public inbox for qemu-devel@nongnu.org
 help / color / mirror / Atom feed
From: Matheus Bernardino <matheus.bernardino@oss.qualcomm.com>
To: Taylor Simpson <ltaylorsimpson@gmail.com>
Cc: qemu-devel@nongnu.org, brian.cain@oss.qualcomm.com, ale@rev.ng,
	anjo@rev.ng, marco.liebel@oss.qualcomm.com, philmd@linaro.org,
	quic_mburton@quicinc.com, sid.manning@oss.qualcomm.com
Subject: Re: [PATCH 07/13] target/hexagon: add v68 HVX IEEE float conversion insns
Date: Tue, 24 Mar 2026 18:04:29 -0300	[thread overview]
Message-ID: <CABrGZ+GO+G2MrnP1W69vsSCrX_QcEsJw5Zhkd5yd_uhdoegpFQ@mail.gmail.com> (raw)
In-Reply-To: <CAATN3Np8aWjb8PyoupVpWCWc8thTLghWn974OVC7M_-opqSrSQ@mail.gmail.com>

On Mon, Mar 23, 2026 at 6:26 PM Taylor Simpson <ltaylorsimpson@gmail.com> wrote:
>
>
>
> On Mon, Mar 23, 2026 at 7:16 AM Matheus Tavares Bernardino <matheus.bernardino@oss.qualcomm.com> wrote:
>>
>>
>> diff --git a/target/hexagon/mmvec/kvx_ieee.c b/target/hexagon/mmvec/kvx_ieee.c
>> index 33621a15f3..bbeec09707 100644
>> --- a/target/hexagon/mmvec/kvx_ieee.c
>> +++ b/target/hexagon/mmvec/kvx_ieee.c
>> @@ -131,3 +131,101 @@ uint16_t qf_min_hf(uint16_t a1, uint16_t a2, float_status *fp_status)
>>      if (float16_is_pos_nan(f2) || float16_is_neg_nan(f1)) return a1;
>>      return fp_min_hf(a1, a2, fp_status);
>>  }
>> +
>> +uint16_t f16_to_uh(uint16_t op1, float_status *fp_status)
>> +{
>> +    return float16_to_uint16_scalbn(make_float16(op1),
>> +                                    float_round_nearest_even,
>
>
> Does HVX always use this rounding mode?  The scalar core uses the rounding mode in USR.

Yeah, almost always this mode, with the exception of some
instructions. It's not configurable via USR (or anything else).

>> +
>> +int32_t conv_w_sf(uint32_t a, float_status *fp_status)
>> +{
>> +    float_status scratch_fpst = {};
>> +    const float32 W_MAX = int32_to_float32(INT32_MAX, &scratch_fpst);
>> +    const float32 W_MIN = int32_to_float32(INT32_MIN, &scratch_fpst);
>> +    float32 f1 = make_float32(a);
>> +
>> +    if (float32_is_any_nan(f1) || float32_is_infinity(f1) ||
>> +        float32_le_quiet(W_MAX, f1, fp_status) ||
>> +        float32_le_quiet(f1, W_MIN, fp_status)) {
>> +        return float32_is_neg(f1) ? INT32_MIN : INT32_MAX;
>> +    }
>
>
> Does float32_to_int32 handle these checks?

Hmm, I don't think they are exactly the same. For example,
float32_to_int32 will return INT32_MAX for any NAN. But the hexagon
implementation here returns INT32_MIN for negative NAN.

>>
>> +    return float32_to_int32_round_to_zero(f1, fp_status);
>
>
> Rounding mode?

