2022-03-14 21:39:25 +08:00
|
|
|
; RUN: opt %loadPolly -basic-aa -polly-stmt-granularity=bb -polly-print-dependences -disable-output < %s | FileCheck %s
|
2014-07-15 08:00:35 +08:00
|
|
|
;
|
|
|
|
; This loopnest contains a reduction which imposes the same dependences as the
|
|
|
|
; accesses to the array A. We need to ensure we keep the dependences of A.
|
|
|
|
;
|
2016-01-15 08:48:42 +08:00
|
|
|
; CHECK: RAW dependences:
|
2016-01-15 23:54:45 +08:00
|
|
|
; CHECK-NEXT: { Stmt_for_body[i0] -> Stmt_for_body[1 + i0] : 0 <= i0 <= 1022 }
|
2016-01-15 08:48:42 +08:00
|
|
|
; CHECK-NEXT: WAR dependences:
|
[Polly] [DependenceInfo] change WAR, WAW generation to correct semantics
= Change of WAR, WAW generation: =
- `buildFlow(Sink, MustSource, MaySource, Sink)` treates any flow of the form
`sink <- may source <- must source` as a *may* dependence.
- we used to call:
```lang=cpp, name=old-flow-call.cpp
Flow = buildFlow(MustWrite, MustWrite, Read, Schedule);
WAW = isl_union_flow_get_must_dependence(Flow);
WAR = isl_union_flow_get_may_dependence(Flow);
```
- This caused some WAW dependences to be treated as WAR dependences.
- Incorrect semantics.
- Now, we call WAR and WAW correctly.
== Correct WAW: ==
```lang=cpp, name=new-waw-call.cpp
Flow = buildFlow(Write, MustWrite, MayWrite, Schedule);
WAW = isl_union_flow_get_may_dependence(Flow);
isl_union_flow_free(Flow);
```
== Correct WAR: ==
```lang=cpp, name=new-war-call.cpp
Flow = buildFlow(Write, Read, MustaWrite, Schedule);
WAR = isl_union_flow_get_must_dependence(Flow);
isl_union_flow_free(Flow);
```
- We want the "shortest" WAR possible (exact dependences).
- We mark all the *must-writes* as may-source, reads as must-souce.
- Then, we ask for *must* dependence.
- This removes all the reads that flow through a *must-write*
before reaching a sink.
- Note that we only block ealier writes with *must-writes*. This is
intuitively correct, as we do not want may-writes to block
must-writes.
- Leaves us with direct (R -> W).
- This affects reduction generation since RED is built using WAW and WAR.
= New StrictWAW for Reductions: =
- We used to call:
```lang=cpp,name=old-waw-war-call.cpp
Flow = buildFlow(MustWrite, MustWrite, Read, Schedule);
WAW = isl_union_flow_get_must_dependence(Flow);
WAR = isl_union_flow_get_may_dependence(Flow);
```
- This *is* the right model of WAW we need for reductions, just not in general.
- Reductions need to track only *strict* WAW, without any interfering reductions.
= Explanation: Why the new WAR dependences in tests are correct: =
- We no longer set WAR = WAR - WAW
- Hence, we will have WAR dependences that were originally removed.
- These may look incorrect, but in fact make sense.
== Code: ==
```lang=llvm, name=new-war-dependence.ll
; void manyreductions(long *A) {
; for (long i = 0; i < 1024; i++)
; for (long j = 0; j < 1024; j++)
; S0: *A += 42;
;
; for (long i = 0; i < 1024; i++)
; for (long j = 0; j < 1024; j++)
; S1: *A += 42;
;
```
=== WAR dependence: ===
{ S0[1023, 1023] -> S1[0, 0] }
- Between `S0[1023, 1023]` and `S1[0, 0]`, we will have the dependences:
```lang=cpp, name=dependence-incorrect, counterexample
S0[1023, 1023]:
*-- tmp = *A (load0)--*
WAR 2 add = tmp + 42 |
*-> *A = add (store0) |
WAR 1
S1[0, 0]: |
tmp = *A (load1) |
add = tmp + 42 |
A = add (store1)<-*
```
- One may assume that WAR2 *hides* WAR1 (since store0 happens before
store1). However, within a statement, Polly has no idea about the
ordering of loads and stores.
- Hence, according to Polly, the code may have looked like this:
```lang=cpp, name=dependence-correct
S0[1023, 1023]:
A = add (store0)
tmp = A (load0) ---*
add = A + 42 |
WAR 1
S1[0, 0]: |
tmp = A (load1) |
add = A + 42 |
A = add (store1) <-*
```
- So, Polly generates (correct) WAR dependences. It does not make sense
to remove these dependences, since they are correct with respect to
Polly's model.
