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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -passes=loop-unroll -S %s | FileCheck %s
target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"
target triple = "arm64-apple-ios5.0.0"
; The loop in the function only contains a few instructions, but they will get
; lowered to a very large amount of target instructions.
define void @loop_with_large_vector_ops(i32 %i, ptr %A, ptr %B) {
; CHECK-LABEL: @loop_with_large_vector_ops(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[IV:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT: [[A_GEP:%.*]] = getelementptr <225 x double>, ptr [[A:%.*]], i32 [[IV]]
; CHECK-NEXT: [[LV_1:%.*]] = load <225 x double>, ptr [[A_GEP]], align 8
; CHECK-NEXT: [[B_GEP:%.*]] = getelementptr <225 x double>, ptr [[A]], i32 [[IV]]
; CHECK-NEXT: [[LV_2:%.*]] = load <225 x double>, ptr [[B_GEP]], align 8
; CHECK-NEXT: [[MUL:%.*]] = fmul <225 x double> [[LV_1]], [[LV_2]]
; CHECK-NEXT: store <225 x double> [[MUL]], ptr [[B_GEP]], align 8
; CHECK-NEXT: [[IV_NEXT]] = add nuw i32 [[IV]], 1
; CHECK-NEXT: [[CMP:%.*]] = icmp ult i32 [[IV_NEXT]], 10
; CHECK-NEXT: br i1 [[CMP]], label [[LOOP]], label [[EXIT:%.*]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br label %loop
loop:
%iv = phi i32 [ 0, %entry ], [ %iv.next, %loop ]
%A.gep = getelementptr <225 x double>, ptr %A, i32 %iv
%lv.1 = load <225 x double>, ptr %A.gep, align 8
%B.gep = getelementptr <225 x double>, ptr %A, i32 %iv
%lv.2 = load <225 x double>, ptr %B.gep, align 8
%mul = fmul <225 x double> %lv.1, %lv.2
store <225 x double> %mul, ptr %B.gep, align 8
%iv.next = add nuw i32 %iv, 1
%cmp = icmp ult i32 %iv.next, 10
br i1 %cmp, label %loop, label %exit
exit:
ret void
}
|
