llvm-6502/test/CodeGen/ARM/atomic-64bit.ll
Tim Northover badb137729 ARM: expand atomic ldrex/strex loops in IR
The previous situation where ATOMIC_LOAD_WHATEVER nodes were expanded
at MachineInstr emission time had grown to be extremely large and
involved, to account for the subtly different code needed for the
various flavours (8/16/32/64 bit, cmpxchg/add/minmax).

Moving this transformation into the IR clears up the code
substantially, and makes future optimisations much easier:

1. an atomicrmw followed by using the *new* value can be more
   efficient. As an IR pass, simple CSE could handle this
   efficiently.
2. Making use of cmpxchg success/failure orderings only has to be done
   in one (simpler) place.
3. The common "cmpxchg; did we store?" idiom can be exposed to
   optimisation.

I intend to gradually improve this situation within the ARM backend
and make sure there are no hidden issues before moving the code out
into CodeGen to be shared with (at least ARM64/AArch64, though I think
PPC & Mips could benefit too).

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@205525 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-03 11:44:58 +00:00

396 lines
12 KiB
LLVM

; RUN: llc < %s -mtriple=armv7-apple-ios | FileCheck %s
; RUN: llc < %s -mtriple=thumbv7-none-linux-gnueabihf -verify-machineinstrs | FileCheck %s --check-prefix=CHECK-THUMB
define i64 @test1(i64* %ptr, i64 %val) {
; CHECK-LABEL: test1:
; CHECK: dmb {{ish$}}
; CHECK: ldrexd [[REG1:(r[0-9]?[02468])]], [[REG2:(r[0-9]?[13579])]]
; CHECK: adds [[REG3:(r[0-9]?[02468])]], [[REG1]]
; CHECK: adc [[REG4:(r[0-9]?[13579])]], [[REG2]]
; CHECK: strexd {{[a-z0-9]+}}, [[REG3]], [[REG4]]
; CHECK: cmp
; CHECK: bne
; CHECK: dmb {{ish$}}
; CHECK-THUMB-LABEL: test1:
; CHECK-THUMB: dmb {{ish$}}
; CHECK-THUMB: ldrexd [[REG1:[a-z0-9]+]], [[REG2:[a-z0-9]+]]
; CHECK-THUMB: adds.w [[REG3:[a-z0-9]+]], [[REG1]]
; CHECK-THUMB: adc.w [[REG4:[a-z0-9]+]], [[REG2]]
; CHECK-THUMB: strexd {{[a-z0-9]+}}, [[REG3]], [[REG4]]
; CHECK-THUMB: cmp
; CHECK-THUMB: bne
; CHECK-THUMB: dmb {{ish$}}
%r = atomicrmw add i64* %ptr, i64 %val seq_cst
ret i64 %r
}
define i64 @test2(i64* %ptr, i64 %val) {
; CHECK-LABEL: test2:
; CHECK: dmb {{ish$}}
; CHECK: ldrexd [[REG1:(r[0-9]?[02468])]], [[REG2:(r[0-9]?[13579])]]
; CHECK: subs [[REG3:(r[0-9]?[02468])]], [[REG1]]
; CHECK: sbc [[REG4:(r[0-9]?[13579])]], [[REG2]]
; CHECK: strexd {{[a-z0-9]+}}, [[REG3]], [[REG4]]
; CHECK: cmp
; CHECK: bne
; CHECK: dmb {{ish$}}
; CHECK-THUMB-LABEL: test2:
; CHECK-THUMB: dmb {{ish$}}
; CHECK-THUMB: ldrexd [[REG1:[a-z0-9]+]], [[REG2:[a-z0-9]+]]
; CHECK-THUMB: subs.w [[REG3:[a-z0-9]+]], [[REG1]]
; CHECK-THUMB: sbc.w [[REG4:[a-z0-9]+]], [[REG2]]
; CHECK-THUMB: strexd {{[a-z0-9]+}}, [[REG3]], [[REG4]]
; CHECK-THUMB: cmp
; CHECK-THUMB: bne
; CHECK-THUMB: dmb {{ish$}}
%r = atomicrmw sub i64* %ptr, i64 %val seq_cst
ret i64 %r
}
define i64 @test3(i64* %ptr, i64 %val) {
; CHECK-LABEL: test3:
; CHECK: dmb {{ish$}}
; CHECK: ldrexd [[REG1:(r[0-9]?[02468])]], [[REG2:(r[0-9]?[13579])]]
; CHECK-DAG: and [[REG3:(r[0-9]?[02468])]], [[REG1]]
; CHECK-DAG: and [[REG4:(r[0-9]?[13579])]], [[REG2]]
; CHECK: strexd {{[a-z0-9]+}}, [[REG3]], [[REG4]]
; CHECK: cmp
; CHECK: bne
; CHECK: dmb {{ish$}}
; CHECK-THUMB-LABEL: test3:
; CHECK-THUMB: dmb {{ish$}}
; CHECK-THUMB: ldrexd [[REG1:[a-z0-9]+]], [[REG2:[a-z0-9]+]]
; CHECK-THUMB-DAG: and.w [[REG3:[a-z0-9]+]], [[REG1]]
; CHECK-THUMB-DAG: and.w [[REG4:[a-z0-9]+]], [[REG2]]
; CHECK-THUMB: strexd {{[a-z0-9]+}}, [[REG3]], [[REG4]]
; CHECK-THUMB: cmp
; CHECK-THUMB: bne
; CHECK-THUMB: dmb {{ish$}}
%r = atomicrmw and i64* %ptr, i64 %val seq_cst
ret i64 %r
}
define i64 @test4(i64* %ptr, i64 %val) {
; CHECK-LABEL: test4:
; CHECK: dmb {{ish$}}
; CHECK: ldrexd [[REG1:(r[0-9]?[02468])]], [[REG2:(r[0-9]?[13579])]]
; CHECK-DAG: orr [[REG3:(r[0-9]?[02468])]], [[REG1]]
; CHECK-DAG: orr [[REG4:(r[0-9]?[13579])]], [[REG2]]
; CHECK: strexd {{[a-z0-9]+}}, [[REG3]], [[REG4]]
; CHECK: cmp
; CHECK: bne
; CHECK: dmb {{ish$}}
; CHECK-THUMB-LABEL: test4:
; CHECK-THUMB: dmb {{ish$}}
; CHECK-THUMB: ldrexd [[REG1:[a-z0-9]+]], [[REG2:[a-z0-9]+]]
; CHECK-THUMB-DAG: orr.w [[REG3:[a-z0-9]+]], [[REG1]]
; CHECK-THUMB-DAG: orr.w [[REG4:[a-z0-9]+]], [[REG2]]
; CHECK-THUMB: strexd {{[a-z0-9]+}}, [[REG3]], [[REG4]]
; CHECK-THUMB: cmp
; CHECK-THUMB: bne
; CHECK-THUMB: dmb {{ish$}}
%r = atomicrmw or i64* %ptr, i64 %val seq_cst
ret i64 %r
}
define i64 @test5(i64* %ptr, i64 %val) {
; CHECK-LABEL: test5:
; CHECK: dmb {{ish$}}
; CHECK: ldrexd [[REG1:(r[0-9]?[02468])]], [[REG2:(r[0-9]?[13579])]]
; CHECK-DAG: eor [[REG3:(r[0-9]?[02468])]], [[REG1]]
; CHECK-DAG: eor [[REG4:(r[0-9]?[13579])]], [[REG2]]
; CHECK: strexd {{[a-z0-9]+}}, [[REG3]], [[REG4]]
; CHECK: cmp
; CHECK: bne
; CHECK: dmb {{ish$}}
; CHECK-THUMB-LABEL: test5:
