mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-12-07 11:38:04 +00:00
ed44540ada
Enable the fusion of arithmetic and logic instructions for Exynos M4. llvm-svn: 351149
113 lines
4.1 KiB
YAML
113 lines
4.1 KiB
YAML
# RUN: llc -o /dev/null 2>&1 %s -mtriple aarch64-unknown -mattr=fuse-arith-logic -run-pass=machine-scheduler -misched-print-dags | FileCheck %s
|
|
# RUN: llc -o /dev/null 2>&1 %s -mtriple aarch64-unknown -mcpu=exynos-m4 -run-pass=machine-scheduler -misched-print-dags | FileCheck %s
|
|
# REQUIRES: asserts
|
|
|
|
---
|
|
name: arith
|
|
body: |
|
|
bb.0.entry:
|
|
%0:gpr32 = SUBWrr undef $w0, undef $w1
|
|
%1:gpr32 = ADDWrr undef $w1, undef $w2
|
|
%2:gpr32 = SUBWrs %0, undef $w2, 0
|
|
%3:gpr32 = ADDWrs %1, undef $w3, 0
|
|
|
|
; CHECK: SU(0): %0:gpr32 = SUBWrr undef $w0, undef $w1
|
|
; CHECK: Successors:
|
|
; CHECK: SU(2): Ord Latency=0 Cluster
|
|
; CHECK: SU(1): %1:gpr32 = ADDWrr undef $w1, undef $w2
|
|
; CHECK: Successors:
|
|
; CHECK: SU(3): Ord Latency=0 Cluster
|
|
; CHECK: SU(2): dead %2:gpr32 = SUBWrs %0:gpr32, undef $w2, 0
|
|
; CHECK: Predecessors:
|
|
; CHECK: SU(0): Ord Latency=0 Cluster
|
|
; CHECK: SU(3): dead %3:gpr32 = ADDWrs %1:gpr32, undef $w3, 0
|
|
; CHECK: Predecessors:
|
|
; CHECK: SU(1): Ord Latency=0 Cluster
|
|
...
|
|
---
|
|
name: compare
|
|
body: |
|
|
bb.0.entry:
|
|
%0:gpr64 = ADDXrr undef $x0, undef $x1
|
|
%1:gpr64 = SUBXrs undef $x1, undef $x2, 0
|
|
%2:gpr64 = ADDSXrr %0, undef $x3, implicit-def $nzcv
|
|
%3:gpr64 = SUBSXrs %1, undef $x4, 0, implicit-def $nzcv
|
|
|
|
; CHECK: SU(0): %0:gpr64 = ADDXrr undef $x0, undef $x1
|
|
; CHECK: Successors:
|
|
; CHECK: SU(2): Ord Latency=0 Cluster
|
|
; CHECK: SU(1): %1:gpr64 = SUBXrs undef $x1, undef $x2, 0
|
|
; CHECK: Successors:
|
|
; CHECK: SU(3): Ord Latency=0 Cluster
|
|
; CHECK: SU(2): dead %2:gpr64 = ADDSXrr %0:gpr64, undef $x3, implicit-def $nzcv
|
|
; CHECK: Predecessors:
|
|
; CHECK: SU(0): Ord Latency=0 Cluster
|
|
; CHECK: SU(3): dead %3:gpr64 = SUBSXrs %1:gpr64, undef $x4, 0, implicit-def $nzcv
|
|
; CHECK: Predecessors:
|
|
; CHECK: SU(1): Ord Latency=0 Cluster
|
|
...
|
|
---
|
|
name: logic
|
|
body: |
|
|
bb.0.entry:
|
|
%0:gpr32 = ADDWrr undef $w0, undef $w1
|
|
%1:gpr64 = SUBXrs undef $x1, undef $x2, 0
|
|
%3:gpr32 = ANDWrs %0, undef $w3, 0
|
|
%4:gpr64 = ORRXrr %1, undef $x4
|
|
|
|
; CHECK: SU(0): %0:gpr32 = ADDWrr undef $w0, undef $w1
|
|
; CHECK: Successors:
|
|
; CHECK: SU(2): Ord Latency=0 Cluster
|
|
; CHECK: SU(1): %1:gpr64 = SUBXrs undef $x1, undef $x2, 0
|
|
; CHECK: Successors:
|
|
; CHECK: SU(3): Ord Latency=0 Cluster
|
|
; CHECK: SU(2): dead %2:gpr32 = ANDWrs %0:gpr32, undef $w3, 0
|
|
; CHECK: Predecessors:
|
|
; CHECK: SU(0): Ord Latency=0 Cluster
|
|
; CHECK: SU(3): dead %3:gpr64 = ORRXrr %1:gpr64, undef $x4
|
|
; CHECK: Predecessors:
|
|
; CHECK: SU(1): Ord Latency=0 Cluster
|
|
...
|
|
---
|
|
name: nope
|
|
body: |
|
|
bb.0.entry:
|
|
; Shifted register.
|
|
%0:gpr32 = SUBWrr undef $w0, undef $w1
|
|
%1:gpr32 = SUBWrs %0, undef $w2, 1
|
|
; CHECK: SU(0): %0:gpr32 = SUBWrr undef $w0, undef $w1
|
|
; CHECK: Successors:
|
|
; CHECK-NOT: SU(1): Ord Latency=0 Cluster
|
|
; CHECK: SU(1): dead %1:gpr32 = SUBWrs %0:gpr32, undef $w2, 1
|
|
|
|
; Multiple successors.
|
|
%2:gpr64 = ADDXrr undef $x0, undef $x1
|
|
%3:gpr32 = EXTRACT_SUBREG %2, %subreg.sub_32
|
|
%4:gpr32 = ANDWrs %3, undef $w2, 0
|
|
%5:gpr64 = ADDSXrr %2, undef $x3, implicit-def $nzcv
|
|
; CHECK: SU(2): %2:gpr64 = ADDXrr undef $x0, undef $x1
|
|
; CHECK: Successors:
|
|
; CHECK-NOT: SU(3): Ord Latency=0 Cluster
|
|
; CHECK: SU(5): Ord Latency=0 Cluster
|
|
; CHECK: SU(3): %3:gpr32 = EXTRACT_SUBREG %2:gpr64, %subreg.sub_32
|
|
; CHECK: SU(5): dead %5:gpr64 = ADDSXrr %2:gpr64, undef $x3, implicit-def $nzcv
|
|
|
|
; Different register sizes.
|
|
%6:gpr32 = SUBWrr undef $w0, undef $w1
|
|
%7:gpr64 = ADDXrr undef $x1, undef $x2
|
|
%8:gpr64 = SUBXrr %7, undef $x3
|
|
%9:gpr32 = ADDWrr %6, undef $w4
|
|
; CHECK: SU(6): %6:gpr32 = SUBWrr undef $w0, undef $w1
|
|
; CHECK: Successors:
|
|
; CHECK-NOT: SU(8): Ord Latency=0 Cluster
|
|
; CHECK: SU(7): %7:gpr64 = ADDXrr undef $x1, undef $x2
|
|
; CHECK: Successors:
|
|
; CHECK-NOT: SU(9): Ord Latency=0 Cluster
|
|
; CHECK: SU(8): dead %8:gpr64 = SUBXrr %7:gpr64, undef $x3
|
|
; CHECK: Predecessors:
|
|
; CHECK: SU(7): Ord Latency=0 Cluster
|
|
; CHECK: SU(9): dead %9:gpr32 = ADDWrr %6:gpr32, undef $w4
|
|
; CHECK: Predecessors:
|
|
; CHECK: SU(6): Ord Latency=0 Cluster
|
|
...
|