replica
/
hanchenye-llvm-project
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
hanchenye-llvm-project/polly/test/DependenceInfo/reduction_privatization_dep...

85 lines
3.0 KiB
LLVM
Raw Normal View History

tests: Drop -polly-detect-unprofitable and -polly-no-early-exit These flags are now always passed to all tests and need to be disabled if not needed. Disabling these flags, rather than passing them to almost all tests, significantly simplfies our RUN: lines. llvm-svn: 249422
2015-10-06 23:36:44 +08:00
; RUN: opt %loadPolly -polly-dependences -analyze < %s | FileCheck %s
Model statement wise reduction dependences + Collect reduction dependences + Introduced TYPE_RED in Dependences.h which can be used to obtain the reduction dependences + Used TYPE_RED to prevent parallelization while we do not have a privatizing code generation + Relax the dependences for non-parallel code generation + Add privatization dependences to ensure correctness + 12 Test cases to check for reduction and privatization dependences llvm-svn: 211369
2014-06-21 00:37:11 +08:00
;
; We have privatization dependences from a textually later statement to a
; textually earlier one, but the dependences still go forward in time.
;
Prepare unit tests for update to ISL 0.16 ISL 0.16 will change how sets are printed which breaks 117 unit tests that text-compare printed sets. This patch re-formats most of these unit tests using a script and small manual editing on top of that. When actually updating ISL, most work is done by just re-running the script to adapt to the changed output. Some tests that compare IR and tests with single CHECK-lines that can be easily updated manually are not included here. The re-format script will also be committed afterwards. The per-test formatter invocation command lines options will not be added in the near future because it is ad hoc and would overwrite the manual edits. Ideally it also shouldn't be required anymore because ISL's set printing has become more stable in 0.16. Differential Revision: http://reviews.llvm.org/D16095 llvm-svn: 257851
2016-01-15 08:48:42 +08:00
; CHECK: RAW dependences:
Update to ISL 0.16.1 llvm-svn: 257898
2016-01-15 23:54:45 +08:00
; CHECK-NEXT: { Stmt_S3[i0] -> Stmt_S2[1 + i0, o1] : 0 <= i0 <= 97 and 0 <= o1 <= 99; Stmt_S1[i0] -> Stmt_S3[i0] : 0 <= i0 <= 98 }
Prepare unit tests for update to ISL 0.16 ISL 0.16 will change how sets are printed which breaks 117 unit tests that text-compare printed sets. This patch re-formats most of these unit tests using a script and small manual editing on top of that. When actually updating ISL, most work is done by just re-running the script to adapt to the changed output. Some tests that compare IR and tests with single CHECK-lines that can be easily updated manually are not included here. The re-format script will also be committed afterwards. The per-test formatter invocation command lines options will not be added in the near future because it is ad hoc and would overwrite the manual edits. Ideally it also shouldn't be required anymore because ISL's set printing has become more stable in 0.16. Differential Revision: http://reviews.llvm.org/D16095 llvm-svn: 257851
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_S3[i0] -> Stmt_S2[1 + i0, o1] : 0 <= i0 <= 97 and 0 <= o1 <= 99; Stmt_S1[i0] -> Stmt_S3[i0] : 0 <= i0 <= 98 }
Prepare unit tests for update to ISL 0.16 ISL 0.16 will change how sets are printed which breaks 117 unit tests that text-compare printed sets. This patch re-formats most of these unit tests using a script and small manual editing on top of that. When actually updating ISL, most work is done by just re-running the script to adapt to the changed output. Some tests that compare IR and tests with single CHECK-lines that can be easily updated manually are not included here. The re-format script will also be committed afterwards. The per-test formatter invocation command lines options will not be added in the near future because it is ad hoc and would overwrite the manual edits. Ideally it also shouldn't be required anymore because ISL's set printing has become more stable in 0.16. Differential Revision: http://reviews.llvm.org/D16095 llvm-svn: 257851
2016-01-15 08:48:42 +08:00
; CHECK-NEXT: WAW dependences:
Update to ISL 0.16.1 llvm-svn: 257898
2016-01-15 23:54:45 +08:00
; CHECK-NEXT: { Stmt_S3[i0] -> Stmt_S2[1 + i0, o1] : 0 <= i0 <= 97 and 0 <= o1 <= 99; Stmt_S1[i0] -> Stmt_S3[i0] : 0 <= i0 <= 98 }
Prepare unit tests for update to ISL 0.16 ISL 0.16 will change how sets are printed which breaks 117 unit tests that text-compare printed sets. This patch re-formats most of these unit tests using a script and small manual editing on top of that. When actually updating ISL, most work is done by just re-running the script to adapt to the changed output. Some tests that compare IR and tests with single CHECK-lines that can be easily updated manually are not included here. The re-format script will also be committed afterwards. The per-test formatter invocation command lines options will not be added in the near future because it is ad hoc and would overwrite the manual edits. Ideally it also shouldn't be required anymore because ISL's set printing has become more stable in 0.16. Differential Revision: http://reviews.llvm.org/D16095 llvm-svn: 257851
