mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 03:02:36 +01:00
e80a23909b
This patch adds
- New arguments to getMinPrefetchStride() to let the target decide on a
per-loop basis if software prefetching should be done even with a stride
within the limit of the hw prefetcher.
- New TTI hook enableWritePrefetching() to let a target do write prefetching
by default (defaults to false).
- In LoopDataPrefetch:
- A search through the whole loop to gather information before emitting any
prefetches. This way the target can get information via new arguments to
getMinPrefetchStride() and emit prefetches more selectively. Collected
information includes: Does the loop have a call, how many memory
accesses, how many of them are strided, how many prefetches will cover
them. This is NFC to before as long as the target does not change its
definition of getMinPrefetchStride().
- If a previous access to the same exact address was 'read', and the
current one is 'write', make it a 'write' prefetch.
- If two accesses that are covered by the same prefetch do not dominate
each other, put the prefetch in a block that dominates both of them.
- If a ConstantMaxTripCount is less than ItersAhead, then skip the loop.
- A SystemZ implementation of getMinPrefetchStride().
Review: Ulrich Weigand, Michael Kruse
Differential Revision: https://reviews.llvm.org/D70228
29 lines
946 B
LLVM
29 lines
946 B
LLVM
; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z14 -prefetch-distance=20 \
|
|
; RUN: -loop-prefetch-writes -stop-after=loop-data-prefetch | FileCheck %s
|
|
;
|
|
; Check that for a load followed by a store to the same address gets a single
|
|
; write prefetch.
|
|
;
|
|
; CHECK-LABEL: for.body
|
|
; CHECK: call void @llvm.prefetch.p0i8(i8* %scevgep{{.*}}, i32 1, i32 3, i32 1
|
|
; CHECK-not: call void @llvm.prefetch
|
|
|
|
define void @fun(i32* nocapture %Src, i32* nocapture readonly %Dst) {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next.9, %for.body ]
|
|
%arrayidx = getelementptr inbounds i32, i32* %Dst, i64 %indvars.iv
|
|
%0 = load i32, i32* %arrayidx, align 4
|
|
%a = add i32 %0, 128
|
|
store i32 %a, i32* %arrayidx, align 4
|
|
%indvars.iv.next.9 = add nuw nsw i64 %indvars.iv, 1600
|
|
%cmp.9 = icmp ult i64 %indvars.iv.next.9, 11200
|
|
br i1 %cmp.9, label %for.body, label %for.cond.cleanup
|
|
|
|
for.cond.cleanup:
|
|
ret void
|
|
}
|
|
|