File: cortex-a57-misched-ldm.ll

package info (click to toggle)
llvm-toolchain-11 1%3A11.0.1-2~deb10u1
  • links: PTS, VCS
  • area: main
  • in suites: buster
  • size: 995,836 kB
  • sloc: cpp: 4,767,656; ansic: 760,916; asm: 477,436; python: 170,940; objc: 69,804; lisp: 29,914; sh: 23,855; f90: 18,173; pascal: 7,551; perl: 7,471; ml: 5,603; awk: 3,489; makefile: 2,573; xml: 915; cs: 573; fortran: 503; javascript: 452
file content (28 lines) | stat: -rw-r--r-- 879 bytes parent folder | download | duplicates (9) 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
 
; REQUIRES: asserts
; RUN: llc < %s -mtriple=armv8r-eabi -mcpu=cortex-a57 -mattr=use-misched -verify-misched -debug-only=machine-scheduler -o - 2>&1 > /dev/null | FileCheck %s

; CHECK:       ********** MI Scheduling **********
; We need second, post-ra scheduling to have LDM instruction combined from single-loads
; CHECK:       ********** MI Scheduling **********
; CHECK:       LDMIA
; CHECK:       rdefs left
; CHECK-NEXT:  Latency            : 3
; CHECK:       Successors:
; CHECK:       Data
; CHECK-SAME:  Latency=3
; CHECK-NEXT:  Data
; CHECK-SAME:  Latency=0

define i32 @foo(i32* %a) nounwind optsize {
entry:
  %b = getelementptr i32, i32* %a, i32 1
  %c = getelementptr i32, i32* %a, i32 2 
  %0 = load i32, i32* %a, align 4
  %1 = load i32, i32* %b, align 4
  %2 = load i32, i32* %c, align 4

  %mul1 = mul i32 %0, %1
  %mul2 = mul i32 %mul1, %2
  ret i32 %mul2
}