mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-11-02 07:11:49 +00:00
5026b2cc8b
To compute the dimensions of the array in a unique way, we split the
delinearization analysis in three steps:
- find parametric terms in all memory access functions
- compute the array dimensions from the set of terms
- compute the delinearized access functions for each dimension
The first step is executed on all the memory access functions such that we
gather all the patterns in which an array is accessed. The second step reduces
all this information in a unique description of the sizes of the array. The
third step is delinearizing each memory access function following the common
description of the shape of the array computed in step 2.
This rewrite of the delinearization pass also solves a problem we had with the
previous implementation: because the previous algorithm was by induction on the
structure of the SCEV, it would not correctly recognize the shape of the array
when the memory access was not following the nesting of the loops: for example,
see polly/test/ScopInfo/multidim_only_ivs_3d_reverse.ll
; void foo(long n, long m, long o, double A[n][m][o]) {
;
; for (long i = 0; i < n; i++)
; for (long j = 0; j < m; j++)
; for (long k = 0; k < o; k++)
; A[i][k][j] = 1.0;
Starting with this patch we no longer delinearize access functions that do not
contain parameters, for example in test/Analysis/DependenceAnalysis/GCD.ll
;; for (long int i = 0; i < 100; i++)
;; for (long int j = 0; j < 100; j++) {
;; A[2*i - 4*j] = i;
;; *B++ = A[6*i + 8*j];
these accesses will not be delinearized as the upper bound of the loops are
constants, and their access functions do not contain SCEVUnknown parameters.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@208232 91177308-0d34-0410-b5e6-96231b3b80d8
64 lines
2.6 KiB
LLVM
64 lines
2.6 KiB
LLVM
; RUN: opt < %s -analyze -delinearize | FileCheck %s
|
|
;
|
|
; void foo(long n, long m, long o, int A[n][m][o]) {
|
|
; for (long i = 0; i < n; i++)
|
|
; for (long j = 0; j < m; j++)
|
|
; for (long k = 0; k < o; k++)
|
|
; A[2*i+3][3*j-4][5*k+7] = 1;
|
|
; }
|
|
|
|
; AddRec: {{{(28 + (4 * (-4 + (3 * %m)) * %o) + %A),+,(8 * %m * %o)}<%for.i>,+,(12 * %o)}<%for.j>,+,20}<%for.k>
|
|
; CHECK: Base offset: %A
|
|
; CHECK: ArrayDecl[UnknownSize][%m][%o] with elements of sizeof(i32) bytes.
|
|
; CHECK: ArrayRef[{3,+,2}<%for.i>][{-4,+,3}<%for.j>][{7,+,5}<%for.k>]
|
|
|
|
define void @foo(i64 %n, i64 %m, i64 %o, i32* nocapture %A) #0 {
|
|
entry:
|
|
%cmp32 = icmp sgt i64 %n, 0
|
|
br i1 %cmp32, label %for.cond1.preheader.lr.ph, label %for.end17
|
|
|
|
for.cond1.preheader.lr.ph: ; preds = %entry
|
|
%cmp230 = icmp sgt i64 %m, 0
|
|
%cmp528 = icmp sgt i64 %o, 0
|
|
br i1 %cmp230, label %for.i, label %for.end17
|
|
|
|
for.inc15.us: ; preds = %for.inc12.us.us, %for.i
|
|
%inc16.us = add nsw i64 %i.033.us, 1
|
|
%exitcond55 = icmp eq i64 %inc16.us, %n
|
|
br i1 %exitcond55, label %for.end17, label %for.i
|
|
|
|
for.i: ; preds = %for.cond1.preheader.lr.ph, %for.inc15.us
|
|
%i.033.us = phi i64 [ %inc16.us, %for.inc15.us ], [ 0, %for.cond1.preheader.lr.ph ]
|
|
%mul8.us = shl i64 %i.033.us, 1
|
|
%add9.us = add nsw i64 %mul8.us, 3
|
|
%0 = mul i64 %add9.us, %m
|
|
%sub.us = add i64 %0, -4
|
|
br i1 %cmp528, label %for.j, label %for.inc15.us
|
|
|
|
for.inc12.us.us: ; preds = %for.k
|
|
%inc13.us.us = add nsw i64 %j.031.us.us, 1
|
|
%exitcond54 = icmp eq i64 %inc13.us.us, %m
|
|
br i1 %exitcond54, label %for.inc15.us, label %for.j
|
|
|
|
for.j: ; preds = %for.i, %for.inc12.us.us
|
|
%j.031.us.us = phi i64 [ %inc13.us.us, %for.inc12.us.us ], [ 0, %for.i ]
|
|
%mul7.us.us = mul nsw i64 %j.031.us.us, 3
|
|
%tmp.us.us = add i64 %sub.us, %mul7.us.us
|
|
%tmp27.us.us = mul i64 %tmp.us.us, %o
|
|
br label %for.k
|
|
|
|
for.k: ; preds = %for.k, %for.j
|
|
%k.029.us.us = phi i64 [ 0, %for.j ], [ %inc.us.us, %for.k ]
|
|
%mul.us.us = mul nsw i64 %k.029.us.us, 5
|
|
%arrayidx.sum.us.us = add i64 %mul.us.us, 7
|
|
%arrayidx10.sum.us.us = add i64 %arrayidx.sum.us.us, %tmp27.us.us
|
|
%arrayidx11.us.us = getelementptr inbounds i32* %A, i64 %arrayidx10.sum.us.us
|
|
store i32 1, i32* %arrayidx11.us.us, align 4
|
|
%inc.us.us = add nsw i64 %k.029.us.us, 1
|
|
%exitcond = icmp eq i64 %inc.us.us, %o
|
|
br i1 %exitcond, label %for.inc12.us.us, label %for.k
|
|
|
|
for.end17: ; preds = %for.inc15.us, %for.cond1.preheader.lr.ph, %entry
|
|
ret void
|
|
}
|