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/ARM/cmpxchg-O0.ll

114 lines
3.9 KiB
LLVM
Raw Normal View History

ARM: use a pseudo-instruction for cmpxchg at -O0. The fast register-allocator cannot cope with inter-block dependencies without spilling. This is fine for ldrex/strex loops coming from atomicrmw instructions where any value produced within a block is dead by the end, but not for cmpxchg. So we lower a cmpxchg at -O0 via a pseudo-inst that gets expanded after regalloc. Fortunately this is at -O0 so we don't have to care about performance. This simplifies the various axes of expansion considerably: we assume a strong seq_cst operation and ensure ordering via the always-present DMB instructions rather than v8 acquire/release instructions. Should fix the 32-bit part of PR25526. llvm-svn: 266679
2016-04-19 05:48:55 +08:00
; RUN: llc -verify-machineinstrs -mtriple=armv7-linux-gnu -O0 %s -o - | FileCheck %s
; RUN: llc -verify-machineinstrs -mtriple=thumbv8-linux-gnu -O0 %s -o - | FileCheck %s
; RUN: llc -verify-machineinstrs -mtriple=thumbv6m-none-eabi -O0 %s -o - | FileCheck %s --check-prefix=CHECK-T1
; CHECK-T1-NOT: ldrex
; CHECK-T1-NOT: strex
define { i8, i1 } @test_cmpxchg_8(i8* %addr, i8 %desired, i8 %new) nounwind {
; CHECK-LABEL: test_cmpxchg_8:
; CHECK: dmb ish
; CHECK: uxtb [[DESIRED:r[0-9]+]], [[DESIRED]]
; CHECK: [[RETRY:.LBB[0-9]+_[0-9]+]]:
; CHECK: ldrexb [[OLD:r[0-9]+]], [r0]
; CHECK: cmp [[OLD]], [[DESIRED]]
; CHECK: bne [[DONE:.LBB[0-9]+_[0-9]+]]
; CHECK: strexb [[STATUS:r[0-9]+]], r2, [r0]
; CHECK: cmp{{(\.w)?}} [[STATUS]], #0
; CHECK: bne [[RETRY]]
; CHECK: [[DONE]]:
; CHECK: cmp{{(\.w)?}} [[OLD]], [[DESIRED]]
[ARM] Set correct successors in CMPXCHG pseudo expansion. transferSuccessors() would LoadCmpBB a successor of DoneBB, whereas it should be a successor of the original MBB. The testcase changes are caused by Thumb2SizeReduction, which was previously confused by the broken CFG. Follow-up to r266679. Unfortunately, it's tricky to catch this in the verifier. llvm-svn: 267778
2016-04-28 04:32:54 +08:00
; CHECK: {{moveq|movweq}} {{r[0-9]+}}, #1
ARM: use a pseudo-instruction for cmpxchg at -O0. The fast register-allocator cannot cope with inter-block dependencies without spilling. This is fine for ldrex/strex loops coming from atomicrmw instructions where any value produced within a block is dead by the end, but not for cmpxchg. So we lower a cmpxchg at -O0 via a pseudo-inst that gets expanded after regalloc. Fortunately this is at -O0 so we don't have to care about performance. This simplifies the various axes of expansion considerably: we assume a strong seq_cst operation and ensure ordering via the always-present DMB instructions rather than v8 acquire/release instructions. Should fix the 32-bit part of PR25526. llvm-svn: 266679
2016-04-19 05:48:55 +08:00
; CHECK: dmb ish
%res = cmpxchg i8* %addr, i8 %desired, i8 %new seq_cst monotonic
ret { i8, i1 } %res
}
define { i16, i1 } @test_cmpxchg_16(i16* %addr, i16 %desired, i16 %new) nounwind {
; CHECK-LABEL: test_cmpxchg_16:
; CHECK: dmb ish
; CHECK: uxth [[DESIRED:r[0-9]+]], [[DESIRED]]
; CHECK: [[RETRY:.LBB[0-9]+_[0-9]+]]:
; CHECK: ldrexh [[OLD:r[0-9]+]], [r0]
; CHECK: cmp [[OLD]], [[DESIRED]]
; CHECK: bne [[DONE:.LBB[0-9]+_[0-9]+]]
; CHECK: strexh [[STATUS:r[0-9]+]], r2, [r0]
; CHECK: cmp{{(\.w)?}} [[STATUS]], #0
; CHECK: bne [[RETRY]]
; CHECK: [[DONE]]:
; CHECK: cmp{{(\.w)?}} [[OLD]], [[DESIRED]]
[ARM] Set correct successors in CMPXCHG pseudo expansion. transferSuccessors() would LoadCmpBB a successor of DoneBB, whereas it should be a successor of the original MBB. The testcase changes are caused by Thumb2SizeReduction, which was previously confused by the broken CFG. Follow-up to r266679. Unfortunately, it's tricky to catch this in the verifier. llvm-svn: 267778