; CHECK-THUMB: dmb {{ish$}}
; CHECK-THUMB: ldrexd [[REG1:[a-z0-9]+]], [[REG2:[a-z0-9]+]]
; CHECK-THUMB-DAG: eor.w [[REG3:[a-z0-9]+]], [[REG1]]
; CHECK-THUMB-DAG: eor.w [[REG4:[a-z0-9]+]], [[REG2]]
; CHECK-THUMB: strexd {{[a-z0-9]+}}, [[REG3]], [[REG4]]
; CHECK-THUMB: cmp
; CHECK-THUMB: bne
; CHECK-THUMB: dmb {{ish$}}
%r = atomicrmw xor i64* %ptr, i64 %val seq_cst
ret i64 %r
}
define i64 @test6(i64* %ptr, i64 %val) {
; CHECK-LABEL: test6:
; CHECK: dmb {{ish$}}
; CHECK: ldrexd [[REG1:(r[0-9]?[02468])]], [[REG2:(r[0-9]?[13579])]]
; CHECK: strexd {{[a-z0-9]+}}, {{r[0-9]?[02468]}}, {{r[0-9]?[13579]}}
; CHECK: cmp
; CHECK: bne
; CHECK: dmb {{ish$}}
; CHECK-THUMB-LABEL: test6:
; CHECK-THUMB: dmb {{ish$}}
; CHECK-THUMB: ldrexd [[REG1:[a-z0-9]+]], [[REG2:[a-z0-9]+]]
; CHECK-THUMB: strexd {{[a-z0-9]+}}, {{[a-z0-9]+}}, {{[a-z0-9]+}}
; CHECK-THUMB: cmp
; CHECK-THUMB: bne
; CHECK-THUMB: dmb {{ish$}}
%r = atomicrmw xchg i64* %ptr, i64 %val seq_cst
ret i64 %r
}
define i64 @test7(i64* %ptr, i64 %val1, i64 %val2) {
; CHECK-LABEL: test7:
; CHECK: dmb {{ish$}}
; CHECK: ldrexd [[REG1:(r[0-9]?[02468])]], [[REG2:(r[0-9]?[13579])]]
; CHECK-DAG: eor [[MISMATCH_LO:r[0-9]+]], [[REG1]], r1
; CHECK-DAG: eor [[MISMATCH_HI:r[0-9]+]], [[REG2]], r2
; CHECK: orrs {{r[0-9]+}}, [[MISMATCH_LO]], [[MISMATCH_HI]]
; CHECK: bne
; CHECK: strexd {{[a-z0-9]+}}, {{r[0-9]?[02468]}}, {{r[0-9]?[13579]}}
; CHECK: cmp
; CHECK: bne
; CHECK: dmb {{ish$}}
; CHECK-THUMB-LABEL: test7:
; CHECK-THUMB: dmb {{ish$}}
; CHECK-THUMB: ldrexd [[REG1:[a-z0-9]+]], [[REG2:[a-z0-9]+]]
; CHECK-THUMB-DAG: eor.w [[MISMATCH_LO:[a-z0-9]+]], [[REG1]], r2
; CHECK-THUMB-DAG: eor.w [[MISMATCH_HI:[a-z0-9]+]], [[REG2]], r3
; CHECK-THUMB: orrs [[MISMATCH_HI]], [[MISMATCH_LO]]
; CHECK-THUMB: bne
; CHECK-THUMB: strexd {{[a-z0-9]+}}, {{[a-z0-9]+}}, {{[a-z0-9]+}}
; CHECK-THUMB: cmp
; CHECK-THUMB: bne
; CHECK-THUMB: dmb {{ish$}}
%r = cmpxchg i64* %ptr, i64 %val1, i64 %val2 seq_cst seq_cst
ret i64 %r
}
; Compiles down to a single ldrexd
define i64 @test8(i64* %ptr) {
; CHECK-LABEL: test8:
; CHECK: ldrexd [[REG1:(r[0-9]?[02468])]], [[REG2:(r[0-9]?[13579])]]
; CHECK: dmb {{ish$}}
; CHECK-THUMB-LABEL: test8:
; CHECK-THUMB: ldrexd [[REG1:[a-z0-9]+]], [[REG2:[a-z0-9]+]]
; CHECK-THUMB: dmb {{ish$}}
%r = load atomic i64* %ptr seq_cst, align 8
ret i64 %r
}
; Compiles down to atomicrmw xchg; there really isn't any more efficient
; way to write it.
