llvm-project/polly/test/MaximalStaticExpansion/working_phi_expansion.ll

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

78 lines
3.2 KiB
LLVM
Raw Normal View History

[Polly][WIP] Scalar fully indexed expansion Summary: This patch comes directly after https://reviews.llvm.org/D34982 which allows fully indexed expansion of MemoryKind::Array. This patch allows expansion for MemoryKind::Value and MemoryKind::PHI. MemoryKind::Value seems to be working with no majors modifications of D34982. A test case has been added. Unfortunatly, no "run time" checks can be done for now because as @Meinersbur explains in a comment on D34982, DependenceInfo need to be cleared and reset to take expansion into account in the remaining part of the Polly pipeline. There is no way to do that in Polly for now. MemoryKind::PHI is not working. Test case is in place, but not working. To expand MemoryKind::Array, we expand first the write and then after the reads. For MemoryKind::PHI, the idea of the current implementation is to exchange the "roles" of the read and write and expand first the read according to its domain and after the writes. But with this strategy, I still encounter the problem of union_map in new access map. For example with the following source code (source code of the test case) : ``` void mse(double A[Ni], double B[Nj]) { int i,j; double tmp = 6; for (i = 0; i < Ni; i++) { for (int j = 0; j<Nj; j++) { tmp = tmp + 2; } B[i] = tmp; } } ``` Polly gives us the following statements and memory accesses : ``` Statements { Stmt_for_body Domain := { Stmt_for_body[i0] : 0 <= i0 <= 9999 }; Schedule := { Stmt_for_body[i0] -> [i0, 0, 0] }; ReadAccess := [Reduction Type: NONE] [Scalar: 1] { Stmt_for_body[i0] -> MemRef_tmp_04__phi[] }; MustWriteAccess := [Reduction Type: NONE] [Scalar: 1] { Stmt_for_body[i0] -> MemRef_tmp_11__phi[] }; Instructions { %tmp.04 = phi double [ 6.000000e+00, %entry.split ], [ %add.lcssa, %for.end ] } Stmt_for_inc Domain := { Stmt_for_inc[i0, i1] : 0 <= i0 <= 9999 and 0 <= i1 <= 9999 }; Schedule := { Stmt_for_inc[i0, i1] -> [i0, 1, i1] }; MustWriteAccess := [Reduction Type: NONE] [Scalar: 1] { Stmt_for_inc[i0, i1] -> MemRef_tmp_11__phi[] }; ReadAccess := [Reduction Type: NONE] [Scalar: 1] { Stmt_for_inc[i0, i1] -> MemRef_tmp_11__phi[] }; MustWriteAccess := [Reduction Type: NONE] [Scalar: 1] { Stmt_for_inc[i0, i1] -> MemRef_add_lcssa__phi[] }; Instructions { %tmp.11 = phi double [ %tmp.04, %for.body ], [ %add, %for.inc ] %add = fadd double %tmp.11, 2.000000e+00 %exitcond = icmp ne i32 %inc, 10000 } Stmt_for_end Domain := { Stmt_for_end[i0] : 0 <= i0 <= 9999 }; Schedule := { Stmt_for_end[i0] -> [i0, 2, 0] }; MustWriteAccess := [Reduction Type: NONE] [Scalar: 1] { Stmt_for_end[i0] -> MemRef_tmp_04__phi[] }; ReadAccess := [Reduction Type: NONE] [Scalar: 1] { Stmt_for_end[i0] -> MemRef_add_lcssa__phi[] }; MustWriteAccess := [Reduction Type: NONE] [Scalar: 0] { Stmt_for_end[i0] -> MemRef_B[i0] }; Instructions { %add.lcssa = phi double [ %add, %for.inc ] store double %add.lcssa, double* %arrayidx, align 8 %exitcond5 = icmp ne i64 %indvars.iv.next, 10000 } } ``` and the following dependences : ``` { Stmt_for_inc[i0, 9999] -> Stmt_for_end[i0] : 0 <= i0 <= 9999; Stmt_for_inc[i0, i1] -> Stmt_for_inc[i0, 1 + i1] : 0 <= i0 <= 9999 and 0 <= i1 <= 9998; Stmt_for_body[i0] -> Stmt_for_inc[i0, 0] : 0 <= i0 <= 9999; Stmt_for_end[i0] -> Stmt_for_body[1 + i0] : 0 <= i0 <= 9998 } ``` When trying to expand this memory access : ``` { Stmt_for_inc[i0, i1] -> MemRef_tmp_11__phi[] }; ``` The new access map would look like this : ``` { Stmt_for_inc[i0, 