maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/polly/test/ScopInfo/multidim_parameter_addrec_p...

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

65 lines
2.2 KiB
LLVM
Raw Normal View History

[polly] Introduce -polly-print-* passes to replace -analyze. The `opt -analyze` option only works with the legacy pass manager and might be removed in the future, as explained in llvm.org/PR53733. This patch introduced -polly-print-* passes that print what the pass would print with the `-analyze` option and replaces all uses of `-analyze` in the regression tests. There are two exceptions: `CodeGen\single_loop_param_less_equal.ll` and `CodeGen\loop_with_condition_nested.ll` use `-analyze on the `-loops` pass which is not part of Polly. Reviewed By: aeubanks Differential Revision: https://reviews.llvm.org/D120782
2022-03-14 21:39:25 +08:00
; RUN: opt %loadPolly -polly-invariant-load-hoisting=true -polly-print-scops -disable-output < %s | FileCheck %s
ScopInfo: Allow simple 'AddRec * Parameter' products in delinearization We also allow such products for cases where 'Parameter' is loaded within the scop, but where we can dynamically verify that the value of 'Parameter' remains unchanged during the execution of the scop. This change relies on Polly's new RequiredILS tracking infrastructure recently contributed by Johannes. llvm-svn: 250019
2015-10-12 16:02:30 +08:00
;
; void foo(float *A, long *p) {
; for (long i = 0; i < 100; i++)
; for (long j = 0; j < 100; j++)
; A[i * (*p) + j] += i + j;
; }
; CHECK: Invariant Accesses: {
; CHECK-NEXT: ReadAccess := [Reduction Type: NONE] [Scalar: 0]
[FIX] Restructure invariant load equivalence classes Sorting is replaced by a demand driven code generation that will pre-load a value when it is needed or, if it was not needed before, at some point determined by the order of invariant accesses in the program. Only in very little cases this demand driven pre-loading will kick in, though it will prevent us from generating faulty code. An example where it is needed is shown in: test/ScopInfo/invariant_loads_complicated_dependences.ll Invariant loads that appear in parameters but are not on the top-level (e.g., the parameter is not a SCEVUnknown) will now be treated correctly. Differential Revision: http://reviews.llvm.org/D13831 llvm-svn: 250655
2015-10-18 20:39:19 +08:00
; CHECK-NEXT: [pval] -> { Stmt_bb5[i0, i1] -> MemRef_p[0] };
; CHECK-NEXT: Execution Context: [pval] -> { : }
ScopInfo: Allow simple 'AddRec * Parameter' products in delinearization We also allow such products for cases where 'Parameter' is loaded within the scop, but where we can dynamically verify that the value of 'Parameter' remains unchanged during the execution of the scop. This change relies on Polly's new RequiredILS tracking infrastructure recently contributed by Johannes. llvm-svn: 250019
2015-10-12 16:02:30 +08:00
; CHECK-NEXT: }
; CHECK: ReadAccess := [Reduction Type: NONE] [Scalar: 0]
[FIX] Restructure invariant load equivalence classes Sorting is replaced by a demand driven code generation that will pre-load a value when it is needed or, if it was not needed before, at some point determined by the order of invariant accesses in the program. Only in very little cases this demand driven pre-loading will kick in, though it will prevent us from generating faulty code. An example where it is needed is shown in: test/ScopInfo/invariant_loads_complicated_dependences.ll Invariant loads that appear in parameters but are not on the top-level (e.g., the parameter is not a SCEVUnknown) will now be treated correctly. Differential Revision: http://reviews.llvm.org/D13831 llvm-svn: 250655
2015-10-18 20:39:19 +08:00
; CHECK: [pval] -> { Stmt_bb5[i0, i1] -> MemRef_A[i0, i1] };
ScopInfo: Allow simple 'AddRec * Parameter' products in delinearization We also allow such products for cases where 'Parameter' is loaded within the scop, but where we can dynamically verify that the value of 'Parameter' remains unchanged during the execution of the scop. This change relies on Polly's new RequiredILS tracking infrastructure recently contributed by Johannes. llvm-svn: 250019
2015-10-12 16:02:30 +08:00
; CHECK: MustWriteAccess := [Reduction Type: NONE] [Scalar: 0]
[FIX] Restructure invariant load equivalence classes Sorting is replaced by a demand driven code generation that will pre-load a value when it is needed or, if it was not needed before, at some point determined by the order of invariant accesses in the program. Only in very little cases this demand driven pre-loading will kick in, though it will prevent us from generating faulty code. An example where it is needed is shown in: test/ScopInfo/invariant_loads_complicated_dependences.ll Invariant loads that appear in parameters but are not on the top-level (e.g., the parameter is not a SCEVUnknown) will now be treated correctly. Differential Revision: http://reviews.llvm.org/D13831 llvm-svn: 250655
2015-10-18 20:39:19 +08:00
; CHECK: [pval] -> { Stmt_bb5[i0, i1] -> MemRef_A[i0, i1] };
ScopInfo: Allow simple 'AddRec * Parameter' products in delinearization We also allow such products for cases where 'Parameter' is loaded within the scop, but where we can dynamically verify that the value of 'Parameter' remains unchanged during the execution of the scop. This change relies on Polly's new RequiredILS tracking infrastructure recently contributed by Johannes. llvm-svn: 250019
2015-10-12 16:02:30 +08:00
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
define void @foo(float* %A, i64* %p) {
bb:
br label %bb2
bb2: ; preds = %bb16, %bb
%i.0 = phi i64 [ 0, %bb ], [ %tmp17, %bb16 ]
%exitcond1 = icmp ne i64 %i.0, 100
br i1 %exitcond1, label %bb3, label %bb18
bb3: ; preds = %bb2
br label %bb4
bb4: ; preds = %bb13, %bb3
%j.0 = phi i64 [ 0, %bb3 ], [ %tmp14, %bb13 ]
%exitcond = icmp ne i64 %j.0, 100
br i1 %exitcond, label %bb5, label %bb15
bb5: ; preds = %bb4
%tmp = add nuw nsw i64 %i.0, %j.0
%tmp6 = sitofp i64 %tmp to float
%pval = load i64, i64* %p, align 8
%tmp8 = mul nsw i64 %i.0, %pval
%tmp9 = add nsw i64 %tmp8, %j.0
%tmp10 = getelementptr inbounds float, float* %A, i64 %tmp9
%tmp11 = load float, float* %tmp10, align 4
%tmp12 = fadd float %tmp11, %tmp6
store float %tmp12, float* %tmp10, align 4
br label %bb13
bb13: ; preds = %bb5
%tmp14 = add nuw nsw i64 %j.0, 1
br label %bb4
bb15: ; preds = %bb4
br label %bb16
bb16: ; preds = %bb15
%tmp17 = add nuw nsw i64 %i.0, 1
br label %bb2
bb18: ; preds = %bb2
ret void
}