This is one of those exceptions I mentioned earlier.


  reply	other threads:[~2026-03-24 21:05 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-03-23 13:15 [PATCH 00/13] hexagon: add missing HVX float instructions Matheus Tavares Bernardino
2026-03-23 13:15 ` [PATCH 01/13] tests/docker: Update hexagon cross toolchain to 22.1.0 Matheus Tavares Bernardino
2026-03-23 13:15 ` [PATCH 02/13] target/hexagon: fix incorrect/too-permissive HVX encodings Matheus Tavares Bernardino
2026-03-23 19:21   ` Taylor Simpson
2026-03-23 13:15 ` [PATCH 03/13] target/hexagon/cpu: add HVX IEEE FP extension Matheus Tavares Bernardino
2026-03-23 19:32   ` Taylor Simpson
2026-03-24 16:52     ` Matheus Bernardino
2026-03-24 18:48       ` Taylor Simpson
2026-03-24 19:20         ` Brian Cain
2026-03-24 19:46           ` Taylor Simpson
2026-03-23 13:15 ` [PATCH 04/13] target/hexagon: add v68 HVX IEEE float arithmetic insns Matheus Tavares Bernardino
2026-03-23 20:28   ` Taylor Simpson
2026-03-24 19:30     ` Matheus Bernardino
2026-03-24 19:51       ` Taylor Simpson
2026-03-24 19:59         ` Matheus Bernardino
2026-03-25  1:18           ` Taylor Simpson
2026-03-23 13:15 ` [PATCH 05/13] target/hexagon: add v68 HVX IEEE float min/max insns Matheus Tavares Bernardino
2026-03-23 20:47   ` Taylor Simpson
2026-03-24 20:15     ` Matheus Bernardino
2026-03-23 13:15 ` [PATCH 06/13] target/hexagon: add v68 HVX IEEE float misc insns Matheus Tavares Bernardino
2026-03-23 21:08   ` Taylor Simpson
2026-03-24 20:25     ` Matheus Bernardino
2026-03-23 13:15 ` [PATCH 07/13] target/hexagon: add v68 HVX IEEE float conversion insns Matheus Tavares Bernardino
2026-03-23 21:25   ` Taylor Simpson
2026-03-24 21:04     ` Matheus Bernardino [this message]
2026-03-25  1:15       ` Taylor Simpson
2026-03-23 13:15 ` [PATCH 08/13] target/hexagon: add v68 HVX IEEE float compare insns Matheus Tavares Bernardino
2026-03-23 21:42   ` Taylor Simpson
2026-03-26 13:00     ` Matheus Bernardino
2026-03-23 13:15 ` [PATCH 09/13] target/hexagon: add v73 HVX IEEE bfloat16 insns Matheus Tavares Bernardino
2026-03-23 22:03   ` Taylor Simpson
2026-03-23 13:15 ` [PATCH 10/13] tests/hexagon: add tests for v68 HVX IEEE float arithmetics Matheus Tavares Bernardino
2026-03-24 19:05   ` Taylor Simpson
2026-03-23 13:15 ` [PATCH 11/13] tests/hexagon: add tests for v68 HVX IEEE float min/max Matheus Tavares Bernardino
2026-03-24 19:07   ` Taylor Simpson
2026-03-23 13:15 ` [PATCH 12/13] tests/hexagon: add tests for v68 HVX IEEE float conversions Matheus Tavares Bernardino
2026-03-24 19:30   ` Taylor Simpson
2026-03-23 13:15 ` [PATCH 13/13] tests/hexagon: add tests for v68 HVX IEEE float comparisons Matheus Tavares Bernardino
2026-03-24 19:37   ` Taylor Simpson

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=CABrGZ+GO+G2MrnP1W69vsSCrX_QcEsJw5Zhkd5yd_uhdoegpFQ@mail.gmail.com \
    --to=matheus.bernardino@oss.qualcomm.com \
    --cc=ale@rev.ng \
    --cc=anjo@rev.ng \
    --cc=brian.cain@oss.qualcomm.com \
    --cc=ltaylorsimpson@gmail.com \
    --cc=marco.liebel@oss.qualcomm.com \
    --cc=philmd@linaro.org \
    --cc=qemu-devel@nongnu.org \
    --cc=quic_mburton@quicinc.com \
    --cc=sid.manning@oss.qualcomm.com \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox