suboptimal. It doesn't really seems to be worth teaching LLVM about individual flags, at least not for this purpose. Reviewers: rnk, jvoung, t.p.northover Subscribers: llvm-commits Differential revision: http://reviews.llvm.org/D6629 llvm-svn: 244503
2015-08-11 04:59:36 +08:00
%v = extractvalue { i64, i1 } %cx, 0
ScheduleDAG: record PhysReg dependencies represented by CopyFromReg nodes x86's CMPXCHG -> EFLAGS consumer wasn't being recorded as a real EFLAGS dependency because it was represented by a pair of CopyFromReg(EFLAGS) -> CopyToReg(EFLAGS) nodes. ScheduleDAG was expecting the source to be an implicit-def on the instruction, where the result numbers in the DAG and the Uses list in TableGen matched up precisely. The Copy notation seems much more robust, so this patch extends ScheduleDAG rather than refactoring x86. Should fix PR20376. llvm-svn: 220529
2014-10-24 06:31:48 +08:00
%p = extractvalue { i64, i1 } %cx, 1
x86: Emit LAHF/SAHF instead of PUSHF/POPF NaCl's sandbox doesn't allow PUSHF/POPF out of security concerns (priviledged emulators have forgotten to mask system bits in the past, and EFLAGS's DF bit is a constant source of hilarity). Commit r220529 fixed PR20376 by saving cmpxchg's flags result using EFLAGS, this commit now generated LAHF/SAHF instead, for all of x86 (not just NaCl) because it leads to an overall performance gain over PUSHF/POPF. As with the previous patch this code generation is pretty bad because it occurs very later, after register allocation, and in many cases it rematerializes flags which were already available (e.g. already in a register through SETE). Fortunately it's somewhat rare that this code needs to fire. I did [[ https://github.com/jfbastien/benchmark-x86-flags | a bit of benchmarking ]], the results on an Intel Haswell E5-2690 CPU at 2.9GHz are: | Time per call (ms) | Runtime (ms) | Benchmark | | 0.000012514 | 6257 | sete.i386 | | 0.000012810 | 6405 | sete.i386-fast | | 0.000010456 | 5228 | sete.x86-64 | | 0.000010496 | 5248 | sete.x86-64-fast | | 0.000012906 | 6453 | lahf-sahf.i386 | | 0.000013236 | 6618 | lahf-sahf.i386-fast | | 0.000010580 | 5290 | lahf-sahf.x86-64 | | 0.000010304 | 5152 | lahf-sahf.x86-64-fast | | 0.000028056 | 14028 | pushf-popf.i386 | | 0.000027160 | 13580 | pushf-popf.i386-fast | | 0.000023810 | 11905 | pushf-popf.x86-64 | | 0.000026468 | 13234 | pushf-popf.x86-64-fast | Clearly `PUSHF`/`POPF` are suboptimal. It doesn't really seems to be worth teaching LLVM about individual flags, at least not for this purpose. Reviewers: rnk, jvoung, t.p.northover Subscribers: llvm-commits Differential revision: http://reviews.llvm.org/D6629 llvm-svn: 244503
2015-08-11 04:59:36 +08:00
call i32 @bar(i64 %v)
ScheduleDAG: record PhysReg dependencies represented by CopyFromReg nodes x86's CMPXCHG -> EFLAGS consumer wasn't being recorded as a real EFLAGS dependency because it was represented by a pair of CopyFromReg(EFLAGS) -> CopyToReg(EFLAGS) nodes. ScheduleDAG was expecting the source to be an implicit-def on the instruction, where the result numbers in the DAG and the Uses list in TableGen matched up precisely. The Copy notation seems much more robust, so this patch extends ScheduleDAG rather than refactoring x86. Should fix PR20376. llvm-svn: 220529
2014-10-24 06:31:48 +08:00
br i1 %p, label %t, label %f
t:
ret i64 42
f:
ret i64 0
}
; Interesting in producing a clobber without any function calls.
