1e7efd397a
In the following loop:
void foo(int *a, int *b, int N) {
for (int i=0; i<N; ++i)
a[i + 4] = a[i] + b[i];
}
The loop dependence constrains the VF to a maximum of (4, fixed), which
would mean using <4 x i32> as the vector type in vectorization.
Extending this to scalable vectorization, a VF of (4, scalable) implies
a vector type of <vscale x 4 x i32>. To determine if this is legal
vscale must be taken into account. For this example, unless
max(vscale)=1, it's unsafe to vectorize.
For SVE, the number of bits in an SVE register is architecturally
defined to be a multiple of 128 bits with a maximum of 2048 bits, thus
the maximum vscale is 16. In the loop above it is therefore unfeasible
to vectorize with SVE. However, in this loop:
void foo(int *a, int *b, int N) {
#pragma clang loop vectorize_width(X, scalable)
for (int i=0; i<N; ++i)
a[i + 32] = a[i] + b[i];
}
As long as max(vscale) multiplied by the number of lanes 'X' doesn't
exceed the dependence distance, it is safe to vectorize. For SVE a VF of
(2, scalable) is within this constraint, since a vector of <16 x 2 x 32>
will have no dependencies between lanes. For any number of lanes larger
than this it would be unsafe to vectorize.
This patch extends 'computeFeasibleMaxVF' to legalize scalable VFs
specified as loop hints, implementing the following behaviour:
* If the backend does not support scalable vectors, ignore the hint.
* If scalable vectorization is unfeasible given the loop
dependence, like in the first example above for SVE, then use a
fixed VF.
* Accept scalable VFs if it's safe to do so.
* Otherwise, clamp scalable VFs that exceed the maximum safe VF.
Reviewed By: sdesmalen, fhahn, david-arm
Differential Revision: https://reviews.llvm.org/D91718
28 lines
938 B
LLVM
28 lines
938 B
LLVM
; REQUIRES: asserts
|
|
; RUN: opt < %s -passes='loop-vectorize' -force-vector-width=2 -force-target-supports-scalable-vectors=true -enable-epilogue-vectorization -epilogue-vectorization-force-VF=2 --debug-only=loop-vectorize -S 2>&1 | FileCheck %s
|
|
|
|
target datalayout = "e-m:e-i64:64-n32:64-v256:256:256-v512:512:512"
|
|
|
|
; Currently we cannot handle scalable vectorization factors.
|
|
; CHECK: LV: Checking a loop in "f1"
|
|
; CHECK: LEV: Epilogue vectorization for scalable vectors not yet supported.
|
|
|
|
define void @f1(i8* %A) {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
|
|
%arrayidx = getelementptr inbounds i8, i8* %A, i64 %iv
|
|
store i8 1, i8* %arrayidx, align 1
|
|
%iv.next = add nuw nsw i64 %iv, 1
|
|
%exitcond = icmp ne i64 %iv.next, 1024
|
|
br i1 %exitcond, label %for.body, label %exit, !llvm.loop !0
|
|
|
|
exit:
|
|
ret void
|
|
}
|
|
|
|
!0 = !{!0, !1}
|
|
!1 = !{!"llvm.loop.vectorize.scalable.enable", i1 true}
|