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/loop-align-cortex-m.ll
Sam Parker 555093ddca [LSR] Generate cross iteration indexes
Modify GenerateConstantOffsetsImpl to create offsets that can be used
by indexed addressing modes. If formulae can be generated which
result in the constant offset being the same size as the recurrence,
we can generate a pre-indexed access. This allows the pointer to be
updated via the single pre-indexed access so that (hopefully) no
add/subs are required to update it for the next iteration. For small
cores, this can significantly improve performance DSP-like loops.

Differential Revision: https://reviews.llvm.org/D55373

llvm-svn: 353403
2019-02-07 13:32:54 +00:00

50 lines
1.4 KiB
LLVM

; RUN: llc -mtriple=thumbv7m-none-eabi %s -mcpu=cortex-m3 -o - | FileCheck %s
; RUN: llc -mtriple=thumbv7m-none-eabi %s -mcpu=cortex-m4 -o - | FileCheck %s
; RUN: llc -mtriple=thumbv8m-none-eabi %s -mcpu=cortex-m33 -o - | FileCheck %s
define void @test_loop_alignment(i32* %in, i32* %out) optsize {
; CHECK-LABEL: test_loop_alignment:
; CHECK: mov{{.*}}, #0
; CHECK: .p2align 2
entry:
br label %loop
loop:
%i = phi i32 [ 0, %entry ], [ %i.next, %loop ]
%in.addr = getelementptr inbounds i32, i32* %in, i32 %i
%lhs = load i32, i32* %in.addr, align 4
%res = mul nsw i32 %lhs, 5
%out.addr = getelementptr inbounds i32, i32* %out, i32 %i
store i32 %res, i32* %out.addr, align 4
%i.next = add i32 %i, 1
%done = icmp eq i32 %i.next, 1024
br i1 %done, label %end, label %loop
end:
ret void
}
define void @test_loop_alignment_minsize(i32* %in, i32* %out) minsize {
; CHECK-LABEL: test_loop_alignment_minsize:
; CHECK: movs {{r[0-9]+}}, #0
; CHECK-NOT: .p2align
entry:
br label %loop
loop:
%i = phi i32 [ 0, %entry ], [ %i.next, %loop ]
%in.addr = getelementptr inbounds i32, i32* %in, i32 %i
%lhs = load i32, i32* %in.addr, align 4
%res = mul nsw i32 %lhs, 5
%out.addr = getelementptr inbounds i32, i32* %out, i32 %i
store i32 %res, i32* %out.addr, align 4
%i.next = add i32 %i, 1
%done = icmp eq i32 %i.next, 1024
br i1 %done, label %end, label %loop
end:
ret void
}