define i32 @test_control_flow(i32* %p, i32 %i, i32 %j) {
x86: Emit LAHF/SAHF instead of PUSHF/POPF NaCl's sandbox doesn't allow PUSHF/POPF out of security concerns (priviledged emulators have forgotten to mask system bits in the past, and EFLAGS's DF bit is a constant source of hilarity). Commit r220529 fixed PR20376 by saving cmpxchg's flags result using EFLAGS, this commit now generated LAHF/SAHF instead, for all of x86 (not just NaCl) because it leads to an overall performance gain over PUSHF/POPF. As with the previous patch this code generation is pretty bad because it occurs very later, after register allocation, and in many cases it rematerializes flags which were already available (e.g. already in a register through SETE). Fortunately it's somewhat rare that this code needs to fire. I did [[ https://github.com/jfbastien/benchmark-x86-flags | a bit of benchmarking ]], the results on an Intel Haswell E5-2690 CPU at 2.9GHz are: | Time per call (ms) | Runtime (ms) | Benchmark | | 0.000012514 | 6257 | sete.i386 | | 0.000012810 | 6405 | sete.i386-fast | | 0.000010456 | 5228 | sete.x86-64 | | 0.000010496 | 5248 | sete.x86-64-fast | | 0.000012906 | 6453 | lahf-sahf.i386 | | 0.000013236 | 6618 | lahf-sahf.i386-fast | | 0.000010580 | 5290 | lahf-sahf.x86-64 | | 0.000010304 | 5152 | lahf-sahf.x86-64-fast | | 0.000028056 | 14028 | pushf-popf.i386 | | 0.000027160 | 13580 | pushf-popf.i386-fast | | 0.000023810 | 11905 | pushf-popf.x86-64 | | 0.000026468 | 13234 | pushf-popf.x86-64-fast | Clearly `PUSHF`/`POPF` are suboptimal. It doesn't really seems to be worth teaching LLVM about individual flags, at least not for this purpose. Reviewers: rnk, jvoung, t.p.northover Subscribers: llvm-commits Differential revision: http://reviews.llvm.org/D6629 llvm-svn: 244503
2015-08-11 04:59:36 +08:00
; i386-LABEL: test_control_flow:
; i386: cmpxchg
; i386-NEXT: jne
; i386f-LABEL: test_control_flow:
; i386f: cmpxchg
; i386f-NEXT: jne
; x8664-LABEL: test_control_flow:
; x8664: cmpxchg
; x8664-NEXT: jne
ScheduleDAG: record PhysReg dependencies represented by CopyFromReg nodes x86's CMPXCHG -> EFLAGS consumer wasn't being recorded as a real EFLAGS dependency because it was represented by a pair of CopyFromReg(EFLAGS) -> CopyToReg(EFLAGS) nodes. ScheduleDAG was expecting the source to be an implicit-def on the instruction, where the result numbers in the DAG and the Uses list in TableGen matched up precisely. The Copy notation seems much more robust, so this patch extends ScheduleDAG rather than refactoring x86. Should fix PR20376. llvm-svn: 220529
2014-10-24 06:31:48 +08:00
X86: Don't emit SAHF/LAHF for 64-bit targets unless explicitly supported These instructions are not supported by all CPUs in 64-bit mode. Emitting them causes Chromium to crash on start-up for users with such chips. (GCC puts these instructions behind -msahf on 64-bit for the same reason.) This patch adds FeatureLAHFSAHF, enables it by default for 32-bit targets and modern CPUs, and changes X86InstrInfo::copyPhysReg back to the lowering from before r244503 when the instructions are not available. Differential Revision: http://reviews.llvm.org/D15240 llvm-svn: 254793
2015-12-05 07:00:33 +08:00
; x8664-sahf-LABEL: test_control_flow:
; x8664-sahf: cmpxchg
; x8664-sahf-NEXT: jne
