1e9fa0b12a
This is the diff associated with {D95267}, and we need to mark $x0 as live whether or not $x0 is dead.
The compiler also needs to mark register $x0 as live in for the following case.
```
$x1 = ADDXri $sp, 16, 0
BL @spam, csr_darwin_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit killed $x1, implicit-def $sp, implicit-def $x0
```
This change fixes an issue where the wrong registers were used when -machine-outliner-reruns>0.
As an example:
```
lang=c
typedef struct {
double v1;
double v2;
} D16;
typedef struct {
D16 v1;
D16 v2;
} D32;
typedef long long LL8;
typedef struct {
long long v1;
long long v2;
} LL16;
typedef struct {
LL16 v1;
LL16 v2;
} LL32;
typedef struct {
LL32 v1;
LL32 v2;
} LL64;
LL8 needx0(LL8 v0, LL8 v1);
void bar(LL64 v1, LL32 v2, LL16 v3, LL32 v4, LL8 v5, D16 v6, D16 v7, D16 v8);
LL8 foo(LL8 v0, LL64 v1, LL32 v2, LL16 v3, LL32 v4, LL8 v5, D16 v6, D16 v7, D16 v8)
{
LL8 result = needx0(v0, 0);
bar(v1, v2, v3, v4, v5, v6, v7, v8);
return result + 1;
}
```
As you can see from the `foo` function, we should not modify the value of `x0` until we call `needx0`.
This code is compiled to give the following instruction MIR code.
```
$sp = frame-setup SUBXri $sp, 256, 0
frame-setup STPDi killed $d13, killed $d12, $sp, 16
frame-setup STPDi killed $d11, killed $d10, $sp, 18
frame-setup STPDi killed $d9, killed $d8, $sp, 20
frame-setup STPXi killed $x26, killed $x25, $sp, 22
frame-setup STPXi killed $x24, killed $x23, $sp, 24
frame-setup STPXi killed $x22, killed $x21, $sp, 26
frame-setup STPXi killed $x20, killed $x19, $sp, 28
...
$x1 = MOVZXi 0, 0
BL @needx0, csr_darwin_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit $x1, implicit-def $sp, implicit-def $x0
...
```
Since there are some other instruction sequences that duplicate `foo`, after the first execution of Machine Outliner you will get:
```
$sp = frame-setup SUBXri $sp, 256, 0
frame-setup STPDi killed $d13, killed $d12, $sp, 16
frame-setup STPDi killed $d11, killed $d10, $sp, 18
frame-setup STPDi killed $d9, killed $d8, $sp, 20
$x7 = ORRXrs $xzr, $lr, 0
BL @OUTLINED_FUNCTION_0, implicit-def $lr, implicit $sp, implicit-def $lr, implicit $sp, implicit $xzr, implicit $x7, implicit $x19, implicit $x20, implicit $x21, implicit $x22, implicit $x23, implicit $x24, implicit $x25, implicit $x26
$lr = ORRXrs $xzr, $x7, 0
...
BL @OUTLINED_FUNCTION_1, implicit-def $lr, implicit $sp, implicit-def $lr, implicit-def $sp, implicit-def $x0, implicit-def $x1, implicit $sp
...
```
For the first time we outlined the following sequence:
```
frame-setup STPXi killed $x26, killed $x25, $sp, 22
frame-setup STPXi killed $x24, killed $x23, $sp, 24
frame-setup STPXi killed $x22, killed $x21, $sp, 26
frame-setup STPXi killed $x20, killed $x19, $sp, 28
```
and
```
$x1 = MOVZXi 0, 0
BL @needx0, csr_darwin_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit $x1, implicit-def $sp, implicit-def $x0
```
When we execute the outline again, we will get:
```
$x0 = ORRXrs $xzr, $lr, 0 <---- here
BL @OUTLINED_FUNCTION_2_0, implicit-def $lr, implicit $sp, implicit-def $sp, implicit-def $lr, implicit $sp, implicit $xzr, implicit $d8, implicit $d9, implicit $d10, implicit $d11, implicit $d12, implicit $d13, implicit $x0
$lr = ORRXrs $xzr, $x0, 0
$x7 = ORRXrs $xzr, $lr, 0
BL @OUTLINED_FUNCTION_0, implicit-def $lr, implicit $sp, implicit-def $lr, implicit $sp, implicit $xzr, implicit $x7, implicit $x19, implicit $x20, implicit $x21, implicit $x22, implicit $x23, implicit $x24, implicit $x25, implicit $x26
$lr = ORRXrs $xzr, $x7, 0
...
BL @OUTLINED_FUNCTION_1, implicit-def $lr, implicit $sp, implicit-def $lr, implicit-def $sp, implicit-def $x0, implicit-def $x1, implicit $sp
```
When calling `OUTLINED_FUNCTION_2_0`, we used `x0` to save the `lr` register.
The reason for the above error appears to be that:
```
BL @OUTLINED_FUNCTION_1, implicit-def $lr, implicit $sp, implicit-def $lr, implicit-def $sp, implicit-def $x0, implicit-def $x1, implicit $sp
```
should be:
```
BL @OUTLINED_FUNCTION_1, implicit-def $lr, implicit $sp, implicit-def $lr, implicit-def $sp, implicit-def $x0, implicit-def $x1, implicit $sp, implicit $x0
```
When processing the same instruction with both `implicit-def $x0` and `implicit $x0` we should keep `implicit $x0`.
A reproducible demo is available at: [https://github.com/DianQK/reproduce_outlined_function_use_live_x0](https://github.com/DianQK/reproduce_outlined_function_use_live_x0).
Reviewed By: jinlin
Differential Revision: https://reviews.llvm.org/D112911
33 lines
1.1 KiB
YAML
33 lines
1.1 KiB
YAML
# RUN: llc -mtriple=aarch64 -run-pass=machine-outliner -verify-machineinstrs %s -o - | FileCheck %s
|
|
|
|
# The test checks whether the compiler updates the side effect of function @OUTLINED_FUNCTION_0 by adding the use of register x20.
|
|
|
|
--- |
|
|
declare void @spam() local_unnamed_addr
|
|
define void @baz() optsize minsize noredzone { ret void }
|
|
...
|
|
---
|
|
name: baz
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $x0, $x20
|
|
|
|
$x0 = COPY renamable $x20
|
|
BL @spam, csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit-def $sp, implicit-def $x0
|
|
renamable $x21 = COPY $x0
|
|
|
|
$x0 = COPY renamable $x20
|
|
BL @spam, csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit-def $sp, implicit-def $x0
|
|
renamable $x22 = COPY $x0
|
|
|
|
$x0 = COPY killed renamable $x20
|
|
BL @spam, csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit-def $sp, implicit-def $x0
|
|
renamable $x3 = COPY $x0
|
|
|
|
RET_ReallyLR
|
|
|
|
...
|
|
|
|
# CHECK: BL @OUTLINED_FUNCTION_0, {{.*}}, implicit $x20{{.*}}
|