define void @test9(i64* %ptr, i64 %val) {
; CHECK-LABEL: test9:
; CHECK: dmb {{ish$}}
; CHECK: ldrexd [[REG1:(r[0-9]?[02468])]], [[REG2:(r[0-9]?[13579])]]
; CHECK: strexd {{[a-z0-9]+}}, {{r[0-9]?[02468]}}, {{r[0-9]?[13579]}}
; CHECK: cmp
; CHECK: bne
; CHECK: dmb {{ish$}}
; CHECK-THUMB-LABEL: test9:
; CHECK-THUMB: dmb {{ish$}}
; CHECK-THUMB: ldrexd [[REG1:[a-z0-9]+]], [[REG2:[a-z0-9]+]]
; CHECK-THUMB: strexd {{[a-z0-9]+}}, {{[a-z0-9]+}}, {{[a-z0-9]+}}
; CHECK-THUMB: cmp
; CHECK-THUMB: bne
; CHECK-THUMB: dmb {{ish$}}
store atomic i64 %val, i64* %ptr seq_cst, align 8
ret void
}
define i64 @test10(i64* %ptr, i64 %val) {
; CHECK-LABEL: test10:
; CHECK: dmb {{ish$}}
; CHECK: ldrexd [[REG1:(r[0-9]?[02468])]], [[REG2:(r[0-9]?[13579])]]
; CHECK: mov [[CARRY_LO:[a-z0-9]+]], #0
; CHECK: mov [[CARRY_HI:[a-z0-9]+]], #0
; CHECK: mov [[OUT_HI:[a-z0-9]+]], r2
; CHECK: cmp [[REG1]], r1
; CHECK: movwls [[CARRY_LO]], #1
; CHECK: cmp [[REG2]], r2
; CHECK: movwle [[CARRY_HI]], #1
; CHECK: moveq [[CARRY_HI]], [[CARRY_LO]]
; CHECK: cmp [[CARRY_HI]], #0
; CHECK: movne [[OUT_HI]], [[REG2]]
; CHECK: mov [[OUT_LO:[a-z0-9]+]], r1
; CHECK: movne [[OUT_LO]], [[REG1]]
; CHECK: strexd {{[a-z0-9]+}}, [[REG3]], [[REG4]]
; CHECK: cmp
; CHECK: bne
; CHECK: dmb {{ish$}}
; CHECK-THUMB-LABEL: test10:
; CHECK-THUMB: dmb {{ish$}}
; CHECK-THUMB: ldrexd [[REG1:[a-z0-9]+]], [[REG2:[a-z0-9]+]]
; CHECK-THUMB: mov.w [[CARRY_LO:[a-z0-9]+]], #0
; CHECK-THUMB: movs [[CARRY_HI:[a-z0-9]+]], #0
; CHECK-THUMB: cmp [[REG1]], r2
; CHECK-THUMB: movls.w [[CARRY_LO]], #1
; CHECK-THUMB: cmp [[REG2]], r3
; CHECK-THUMB: movle [[CARRY_HI]], #1
; CHECK-THUMB: moveq [[CARRY_HI]], [[CARRY_LO]]
; CHECK-THUMB: mov [[OUT_HI:[a-z0-9]+]], r3
; CHECK-THUMB: cmp [[CARRY_HI]], #0
; CHECK-THUMB: mov [[OUT_LO:[a-z0-9]+]], r2
; CHECK-THUMB: movne [[OUT_HI]], [[REG2]]
; CHECK-THUMB: movne [[OUT_LO]], [[REG1]]
; CHECK-THUMB: strexd {{[a-z0-9]+}}, [[REG3]], [[REG4]]
; CHECK-THUMB: cmp
; CHECK-THUMB: bne
; CHECK-THUMB: dmb {{ish$}}
%r = atomicrmw min i64* %ptr, i64 %val seq_cst
ret i64 %r
}
define i64 @test11(i64* %ptr, i64 %val) {
; CHECK-LABEL: test11:
; CHECK: dmb {{ish$}}