ScheduleDAG: record PhysReg dependencies represented by CopyFromReg nodes x86's CMPXCHG -> EFLAGS consumer wasn't being recorded as a real EFLAGS dependency because it was represented by a pair of CopyFromReg(EFLAGS) -> CopyToReg(EFLAGS) nodes. ScheduleDAG was expecting the source to be an implicit-def on the instruction, where the result numbers in the DAG and the Uses list in TableGen matched up precisely. The Copy notation seems much more robust, so this patch extends ScheduleDAG rather than refactoring x86. Should fix PR20376. llvm-svn: 220529
2014-10-24 06:31:48 +08:00
entry:
%cmp = icmp sgt i32 %i, %j
br i1 %cmp, label %loop_start, label %cond.end
loop_start:
br label %while.condthread-pre-split.i
while.condthread-pre-split.i:
[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
%.pr.i = load i32, i32* %p, align 4
ScheduleDAG: record PhysReg dependencies represented by CopyFromReg nodes x86's CMPXCHG -> EFLAGS consumer wasn't being recorded as a real EFLAGS dependency because it was represented by a pair of CopyFromReg(EFLAGS) -> CopyToReg(EFLAGS) nodes. ScheduleDAG was expecting the source to be an implicit-def on the instruction, where the result numbers in the DAG and the Uses list in TableGen matched up precisely. The Copy notation seems much more robust, so this patch extends ScheduleDAG rather than refactoring x86. Should fix PR20376. llvm-svn: 220529
2014-10-24 06:31:48 +08:00
br label %while.cond.i
while.cond.i:
%0 = phi i32 [ %.pr.i, %while.condthread-pre-split.i ], [ 0, %while.cond.i ]
%tobool.i = icmp eq i32 %0, 0
br i1 %tobool.i, label %while.cond.i, label %while.body.i
while.body.i:
%.lcssa = phi i32 [ %0, %while.cond.i ]
%1 = cmpxchg i32* %p, i32 %.lcssa, i32 %.lcssa seq_cst seq_cst
%2 = extractvalue { i32, i1 } %1, 1
br i1 %2, label %cond.end.loopexit, label %while.condthread-pre-split.i
cond.end.loopexit:
br label %cond.end
cond.end:
%cond = phi i32 [ %i, %entry ], [ 0, %cond.end.loopexit ]
ret i32 %cond
}
; This one is an interesting case because CMOV doesn't have a chain
; operand. Naive attempts to limit cmpxchg EFLAGS use are likely to fail here.
define i32 @test_feed_cmov(i32* %addr, i32 %desired, i32 %new) {
x86: Emit LAHF/SAHF instead of PUSHF/POPF NaCl's sandbox doesn't allow PUSHF/POPF out of security concerns (priviledged emulators have forgotten to mask system bits in the past, and EFLAGS's DF bit is a constant source of hilarity). Commit r220529 fixed PR20376 by saving cmpxchg's flags result using EFLAGS, this commit now generated LAHF/SAHF instead, for all of x86 (not just NaCl) because it leads to an overall performance gain over PUSHF/POPF. As with the previous patch this code generation is pretty bad because it occurs very later, after register allocation, and in many cases it rematerializes flags which were already available (e.g. already in a register through SETE). Fortunately it's somewhat rare that this code needs to fire. I did [[ https://github.com/jfbastien/benchmark-x86-flags | a bit of benchmarking ]], the results on an Intel Haswell E5-2690 CPU at 2.9GHz are: | Time per call (ms) | Runtime (ms) | Benchmark | | 0.000012514 | 6257 | sete.i386 | | 0.000012810 | 6405 | sete.i386-fast | | 0.000010456 | 5228 | sete.x86-64 | | 0.000010496 | 5248 | sete.x86-64-fast | | 0.000012906 | 6453 | lahf-sahf.i386 | | 0.000013236 | 6618 | lahf-sahf.i386-fast | | 0.000010580 | 5290 | lahf-sahf.x86-64 | | 0.000010304 | 5152 | lahf-sahf.x86-64-fast | | 0.000028056 | 14028 | pushf-popf.i386 | | 0.000027160 | 13580 | pushf-popf.i386-fast | | 0.000023810 | 11905 | pushf-popf.x86-64 | | 0.000026468 | 13234 | pushf-popf.x86-64-fast | Clearly `PUSHF`/`POPF` are suboptimal. It doesn't really seems to be worth teaching LLVM about individual flags, at least not for this purpose. Reviewers: rnk, jvoung, t.p.northover Subscribers: llvm-commits Differential revision: http://reviews.llvm.org/D6629 llvm-svn: 244503