Reviewers: grosser, Meinersbur
tags: #polly
Differential revision: https://reviews.llvm.org/D31386
llvm-svn: 299429
2017-04-04 21:08:23 +08:00
|
|
|
; CHECK-NEXT: { Stmt_for_body[i0] -> Stmt_for_body[1 + i0] : 0 <= i0 <= 1022 }
|
2016-01-15 08:48:42 +08:00
|
|
|
; CHECK-NEXT: WAW dependences:
|
2016-01-15 23:54:45 +08:00
|
|
|
; CHECK-NEXT: { Stmt_for_body[i0] -> Stmt_for_body[1 + i0] : 0 <= i0 <= 1022 }
|
2016-01-15 08:48:42 +08:00
|
|
|
; CHECK-NEXT: Reduction dependences:
|
2016-01-15 23:54:45 +08:00
|
|
|
; CHECK-NEXT: { Stmt_for_body[i0] -> Stmt_for_body[1 + i0] : 0 <= i0 <= 1022 }
|
2014-07-15 08:00:35 +08:00
|
|
|
;
|
|
|
|
;
|
|
|
|
; void AandSum(int *restrict sum, int *restrict A) {
|
|
|
|
; for (int i = 0; i < 1024; i++) {
|
|
|
|
; A[i] = A[i] + A[i - 1];
|
|
|
|
; A[i - 1] = A[i] + A[i - 2];
|
|
|
|
; *sum += i;
|
|
|
|
; }
|
|
|
|
; }
|
|
|
|
;
|
|
|
|
target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-n32-S64"
|
|
|
|
|
|
|
|
define void @AandSum(i32* noalias %sum, i32* noalias %A) {
|
|
|
|
entry:
|
|
|
|
br label %for.cond
|
|
|
|
|
|
|
|
for.cond: ; preds = %for.inc, %entry
|
|
|
|
%i.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
|
|
|
|
%exitcond = icmp ne i32 %i.0, 1024
|
|
|
|
br i1 %exitcond, label %for.body, label %for.end
|
|
|
|
|
|
|
|
for.body: ; preds = %for.cond
|
2015-02-28 03:20:19 +08:00
|
|
|
%arrayidx = getelementptr inbounds i32, i32* %A, i32 %i.0
|
2015-02-28 05:22:50 +08:00
|
|
|
%tmp = load i32, i32* %arrayidx, align 4
|
2014-07-15 08:00:35 +08:00
|
|
|
%sub = add nsw i32 %i.0, -1
|
2015-02-28 03:20:19 +08:00
|
|
|
%arrayidx1 = getelementptr inbounds i32, i32* %A, i32 %sub
|
2015-02-28 05:22:50 +08:00
|
|
|
%tmp1 = load i32, i32* %arrayidx1, align 4
|
2014-07-15 08:00:35 +08:00
|
|
|
%add = add nsw i32 %tmp, %tmp1
|
2015-02-28 03:20:19 +08:00
|
|
|
%arrayidx2 = getelementptr inbounds i32, i32* %A, i32 %i.0
|
2014-07-15 08:00:35 +08:00
|
|
|
store i32 %add, i32* %arrayidx2, align 4
|
|
|
|
%sub4 = add nsw i32 %i.0, -2
|
2015-02-28 03:20:19 +08:00
|
|
|
%arrayidx5 = getelementptr inbounds i32, i32* %A, i32 %sub4
|
2015-02-28 05:22:50 +08:00
|
|
|
%tmp2 = load i32, i32* %arrayidx5, align 4
|
2014-07-15 08:00:35 +08:00
|
|
|
%add6 = add nsw i32 %add, %tmp2
|
|
|
|
%sub7 = add nsw i32 %i.0, -1
|
2015-02-28 03:20:19 +08:00
|
|
|
%arrayidx8 = getelementptr inbounds i32, i32* %A, i32 %sub7
|
2014-07-15 08:00:35 +08:00
|
|
|
store i32 %add6, i32* %arrayidx8, align 4
|
2015-02-28 05:22:50 +08:00
|
|
|
%tmp3 = load i32, i32* %sum, align 4
|
2014-07-15 08:00:35 +08:00
|
|
|
%add9 = add nsw i32 %tmp3, %i.0
|
|
|
|
store i32 %add9, i32* %sum, align 4
|
|
|
|
br label %for.inc
|
|
|
|
|
|
|
|
for.inc: ; preds = %for.body
|
|
|
|
%inc = add nsw i32 %i.0, 1
|
|
|
|
br label %for.cond
|
|
|
|
|
|
|
|
for.end: ; preds = %for.cond
|
|
|
|
ret void
|
|
|
|
}
|