File: full-unroll-heuristics-dce.ll

package info (click to toggle)
llvm-toolchain-9 1%3A9.0.1-16.1
  • links: PTS, VCS
  • area: main
  • in suites: bullseye
  • size: 882,388 kB
  • sloc: cpp: 4,167,636; ansic: 714,256; asm: 457,610; python: 155,927; objc: 65,094; sh: 42,856; lisp: 26,908; perl: 7,786; pascal: 7,722; makefile: 6,881; ml: 5,581; awk: 3,648; cs: 2,027; xml: 888; javascript: 381; ruby: 156
file content (39 lines) | stat: -rw-r--r-- 1,832 bytes parent folder | download | duplicates (6)
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
; RUN: opt < %s -S -loop-unroll -unroll-max-iteration-count-to-analyze=100 -unroll-threshold=12 -unroll-max-percent-threshold-boost=400 | FileCheck %s
; RUN: opt < %s -S -passes='require<opt-remark-emit>,loop(unroll-full)' -unroll-max-iteration-count-to-analyze=100 -unroll-threshold=12 -unroll-max-percent-threshold-boost=400 | FileCheck %s
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"

@known_constant = internal unnamed_addr constant [10 x i32] [i32 0, i32 0, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0, i32 0], align 16

; If a load becomes a constant after loop unrolling, we sometimes can simplify
; CFG. This test verifies that we handle such cases.
; After one operand in an instruction is constant-folded and the
; instruction is simplified, the other operand might become dead.
; In this test we have::
; for i in 1..10:
;   r += A[i] * B[i]
; A[i] is 0 almost at every iteration, so there is no need in loading B[i] at
; all.


; CHECK-LABEL: @unroll_dce
; CHECK-NOT:   br i1 %exitcond, label %for.end, label %for.body
define i32 @unroll_dce(i32* noalias nocapture readonly %b) {
entry:
  br label %for.body

for.body:                                         ; preds = %for.body, %entry
  %iv.0 = phi i64 [ 0, %entry ], [ %iv.1, %for.body ]
  %r.0 = phi i32 [ 0, %entry ], [ %r.1, %for.body ]
  %arrayidx1 = getelementptr inbounds [10 x i32], [10 x i32]* @known_constant, i64 0, i64 %iv.0
  %x1 = load i32, i32* %arrayidx1, align 4
  %arrayidx2 = getelementptr inbounds i32, i32* %b, i64 %iv.0
  %x2 = load i32, i32* %arrayidx2, align 4
  %mul = mul i32 %x1, %x2
  %r.1 = add i32 %mul, %r.0
  %iv.1 = add nuw nsw i64 %iv.0, 1
  %exitcond = icmp eq i64 %iv.1, 10
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body
  ret i32 %r.1
}