2015-08-11 04:59:36 +08:00
; i386-LABEL: test_feed_cmov:
; i386: cmpxchgl
; i386-NEXT: seto %al
; i386-NEXT: lahf
; i386-NEXT: movl %eax, [[FLAGS:%.*]]
; i386-NEXT: calll foo
; i386-NEXT: pushl %eax
; i386-NEXT: movl [[FLAGS]], %eax
; i386-NEXT: addb $127, %al
; i386-NEXT: sahf
; i386-NEXT: popl %eax
; i386f-LABEL: test_feed_cmov:
; i386f: cmpxchgl
; i386f-NEXT: seto %al
; i386f-NEXT: lahf
; i386f-NEXT: movl %eax, [[FLAGS:%.*]]
; i386f-NEXT: calll foo
; i386f-NEXT: pushl %eax
; i386f-NEXT: movl [[FLAGS]], %eax
; i386f-NEXT: addb $127, %al
; i386f-NEXT: sahf
; i386f-NEXT: popl %eax
; x8664-LABEL: test_feed_cmov:
X86: Don't emit SAHF/LAHF for 64-bit targets unless explicitly supported These instructions are not supported by all CPUs in 64-bit mode. Emitting them causes Chromium to crash on start-up for users with such chips. (GCC puts these instructions behind -msahf on 64-bit for the same reason.) This patch adds FeatureLAHFSAHF, enables it by default for 32-bit targets and modern CPUs, and changes X86InstrInfo::copyPhysReg back to the lowering from before r244503 when the instructions are not available. Differential Revision: http://reviews.llvm.org/D15240 llvm-svn: 254793
2015-12-05 07:00:33 +08:00
; x8664: cmpxchg
; x8664: pushfq
; x8664-NEXT: popq [[FLAGS:%.*]]
; x8664-NEXT: callq foo
; x8664-NEXT: pushq [[FLAGS]]
; x8664-NEXT: popfq
; x8664-sahf-LABEL: test_feed_cmov:
; x8664-sahf: cmpxchgl
[MachineBasicBlock] Take advantage of the partially dead information. Thanks to that information we wouldn't lie on a register being live whereas it is not. llvm-svn: 267622
2016-04-27 07:14:29 +08:00
; RAX is dead, do not push or pop it.
MachineInstrBundle: Fix reversed isSuperRegisterEq() call Unfortunately this fix had the effect of exposing the -verify-machineinstrs FIXME of X86InstrInfo.cpp in two testcases for which I disabled it for now. Two testcases also have additional pushq/popq where the corrected code cannot prove that %rax is dead any longer. Looking at the examples, this could potentially be fixed by improving computeRegisterLiveness() to check the live-in lists of the successors blocks when reaching the end of a block. This fixes http://llvm.org/PR25951. llvm-svn: 256799
2016-01-05 08:45:35 +08:00
; x8664-sahf-NEXT: seto %al
X86: Don't emit SAHF/LAHF for 64-bit targets unless explicitly supported These instructions are not supported by all CPUs in 64-bit mode. Emitting them causes Chromium to crash on start-up for users with such chips. (GCC puts these instructions behind -msahf on 64-bit for the same reason.) This patch adds FeatureLAHFSAHF, enables it by default for 32-bit targets and modern CPUs, and changes X86InstrInfo::copyPhysReg back to the lowering from before r244503 when the instructions are not available. Differential Revision: http://reviews.llvm.org/D15240 llvm-svn: 254793
2015-12-05 07:00:33 +08:00
