llvm-6502/test/CodeGen/ARM/dyn-stackalloc.ll
Hal Finkel 39b09ae788 Revert "r226086 - Revert "r226071 - [RegisterCoalescer] Remove copies to reserved registers""
Reapply r226071 with fixes. Two fixes:

 1. We need to manually remove the old and create the new 'deaf defs'
    associated with physical register definitions when we move the definition of
    the physical register from the copy point to the point of the original vreg def.

    This problem was picked up by the machinstr verifier, and could trigger a
    verification failure on test/CodeGen/X86/2009-02-12-DebugInfoVLA.ll, so I've
    turned on the verifier in the tests.

 2. When moving the def point of the phys reg up, we need to make sure that it
    is neither defined nor read in between the two instructions. We don't, however,
    extend the live ranges of phys reg defs to cover uses, so just checking for
    live-range overlap between the pair interval and the phys reg aliases won't
    pick up reads. As a result, we manually iterate over the range and check for
    reads.

    A test soon to be committed to the PowerPC backend will test this change.

Original commit message:

[RegisterCoalescer] Remove copies to reserved registers

This allows the RegisterCoalescer to join "non-flipped" range pairs with a
physical destination register -- which allows the RegisterCoalescer to remove
copies like this:

<vreg> = something (maybe a load, for example)
... (things that don't use PHYSREG)
PHYSREG = COPY <vreg>

(with all of the restrictions normally applied by the RegisterCoalescer: having
compatible register classes, etc. )

Previously, the RegisterCoalescer handled only the opposite case (copying
*from* a physical register). I don't handle the problem fully here, but try to
get the common case where there is only one use of <vreg> (the COPY).

An upcoming commit to the PowerPC backend will make this pattern much more
common on PPC64/ELF systems.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@226200 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-15 20:32:09 +00:00

69 lines
2.2 KiB
LLVM

; RUN: llc -mcpu=generic -mtriple=arm-eabi -verify-machineinstrs < %s | FileCheck %s
%struct.comment = type { i8**, i32*, i32, i8* }
%struct.info = type { i32, i32, i32, i32, i32, i32, i32, i8* }
%struct.state = type { i32, %struct.info*, float**, i32, i32, i32, i32, i32, i32, i32, i32, i32, i64, i64, i64, i64, i64, i64, i8* }
@str215 = external global [2 x i8]
define void @t1(%struct.state* %v) {
; Make sure we generate:
; sub sp, sp, r1
; instead of:
; sub r1, sp, r1
; mov sp, r1
; CHECK-LABEL: @t1
; CHECK: bic [[REG1:r[0-9]+]],
; CHECK-NOT: sub r{{[0-9]+}}, sp, [[REG1]]
; CHECK: sub sp, sp, [[REG1]]
%tmp6 = load i32* null
%tmp8 = alloca float, i32 %tmp6
store i32 1, i32* null
br i1 false, label %bb123.preheader, label %return
bb123.preheader: ; preds = %0
br i1 false, label %bb43, label %return
bb43: ; preds = %bb123.preheader
call fastcc void @f1(float* %tmp8, float* null, i32 0)
%tmp70 = load i32* null
%tmp85 = getelementptr float* %tmp8, i32 0
call fastcc void @f2(float* null, float* null, float* %tmp85, i32 %tmp70)
ret void
return: ; preds = %bb123.preheader, %0
ret void
}
declare fastcc void @f1(float*, float*, i32)
declare fastcc void @f2(float*, float*, float*, i32)
define void @t2(%struct.comment* %vc, i8* %tag, i8* %contents) {
%tmp1 = call i32 @strlen(i8* %tag)
%tmp3 = call i32 @strlen(i8* %contents)
%tmp4 = add i32 %tmp1, 2
%tmp5 = add i32 %tmp4, %tmp3
%tmp6 = alloca i8, i32 %tmp5
%tmp9 = call i8* @strcpy(i8* %tmp6, i8* %tag)
%tmp6.len = call i32 @strlen(i8* %tmp6)
%tmp6.indexed = getelementptr i8* %tmp6, i32 %tmp6.len
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp6.indexed, i8* getelementptr inbounds ([2 x i8]* @str215, i32 0, i32 0), i32 2, i32 1, i1 false)
%tmp15 = call i8* @strcat(i8* %tmp6, i8* %contents)
call fastcc void @comment_add(%struct.comment* %vc, i8* %tmp6)
ret void
}
declare i32 @strlen(i8*)
declare i8* @strcat(i8*, i8*)
declare fastcc void @comment_add(%struct.comment*, i8*)
declare i8* @strcpy(i8*, i8*)
declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind