Docs: OCL_STRICT_CONFORMANCE is default-on since 1.1

Submitted by Rebecca N. Palmer on Oct. 27, 2017, 7:23 p.m.

Details

Message ID ddf30f7d-e9de-11ef-68ac-805b22a21500@zoho.com
State New
Series "Docs: OCL_STRICT_CONFORMANCE is default-on since 1.1"
Headers show

Commit Message

Rebecca N. Palmer Oct. 27, 2017, 7:23 p.m.
Signed-off-by: Rebecca N. Palmer <rebecca_palmer@zoho.com>

Patch hide | download patch | download mbox

--- a/docs/Beignet/Backend.mdwn
+++ b/docs/Beignet/Backend.mdwn
@@ -37,9 +37,7 @@  Environment variables are used all over
   precision math instructions compliant with OpenCL Spec. So we provide a
   software version to meet the high precision requirement. Obviously the
   software version's performance is not as good as native version supported by
-  GEN hardware. What's more, most graphics application don't need this high
-  precision, so we choose 0 as the default value. So OpenCL apps do not suffer
-  the performance penalty for using high precision math functions.
+  GEN hardware.
 
 - `OCL_SIMD_WIDTH` `(8 or 16)`. Select the number of lanes per hardware thread,
   Normally, you don't need to set it, we will select suitable simd width for

Comments

Yang, Rong R Nov. 1, 2017, 8:03 a.m.
LGTM, pushed, thanks.

> -----Original Message-----

> From: Beignet [mailto:beignet-bounces@lists.freedesktop.org] On Behalf Of

> Rebecca N. Palmer

> Sent: Saturday, October 28, 2017 3:24 AM

> To: beignet@lists.freedesktop.org

> Subject: [Beignet] [PATCH] Docs: OCL_STRICT_CONFORMANCE is default-on

> since 1.1

> 

> Signed-off-by: Rebecca N. Palmer <rebecca_palmer@zoho.com>

> 

> --- a/docs/Beignet/Backend.mdwn

> +++ b/docs/Beignet/Backend.mdwn

> @@ -37,9 +37,7 @@ Environment variables are used all over

>    precision math instructions compliant with OpenCL Spec. So we provide a

>    software version to meet the high precision requirement. Obviously the

>    software version's performance is not as good as native version supported by

> -  GEN hardware. What's more, most graphics application don't need this high

> -  precision, so we choose 0 as the default value. So OpenCL apps do not suffer

> -  the performance penalty for using high precision math functions.

> +  GEN hardware.

> 

>  - `OCL_SIMD_WIDTH` `(8 or 16)`. Select the number of lanes per hardware

> thread,

>    Normally, you don't need to set it, we will select suitable simd width for

> 

> _______________________________________________

> Beignet mailing list

> Beignet@lists.freedesktop.org

> https://lists.freedesktop.org/mailman/listinfo/beignet