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/ARM/loop-align-cortex-m.ll

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

50 lines
1.4 KiB
LLVM
Raw Normal View History

ARM: align loops to 4 bytes on Cortex-M3 and Cortex-M4. The Technical Reference Manuals for these two CPUs state that branching to an unaligned 32-bit instruction incurs an extra pipeline reload penalty. That's bad. This also enables the optimization at -Os since it costs on average one byte per loop in return for 1 cycle per iteration, which is pretty good going. llvm-svn: 342127
2018-09-13 18:28:05 +08:00
; 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
[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 21:32:54 +08:00
; RUN: llc -mtriple=thumbv8m-none-eabi %s -mcpu=cortex-m33 -o - | FileCheck %s
ARM: align loops to 4 bytes on Cortex-M3 and Cortex-M4. The Technical Reference Manuals for these two CPUs state that branching to an unaligned 32-bit instruction incurs an extra pipeline reload penalty. That's bad. This also enables the optimization at -Os since it costs on average one byte per loop in return for 1 cycle per iteration, which is pretty good going. llvm-svn: 342127
2018-09-13 18:28:05 +08:00
define void @test_loop_alignment(i32* %in, i32* %out) optsize {
; CHECK-LABEL: test_loop_alignment:
[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 21:32:54 +08:00
; CHECK: mov{{.*}}, #0
ARM: align loops to 4 bytes on Cortex-M3 and Cortex-M4. The Technical Reference Manuals for these two CPUs state that branching to an unaligned 32-bit instruction incurs an extra pipeline reload penalty. That's bad. This also enables the optimization at -Os since it costs on average one byte per loop in return for 1 cycle per iteration, which is pretty good going. llvm-svn: 342127
2018-09-13 18:28:05 +08:00
; 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
}