cortex-a57-misched-vldm-wrback.ll
1.37 KB
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
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
; 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
;
@a = global double 0.0, align 4
@b = global double 0.0, align 4
@c = global double 0.0, align 4
; CHECK: ********** MI Scheduling **********
; We need second, post-ra scheduling to have VLDM instruction combined from single-loads
; CHECK: ********** MI Scheduling **********
; CHECK: VLDMDIA_UPD
; CHECK: rdefs left
; CHECK-NEXT: Latency : 6
; CHECK: Successors:
; CHECK: Data
; CHECK-SAME: Latency=1
; CHECK-NEXT: Data
; CHECK-SAME: Latency=1
; CHECK-NEXT: Data
; CHECK-SAME: Latency=5
; CHECK-NEXT: Data
; CHECK-SAME: Latency=0
; CHECK-NEXT: Data
; CHECK-SAME: Latency=0
define i32 @bar(i32* %iptr) minsize optsize {
%1 = load double, double* @a, align 8
%2 = load double, double* @b, align 8
%3 = load double, double* @c, align 8
%ptr_after = getelementptr double, double* @a, i32 3
%ptr_new_ival = ptrtoint double* %ptr_after to i32
%ptr_new = inttoptr i32 %ptr_new_ival to i32*
store i32 %ptr_new_ival, i32* %iptr, align 8
%v1 = fptoui double %1 to i32
%mul1 = mul i32 %ptr_new_ival, %v1
%v2 = fptoui double %2 to i32
%v3 = fptoui double %3 to i32
%mul2 = mul i32 %mul1, %v2
%mul3 = mul i32 %mul2, %v3
ret i32 %mul3
}