llvm-6502/test/CodeGen/ARM/2015-01-21-thumbv4t-ldstr-opt.ll
Renato Golin b451f4e376 Improve handling of stack accesses in Thumb-1
Thumb-1 only allows SP-based LDR and STR to be word-sized, and SP-base LDR,
STR, and ADD only allow offsets that are a multiple of 4. Make some changes
to better make use of these instructions:

* Use word loads for anyext byte and halfword loads from the stack.
* Enforce 4-byte alignment on objects accessed in this way, to ensure that
  the offset is valid.
* Do the same for objects whose frame index is used, in order to avoid having
  to use more than one ADD to generate the frame index.
* Correct how many bits of offset we think AddrModeT1_s has.

Patch by John Brawn.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@230496 91177308-0d34-0410-b5e6-96231b3b80d8
2015-02-25 14:41:06 +00:00

49 lines
1.4 KiB
LLVM

; RUN: llc -mtriple=thumbv4t-none--eabi < %s | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-V4T
; RUN: llc -mtriple=thumbv6m-none--eabi < %s | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-V6M
; CHECK-LABEL: test1
define i32 @test1(i32* %p) {
; Offsets less than 8 can be generated in a single add
; CHECK: adds [[NEWBASE:r[0-9]]], r0, #4
%1 = getelementptr inbounds i32* %p, i32 1
%2 = getelementptr inbounds i32* %p, i32 2
%3 = getelementptr inbounds i32* %p, i32 3
%4 = getelementptr inbounds i32* %p, i32 4
; CHECK-NEXT: ldm [[NEWBASE]],
%5 = load i32* %1, align 4
%6 = load i32* %2, align 4
%7 = load i32* %3, align 4
%8 = load i32* %4, align 4
%9 = add nsw i32 %5, %6
%10 = add nsw i32 %9, %7
%11 = add nsw i32 %10, %8
ret i32 %11
}
; CHECK-LABEL: test2
define i32 @test2(i32* %p) {
; Offsets >=8 require a mov and an add
; CHECK-V4T: movs [[NEWBASE:r[0-9]]], r0
; CHECK-V6M: mov [[NEWBASE:r[0-9]]], r0
; CHECK-NEXT: adds [[NEWBASE]], #8
%1 = getelementptr inbounds i32* %p, i32 2
%2 = getelementptr inbounds i32* %p, i32 3
%3 = getelementptr inbounds i32* %p, i32 4
%4 = getelementptr inbounds i32* %p, i32 5
; CHECK-NEXT: ldm [[NEWBASE]],
%5 = load i32* %1, align 4
%6 = load i32* %2, align 4
%7 = load i32* %3, align 4
%8 = load i32* %4, align 4
%9 = add nsw i32 %5, %6
%10 = add nsw i32 %9, %7
%11 = add nsw i32 %10, %8
ret i32 %11
}