2016-01-15 08:48:42 +08:00
; CHECK-NEXT: Reduction dependences:
Update to ISL 0.16.1 llvm-svn: 257898
2016-01-15 23:54:45 +08:00
; CHECK-NEXT: { Stmt_S2[i0, i1] -> Stmt_S2[i0, 1 + i1] : 0 <= i0 <= 98 and 0 <= i1 <= 98 }
Model statement wise reduction dependences + Collect reduction dependences + Introduced TYPE_RED in Dependences.h which can be used to obtain the reduction dependences + Used TYPE_RED to prevent parallelization while we do not have a privatizing code generation + Relax the dependences for non-parallel code generation + Add privatization dependences to ensure correctness + 12 Test cases to check for reduction and privatization dependences llvm-svn: 211369
2014-06-21 00:37:11 +08:00
;
; void f(int *sum) {
; int i, j;
; for (i = 0; i < 99; i++) {
; S1: sum[i + 1] += 42;
; for (j = 0; j < 100; j++)
; S2: sum[i] += i * j;
; S3: sum[i + 1] += 7;
; }
; }
;
target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-n32-S64"
define void @f(i32* %sum) {
entry:
br label %for.cond
for.cond: ; preds = %for.inc10, %entry
%i.0 = phi i32 [ 0, %entry ], [ %inc11, %for.inc10 ]
%exitcond1 = icmp ne i32 %i.0, 99
br i1 %exitcond1, label %for.body, label %for.end12
for.body: ; preds = %for.cond
br label %S1
S1: ; preds = %for.body
%add = add nsw i32 %i.0, 1
Update Polly tests to handle explicitly typed gep changes in LLVM llvm-svn: 230784
2015-02-28 03:20:19 +08:00
%arrayidx = getelementptr inbounds i32, i32* %sum, i32 %add
Update Polly tests to handle explicitly typed load changes in LLVM. llvm-svn: 230796
2015-02-28 05:22:50 +08:00
%tmp = load i32, i32* %arrayidx, align 4
Model statement wise reduction dependences + Collect reduction dependences + Introduced TYPE_RED in Dependences.h which can be used to obtain the reduction dependences + Used TYPE_RED to prevent parallelization while we do not have a privatizing code generation + Relax the dependences for non-parallel code generation + Add privatization dependences to ensure correctness + 12 Test cases to check for reduction and privatization dependences llvm-svn: 211369
2014-06-21 00:37:11 +08:00
%add1 = add nsw i32 %tmp, 42
store i32 %add1, i32* %arrayidx, align 4
br label %for.cond2
for.cond2: ; preds = %for.inc, %S1
%j.0 = phi i32 [ 0, %S1 ], [ %inc, %for.inc ]
%exitcond = icmp ne i32 %j.0, 100
br i1 %exitcond, label %for.body4, label %for.end
for.body4: ; preds = %for.cond2
br label %S2
S2: ; preds = %for.body4
%mul = mul nsw i32 %i.0, %j.0
Update Polly tests to handle explicitly typed gep changes in LLVM llvm-svn: 230784
2015-02-28 03:20:19 +08:00
%arrayidx5 = getelementptr inbounds i32, i32* %sum, i32 %i.0
Update Polly tests to handle explicitly typed load changes in LLVM. llvm-svn: 230796
2015-02-28 05:22:50 +08:00
%tmp2 = load i32, i32* %arrayidx5, align 4
Model statement wise reduction dependences + Collect reduction dependences + Introduced TYPE_RED in Dependences.h which can be used to obtain the reduction dependences + Used TYPE_RED to prevent parallelization while we do not have a privatizing code generation + Relax the dependences for non-parallel code generation + Add privatization dependences to ensure correctness + 12 Test cases to check for reduction and privatization dependences llvm-svn: 211369
2014-06-21 00:37:11 +08:00
%add6 = add nsw i32 %tmp2, %mul
store i32 %add6, i32* %arrayidx5, align 4
br label %for.inc
for.inc: ; preds = %S2
%inc = add nsw i32 %j.0, 1
br label %for.cond2
for.end: ; preds = %for.cond2
br label %S3
S3: ; preds = %for.end
%add7 = add nsw i32 %i.0, 1
Update Polly tests to handle explicitly typed gep changes in LLVM llvm-svn: 230784
2015-02-28 03:20:19 +08:00
%arrayidx8 = getelementptr inbounds i32, i32* %sum, i32 %add7
Update Polly tests to handle explicitly typed load changes in LLVM. llvm-svn: 230796
2015-02-28 05:22:50 +08:00
%tmp3 = load i32, i32* %arrayidx8, align 4
Model statement wise reduction dependences + Collect reduction dependences + Introduced TYPE_RED in Dependences.h which can be used to obtain the reduction dependences + Used TYPE_RED to prevent parallelization while we do not have a privatizing code generation + Relax the dependences for non-parallel code generation + Add privatization dependences to ensure correctness + 12 Test cases to check for reduction and privatization dependences llvm-svn: 211369
2014-06-21 00:37:11 +08:00
%add9 = add nsw i32 %tmp3, 7
store i32 %add9, i32* %arrayidx8, align 4
br label %for.inc10
for.inc10: ; preds = %S3
%inc11 = add nsw i32 %i.0, 1
br label %for.cond
for.end12: ; preds = %for.cond
ret void
}