2016-04-28 04:32:54 +08:00
; CHECK: {{moveq|movweq}} {{r[0-9]+}}, #1
ARM: use a pseudo-instruction for cmpxchg at -O0. The fast register-allocator cannot cope with inter-block dependencies without spilling. This is fine for ldrex/strex loops coming from atomicrmw instructions where any value produced within a block is dead by the end, but not for cmpxchg. So we lower a cmpxchg at -O0 via a pseudo-inst that gets expanded after regalloc. Fortunately this is at -O0 so we don't have to care about performance. This simplifies the various axes of expansion considerably: we assume a strong seq_cst operation and ensure ordering via the always-present DMB instructions rather than v8 acquire/release instructions. Should fix the 32-bit part of PR25526. llvm-svn: 266679
2016-04-19 05:48:55 +08:00
; CHECK: dmb ish
%res = cmpxchg i16* %addr, i16 %desired, i16 %new seq_cst monotonic
ret { i16, i1 } %res
}
define { i32, i1 } @test_cmpxchg_32(i32* %addr, i32 %desired, i32 %new) nounwind {
; CHECK-LABEL: test_cmpxchg_32:
; CHECK: dmb ish
; CHECK-NOT: uxt
; CHECK: [[RETRY:.LBB[0-9]+_[0-9]+]]:
; CHECK: ldrex [[OLD:r[0-9]+]], [r0]
; CHECK: cmp [[OLD]], [[DESIRED]]
; CHECK: bne [[DONE:.LBB[0-9]+_[0-9]+]]
; CHECK: strex [[STATUS:r[0-9]+]], r2, [r0]
; CHECK: cmp{{(\.w)?}} [[STATUS]], #0
; CHECK: bne [[RETRY]]
; CHECK: [[DONE]]:
; CHECK: cmp{{(\.w)?}} [[OLD]], [[DESIRED]]
[ARM] Set correct successors in CMPXCHG pseudo expansion. transferSuccessors() would LoadCmpBB a successor of DoneBB, whereas it should be a successor of the original MBB. The testcase changes are caused by Thumb2SizeReduction, which was previously confused by the broken CFG. Follow-up to r266679. Unfortunately, it's tricky to catch this in the verifier. llvm-svn: 267778
2016-04-28 04:32:54 +08:00
; CHECK: {{moveq|movweq}} {{r[0-9]+}}, #1
ARM: use a pseudo-instruction for cmpxchg at -O0. The fast register-allocator cannot cope with inter-block dependencies without spilling. This is fine for ldrex/strex loops coming from atomicrmw instructions where any value produced within a block is dead by the end, but not for cmpxchg. So we lower a cmpxchg at -O0 via a pseudo-inst that gets expanded after regalloc. Fortunately this is at -O0 so we don't have to care about performance. This simplifies the various axes of expansion considerably: we assume a strong seq_cst operation and ensure ordering via the always-present DMB instructions rather than v8 acquire/release instructions. Should fix the 32-bit part of PR25526. llvm-svn: 266679
2016-04-19 05:48:55 +08:00
; CHECK: dmb ish
%res = cmpxchg i32* %addr, i32 %desired, i32 %new seq_cst monotonic
ret { i32, i1 } %res
}
define { i64, i1 } @test_cmpxchg_64(i64* %addr, i64 %desired, i64 %new) nounwind {
; CHECK-LABEL: test_cmpxchg_64:
; CHECK: dmb ish
; CHECK-NOT: uxt
; CHECK: [[RETRY:.LBB[0-9]+_[0-9]+]]:
; CHECK: ldrexd [[OLDLO:r[0-9]+]], [[OLDHI:r[0-9]+]], [r0]
; CHECK: cmp [[OLDLO]], r6
[ARM] Fix for 64-bit CAS expansion on ARM32 with -O0 Summary: This patch fixes comparison of 64-bit atomic with its expected value in CMP_SWAP_64 expansion. Currently, the low words are compared with CMP, while the high words are compared with SBC. SBC expects the carry flag to be set if CMP detects a difference. CMP might leave the carry unset for unequal arguments though if the first one is >= than the second. This might cause the comparison logic to detect false equality. Example of the broken C++ code: ``` std::atomic<long long> at(2); long long ll = 1; std::atomic_compare_exchange_strong(&at, &ll, 3); ``` Even though the atomic `at` and the expected value `ll` are not equal and `atomic_compare_exchange_strong` returns `false`, `at` is changed to 3. The patch replaces SBC with CMPEQ. Reviewers: t.p.northover Subscribers: aemerson, rengolin, llvm-commits, asl Differential Revision: https://reviews.llvm.org/D27315 llvm-svn: 288433
