From: Tobias Klausmann <tobias.johannes.klausmann-AqjdNwhu20eELgA04lAiVw@public.gmane.org>
To: Ilia Mirkin <imirkin-FrUbXkNCsVf2fBVCVOL8/A@public.gmane.org>
Cc: nouveau-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org
Subject: Re: [PATCH 3/4] nvc0/ir: optimize set & 1.0 to produce boolean-float sets
Date: Sat, 9 May 2015 17:27:16 +0200 [thread overview]
Message-ID: <554E2754.5080904@mni.thm.de> (raw)
In-Reply-To: <1431149707-7159-3-git-send-email-imirkin-FrUbXkNCsVf2fBVCVOL8/A@public.gmane.org>
On 09.05.2015 07:35, Ilia Mirkin wrote:
> This has started to happen more now that the backend is producing
> KILL_IF more often.
>
> Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
> ---
> .../drivers/nouveau/codegen/nv50_ir_peephole.cpp | 29 ++++++++++++++++++++++
> .../nouveau/codegen/nv50_ir_target_nv50.cpp | 2 ++
> 2 files changed, 31 insertions(+)
>
> diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
> index 14446b6..d8af19a 100644
> --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
> +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
> @@ -973,6 +973,35 @@ ConstantFolding::opnd(Instruction *i, ImmediateValue &imm0, int s)
> }
> break;
>
> + case OP_AND:
> + {
> + CmpInstruction *cmp = i->getSrc(t)->getInsn()->asCmp();
> + if (!cmp || cmp->op == OP_SLCT)
how about if (cmp == NULL || ...) and kill the same condition later?
> + return;
> + if (!prog->getTarget()->isOpSupported(cmp->op, TYPE_F32))
> + return;
> + if (imm0.reg.data.f32 != 1.0)
> + return;
> + if (cmp == NULL)
> + return;
> + if (i->getSrc(t)->getInsn()->dType != TYPE_U32)
> + return;
> +
> + i->getSrc(t)->getInsn()->dType = TYPE_F32;
> + if (i->src(t).mod != Modifier(0)) {
> + assert(i->src(t).mod == Modifier(NV50_IR_MOD_NOT));
> + i->src(t).mod = Modifier(0);
> + cmp->setCond = reverseCondCode(cmp->setCond);
> + }
> + i->op = OP_MOV;
> + i->setSrc(s, NULL);
> + if (t) {
> + i->setSrc(0, i->getSrc(t));
> + i->setSrc(t, NULL);
> + }
> + }
> + break;
> +
> case OP_SHL:
> {
> if (s != 1 || i->src(0).mod != Modifier(0))
> diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nv50.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nv50.cpp
> index 178a167..70180eb 100644
> --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nv50.cpp
> +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nv50.cpp
> @@ -413,6 +413,8 @@ TargetNV50::isOpSupported(operation op, DataType ty) const
> return false;
> case OP_SAD:
> return ty == TYPE_S32;
> + case OP_SET:
> + return !isFloatType(ty);
> default:
> return true;
> }
_______________________________________________
Nouveau mailing list
Nouveau@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/nouveau
next prev parent reply other threads:[~2015-05-09 15:27 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-05-09 5:35 [PATCH 1/4] nvc0/ir: avoid jumping to a sched instruction Ilia Mirkin
[not found] ` <1431149707-7159-1-git-send-email-imirkin-FrUbXkNCsVf2fBVCVOL8/A@public.gmane.org>
2015-05-09 5:35 ` [PATCH 2/4] nvc0/ir: allow iset to produce a boolean float Ilia Mirkin
2015-05-09 5:35 ` [PATCH 3/4] nvc0/ir: optimize set & 1.0 to produce boolean-float sets Ilia Mirkin
[not found] ` <1431149707-7159-3-git-send-email-imirkin-FrUbXkNCsVf2fBVCVOL8/A@public.gmane.org>
2015-05-09 15:27 ` Tobias Klausmann [this message]
[not found] ` <554E2754.5080904-AqjdNwhu20eELgA04lAiVw@public.gmane.org>
2015-05-09 17:53 ` Ilia Mirkin
[not found] ` <CAKb7Uvg-2tUxSpkXVh9M+a6G2bTO97MzowN=r0jRbYh5DiFmYw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2015-05-09 19:47 ` Tobias Klausmann
2015-05-09 5:35 ` [PATCH 4/4] nv50/ir: allow OP_SET to merge with OP_SET_AND/etc as well as a neg Ilia Mirkin
[not found] ` <1431149707-7159-4-git-send-email-imirkin-FrUbXkNCsVf2fBVCVOL8/A@public.gmane.org>
2015-05-09 20:04 ` Tobias Klausmann
[not found] ` <554E685B.1040602-AqjdNwhu20eELgA04lAiVw@public.gmane.org>
2015-05-09 20:07 ` Ilia Mirkin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=554E2754.5080904@mni.thm.de \
--to=tobias.johannes.klausmann-aqjdnwhu20eelga04laivw@public.gmane.org \
--cc=imirkin-FrUbXkNCsVf2fBVCVOL8/A@public.gmane.org \
--cc=nouveau-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.