; CHECK: ldrexd [[REG1:(r[0-9]?[02468])]], [[REG2:(r[0-9]?[13579])]]
; CHECK: mov [[CARRY_LO:[a-z0-9]+]], #0
; CHECK: mov [[CARRY_HI:[a-z0-9]+]], #0
; CHECK: mov [[OUT_HI:[a-z0-9]+]], r2
; CHECK: cmp [[REG1]], r1
; CHECK: movwls [[CARRY_LO]], #1
; CHECK: cmp [[REG2]], r2
; CHECK: movwls [[CARRY_HI]], #1
; CHECK: moveq [[CARRY_HI]], [[CARRY_LO]]
; CHECK: cmp [[CARRY_HI]], #0
; CHECK: movne [[OUT_HI]], [[REG2]]
; CHECK: mov [[OUT_LO:[a-z0-9]+]], r1
; CHECK: movne [[OUT_LO]], [[REG1]]
; CHECK: strexd {{[a-z0-9]+}}, [[REG3]], [[REG4]]
; CHECK: cmp
; CHECK: bne
; CHECK: dmb {{ish$}}
; CHECK-THUMB-LABEL: test11:
; CHECK-THUMB: dmb {{ish$}}
; CHECK-THUMB: ldrexd [[REG1:[a-z0-9]+]], [[REG2:[a-z0-9]+]]
; CHECK-THUMB: mov.w [[CARRY_LO:[a-z0-9]+]], #0
; CHECK-THUMB: movs [[CARRY_HI:[a-z0-9]+]], #0
; CHECK-THUMB: cmp [[REG1]], r2
; CHECK-THUMB: movls.w [[CARRY_LO]], #1
; CHECK-THUMB: cmp [[REG2]], r3
; CHECK-THUMB: movls [[CARRY_HI]], #1
; CHECK-THUMB: moveq [[CARRY_HI]], [[CARRY_LO]]
; CHECK-THUMB: mov [[OUT_HI:[a-z0-9]+]], r3
; CHECK-THUMB: cmp [[CARRY_HI]], #0
; CHECK-THUMB: mov [[OUT_LO:[a-z0-9]+]], r2
; CHECK-THUMB: movne [[OUT_HI]], [[REG2]]
; CHECK-THUMB: movne [[OUT_LO]], [[REG1]]
; CHECK-THUMB: strexd {{[a-z0-9]+}}, [[REG3]], [[REG4]]
; CHECK-THUMB: cmp
; CHECK-THUMB: bne
; CHECK-THUMB: dmb {{ish$}}
%r = atomicrmw umin i64* %ptr, i64 %val seq_cst
ret i64 %r
}
define i64 @test12(i64* %ptr, i64 %val) {
; CHECK-LABEL: test12:
; CHECK: dmb {{ish$}}
; CHECK: ldrexd [[REG1:(r[0-9]?[02468])]], [[REG2:(r[0-9]?[13579])]]
; CHECK: mov [[CARRY_LO:[a-z0-9]+]], #0
; CHECK: mov [[CARRY_HI:[a-z0-9]+]], #0
; CHECK: mov [[OUT_HI:[a-z0-9]+]], r2
; CHECK: cmp [[REG1]], r1
; CHECK: movwhi [[CARRY_LO]], #1
; CHECK: cmp [[REG2]], r2
; CHECK: movwgt [[CARRY_HI]], #1
; CHECK: moveq [[CARRY_HI]], [[CARRY_LO]]
; CHECK: cmp [[CARRY_HI]], #0
; CHECK: movne [[OUT_HI]], [[REG2]]
; CHECK: mov [[OUT_LO:[a-z0-9]+]], r1
; CHECK: movne [[OUT_LO]], [[REG1]]
; CHECK: strexd {{[a-z0-9]+}}, [[REG3]], [[REG4]]
; CHECK: cmp
; CHECK: bne
; CHECK: dmb {{ish$}}
; CHECK-THUMB-LABEL: test12:
; CHECK-THUMB: dmb {{ish$}}
; CHECK-THUMB: ldrexd [[REG1:[a-z0-9]+]], [[REG2:[a-z0-9]+]]