2016-12-02 06:58:35 +08:00
; CHECK: cmpeq [[OLDHI]], r7
ARM: use a pseudo-instruction for cmpxchg at -O0. The fast register-allocator cannot cope with inter-block dependencies without spilling. This is fine for ldrex/strex loops coming from atomicrmw instructions where any value produced within a block is dead by the end, but not for cmpxchg. So we lower a cmpxchg at -O0 via a pseudo-inst that gets expanded after regalloc. Fortunately this is at -O0 so we don't have to care about performance. This simplifies the various axes of expansion considerably: we assume a strong seq_cst operation and ensure ordering via the always-present DMB instructions rather than v8 acquire/release instructions. Should fix the 32-bit part of PR25526. llvm-svn: 266679
2016-04-19 05:48:55 +08:00
; CHECK: bne [[DONE:.LBB[0-9]+_[0-9]+]]
[ARM] Fix for 64-bit CAS expansion on ARM32 with -O0 Summary: This patch fixes comparison of 64-bit atomic with its expected value in CMP_SWAP_64 expansion. Currently, the low words are compared with CMP, while the high words are compared with SBC. SBC expects the carry flag to be set if CMP detects a difference. CMP might leave the carry unset for unequal arguments though if the first one is >= than the second. This might cause the comparison logic to detect false equality. Example of the broken C++ code: ``` std::atomic<long long> at(2); long long ll = 1; std::atomic_compare_exchange_strong(&at, &ll, 3); ``` Even though the atomic `at` and the expected value `ll` are not equal and `atomic_compare_exchange_strong` returns `false`, `at` is changed to 3. The patch replaces SBC with CMPEQ. Reviewers: t.p.northover Subscribers: aemerson, rengolin, llvm-commits, asl Differential Revision: https://reviews.llvm.org/D27315 llvm-svn: 288433
2016-12-02 06:58:35 +08:00
; CHECK: strexd [[STATUS:r[0-9]+]], r4, r5, [r0]
ARM: use a pseudo-instruction for cmpxchg at -O0. The fast register-allocator cannot cope with inter-block dependencies without spilling. This is fine for ldrex/strex loops coming from atomicrmw instructions where any value produced within a block is dead by the end, but not for cmpxchg. So we lower a cmpxchg at -O0 via a pseudo-inst that gets expanded after regalloc. Fortunately this is at -O0 so we don't have to care about performance. This simplifies the various axes of expansion considerably: we assume a strong seq_cst operation and ensure ordering via the always-present DMB instructions rather than v8 acquire/release instructions. Should fix the 32-bit part of PR25526. llvm-svn: 266679
2016-04-19 05:48:55 +08:00
; CHECK: cmp{{(\.w)?}} [[STATUS]], #0
; CHECK: bne [[RETRY]]
; CHECK: [[DONE]]:
; CHECK: dmb ish
%res = cmpxchg i64* %addr, i64 %desired, i64 %new seq_cst monotonic
ret { i64, i1 } %res
}
ARM: fix assertion failure on -O0 cmpxchg. Because lowering of CMP_SWAP_64 occurs during type legalization, there can be i64 types produced by more than just a BUILD_PAIR or similar. My initial tests used just incoming function args. llvm-svn: 266828
2016-04-20 06:25:02 +08:00
define { i64, i1 } @test_nontrivial_args(i64* %addr, i64 %desired, i64 %new) {
; CHECK-LABEL: test_nontrivial_args:
; CHECK: dmb ish
; CHECK-NOT: uxt
; CHECK: [[RETRY:.LBB[0-9]+_[0-9]+]]:
; CHECK: ldrexd [[OLDLO:r[0-9]+]], [[OLDHI:r[0-9]+]], [r0]
; CHECK: cmp [[OLDLO]], {{r[0-9]+}}
