1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 03:02:36 +01:00
llvm-mirror/test/CodeGen/ARM/dag-combine-ldst.ll
Nirav Dave 3633380341 Elide stores which are overwritten without being observed.
Summary:
In SelectionDAG, when a store is immediately chained to another store
to the same address, elide the first store as it has no observable
effects. This is causes small improvements dealing with intrinsics
lowered to stores.

Test notes:

* Many testcases overwrite store addresses multiple times and needed
  minor changes, mainly making stores volatile to prevent the
  optimization from optimizing the test away.

* Many X86 test cases optimized out instructions associated with
  associated with va_start.

* Note that test_splat in CodeGen/AArch64/misched-stp.ll no longer has
  dependencies to check and can probably be removed and potentially
  replaced with another test.

Reviewers: rnk, john.brawn

Subscribers: aemerson, rengolin, qcolombet, jyknight, nemanjai, nhaehnle, javed.absar, llvm-commits

Differential Revision: https://reviews.llvm.org/D33206

llvm-svn: 303198
2017-05-16 19:43:56 +00:00

42 lines
1.4 KiB
LLVM

; RUN: llc < %s -mtriple=arm-eabi -mattr=+v4t -O0 | FileCheck %s -check-prefix=CHECK -check-prefix=CHECK_O0
; RUN: llc < %s -mtriple=arm-eabi -mattr=+v4t -O1 | FileCheck %s -check-prefix=CHECK -check-prefix=CHECK_O1
; In /O0, the addition must not be eliminated. This happens when the load
; and store are folded by the DAGCombiner. In /O1 and above, the optimization
; must be executed.
; CHECK-LABEL: {{^}}main
; CHECK: mov [[TMP:r[0-9]+]], #0
; CHECK-NEXT: str [[TMP]], [sp, #4]
; CHECK_O0: str [[TMP]], [sp]
; CHECK_O0: ldr [[TMP:r[0-9]+]], [sp]
; CHECK_O0-NEXT: add [[TMP]], [[TMP]], #2
; CHECK_O1-NOT: ldr [[TMP:r[0-9]+]], [sp]
; CHECK_O1-NOT: add [[TMP]], [[TMP]], #2
define i32 @main() {
bb:
%tmp = alloca i32, align 4
%tmp1 = alloca i32, align 4
store i32 0, i32* %tmp, align 4
store i32 0, i32* %tmp1, align 4
%tmp2 = load i32, i32* %tmp1, align 4
%tmp3 = add nsw i32 %tmp2, 2
store i32 %tmp3, i32* %tmp1, align 4
%tmp4 = load i32, i32* %tmp1, align 4
%tmp5 = icmp eq i32 %tmp4, 2
br i1 %tmp5, label %bb6, label %bb7
bb6: ; preds = %bb
store i32 0, i32* %tmp, align 4
br label %bb8
bb7: ; preds = %bb
store i32 5, i32* %tmp, align 4
br label %bb8
bb8: ; preds = %bb7, %bb6
%tmp9 = load i32, i32* %tmp, align 4
ret i32 %tmp9
}