; CHECK-THUMB: mov.w [[CARRY_LO:[a-z0-9]+]], #0
; CHECK-THUMB: movs [[CARRY_HI:[a-z0-9]+]], #0
; CHECK-THUMB: cmp [[REG1]], r2
; CHECK-THUMB: movhi.w [[CARRY_LO]], #1
; CHECK-THUMB: cmp [[REG2]], r3
; CHECK-THUMB: movgt [[CARRY_HI]], #1
; CHECK-THUMB: moveq [[CARRY_HI]], [[CARRY_LO]]
; CHECK-THUMB: mov [[OUT_HI:[a-z0-9]+]], r3
; CHECK-THUMB: cmp [[CARRY_HI]], #0
; CHECK-THUMB: mov [[OUT_LO:[a-z0-9]+]], r2
; CHECK-THUMB: movne [[OUT_HI]], [[REG2]]
; CHECK-THUMB: movne [[OUT_LO]], [[REG1]]
; CHECK-THUMB: strexd {{[a-z0-9]+}}, [[REG3]], [[REG4]]
; CHECK-THUMB: cmp
; CHECK-THUMB: bne
; CHECK-THUMB: dmb {{ish$}}
%r = atomicrmw max i64* %ptr, i64 %val seq_cst
ret i64 %r
}
define i64 @test13(i64* %ptr, i64 %val) {
; CHECK-LABEL: test13:
; CHECK: dmb {{ish$}}
; CHECK: ldrexd [[REG1:(r[0-9]?[02468])]], [[REG2:(r[0-9]?[13579])]]
; CHECK: mov [[CARRY_LO:[a-z0-9]+]], #0
; CHECK: mov [[CARRY_HI:[a-z0-9]+]], #0
; CHECK: mov [[OUT_HI:[a-z0-9]+]], r2
; CHECK: cmp [[REG1]], r1
; CHECK: movwhi [[CARRY_LO]], #1
; CHECK: cmp [[REG2]], r2
; CHECK: movwhi [[CARRY_HI]], #1
; CHECK: moveq [[CARRY_HI]], [[CARRY_LO]]
; CHECK: cmp [[CARRY_HI]], #0
; CHECK: movne [[OUT_HI]], [[REG2]]
; CHECK: mov [[OUT_LO:[a-z0-9]+]], r1
; CHECK: movne [[OUT_LO]], [[REG1]]
; CHECK: strexd {{[a-z0-9]+}}, [[REG3]], [[REG4]]
; CHECK: cmp
; CHECK: bne
; CHECK: dmb {{ish$}}
; CHECK-THUMB-LABEL: test13:
; CHECK-THUMB: dmb {{ish$}}
; CHECK-THUMB: ldrexd [[REG1:[a-z0-9]+]], [[REG2:[a-z0-9]+]]
; CHECK-THUMB: mov.w [[CARRY_LO:[a-z0-9]+]], #0
; CHECK-THUMB: movs [[CARRY_HI:[a-z0-9]+]], #0
; CHECK-THUMB: cmp [[REG1]], r2
; CHECK-THUMB: movhi.w [[CARRY_LO]], #1
; CHECK-THUMB: cmp [[REG2]], r3
; CHECK-THUMB: movhi [[CARRY_HI]], #1
; CHECK-THUMB: moveq [[CARRY_HI]], [[CARRY_LO]]
; CHECK-THUMB: mov [[OUT_HI:[a-z0-9]+]], r3
; CHECK-THUMB: cmp [[CARRY_HI]], #0
; CHECK-THUMB: mov [[OUT_LO:[a-z0-9]+]], r2
; CHECK-THUMB: movne [[OUT_HI]], [[REG2]]
; CHECK-THUMB: movne [[OUT_LO]], [[REG1]]
; CHECK-THUMB: strexd {{[a-z0-9]+}}, [[REG3]], [[REG4]]
; CHECK-THUMB: cmp
; CHECK-THUMB: bne
; CHECK-THUMB: dmb {{ish$}}
%r = atomicrmw umax i64* %ptr, i64 %val seq_cst
ret i64 %r
}