[ARM] Fix for 64-bit CAS expansion on ARM32 with -O0 Summary: This patch fixes comparison of 64-bit atomic with its expected value in CMP_SWAP_64 expansion. Currently, the low words are compared with CMP, while the high words are compared with SBC. SBC expects the carry flag to be set if CMP detects a difference. CMP might leave the carry unset for unequal arguments though if the first one is >= than the second. This might cause the comparison logic to detect false equality. Example of the broken C++ code: ``` std::atomic<long long> at(2); long long ll = 1; std::atomic_compare_exchange_strong(&at, &ll, 3); ``` Even though the atomic `at` and the expected value `ll` are not equal and `atomic_compare_exchange_strong` returns `false`, `at` is changed to 3. The patch replaces SBC with CMPEQ. Reviewers: t.p.northover Subscribers: aemerson, rengolin, llvm-commits, asl Differential Revision: https://reviews.llvm.org/D27315 llvm-svn: 288433
2016-12-02 06:58:35 +08:00
; CHECK: cmpeq [[OLDHI]], {{r[0-9]+}}
ARM: fix assertion failure on -O0 cmpxchg. Because lowering of CMP_SWAP_64 occurs during type legalization, there can be i64 types produced by more than just a BUILD_PAIR or similar. My initial tests used just incoming function args. llvm-svn: 266828
2016-04-20 06:25:02 +08:00
; CHECK: bne [[DONE:.LBB[0-9]+_[0-9]+]]
[ARM] Fix for 64-bit CAS expansion on ARM32 with -O0 Summary: This patch fixes comparison of 64-bit atomic with its expected value in CMP_SWAP_64 expansion. Currently, the low words are compared with CMP, while the high words are compared with SBC. SBC expects the carry flag to be set if CMP detects a difference. CMP might leave the carry unset for unequal arguments though if the first one is >= than the second. This might cause the comparison logic to detect false equality. Example of the broken C++ code: ``` std::atomic<long long> at(2); long long ll = 1; std::atomic_compare_exchange_strong(&at, &ll, 3); ``` Even though the atomic `at` and the expected value `ll` are not equal and `atomic_compare_exchange_strong` returns `false`, `at` is changed to 3. The patch replaces SBC with CMPEQ. Reviewers: t.p.northover Subscribers: aemerson, rengolin, llvm-commits, asl Differential Revision: https://reviews.llvm.org/D27315 llvm-svn: 288433
2016-12-02 06:58:35 +08:00
; CHECK: strexd [[STATUS:r[0-9]+]], {{r[0-9]+}}, {{r[0-9]+}}, [r0]
ARM: fix assertion failure on -O0 cmpxchg. Because lowering of CMP_SWAP_64 occurs during type legalization, there can be i64 types produced by more than just a BUILD_PAIR or similar. My initial tests used just incoming function args. llvm-svn: 266828
2016-04-20 06:25:02 +08:00
; CHECK: cmp{{(\.w)?}} [[STATUS]], #0
; CHECK: bne [[RETRY]]
; CHECK: [[DONE]]:
; CHECK: dmb ish
%desired1 = add i64 %desired, 1
%new1 = add i64 %new, 1
%res = cmpxchg i64* %addr, i64 %desired1, i64 %new1 seq_cst seq_cst
ret { i64, i1 } %res
}
ARM: Do not attempt to modify register class of physregs. Physregs have no associated register class, do not attempt to modify it in Thumb2InstrInfo::storeRegToStackSlot()/loadFromStackSlot(). llvm-svn: 271339
2016-06-01 05:39:12 +08:00
ARM: Improve/fix comment in recently added test. llvm-svn: 271340
2016-06-01 05:59:59 +08:00
; The following used to trigger an assertion when creating a spill on thumb2
; for a physreg with RC==GPRPairRegClass.
ARM: Do not attempt to modify register class of physregs. Physregs have no associated register class, do not attempt to modify it in Thumb2InstrInfo::storeRegToStackSlot()/loadFromStackSlot(). llvm-svn: 271339
2016-06-01 05:39:12 +08:00
; CHECK-LABEL: test_cmpxchg_spillbug:
; CHECK: ldrexd
; CHECK: strexd
; CHECK: bne
define void @test_cmpxchg_spillbug() {
%v = cmpxchg i64* undef, i64 undef, i64 undef seq_cst seq_cst
ret void
}