; x8664-sahf-NEXT: lahf
; x8664-sahf-NEXT: movq %rax, [[FLAGS:%.*]]
; x8664-sahf-NEXT: callq foo
; x8664-sahf-NEXT: pushq %rax
; x8664-sahf-NEXT: movq [[FLAGS]], %rax
; x8664-sahf-NEXT: addb $127, %al
; x8664-sahf-NEXT: sahf
; x8664-sahf-NEXT: popq %rax
ScheduleDAG: record PhysReg dependencies represented by CopyFromReg nodes x86's CMPXCHG -> EFLAGS consumer wasn't being recorded as a real EFLAGS dependency because it was represented by a pair of CopyFromReg(EFLAGS) -> CopyToReg(EFLAGS) nodes. ScheduleDAG was expecting the source to be an implicit-def on the instruction, where the result numbers in the DAG and the Uses list in TableGen matched up precisely. The Copy notation seems much more robust, so this patch extends ScheduleDAG rather than refactoring x86. Should fix PR20376. llvm-svn: 220529
2014-10-24 06:31:48 +08:00
%res = cmpxchg i32* %addr, i32 %desired, i32 %new seq_cst seq_cst
%success = extractvalue { i32, i1 } %res, 1
x86: Emit LAHF/SAHF instead of PUSHF/POPF NaCl's sandbox doesn't allow PUSHF/POPF out of security concerns (priviledged emulators have forgotten to mask system bits in the past, and EFLAGS's DF bit is a constant source of hilarity). Commit r220529 fixed PR20376 by saving cmpxchg's flags result using EFLAGS, this commit now generated LAHF/SAHF instead, for all of x86 (not just NaCl) because it leads to an overall performance gain over PUSHF/POPF. As with the previous patch this code generation is pretty bad because it occurs very later, after register allocation, and in many cases it rematerializes flags which were already available (e.g. already in a register through SETE). Fortunately it's somewhat rare that this code needs to fire. I did [[ https://github.com/jfbastien/benchmark-x86-flags | a bit of benchmarking ]], the results on an Intel Haswell E5-2690 CPU at 2.9GHz are: | Time per call (ms) | Runtime (ms) | Benchmark | | 0.000012514 | 6257 | sete.i386 | | 0.000012810 | 6405 | sete.i386-fast | | 0.000010456 | 5228 | sete.x86-64 | | 0.000010496 | 5248 | sete.x86-64-fast | | 0.000012906 | 6453 | lahf-sahf.i386 | | 0.000013236 | 6618 | lahf-sahf.i386-fast | | 0.000010580 | 5290 | lahf-sahf.x86-64 | | 0.000010304 | 5152 | lahf-sahf.x86-64-fast | | 0.000028056 | 14028 | pushf-popf.i386 | | 0.000027160 | 13580 | pushf-popf.i386-fast | | 0.000023810 | 11905 | pushf-popf.x86-64 | | 0.000026468 | 13234 | pushf-popf.x86-64-fast | Clearly `PUSHF`/`POPF` are suboptimal. It doesn't really seems to be worth teaching LLVM about individual flags, at least not for this purpose. Reviewers: rnk, jvoung, t.p.northover Subscribers: llvm-commits Differential revision: http://reviews.llvm.org/D6629 llvm-svn: 244503
2015-08-11 04:59:36 +08:00
%rhs = call i32 @foo()
ScheduleDAG: record PhysReg dependencies represented by CopyFromReg nodes x86's CMPXCHG -> EFLAGS consumer wasn't being recorded as a real EFLAGS dependency because it was represented by a pair of CopyFromReg(EFLAGS) -> CopyToReg(EFLAGS) nodes. ScheduleDAG was expecting the source to be an implicit-def on the instruction, where the result numbers in the DAG and the Uses list in TableGen matched up precisely. The Copy notation seems much more robust, so this patch extends ScheduleDAG rather than refactoring x86. Should fix PR20376. llvm-svn: 220529
2014-10-24 06:31:48 +08:00
%ret = select i1 %success, i32 %new, i32 %rhs
ret i32 %ret
}