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/atomic128.ll

289 lines
7.8 KiB
LLVM
Raw Normal View History

X86: expand atomics in IR instead of as MachineInstrs. The logic for expanding atomics that aren't natively supported in terms of cmpxchg loops is much simpler to express at the IR level. It also allows the normal optimisations and CodeGen improvements to help out with atomics, instead of using a limited set of possible instructions.. rdar://problem/13496295 llvm-svn: 212119
2014-07-02 02:53:31 +08:00
; RUN: llc < %s -mtriple=x86_64-apple-macosx10.9 -verify-machineinstrs -mattr=cx16 | FileCheck %s
@var = global i128 0
define i128 @val_compare_and_swap(i128* %p, i128 %oldval, i128 %newval) {
; CHECK-LABEL: val_compare_and_swap:
; CHECK: movq %rsi, %rax
; CHECK: movq %rcx, %rbx
; CHECK: movq %r8, %rcx
; CHECK: lock
; CHECK: cmpxchg16b (%rdi)
%pair = cmpxchg i128* %p, i128 %oldval, i128 %newval acquire acquire
%val = extractvalue { i128, i1 } %pair, 0
ret i128 %val
}
define void @fetch_and_nand(i128* %p, i128 %bits) {
; CHECK-LABEL: fetch_and_nand:
; CHECK-DAG: movq %rdx, [[INCHI:%[a-z0-9]+]]
; CHECK-DAG: movq (%rdi), %rax
; CHECK-DAG: movq 8(%rdi), %rdx
; CHECK: [[LOOP:.?LBB[0-9]+_[0-9]+]]:
; CHECK: movq %rdx, %rcx
; CHECK: andq [[INCHI]], %rcx
; CHECK: movq %rax, %rbx
; INCLO equivalent comes in in %rsi, so it makes sense it stays there.
; CHECK: andq %rsi, %rbx
; CHECK: notq %rbx
; CHECK: notq %rcx
; CHECK: lock
; CHECK: cmpxchg16b (%rdi)
; CHECK: jne [[LOOP]]
; CHECK: movq %rax, _var
; CHECK: movq %rdx, _var+8
%val = atomicrmw nand i128* %p, i128 %bits release
store i128 %val, i128* @var, align 16
ret void
}
define void @fetch_and_or(i128* %p, i128 %bits) {
; CHECK-LABEL: fetch_and_or:
; CHECK-DAG: movq %rdx, [[INCHI:%[a-z0-9]+]]
; CHECK-DAG: movq (%rdi), %rax
; CHECK-DAG: movq 8(%rdi), %rdx
; CHECK: [[LOOP:.?LBB[0-9]+_[0-9]+]]:
; CHECK: movq %rax, %rbx
; INCLO equivalent comes in in %rsi, so it makes sense it stays there.
; CHECK: orq %rsi, %rbx
; CHECK: movq %rdx, %rcx
; CHECK: orq [[INCHI]], %rcx
; CHECK: lock
; CHECK: cmpxchg16b (%rdi)
; CHECK: jne [[LOOP]]
; CHECK: movq %rax, _var
; CHECK: movq %rdx, _var+8
%val = atomicrmw or i128* %p, i128 %bits seq_cst
store i128 %val, i128* @var, align 16
ret void
}
define void @fetch_and_add(i128* %p, i128 %bits) {
; CHECK-LABEL: fetch_and_add:
; CHECK-DAG: movq %rdx, [[INCHI:%[a-z0-9]+]]
; CHECK-DAG: movq (%rdi), %rax
; CHECK-DAG: movq 8(%rdi), %rdx
; CHECK: [[LOOP:.?LBB[0-9]+_[0-9]+]]:
; CHECK: movq %rax, %rbx
; INCLO equivalent comes in in %rsi, so it makes sense it stays there.
