* [PATCH] tree-optimization/114921 - _Float16 -> __bf16 isn't noop
@ 2024-05-02 12:18 Richard Biener
0 siblings, 0 replies; 3+ messages in thread
From: Richard Biener @ 2024-05-02 12:18 UTC (permalink / raw)
To: gcc-patches
The vectorizer handles a _Float16 to __bf16 conversion through
vectorizable_assignment, thinking it's a noop. The following
fixes this by making the same-size check stricter, requiring
the same vector component mode.
Posted again for the arm CI
PR tree-optimization/114921
* tree-vect-stmts.cc (vectorizable_assignment): Require
same vector component modes for input and output.
---
gcc/tree-vect-stmts.cc | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc
index f8d8636b139..adb6ef53254 100644
--- a/gcc/tree-vect-stmts.cc
+++ b/gcc/tree-vect-stmts.cc
@@ -5961,8 +5961,8 @@ vectorizable_assignment (vec_info *vinfo,
|| code == VIEW_CONVERT_EXPR)
&& (!vectype_in
|| maybe_ne (TYPE_VECTOR_SUBPARTS (vectype_in), nunits)
- || maybe_ne (GET_MODE_SIZE (TYPE_MODE (vectype)),
- GET_MODE_SIZE (TYPE_MODE (vectype_in)))))
+ || (TYPE_MODE (TREE_TYPE (vectype))
+ != TYPE_MODE (TREE_TYPE (vectype_in)))))
return false;
if (VECTOR_BOOLEAN_TYPE_P (vectype) != VECTOR_BOOLEAN_TYPE_P (vectype_in))
--
2.35.3
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH] tree-optimization/114921 - _Float16 -> __bf16 isn't noop
@ 2024-05-02 12:13 Richard Biener
0 siblings, 0 replies; 3+ messages in thread
From: Richard Biener @ 2024-05-02 12:13 UTC (permalink / raw)
To: gcc-patches
On Thu, 2 May 2024, Richard Biener wrote:
> The vectorizer handles a _Float16 to __bf16 conversion through
> vectorizable_assignment, thinking it's a noop. The following
> fixes this by making the same-size check stricter, requiring
> the same vector component mode.
>
> Bootstrap & regtest running on x86_64-unknown-linux-gnu. I couldn't
> manage to produce a meaningful (runtime) testcase.
>
> PR tree-optimization/114921
> * tree-vect-stmts.cc (vectorizable_assignment): Require
> same vector component modes for input and output.
> ---
> gcc/tree-vect-stmts.cc | 3 +--
> 1 file changed, 1 insertion(+), 2 deletions(-)
>
> diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc
> index f8d8636b139..5ec053755a2 100644
> --- a/gcc/tree-vect-stmts.cc
> +++ b/gcc/tree-vect-stmts.cc
> @@ -5961,8 +5961,7 @@ vectorizable_assignment (vec_info *vinfo,
> || code == VIEW_CONVERT_EXPR)
> && (!vectype_in
> || maybe_ne (TYPE_VECTOR_SUBPARTS (vectype_in), nunits)
> - || maybe_ne (GET_MODE_SIZE (TYPE_MODE (vectype)),
> - GET_MODE_SIZE (TYPE_MODE (vectype_in)))))
> + || TYPE_MODE (vectype) != TYPE_MODE (vectype_in)))
- || maybe_ne (GET_MODE_SIZE (TYPE_MODE (vectype)),
- GET_MODE_SIZE (TYPE_MODE (vectype_in)))))
+ || (TYPE_MODE (TREE_TYPE (vectype))
+ != TYPE_MODE (TREE_TYPE (vectype_in)))))
actually so it matches the comment in the commit message. ISTR
we have v4si and v2six2 modes on some archs that we possibly want
to inter-operate with through vectorizable_assignment.
Richard.
^ permalink raw reply [flat|nested] 3+ messages in thread
* [PATCH] tree-optimization/114921 - _Float16 -> __bf16 isn't noop
@ 2024-05-02 11:59 Richard Biener
0 siblings, 0 replies; 3+ messages in thread
From: Richard Biener @ 2024-05-02 11:59 UTC (permalink / raw)
To: gcc-patches
The vectorizer handles a _Float16 to __bf16 conversion through
vectorizable_assignment, thinking it's a noop. The following
fixes this by making the same-size check stricter, requiring
the same vector component mode.
Bootstrap & regtest running on x86_64-unknown-linux-gnu. I couldn't
manage to produce a meaningful (runtime) testcase.
PR tree-optimization/114921
* tree-vect-stmts.cc (vectorizable_assignment): Require
same vector component modes for input and output.
---
gcc/tree-vect-stmts.cc | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc
index f8d8636b139..5ec053755a2 100644
--- a/gcc/tree-vect-stmts.cc
+++ b/gcc/tree-vect-stmts.cc
@@ -5961,8 +5961,7 @@ vectorizable_assignment (vec_info *vinfo,
|| code == VIEW_CONVERT_EXPR)
&& (!vectype_in
|| maybe_ne (TYPE_VECTOR_SUBPARTS (vectype_in), nunits)
- || maybe_ne (GET_MODE_SIZE (TYPE_MODE (vectype)),
- GET_MODE_SIZE (TYPE_MODE (vectype_in)))))
+ || TYPE_MODE (vectype) != TYPE_MODE (vectype_in)))
return false;
if (VECTOR_BOOLEAN_TYPE_P (vectype) != VECTOR_BOOLEAN_TYPE_P (vectype_in))
--
2.35.3
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2024-05-02 12:18 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2024-05-02 12:18 [PATCH] tree-optimization/114921 - _Float16 -> __bf16 isn't noop Richard Biener
-- strict thread matches above, loose matches on Subject: below --
2024-05-02 12:13 Richard Biener
2024-05-02 11:59 Richard Biener
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).