mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-24 03:33:20 +01:00
509d3200f9
Summary: This patch adds an analysis pass to collect loop nests and summarize properties of the nest (e.g the nest depth, whether the nest is perfect, what's the innermost loop, etc...). The motivation for this patch was discussed at the latest meeting of the LLVM loop group (https://ibm.box.com/v/llvm-loop-nest-analysis) where we discussed the unimodular loop transformation framework ( “A Loop Transformation Theory and an Algorithm to Maximize Parallelism”, Michael E. Wolf and Monica S. Lam, IEEE TPDS, October 1991). The unimodular framework provides a convenient way to unify legality checking and code generation for several loop nest transformations (e.g. loop reversal, loop interchange, loop skewing) and their compositions. Given that the unimodular framework is applicable to perfect loop nests this is one property of interest we expose in this analysis. Several other utility functions are also provided. In the future other properties of interest can be added in a centralized place. Authored By: etiotto Reviewer: Meinersbur, bmahjour, kbarton, Whitney, dmgreen, fhahn, reames, hfinkel, jdoerfert, ppc-slack Reviewed By: Meinersbur Subscribers: bryanpkc, ppc-slack, mgorny, hiraditya, llvm-commits Tag: LLVM Differential Revision: https://reviews.llvm.org/D68789
36 lines
1.2 KiB
LLVM
36 lines
1.2 KiB
LLVM
; RUN: opt < %s -passes='print<loopnest>' -disable-output 2>&1 | FileCheck %s
|
|
|
|
; Test that the loop nest analysis is able to analyze an infinite loop in a loop nest.
|
|
define void @test1(i32** %A, i1 %cond) {
|
|
; CHECK-LABEL: IsPerfect=true, Depth=1, OutermostLoop: for.inner, Loops: ( for.inner )
|
|
; CHECK-LABEL: IsPerfect=false, Depth=2, OutermostLoop: for.outer, Loops: ( for.outer for.inner )
|
|
; CHECK-LABEL: IsPerfect=true, Depth=1, OutermostLoop: for.infinite, Loops: ( for.infinite )
|
|
entry:
|
|
br label %for.outer
|
|
|
|
for.outer:
|
|
%i = phi i64 [ 0, %entry ], [ %inc_i, %for.outer.latch ]
|
|
br i1 %cond, label %for.inner, label %for.infinite
|
|
|
|
for.inner:
|
|
%j = phi i64 [ 0, %for.outer ], [ %inc_j, %for.inner ]
|
|
%arrayidx_i = getelementptr inbounds i32*, i32** %A, i64 %i
|
|
%0 = load i32*, i32** %arrayidx_i, align 8
|
|
%arrayidx_j = getelementptr inbounds i32, i32* %0, i64 %j
|
|
store i32 0, i32* %arrayidx_j, align 4
|
|
%inc_j = add nsw i64 %j, 1
|
|
%cmp_j = icmp slt i64 %inc_j, 100
|
|
br i1 %cmp_j, label %for.inner, label %for.outer.latch
|
|
|
|
for.infinite:
|
|
br label %for.infinite
|
|
|
|
for.outer.latch:
|
|
%inc_i = add nsw i64 %i, 1
|
|
%cmp_i = icmp slt i64 %inc_i, 100
|
|
br i1 %cmp_i, label %for.outer, label %for.end
|
|
|
|
for.end:
|
|
ret void
|
|
}
|