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/Thumb/copy_thumb.ll

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

33 lines
1.4 KiB
LLVM
Raw Normal View History

Lower thumbv4t & thumbv5 lo->lo copies through a push-pop sequence On pre-v6 hardware, 'MOV lo, lo' gives undefined results, so such copies need to be avoided. This patch trades simplicity for implementation time at the expense of performance... As they say: correctness first, then performance. See http://lists.cs.uiuc.edu/pipermail/llvmdev/2014-August/075998.html for a few ideas on how to make this better. llvm-svn: 216138
2014-08-21 07:38:50 +08:00
; RUN: llc -mtriple=armv4-none--eabi < %s | FileCheck %s --check-prefix=CHECK-LOLOMOV
; RUN: llc -mtriple=armv4t-none--eabi < %s | FileCheck %s --check-prefix=CHECK-LOLOMOV
; RUN: llc -mtriple=armv5-none--eabi < %s | FileCheck %s --check-prefix=CHECK-LOLOMOV
; RUN: llc -mtriple=armv6-none--eabi < %s | FileCheck %s --check-prefix=CHECK-LOLOMOV
; RUN: llc -mtriple=armv7-none--eabi < %s | FileCheck %s --check-prefix=CHECK-LOLOMOV
; RUN: llc -mtriple=thumbv6-none--eabi < %s | FileCheck %s --check-prefix=CHECK-LOLOMOV
; RUN: llc -mtriple=thumbv7-none--eabi < %s | FileCheck %s --check-prefix=CHECK-LOLOMOV
; CHECK-LOLOMOV-LABEL: foo
; CHECK-LOLOMOV: mov [[TMP:r[0-7]]], [[SRC1:r[01]]]
; CHECK-LOLOMOV-NEXT: mov [[SRC1]], [[SRC2:r[01]]]
; CHECK-LOLOMOV-NEXT: mov [[SRC2]], [[TMP]]
; CHECK-LOLOMOV-LABEL: bar
; CHECK-LOLOMOV-LABEL: fnend
;
; 'MOV lo, lo' in Thumb mode produces undefined results on pre-v6 hardware
; RUN: llc -mtriple=thumbv4t-none--eabi < %s | FileCheck %s --check-prefix=CHECK-NOLOLOMOV
; RUN: llc -mtriple=thumbv5-none--eabi < %s | FileCheck %s --check-prefix=CHECK-NOLOLOMOV
; CHECK-NOLOLOMOV-LABEL: foo
In Thumb1, materialize a move between low registers as a `movs`, if CPSR isn't live. Summary: Previously, it had always been materialized as a push/pop sequence. Reviewers: labrinea, jroelofs Reviewed By: jroelofs Subscribers: llvm-commits, rengolin Differential Revision: https://reviews.llvm.org/D30648 llvm-svn: 297134
2017-03-07 17:38:16 +08:00
; CHECK-NOLOLOMOV: movs [[TMP:r[0-7]]], [[SRC1:r[01]]]
; CHECK-NOLOLOMOV-NEXT: movs [[SRC1]], [[SRC2:r[01]]]
; CHECK-NOLOLOMOV-NEXT: movs [[SRC2]], [[TMP]]
Lower thumbv4t & thumbv5 lo->lo copies through a push-pop sequence On pre-v6 hardware, 'MOV lo, lo' gives undefined results, so such copies need to be avoided. This patch trades simplicity for implementation time at the expense of performance... As they say: correctness first, then performance. See http://lists.cs.uiuc.edu/pipermail/llvmdev/2014-August/075998.html for a few ideas on how to make this better. llvm-svn: 216138
2014-08-21 07:38:50 +08:00
; CHECK-NOLOLOMOV-LABEL: bar
; CHECK-NOLOLOMOV-LABEL: fnend
declare void @bar(i32, i32)
define void @foo(i32 %a, i32 %b) {
entry:
call void @bar(i32 %b, i32 %a);
ret void
}