1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-24 03:33:20 +01:00
llvm-mirror/test/Analysis/LoopAccessAnalysis/multiple-strides-rt-memory-checks.ll
Dorit Nuzman 15c8d7c6d1 [LV/LoopAccess] Check statically if an unknown dependence distance can be
proven larger than the loop-count

This fixes PR31098: Try to resolve statically data-dependences whose
compile-time-unknown distance can be proven larger than the loop-count, 
instead of resorting to runtime dependence checking (which are not always 
possible).

For vectorization it is sufficient to prove that the dependence distance 
is >= VF; But in some cases we can prune unknown dependence distances early,
and even before selecting the VF, and without a runtime test, by comparing 
the distance against the loop iteration count. Since the vectorized code 
will be executed only if LoopCount >= VF, proving distance >= LoopCount 
also guarantees that distance >= VF. This check is also equivalent to the 
Strong SIV Test.

Reviewers: mkuper, anemet, sanjoy

Differential Revision: https://reviews.llvm.org/D28044

llvm-svn: 294892
2017-02-12 09:32:53 +00:00

69 lines
2.0 KiB
LLVM

; RUN: opt -loop-accesses -analyze -S < %s | FileCheck %s
; RUN: opt -passes='require<scalar-evolution>,require<aa>,loop(print-access-info)' -disable-output < %s 2>&1 | FileCheck %s
; This is the test case from PR26314.
; When we were retrying dependence checking with memchecks only,
; the loop-invariant access in the inner loop was incorrectly determined to be wrapping
; because it was not strided in the inner loop.
; #define Z 32
; typedef struct s {
; int v1[Z];
; int v2[Z];
; int v3[Z][Z];
; } s;
;
; void slow_function (s* const obj, int z) {
; for (int j=0; j<Z; j++) {
; for (int k=0; k<z; k++) {
; int x = obj->v1[k] + obj->v2[j];
; obj->v3[j][k] += x;
; }
; }
; }
; CHECK: function 'Test':
; CHECK: .inner:
; CHECK-NEXT: Memory dependences are safe
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
; CHECK: Check 0:
; CHECK: Check 1:
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
%struct.s = type { [32 x i32], [32 x i32], [32 x [32 x i32]] }
define void @Test(%struct.s* nocapture %obj, i64 %z) #0 {
br label %.outer.preheader
.outer.preheader:
%i = phi i64 [ 0, %0 ], [ %i.next, %.outer ]
%1 = getelementptr inbounds %struct.s, %struct.s* %obj, i64 0, i32 1, i64 %i
br label %.inner
.exit:
ret void
.outer:
%i.next = add nuw nsw i64 %i, 1
%exitcond.outer = icmp eq i64 %i.next, 32
br i1 %exitcond.outer, label %.exit, label %.outer.preheader
.inner:
%j = phi i64 [ 0, %.outer.preheader ], [ %j.next, %.inner ]
%2 = getelementptr inbounds %struct.s, %struct.s* %obj, i64 0, i32 0, i64 %j
%3 = load i32, i32* %2
%4 = load i32, i32* %1
%5 = add nsw i32 %4, %3
%6 = getelementptr inbounds %struct.s, %struct.s* %obj, i64 0, i32 2, i64 %i, i64 %j
%7 = load i32, i32* %6
%8 = add nsw i32 %5, %7
store i32 %8, i32* %6
%j.next = add nuw nsw i64 %j, 1
%exitcond.inner = icmp eq i64 %j.next, %z
br i1 %exitcond.inner, label %.outer, label %.inner
}