4ea121c904
There are a few issues with the code we generate for atomic operations and the way we generate it: - Hard coded CR0 for compares - Order of operands for compares not conducive to emitting compare-immediate or for CSE of compares - Missing MachineMemOperand for st[bhwd]cx intrinsics - Missing intrinsic properties for the same - Unnecessary blocks with store conditional instructions to clear reservation (which ends up hindering performance) - Move from CR instructions just to compare the result of a store conditional with zero (even though it is a record-form) This patch aims to resolve all of those issues. Differential revision: https://reviews.llvm.org/D134783
84 lines
2.9 KiB
LLVM
84 lines
2.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -verify-machineinstrs -mtriple=powerpc64-unknown-unknown \
|
|
; RUN: < %s | FileCheck --check-prefix=CHECK-64 %s
|
|
; RUN: llc -verify-machineinstrs -mtriple=powerpc-unknown-unknown \
|
|
; RUN: < %s | FileCheck --check-prefix=CHECK-32 %s
|
|
|
|
define float @test_add(float* %ptr, float %incr) {
|
|
; CHECK-64-LABEL: test_add:
|
|
; CHECK-64: # %bb.0: # %entry
|
|
; CHECK-64-NEXT: sync
|
|
; CHECK-64-NEXT: lfs 0, 0(3)
|
|
; CHECK-64-NEXT: b .LBB0_2
|
|
; CHECK-64-NEXT: .LBB0_1: # %atomicrmw.start
|
|
; CHECK-64-NEXT: #
|
|
; CHECK-64-NEXT: stw 6, -4(1)
|
|
; CHECK-64-NEXT: cmplw 6, 4
|
|
; CHECK-64-NEXT: lfs 0, -4(1)
|
|
; CHECK-64-NEXT: beq 0, .LBB0_5
|
|
; CHECK-64-NEXT: .LBB0_2: # %atomicrmw.start
|
|
; CHECK-64-NEXT: # =>This Loop Header: Depth=1
|
|
; CHECK-64-NEXT: # Child Loop BB0_3 Depth 2
|
|
; CHECK-64-NEXT: fadds 2, 0, 1
|
|
; CHECK-64-NEXT: stfs 2, -8(1)
|
|
; CHECK-64-NEXT: stfs 0, -12(1)
|
|
; CHECK-64-NEXT: lwz 5, -8(1)
|
|
; CHECK-64-NEXT: lwz 4, -12(1)
|
|
; CHECK-64-NEXT: .LBB0_3: # %atomicrmw.start
|
|
; CHECK-64-NEXT: # Parent Loop BB0_2 Depth=1
|
|
; CHECK-64-NEXT: # => This Inner Loop Header: Depth=2
|
|
; CHECK-64-NEXT: lwarx 6, 0, 3
|
|
; CHECK-64-NEXT: cmpw 6, 4
|
|
; CHECK-64-NEXT: bne 0, .LBB0_1
|
|
; CHECK-64-NEXT: # %bb.4: # %atomicrmw.start
|
|
; CHECK-64-NEXT: #
|
|
; CHECK-64-NEXT: stwcx. 5, 0, 3
|
|
; CHECK-64-NEXT: bne 0, .LBB0_3
|
|
; CHECK-64-NEXT: b .LBB0_1
|
|
; CHECK-64-NEXT: .LBB0_5: # %atomicrmw.end
|
|
; CHECK-64-NEXT: fmr 1, 0
|
|
; CHECK-64-NEXT: lwsync
|
|
; CHECK-64-NEXT: blr
|
|
;
|
|
; CHECK-32-LABEL: test_add:
|
|
; CHECK-32: # %bb.0: # %entry
|
|
; CHECK-32-NEXT: stwu 1, -32(1)
|
|
; CHECK-32-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-32-NEXT: sync
|
|
; CHECK-32-NEXT: lfs 0, 0(3)
|
|
; CHECK-32-NEXT: b .LBB0_2
|
|
; CHECK-32-NEXT: .LBB0_1: # %atomicrmw.start
|
|
; CHECK-32-NEXT: #
|
|
; CHECK-32-NEXT: stw 6, 28(1)
|
|
; CHECK-32-NEXT: cmplw 6, 4
|
|
; CHECK-32-NEXT: lfs 0, 28(1)
|
|
; CHECK-32-NEXT: beq 0, .LBB0_5
|
|
; CHECK-32-NEXT: .LBB0_2: # %atomicrmw.start
|
|
; CHECK-32-NEXT: # =>This Loop Header: Depth=1
|
|
; CHECK-32-NEXT: # Child Loop BB0_3 Depth 2
|
|
; CHECK-32-NEXT: fadds 2, 0, 1
|
|
; CHECK-32-NEXT: stfs 2, 24(1)
|
|
; CHECK-32-NEXT: stfs 0, 20(1)
|
|
; CHECK-32-NEXT: lwz 5, 24(1)
|
|
; CHECK-32-NEXT: lwz 4, 20(1)
|
|
; CHECK-32-NEXT: .LBB0_3: # %atomicrmw.start
|
|
; CHECK-32-NEXT: # Parent Loop BB0_2 Depth=1
|
|
; CHECK-32-NEXT: # => This Inner Loop Header: Depth=2
|
|
; CHECK-32-NEXT: lwarx 6, 0, 3
|
|
; CHECK-32-NEXT: cmpw 6, 4
|
|
; CHECK-32-NEXT: bne 0, .LBB0_1
|
|
; CHECK-32-NEXT: # %bb.4: # %atomicrmw.start
|
|
; CHECK-32-NEXT: #
|
|
; CHECK-32-NEXT: stwcx. 5, 0, 3
|
|
; CHECK-32-NEXT: bne 0, .LBB0_3
|
|
; CHECK-32-NEXT: b .LBB0_1
|
|
; CHECK-32-NEXT: .LBB0_5: # %atomicrmw.end
|
|
; CHECK-32-NEXT: fmr 1, 0
|
|
; CHECK-32-NEXT: lwsync
|
|
; CHECK-32-NEXT: addi 1, 1, 32
|
|
; CHECK-32-NEXT: blr
|
|
entry:
|
|
%r = atomicrmw fadd float* %ptr, float %incr seq_cst
|
|
ret float %r
|
|
}
|