; CHECK: addq %rsi, %rbx
; CHECK: movq %rdx, %rcx
; CHECK: adcq [[INCHI]], %rcx
; CHECK: lock
; CHECK: cmpxchg16b (%rdi)
; CHECK: jne [[LOOP]]
; CHECK: movq %rax, _var
; CHECK: movq %rdx, _var+8
%val = atomicrmw add i128* %p, i128 %bits seq_cst
store i128 %val, i128* @var, align 16
ret void
}
define void @fetch_and_sub(i128* %p, i128 %bits) {
; CHECK-LABEL: fetch_and_sub:
; CHECK-DAG: movq %rdx, [[INCHI:%[a-z0-9]+]]
; CHECK-DAG: movq (%rdi), %rax
; CHECK-DAG: movq 8(%rdi), %rdx
; CHECK: [[LOOP:.?LBB[0-9]+_[0-9]+]]:
; CHECK: movq %rax, %rbx
; INCLO equivalent comes in in %rsi, so it makes sense it stays there.
; CHECK: subq %rsi, %rbx
; CHECK: movq %rdx, %rcx
; CHECK: sbbq [[INCHI]], %rcx
; CHECK: lock
; CHECK: cmpxchg16b (%rdi)
; CHECK: jne [[LOOP]]
; CHECK: movq %rax, _var
; CHECK: movq %rdx, _var+8
%val = atomicrmw sub i128* %p, i128 %bits seq_cst
store i128 %val, i128* @var, align 16
ret void
}
define void @fetch_and_min(i128* %p, i128 %bits) {
; CHECK-LABEL: fetch_and_min:
; CHECK-DAG: movq %rdx, [[INCHI:%[a-z0-9]+]]
; CHECK-DAG: movq (%rdi), %rax
; CHECK-DAG: movq 8(%rdi), %rdx
; CHECK: [[LOOP:.?LBB[0-9]+_[0-9]+]]:
X86: More efficient legalization of wide integer compares In particular, this makes the code for 64-bit compares on 32-bit targets much more efficient. Example: define i32 @test_slt(i64 %a, i64 %b) { entry: %cmp = icmp slt i64 %a, %b br i1 %cmp, label %bb1, label %bb2 bb1: ret i32 1 bb2: ret i32 2 } Before this patch: test_slt: movl 4(%esp), %eax movl 8(%esp), %ecx cmpl 12(%esp), %eax setae %al cmpl 16(%esp), %ecx setge %cl je .LBB2_2 movb %cl, %al .LBB2_2: testb %al, %al jne .LBB2_4 movl $1, %eax retl .LBB2_4: movl $2, %eax retl After this patch: test_slt: movl 4(%esp), %eax movl 8(%esp), %ecx cmpl 12(%esp), %eax sbbl 16(%esp), %ecx jge .LBB1_2 movl $1, %eax retl .LBB1_2: movl $2, %eax retl Differential Revision: http://reviews.llvm.org/D14496 llvm-svn: 253572
2015-11-20 00:35:08 +08:00
; CHECK: cmpq
; CHECK: sbbq
; CHECK: setg
X86: expand atomics in IR instead of as MachineInstrs. The logic for expanding atomics that aren't natively supported in terms of cmpxchg loops is much simpler to express at the IR level. It also allows the normal optimisations and CodeGen improvements to help out with atomics, instead of using a limited set of possible instructions.. rdar://problem/13496295 llvm-svn: 212119
2014-07-02 02:53:31 +08:00
; CHECK: cmovneq %rax, %rbx
; CHECK: movq [[INCHI]], %rcx
; CHECK: cmovneq %rdx, %rcx
; CHECK: lock
; CHECK: cmpxchg16b (%rdi)
; CHECK: jne [[LOOP]]
; CHECK: movq %rax, _var
; CHECK: movq %rdx, _var+8
%val = atomicrmw min i128* %p, i128 %bits seq_cst
store i128 %val, i128* @var, align 16
ret void
}
define void @fetch_and_max(i128* %p, i128 %bits) {
; CHECK-LABEL: fetch_and_max:
; CHECK-DAG: movq %rdx, [[INCHI:%[a-z0-9]+]]
; CHECK-DAG: movq (%rdi), %rax
; CHECK-DAG: movq 8(%rdi), %rdx
; CHECK: [[LOOP:.?LBB[0-9]+_[0-9]+]]:
X86: More efficient legalization of wide integer compares In particular, this makes the code for 64-bit compares on 32-bit targets much more efficient. Example: define i32 @test_slt(i64 %a, i64 %b) { entry: %cmp = icmp slt i64 %a, %b br i1 %cmp, label %bb1, label %bb2 bb1: ret i32 1 bb2: ret i32 2 } Before this patch: test_slt: movl 4(%esp), %eax movl 8(%esp), %ecx cmpl 12(%esp), %eax setae %al cmpl 16(%esp), %ecx setge %cl je .LBB2_2 movb %cl, %al .LBB2_2: testb %al, %al jne .LBB2_4 movl $1, %eax retl .LBB2_4: movl $2, %eax retl After this patch: test_slt: movl 4(%esp), %eax movl 8(%esp), %ecx cmpl 12(%esp), %eax sbbl 16(%esp), %ecx jge .LBB1_2 movl $1, %eax retl .LBB1_2: movl $2, %eax retl Differential Revision: http://reviews.llvm.org/D14496 llvm-svn: 253572
2015-11-20 00:35:08 +08:00
; CHECK: cmpq
; CHECK: sbbq
; CHECK: setge
X86: expand atomics in IR instead of as MachineInstrs. The logic for expanding atomics that aren't natively supported in terms of cmpxchg loops is much simpler to express at the IR level. It also allows the normal optimisations and CodeGen improvements to help out with atomics, instead of using a limited set of possible instructions.. rdar://problem/13496295 llvm-svn: 212119
2014-07-02 02:53:31 +08:00
; CHECK: cmovneq %rax, %rbx
; CHECK: movq [[INCHI]], %rcx
; CHECK: cmovneq %rdx, %rcx
; CHECK: lock
; CHECK: cmpxchg16b (%rdi)
; CHECK: jne [[LOOP]]
; CHECK: movq %rax, _var
; CHECK: movq %rdx, _var+8
%val = atomicrmw max i128* %p, i128 %bits seq_cst
store i128 %val, i128* @var, align 16
ret void
}
define void @fetch_and_umin(i128* %p, i128 %bits) {
; CHECK-LABEL: fetch_and_umin:
; CHECK-DAG: movq %rdx, [[INCHI:%[a-z0-9]+]]
; CHECK-DAG: movq (%rdi), %rax
; CHECK-DAG: movq 8(%rdi), %rdx
; CHECK: [[LOOP:.?LBB[0-9]+_[0-9]+]]:
X86: More efficient legalization of wide integer compares In particular, this makes the code for 64-bit compares on 32-bit targets much more efficient. Example: define i32 @test_slt(i64 %a, i64 %b) { entry: %cmp = icmp slt i64 %a, %b br i1 %cmp, label %bb1, label %bb2 bb1: ret i32 1 bb2: ret i32 2 } Before this patch: test_slt: movl 4(%esp), %eax movl 8(%esp), %ecx cmpl 12(%esp), %eax setae %al cmpl 16(%esp), %ecx setge %cl je .LBB2_2 movb %cl, %al .LBB2_2: testb %al, %al jne .LBB2_4 movl $1, %eax retl .LBB2_4: movl $2, %eax retl After this patch: test_slt: movl 4(%esp), %eax movl 8(%esp), %ecx cmpl 12(%esp), %eax sbbl 16(%esp), %ecx jge .LBB1_2 movl $1, %eax retl .LBB1_2: movl $2, %eax retl Differential Revision: http://reviews.llvm.org/D14496 llvm-svn: 253572
2015-11-20 00:35:08 +08:00
; CHECK: cmpq
; CHECK: sbbq
; CHECK: seta
X86: expand atomics in IR instead of as MachineInstrs. The logic for expanding atomics that aren't natively supported in terms of cmpxchg loops is much simpler to express at the IR level. It also allows the normal optimisations and CodeGen improvements to help out with atomics, instead of using a limited set of possible instructions.. rdar://problem/13496295 llvm-svn: 212119
2014-07-02 02:53:31 +08:00
; CHECK: cmovneq %rax, %rbx
; CHECK: movq [[INCHI]], %rcx
; CHECK: cmovneq %rdx, %rcx
; CHECK: lock
; CHECK: cmpxchg16b (%rdi)
; CHECK: jne [[LOOP]]
; CHECK: movq %rax, _var
; CHECK: movq %rdx, _var+8
%val = atomicrmw umin i128* %p, i128 %bits seq_cst
store i128 %val, i128* @var, align 16
ret void
}
define void @fetch_and_umax(i128* %p, i128 %bits) {
; CHECK-LABEL: fetch_and_umax:
; CHECK-DAG: movq %rdx, [[INCHI:%[a-z0-9]+]]
; CHECK-DAG: movq (%rdi), %rax
; CHECK-DAG: movq 8(%rdi), %rdx
; CHECK: [[LOOP:.?LBB[0-9]+_[0-9]+]]:
X86: More efficient legalization of wide integer compares In particular, this makes the code for 64-bit compares on 32-bit targets much more efficient. Example: define i32 @test_slt(i64 %a, i64 %b) { entry: %cmp = icmp slt i64 %a, %b br i1 %cmp, label %bb1, label %bb2 bb1: ret i32 1 bb2: ret i32 2 } Before this patch: test_slt: movl 4(%esp), %eax movl 8(%esp), %ecx cmpl 12(%esp), %eax setae %al cmpl 16(%esp), %ecx setge %cl je .LBB2_2 movb %cl, %al .LBB2_2: testb %al, %al jne .LBB2_4 movl $1, %eax retl .LBB2_4: movl $2, %eax retl After this patch: test_slt: movl 4(%esp), %eax movl 8(%esp), %ecx cmpl 12(%esp), %eax sbbl 16(%esp), %ecx jge .LBB1_2 movl $1, %eax retl .LBB1_2: movl $2, %eax retl Differential Revision: http://reviews.llvm.org/D14496 llvm-svn: 253572
2015-11-20 00:35:08 +08:00
; CHECK: cmpq
; CHECK: sbbq
; CHECK: setb
X86: expand atomics in IR instead of as MachineInstrs. The logic for expanding atomics that aren't natively supported in terms of cmpxchg loops is much simpler to express at the IR level. It also allows the normal optimisations and CodeGen improvements to help out with atomics, instead of using a limited set of possible instructions.. rdar://problem/13496295 llvm-svn: 212119
2014-07-02 02:53:31 +08:00
; CHECK: cmovneq %rax, %rbx
; CHECK: movq [[INCHI]], %rcx
; CHECK: cmovneq %rdx, %rcx
; CHECK: lock
; CHECK: cmpxchg16b (%rdi)
; CHECK: jne [[LOOP]]
; CHECK: movq %rax, _var
; CHECK: movq %rdx, _var+8
%val = atomicrmw umax i128* %p, i128 %bits seq_cst
store i128 %val, i128* @var, align 16
ret void
}
define i128 @atomic_load_seq_cst(i128* %p) {
; CHECK-LABEL: atomic_load_seq_cst:
; CHECK: xorl %eax, %eax
; CHECK: xorl %edx, %edx
; CHECK: xorl %ebx, %ebx
; CHECK: xorl %ecx, %ecx
; CHECK: lock
; CHECK: cmpxchg16b (%rdi)
[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
%r = load atomic i128, i128* %p seq_cst, align 16
X86: expand atomics in IR instead of as MachineInstrs. The logic for expanding atomics that aren't natively supported in terms of cmpxchg loops is much simpler to express at the IR level. It also allows the normal optimisations and CodeGen improvements to help out with atomics, instead of using a limited set of possible instructions.. rdar://problem/13496295 llvm-svn: 212119
2014-07-02 02:53:31 +08:00
ret i128 %r
}
define i128 @atomic_load_relaxed(i128* %p) {
; CHECK: atomic_load_relaxed:
; CHECK: xorl %eax, %eax
; CHECK: xorl %edx, %edx
; CHECK: xorl %ebx, %ebx
; CHECK: xorl %ecx, %ecx
; CHECK: lock
; CHECK: cmpxchg16b (%rdi)
[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
%r = load atomic i128, i128* %p monotonic, align 16
X86: expand atomics in IR instead of as MachineInstrs. The logic for expanding atomics that aren't natively supported in terms of cmpxchg loops is much simpler to express at the IR level. It also allows the normal optimisations and CodeGen improvements to help out with atomics, instead of using a limited set of possible instructions.. rdar://problem/13496295 llvm-svn: 212119
2014-07-02 02:53:31 +08:00
ret i128 %r
}
define void @atomic_store_seq_cst(i128* %p, i128 %in) {
; CHECK-LABEL: atomic_store_seq_cst:
; CHECK: movq %rdx, %rcx
; CHECK: movq %rsi, %rbx
; CHECK: movq (%rdi), %rax
; CHECK: movq 8(%rdi), %rdx
; CHECK: [[LOOP:.?LBB[0-9]+_[0-9]+]]:
; CHECK: lock
; CHECK: cmpxchg16b (%rdi)
; CHECK: jne [[LOOP]]
X86: remove temporary atomicrmw used during lowering. We construct a temporary "atomicrmw xchg" instruction when lowering atomic stores for widths that aren't supported natively. This isn't on the top-level worklist though, so it won't be removed automatically and we have to do it ourselves once that itself has been lowered. Thanks Saleem for pointing this out! llvm-svn: 212948
2014-07-14 23:31:13 +08:00
; CHECK-NOT: callq ___sync_lock_test_and_set_16
X86: expand atomics in IR instead of as MachineInstrs. The logic for expanding atomics that aren't natively supported in terms of cmpxchg loops is much simpler to express at the IR level. It also allows the normal optimisations and CodeGen improvements to help out with atomics, instead of using a limited set of possible instructions.. rdar://problem/13496295 llvm-svn: 212119
2014-07-02 02:53:31 +08:00
store atomic i128 %in, i128* %p seq_cst, align 16
ret void
}
define void @atomic_store_release(i128* %p, i128 %in) {
; CHECK-LABEL: atomic_store_release:
; CHECK: movq %rdx, %rcx
; CHECK: movq %rsi, %rbx
; CHECK: movq (%rdi), %rax
; CHECK: movq 8(%rdi), %rdx
; CHECK: [[LOOP:.?LBB[0-9]+_[0-9]+]]:
; CHECK: lock
; CHECK: cmpxchg16b (%rdi)
; CHECK: jne [[LOOP]]
store atomic i128 %in, i128* %p release, align 16
ret void
}
define void @atomic_store_relaxed(i128* %p, i128 %in) {
; CHECK-LABEL: atomic_store_relaxed:
; CHECK: movq %rdx, %rcx
; CHECK: movq %rsi, %rbx
; CHECK: movq (%rdi), %rax
; CHECK: movq 8(%rdi), %rdx
; CHECK: [[LOOP:.?LBB[0-9]+_[0-9]+]]:
; CHECK: lock
; CHECK: cmpxchg16b (%rdi)
; CHECK: jne [[LOOP]]
store atomic i128 %in, i128* %p unordered, align 16
ret void
}