mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-22 04:22:57 +02:00
05a99347e9
Reapply r242500 now that the swift schedmodel includes LDRLIT. This is mostly done to disable the PostRAScheduler which optimizes for instruction latencies which isn't a good fit for out-of-order architectures. This also allows to leave out the itinerary table in swift in favor of the SchedModel ones. This change leads to performance improvements/regressions by as much as 10% in some benchmarks, in fact we loose 0.4% performance over the llvm-testsuite for reasons that appear to be unknown or out of the compilers control. rdar://20803802 documents the investigation of these effects. While it is probably a good idea to perform the same switch for the other ARM out-of-order CPUs, I limited this change to swift as I cannot perform the benchmark verification on the other CPUs. Differential Revision: http://reviews.llvm.org/D10513 llvm-svn: 242588
108 lines
2.5 KiB
LLVM
108 lines
2.5 KiB
LLVM
; RUN: llc -mtriple=thumbv7s-apple-ios7.0 -o - %s | FileCheck %s
|
|
|
|
define i32 @test_return(i32* %p, i32 %oldval, i32 %newval) {
|
|
; CHECK-LABEL: test_return:
|
|
|
|
; CHECK: dmb ishst
|
|
|
|
; CHECK: [[LOOP:LBB[0-9]+_[0-9]+]]:
|
|
; CHECK: ldrex [[LOADED:r[0-9]+]], [r0]
|
|
; CHECK: cmp [[LOADED]], r1
|
|
; CHECK: bne [[FAILED:LBB[0-9]+_[0-9]+]]
|
|
|
|
; CHECK: strex [[STATUS:r[0-9]+]], {{r[0-9]+}}, [r0]
|
|
; CHECK: cmp [[STATUS]], #0
|
|
; CHECK: bne [[LOOP]]
|
|
|
|
; CHECK-NOT: cmp {{r[0-9]+}}, {{r[0-9]+}}
|
|
; CHECK: dmb ish
|
|
; CHECK: movs r0, #1
|
|
; CHECK: bx lr
|
|
|
|
; CHECK: [[FAILED]]:
|
|
; CHECK-NOT: cmp {{r[0-9]+}}, {{r[0-9]+}}
|
|
; CHECK: dmb ish
|
|
; CHECK: movs r0, #0
|
|
; CHECK: bx lr
|
|
|
|
%pair = cmpxchg i32* %p, i32 %oldval, i32 %newval seq_cst seq_cst
|
|
%success = extractvalue { i32, i1 } %pair, 1
|
|
%conv = zext i1 %success to i32
|
|
ret i32 %conv
|
|
}
|
|
|
|
define i1 @test_return_bool(i8* %value, i8 %oldValue, i8 %newValue) {
|
|
; CHECK-LABEL: test_return_bool:
|
|
|
|
; CHECK: dmb ishst
|
|
; CHECK: uxtb [[OLDBYTE:r[0-9]+]], r1
|
|
|
|
; CHECK: [[LOOP:LBB[0-9]+_[0-9]+]]:
|
|
; CHECK: ldrexb [[LOADED:r[0-9]+]], [r0]
|
|
; CHECK: cmp [[LOADED]], [[OLDBYTE]]
|
|
; CHECK: bne [[FAIL:LBB[0-9]+_[0-9]+]]
|
|
|
|
; CHECK: strexb [[STATUS:r[0-9]+]], {{r[0-9]+}}, [r0]
|
|
; CHECK: cmp [[STATUS]], #0
|
|
; CHECK: bne [[LOOP]]
|
|
|
|
; FIXME: this eor is redundant. Need to teach DAG combine that.
|
|
; CHECK-NOT: cmp {{r[0-9]+}}, {{r[0-9]+}}
|
|
; CHECK: movs [[TMP:r[0-9]+]], #1
|
|
; CHECK: eor r0, [[TMP]], #1
|
|
; CHECK: bx lr
|
|
|
|
; CHECK: [[FAIL]]:
|
|
; CHECK: movs [[TMP:r[0-9]+]], #0
|
|
; CHECK: eor r0, [[TMP]], #1
|
|
; CHECK: bx lr
|
|
|
|
|
|
%pair = cmpxchg i8* %value, i8 %oldValue, i8 %newValue acq_rel monotonic
|
|
%success = extractvalue { i8, i1 } %pair, 1
|
|
%failure = xor i1 %success, 1
|
|
ret i1 %failure
|
|
}
|
|
|
|
define void @test_conditional(i32* %p, i32 %oldval, i32 %newval) {
|
|
; CHECK-LABEL: test_conditional:
|
|
|
|
; CHECK: dmb ishst
|
|
|
|
; CHECK: [[LOOP:LBB[0-9]+_[0-9]+]]:
|
|
; CHECK: ldrex [[LOADED:r[0-9]+]], [r0]
|
|
; CHECK: cmp [[LOADED]], r1
|
|
; CHECK: bne [[FAILED:LBB[0-9]+_[0-9]+]]
|
|
|
|
; CHECK: strex [[STATUS:r[0-9]+]], r2, [r0]
|
|
; CHECK: cmp [[STATUS]], #0
|
|
; CHECK: bne [[LOOP]]
|
|
|
|
; CHECK-NOT: cmp {{r[0-9]+}}, {{r[0-9]+}}
|
|
; CHECK: dmb ish
|
|
; CHECK: b.w _bar
|
|
|
|
; CHECK: [[FAILED]]:
|
|
; CHECK-NOT: cmp {{r[0-9]+}}, {{r[0-9]+}}
|
|
; CHECK: dmb ish
|
|
; CHECK: b.w _baz
|
|
|
|
%pair = cmpxchg i32* %p, i32 %oldval, i32 %newval seq_cst seq_cst
|
|
%success = extractvalue { i32, i1 } %pair, 1
|
|
br i1 %success, label %true, label %false
|
|
|
|
true:
|
|
tail call void @bar() #2
|
|
br label %end
|
|
|
|
false:
|
|
tail call void @baz() #2
|
|
br label %end
|
|
|
|
end:
|
|
ret void
|
|
}
|
|
|
|
declare void @bar()
|
|
declare void @baz()
|