9999] -> MemRef_tmp_11__phi_exp[i0] : 0 <= i0 <= 9999; Stmt_for_inc[i0, i1] ->MemRef_tmp_11__phi_exp[i0, 1 + i1] : 0 <= i0 <= 9999 and 0 <= i1 <= 9998 } ``` The idea to implement the expansion for PHI access is an idea from @Meinersbur and I don't understand why my implementation does not work. I should have miss something in the understanding of the idea. Contributed by: Nicolas Bonfante <nicolas.bonfante@gmail.com> Reviewers: Meinersbur, simbuerg, bollu Reviewed By: Meinersbur Subscribers: llvm-commits, pollydev, Meinersbur Differential Revision: https://reviews.llvm.org/D36647 llvm-svn: 311619
2017-08-24 08:04:45 +08:00
; RUN: opt %loadPolly -polly-mse -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -polly-mse -pass-remarks-analysis="polly-mse" -analyze < %s 2>&1 | FileCheck %s --check-prefix=MSE
;
; Verify that the accesses are correctly expanded for MemoryKind::PHI
; tmp_04 is not expanded because it need copy-in.
;
; Original source code :
;
; #define Ni 10000
; #define Nj 10000
;
; void mse(double A[Ni], double B[Nj]) {
; int i,j;
; double tmp = 6;
; for (i = 0; i < Ni; i++) {
; for (int j = 0; j<Nj; j++) {
; tmp = tmp + 2;
; }
; B[i] = tmp;
; }
;
; Check that the pass detects that tmp_04 reads from original value.
;
; MSE: MemRef_tmp_04__phi read from its original value.
;
; Check that the SAI are created except the expanded SAI of tmp_04.
;
; CHECK-NOT: double MemRef_tmp_04__phi_Stmt_for_body_expanded[10000]; // Element size 8
; CHECK: double MemRef_tmp_11__phi_Stmt_for_inc_expanded[10000][10000]; // Element size
; CHECK: double MemRef_add_lcssa__phi_Stmt_for_end_expanded[10000]; // Element size 8
; CHECK: double MemRef_B_Stmt_for_end_expanded[10000]; // Element size 8
;
; Check that the memory accesses are modified except those related to tmp_04.
;
; CHECK-NOT: new: { Stmt_for_body[i0] -> MemRef_tmp_04__phi_Stmt_for_body_expanded[i0] };
; CHECK: new: { Stmt_for_body[i0] -> MemRef_tmp_11__phi_Stmt_for_inc_expanded[i0, 0] };
; CHECK: new: { Stmt_for_inc[i0, i1] -> MemRef_tmp_11__phi_Stmt_for_inc_expanded[i0, 1 + i1] : i1 <= 9998 };
; CHECK: new: { Stmt_for_inc[i0, i1] -> MemRef_tmp_11__phi_Stmt_for_inc_expanded[i0, i1] };
; CHECK: new: { Stmt_for_inc[i0, 9999] -> MemRef_add_lcssa__phi_Stmt_for_end_expanded[i0] };
; CHECK-NOT: new: { Stmt_for_end[i0] -> MemRef_tmp_04__phi_Stmt_for_body_expanded[1 + i0] : i0 <= 9998 };
; CHECK: new: { Stmt_for_end[i0] -> MemRef_add_lcssa__phi_Stmt_for_end_expanded[i0] };
; CHECK: new: { Stmt_for_end[i0] -> MemRef_B_Stmt_for_end_expanded[i0] };
;
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
define void @tmp(double* %A, double* %B) {
entry:
br label %entry.split
entry.split: ; preds = %entry
br label %for.body
for.body: ; preds = %entry.split, %for.end
%indvars.iv = phi i64 [ 0, %entry.split ], [ %indvars.iv.next, %for.end ]
%tmp.04 = phi double [ 6.000000e+00, %entry.split ], [ %add.lcssa, %for.end ]
br label %for.inc
for.inc: ; preds = %for.body, %for.inc
%j1.02 = phi i32 [ 0, %for.body ], [ %inc, %for.inc ]
%tmp.11 = phi double [ %tmp.04, %for.body ], [ %add, %for.inc ]
%add = fadd double %tmp.11, 2.000000e+00
%inc = add nuw nsw i32 %j1.02, 1
%exitcond = icmp ne i32 %inc, 10000
br i1 %exitcond, label %for.inc, label %for.end
for.end: ; preds = %for.inc
%add.lcssa = phi double [ %add, %for.inc ]
%arrayidx = getelementptr inbounds double, double* %B, i64 %indvars.iv
store double %add.lcssa, double* %arrayidx, align 8
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond5 = icmp ne i64 %indvars.iv.next, 10000
br i1 %exitcond5, label %for.body, label %for.end7
for.end7: ; preds = %for.end
ret void
}