b7315ffc3c
This patch adds initial support for a pointer diff based runtime check scheme for vectorization. This scheme requires fewer computations and checks than the existing full overlap checking, if it is applicable. The main idea is to only check if source and sink of a dependency are far enough apart so the accesses won't overlap in the vector loop. To do so, it is sufficient to compute the difference and compare it to the `VF * UF * AccessSize`. It is sufficient to check `(Sink - Src) <u VF * UF * AccessSize` to rule out a backwards dependence in the vector loop with the given VF and UF. If Src >=u Sink, there is not dependence preventing vectorization, hence the overflow should not matter and using the ULT should be sufficient. Note that the initial version is restricted in multiple ways: 1. Pointers must only either be read or written, by a single instruction (this allows re-constructing source/sink for dependences with the available information) 2. Source and sink pointers must be add-recs, with matching steps 3. The step must be a constant. 3. abs(step) == AccessSize. Most of those restrictions can be relaxed in the future. See https://github.com/llvm/llvm-project/issues/53590. Reviewed By: dmgreen Differential Revision: https://reviews.llvm.org/D119078
43 lines
1.9 KiB
LLVM
43 lines
1.9 KiB
LLVM
; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s
|
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
|
|
|
define void @add_ints(i32* nocapture %A, i32* nocapture %B, i32* nocapture %C) {
|
|
; CHECK-LABEL: @add_ints(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_MEMCHECK:%.*]]
|
|
; CHECK-LABEL: vector.memcheck:
|
|
; CHECK-NEXT: [[A1:%.*]] = ptrtoint i32* [[A:%.*]] to i64
|
|
; CHECK-NEXT: [[B2:%.*]] = ptrtoint i32* [[B:%.*]] to i64
|
|
; CHECK-NEXT: [[C3:%.*]] = ptrtoint i32* [[C:%.*]] to i64
|
|
; CHECK-NEXT: [[TMP0:%.*]] = sub i64 [[A1]], [[B2]]
|
|
; CHECK-NEXT: [[DIFF_CHECK:%.*]] = icmp ult i64 [[TMP0]], 16
|
|
; CHECK-NEXT: [[TMP1:%.*]] = sub i64 [[A1]], [[C3]]
|
|
; CHECK-NEXT: [[DIFF_CHECK4:%.*]] = icmp ult i64 [[TMP1]], 16
|
|
; CHECK-NEXT: [[CONFLICT_RDX:%.*]] = or i1 [[DIFF_CHECK]], [[DIFF_CHECK4]]
|
|
; CHECK-NEXT: br i1 [[CONFLICT_RDX]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
|
|
; CHECK: vector.ph:
|
|
; CHECK-NEXT: br label %vector.body
|
|
; CHECK: vector.body:
|
|
;
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%arrayidx = getelementptr inbounds i32, i32* %B, i64 %indvars.iv
|
|
%0 = load i32, i32* %arrayidx, align 4
|
|
%arrayidx2 = getelementptr inbounds i32, i32* %C, i64 %indvars.iv
|
|
%1 = load i32, i32* %arrayidx2, align 4
|
|
%add = add nsw i32 %1, %0
|
|
%arrayidx4 = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
|
|
store i32 %add, i32* %arrayidx4, align 4
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, 200
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end:
|
|
ret void
|
|
}
|