llvm-6502/test/CodeGen/Thumb/stm-merge.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

42 lines
1.6 KiB
LLVM

; RUN: llc -mtriple=thumbv6m-eabi -verify-machineinstrs %s -o - | FileCheck %s
target datalayout = "e-m:e-p:32:32-i1:8:32-i8:8:32-i16:16:32-i64:64-v128:64:128-a:0:32-n32-S64"
target triple = "thumbv6m--linux-gnueabi"
@d = internal unnamed_addr global i32 0, align 4
@c = internal global i32* null, align 4
@e = internal unnamed_addr global i32* null, align 4
; Function Attrs: nounwind optsize
define void @fn1(i32 %x, i32 %y, i32 %z) #0 {
entry:
; CHECK-LABEL: fn1:
; CHECK: stm r[[BASE:[0-9]]]!, {{.*}}
; CHECK-NOT: {{.*}} r[[BASE]]
%g = alloca i32, align 4
%h = alloca i32, align 4
%i = alloca i32, align 4
store i32 %x, i32* %i, align 4
store i32 %y, i32* %h, align 4
store i32 %z, i32* %g, align 4
%.pr = load i32* @d, align 4
%cmp11 = icmp slt i32 %.pr, 1
br i1 %cmp11, label %for.inc.lr.ph, label %for.body5
for.inc.lr.ph: ; preds = %entry
store i32 1, i32* @d, align 4
br label %for.body5
for.body5: ; preds = %entry, %for.inc.lr.ph, %for.body5
%f.010 = phi i32 [ %inc7, %for.body5 ], [ 0, %for.inc.lr.ph ], [ 0, %entry ]
store volatile i32* %g, i32** @c, align 4
%inc7 = add nsw i32 %f.010, 1
%exitcond = icmp eq i32 %inc7, 2
br i1 %exitcond, label %for.end8, label %for.body5
for.end8: ; preds = %for.body5
store i32* %h, i32** @e, align 4
ret void
}
attributes #0 = { nounwind optsize "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }