Re: [Beignet] [PATCH] GBE: Remove TBAA.

Please skip this patch. I have sent another patch to solve the problem. Ruiling > -Original Message- > From: Song, Ruiling > Sent: Wednesday, October 18, 2017 11:03 AM > To: beignet@lists.freedesktop.org > Cc: Song, Ruiling <ruiling.s...@intel.com> > Subject:

Re: [Beignet] [Patch V2 2/2] GBE: enable llvm5.0 support.

This version looks good! Ruiling -Original Message- From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of Yang Rong Sent: Wednesday, September 20, 2017 4:18 PM To: beignet@lists.freedesktop.org Cc: Yang, Rong R Subject: [Beignet] [Patch V2

Re: [Beignet] [PATCH] libocl: Consider only bottom ilogb(2m-1)+1 bits

LGTM Ruiling -Original Message- From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of Jan Vesely Sent: Tuesday, September 19, 2017 1:13 PM To: beignet@lists.freedesktop.org Subject: [Beignet] [PATCH] libocl: Consider only bottom ilogb(2m-1)+1 bits Signed-off-by: Jan

Re: [Beignet] [PATCH] libocl: Add shuffle and shuffle2 builtins for half type

LGTM Ruiling -Original Message- From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of Jan Vesely Sent: Tuesday, September 19, 2017 12:17 PM To: beignet@lists.freedesktop.org Subject: [Beignet] [PATCH] libocl: Add shuffle and shuffle2 builtins for half type

Re: [Beignet] [PATCH] Runtime: fix a build warning.

LGTM Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Yang Rong > Sent: Wednesday, July 12, 2017 6:33 PM > To: beignet@lists.freedesktop.org > Cc: Yang, Rong R > Subject: [Beignet] [PATCH] Runtime: fix a

Re: [Beignet] [PATCH] GBE: fix a errMsg uninitialized build warning.

LGTM Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Yang Rong > Sent: Thursday, July 27, 2017 1:46 PM > To: beignet@lists.freedesktop.org > Cc: Yang, Rong R > Subject: [Beignet] [PATCH] GBE: fix a errMsg

Re: [Beignet] [PATCH] Runtime: fix the context ref is not 0 assert when delete.

LGTM Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Yang Rong > Sent: Thursday, July 20, 2017 1:40 PM > To: beignet@lists.freedesktop.org > Cc: Yang, Rong R > Subject: [Beignet] [PATCH] Runtime: fix the

Re: [Beignet] [PATCH] GBE: Fix a assert in CleanLlvmResource.

I think using atexit() in a dlopen library may be unsafe. Take a look at this. https://stackoverflow.com/questions/17350308/atexit-considered-harmful "Interaction of atexit with dlopen or other methods of loading libraries dynamically is not defined. A library which has registered atexit handlers

Re: [Beignet] [PATCH] Runtime: fix a cl_gpgpu_bind_image_for_vme NULL SIGSEGV.

LGTM! the function pointer may be null for some platform. Thanks! Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Yang Rong > Sent: Friday, July 21, 2017 12:11 PM > To: beignet@lists.freedesktop.org > Cc: Yang, Rong R

Re: [Beignet] [Patch V2] cmake: add option OCL_ICD_INSTALL_PREFIX to set icd file install path.

Looks good. Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Yang Rong > Sent: Wednesday, April 26, 2017 2:04 PM > To: beignet@lists.freedesktop.org > Cc: Yang, Rong R > Subject: [Beignet] [Patch V2] cmake:

Re: [Beignet] [PATCH] backend: refine global immediate optimization

Hi Yang Rong, Please help merge this patch. These lines of code cause build error. And in fact they are not needed. Hi Yichao, Sorry for this. In fact these two lines of code should be removed. Thanks! Ruiling > -Original Message- > From: Beignet

Re: [Beignet] [PATCH 1/3] Runtime: fix a recurrent release context error.

> -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Yang Rong > Sent: Tuesday, June 20, 2017 7:08 PM > To: beignet@lists.freedesktop.org > Cc: Yang, Rong R > Subject: [Beignet] [PATCH 1/3] Runtime: fix a recurrent

Re: [Beignet] [PATCH V4] backend: add global immediate optimization

LGTM Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > rander.wang > Sent: Wednesday, June 14, 2017 1:56 PM > To: beig...@freedesktop.org > Cc: Wang, Rander > Subject: [Beignet] [PATCH V4] backend: add

Re: [Beignet] [PATCH V2] backend: refine load/store merging algorithm

LGTM Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > rander.wang > Sent: Friday, June 16, 2017 9:50 AM > To: beig...@freedesktop.org > Cc: Wang, Rander > Subject: [Beignet] [PATCH V2] backend: refine

Re: [Beignet] [PATCH V2] backend: add global immediate optimization

> -Original Message- > From: Wang, Rander > Sent: Tuesday, June 13, 2017 1:24 PM > To: Song, Ruiling <ruiling.s...@intel.com>; beig...@freedesktop.org > Subject: RE: [Beignet] [PATCH V2] backend: add global immediate optimization > > > > -----O

Re: [Beignet] [PATCH V2] backend: add global immediate optimization

> + else if (src0.type == GEN_TYPE_D || src0.type == GEN_TYPE_UD) > + { > +int s0 = src0.value.d; > +if (src0.absolute) > + s0 = fabs(s0); Here I think it should be abs(s0), right? > +if (src0.negation) > + s0 = -s0;

Re: [Beignet] Can I still compile for SandyBridge ?

Hi Adrian, Beignet has never supported SandyBridge(SNB) since project start. Even if you make some modification to let the source code compile successfully, You will still fail to run any OpenCL program as the OpenCL compiler in Beignet only target graphics processor since IvyBridge. Thanks!

Re: [Beignet] Random error with very low prabability in Haswell platform

Do you mean the ECC (Error Correcting Codes) on Intel GPU by “hardware mistakes”? Intel GPU adds one bit ECC support to L3 Cache since Broadwell. For details, you can look at: https://01.org/sites/default/files/documentation/intel-gfx-prm-osrc-bdw-vol07-3d_media_gpgpu_3.pdf I am not sure whether

Re: [Beignet] [PATCH newRT] Add cl_gen_device_common.h file.

> -Original Message- > From: Rebecca N. Palmer [mailto:rebecca_pal...@zoho.com] > Sent: Friday, April 7, 2017 2:50 PM > To: Song, Ruiling <ruiling.s...@intel.com>; beignet@lists.freedesktop.org > Subject: Re: [Beignet] [PATCH newRT] Add cl_gen_device_common.h

Re: [Beignet] [PATCH 1/2] Backend: Store the spill register information

> -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Xiuli Pan > Sent: Thursday, March 23, 2017 3:13 PM > To: beignet@lists.freedesktop.org > Cc: Pan, Xiuli > Subject: [Beignet] [PATCH 1/2] Backend: Store the spill

Re: [Beignet] [PATCH newRT] Add cl_gen_device_common.h file.

> -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Rebecca N. Palmer > Sent: Friday, March 31, 2017 2:37 PM > To: beignet@lists.freedesktop.org > Subject: Re: [Beignet] [PATCH newRT] Add cl_gen_device_common.h file. > > +#ifdef

Re: [Beignet] [PATCH] backend: add double support to fmax

> -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > rander > Sent: Monday, March 27, 2017 5:40 PM > To: beig...@freedesktop.org > Cc: Wang, Rander > Subject: [Beignet] [PATCH] backend: add double support to fmax > >

Re: [Beignet] [PATCH] utests: add utest to double version of log, log2, log10

> -Original Message- > From: Wang, Rander > Sent: Wednesday, March 29, 2017 1:12 PM > To: Song, Ruiling <ruiling.s...@intel.com>; beig...@freedesktop.org > Subject: RE: [Beignet] [PATCH] utests: add utest to double version of log, > log2, > log10 > > A

Re: [Beignet] [PATCH] utests: add utest to double version of log, log2, log10

> +static void builtin_double_logx(void) > +{ > + // Setup kernel and buffers > + int k, i, index_cur; > + unsigned long gpu_data[max_function * count_input] = {0}; > + float diff; > + char log[256] = {0}; > + > + OCL_CREATE_KERNEL("builtin_double_logx"); > + I just thought of a problem.

Re: [Beignet] [PATCH 5/7] Backend: Refine LLVM version check macro

> -#if LLVM_VERSION_MAJOR == 3 && LLVM_VERSION_MINOR >= 9 > +#if LLVM_VERSION_MAJOR * 10 + LLVM_VERSION_MINOR >= 39 I think it is better to add "LLVM_VERSION" in llvm_includes.hpp: #define LLVM_VERSION (LLVM_VERSION_MAJOR * 10 + LLVM_VERSION_MINOR) So at each place we only check LLVM_VERSION

Re: [Beignet] [PATCH] intel: Check that we can reserve the zero-offset

I am Ok with this. Ruiling ___ Beignet mailing list Beignet@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/beignet

Re: [Beignet] [PATCH v2] Provide more possible candidate of load/store as possible.

may not be applied to other platform. How much will the patch affect the compile time? From: yan.wang [mailto:yan.w...@linux.intel.com] Sent: Friday, March 10, 2017 10:52 AM To: Song, Ruiling <ruiling.s...@intel.com>; beignet <beignet@lists.freedesktop.org> Subject: Re: Re: [Beigne

Re: [Beignet] [PATCH 5/5] Backend: add double support to bitselect

LGTM - Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > rander > Sent: Tuesday, March 7, 2017 9:56 AM > To: beig...@freedesktop.org > Cc: Wang, Rander > Subject: [Beignet] [PATCH 5/5] Backend: add double

Re: [Beignet] [PATCH 4/4] Backend:add double support for some relation function

LGTM - Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > rander > Sent: Monday, March 6, 2017 5:48 PM > To: beig...@freedesktop.org > Cc: Wang, Rander > Subject: [Beignet] [PATCH 4/4] Backend:add double

Re: [Beignet] [PATCH v2] Provide more possible candidate of load/store as possible.

> -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > yan.w...@linux.intel.com > Sent: Thursday, March 9, 2017 5:41 PM > To: beignet@lists.freedesktop.org > Cc: Yan Wang > Subject: [Beignet] [PATCH v2] Provide more

Re: [Beignet] [PATCH 2/2] Backend: refine the geometry function

> -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > rander > Sent: Monday, March 6, 2017 10:20 AM > To: beignet@lists.freedesktop.org > Cc: Wang, Rander > Subject: [Beignet] [PATCH 2/2] Backend: refine the geometry

Re: [Beignet] [PATCH 7/7] Backend: for BDW and after, According to BSpec no need to split CMP when src is DW DF

LGTM Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > rander > Sent: Tuesday, March 7, 2017 10:25 AM > To: beig...@freedesktop.org > Cc: Wang, Rander > Subject: [Beignet] [PATCH 7/7] Backend: for BDW and

Re: [Beignet] [PATCH] Backend: for BDW and after, According to BSpec no need to split CMP when src is DW DF

> -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > rander > Sent: Monday, February 27, 2017 12:25 PM > To: beignet@lists.freedesktop.org > Cc: Wang, Rander > Subject: [Beignet] [PATCH] Backend: for BDW and after,

Re: [Beignet] [PATCH] Backend: for BDW and after, According to BSpec no need to split CMP when src is DW DF

> -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > rander > Sent: Friday, February 17, 2017 10:42 AM > To: beignet@lists.freedesktop.org > Cc: Wang, Rander > Subject: [Beignet] [PATCH] Backend: for BDW and after,

Re: [Beignet] [PATCH] add selection IR SEL_OP_LABEL and SEL_OP_BRANCH.

> -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > xionghu@intel.com > Sent: Wednesday, February 8, 2017 6:59 PM > To: beignet@lists.freedesktop.org > Cc: Luo, Xionghu > Subject: [Beignet] [PATCH] add selection

Re: [Beignet] [PATCH v3 2/3] revert patch 2edb7451a8f92295f79e29ef16740b5cd16127f2.

The patchset LGTM. Thanks for you hard work to make the code more clean! - Ruiling ___ Beignet mailing list Beignet@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/beignet

Re: [Beignet] [PATCH 1/2] GBE: use shl instead of multiply as possible.

The patchset LGTM Ruiling ___ Beignet mailing list Beignet@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/beignet

Re: [Beignet] [PATCH] Doc: add OpenCL 2.0 section to readme.

Basically looks good, But some typos. > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Yang Rong > Sent: Friday, January 20, 2017 5:34 PM > To: beignet@lists.freedesktop.org > Cc: Yang, Rong R > Subject: [Beignet]

Re: [Beignet] [PATCH] Doc: add android build howto.

Looks good, only some grammar suggestions. > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Yang Rong > Sent: Friday, January 20, 2017 5:41 PM > To: beignet@lists.freedesktop.org > Cc: Yang, Rong R > Subject:

Re: [Beignet] [Patch V2 1/2] GBE: fix legacy read64 mix pointer bug.

LG - Ruiling ___ Beignet mailing list Beignet@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/beignet

Re: [Beignet] [PATCH] GBE: fix two mix pointer bug.

> -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Yang Rong > Sent: Friday, January 6, 2017 10:59 PM > To: beignet@lists.freedesktop.org > Cc: Yang, Rong R > Subject: [Beignet] [PATCH] GBE: fix two mix pointer bug. >

Re: [Beignet] [Patch V2] GBE: correct the llvm.loop.unroll.enable meta.

> -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Yang Rong > Sent: Thursday, December 29, 2016 6:32 PM > To: beignet@lists.freedesktop.org > Cc: Yang, Rong R > Subject: [Beignet] [Patch V2] GBE: correct the

Re: [Beignet] [PATCH] eliminate build warnings in i386 system.

LGTM - Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Yang Rong > Sent: Thursday, December 8, 2016 6:03 PM > To: beignet@lists.freedesktop.org > Cc: Meng Mengmeng ; Yang, Rong R >

Re: [Beignet] [PATCH] Add the NULL pointer check.

Looks good. - Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Yang Rong > Sent: Friday, December 16, 2016 5:00 PM > To: beignet@lists.freedesktop.org > Cc: Yang, Rong R > Subject: [Beignet] [PATCH] Add the

Re: [Beignet] [PATCH 2/2] utest: suspend deprecated-declarations warning.

The patchset LGTM > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Yang Rong > Sent: Wednesday, December 7, 2016 5:16 PM > To: beignet@lists.freedesktop.org > Cc: Yang, Rong R > Subject: [Beignet] [PATCH 2/2] utest:

Re: [Beignet] [PATCH] Avoid possible invalid pointer by vector interator.

Looks good. Thanks for the fix. - Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > yan.w...@linux.intel.com > Sent: Wednesday, December 28, 2016 4:28 PM > To: beignet@lists.freedesktop.org > Cc: Yan Wang

Re: [Beignet] [PATCH] GBE: fix a src/dst register reuse bug.

> -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Yang Rong > Sent: Tuesday, December 20, 2016 4:47 PM > To: beignet@lists.freedesktop.org > Cc: Yang, Rong R > Subject: [Beignet] [PATCH] GBE: fix a src/dst register

Re: [Beignet] [PATCH 10/19] OCL20: enable -cl-std=CL2.0.

The first 10 patches in the patchset LGTM. As the last 9 patches are related to device_enqueue. I am not sure Xiuli would have any comments? Thanks! Ruiling ___ Beignet mailing list Beignet@lists.freedesktop.org

Re: [Beignet] [PATCH 1/3] do not touch src1 when setting instruction header

The patchset LGTM. ___ Beignet mailing list Beignet@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/beignet

Re: [Beignet] [PATCH 2/4] support sends (split send) for untyped write

> -Original Message- > From: Guo, Yejun > Sent: Thursday, November 24, 2016 10:55 AM > To: Song, Ruiling <ruiling.s...@intel.com>; beignet@lists.freedesktop.org > Subject: RE: [Beignet] [PATCH 2/4] support sends (split send) for untyped > write > >

Re: [Beignet] [PATCH v2] Fix bug: Initialize bti of LoadInstuctionPattern::shootByteGatherMsg().

Looks good. Thanks for the fix. - Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > yan.w...@linux.intel.com > Sent: Thursday, November 24, 2016 2:55 PM > To: beignet@lists.freedesktop.org > Cc: Yan Wang

Re: [Beignet] [PATCH 1/4] prepare gen9 sends binary format and enable the ASM dump for sends

> -Original Message- > From: Guo, Yejun > Sent: Thursday, November 24, 2016 10:21 AM > To: Song, Ruiling <ruiling.s...@intel.com>; beignet@lists.freedesktop.org > Subject: RE: [Beignet] [PATCH 1/4] prepare gen9 sends binary format and enable > the ASM dump for se

Re: [Beignet] [PATCH 2/4] support sends (split send) for untyped write

> -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Guo, Yejun > Sent: Tuesday, November 22, 2016 2:43 PM > To: beignet@lists.freedesktop.org > Cc: Guo, Yejun > Subject: [Beignet] [PATCH 2/4] support sends (split send)

Re: [Beignet] [PATCH 1/4] prepare gen9 sends binary format and enable the ASM dump for sends

> -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Guo, Yejun > Sent: Tuesday, November 22, 2016 2:42 PM > To: beignet@lists.freedesktop.org > Cc: Guo, Yejun > Subject: [Beignet] [PATCH 1/4] prepare gen9 sends binary

Re: [Beignet] [PATCH] intel: Check that we can reserve the zero-offset

> -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Chris Wilson > Sent: Monday, November 14, 2016 9:35 PM > To: beignet@lists.freedesktop.org > Cc: Chris Wilson > Subject: [Beignet] [PATCH] intel: Check that we

Re: [Beignet] [PATCH V3 3/3] Backend: Add hole reuse in reg alloction

> -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Xiuli Pan > Sent: Tuesday, November 1, 2016 3:17 PM > To: beignet@lists.freedesktop.org > Cc: Pan, Xiuli > Subject: [Beignet] [PATCH V3 3/3] Backend: Add hole reuse in

Re: [Beignet] [PATCH] GBE: Fix assert when get metadata llvm.loop.unroll.enable.

-Original Message- From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of Yang Rong Sent: Thursday, October 27, 2016 4:03 PM To: beignet@lists.freedesktop.org Cc: Yang, Rong R Subject: [Beignet] [PATCH] GBE: Fix assert when get metadata

Re: [Beignet] [PATCH V2 5/5] Backend: Add support for LLVM 3.9 release

Hi Rong, The patchset is good, I think we can merge it. Thanks! Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Xiuli Pan > Sent: Tuesday, September 27, 2016 1:11 PM > To: beignet@lists.freedesktop.org > Cc: Pan, Xiuli

Re: [Beignet] [PATCH] Backend: Refine replace src for write instruction

> -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Xiuli Pan > Sent: Friday, September 9, 2016 1:41 PM > To: beignet@lists.freedesktop.org > Cc: Li, Peng ; Pan, Xiuli > Subject: [Beignet] [PATCH]

Re: [Beignet] [PATCH] Runtime: Add assert of pthread_getspecific.

It's ok for me. Thanks! Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Yang, Rong R > Sent: Thursday, August 4, 2016 4:00 PM > To: beignet@lists.freedesktop.org > Subject: Re: [Beignet] [PATCH] Runtime: Add assert of

Re: [Beignet] [PATCH 1/2] FindLLVM: allow LLVM/Clang 3.8 and reorder the llvm-config priority.

LGTM Thanks! Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Yang Rong > Sent: Monday, August 1, 2016 2:48 PM > To: beignet@lists.freedesktop.org > Cc: Yang, Rong R > Subject: [Beignet] [PATCH 1/2]

Re: [Beignet] [PATCH] Runtime: fix a string overflow.

LGTM Thanks! Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Yang Rong > Sent: Monday, July 18, 2016 12:45 PM > To: beignet@lists.freedesktop.org > Cc: Yang, Rong R > Subject: [Beignet] [PATCH] Runtime:

Re: [Beignet] [PATCH 2/4] Backend: Optimization internal math, lower polynomials

Hi Grigore, After applying the patchset. Looks like some utest failed. These failure relate to gamma functions. Ocl spec requires tgamma() should be < 16ulp. Although ocl spec does not give out ulp for lgamma and lgamma_r. I think if we can make it under 16ulp. That is acceptable. Please help to

Re: [Beignet] [PATCH] GBE: handle mad with execution width of one.

Ping for review > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Ruiling Song > Sent: Thursday, July 7, 2016 3:18 PM > To: beignet@lists.freedesktop.org > Cc: Song, Ruiling <ruiling.s...@intel.com> > Subject: [B

Re: [Beignet] [PATCH 1/2] GBE: Handle null and uninitialized pointer when do pointer/bti analysis.

> -Original Message- > From: Song, Ruiling > Sent: Monday, July 4, 2016 3:58 PM > To: beignet@lists.freedesktop.org > Cc: Song, Ruiling <ruiling.s...@intel.com> > Subject: [PATCH 1/2] GBE: Handle null and uninitialized pointer when do > pointer/bti analysi

Re: [Beignet] [PATCH 4/4] Backend: Optimization internal math, use mad

This one plus the previous version three patches looks good. This is big performance improvement to the math functions. Thanks! Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Grigore Lupescu > Sent: Tuesday, July 19, 2016 4:38

Re: [Beignet] [PATCH] GBE: reorder the condition to avoid array overflow.

LGTM. The condition check should be in the new order. Thanks! Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Yang Rong > Sent: Friday, July 1, 2016 5:41 PM > To: beignet@lists.freedesktop.org > Cc: Yang, Rong R

Re: [Beignet] [Intel-gfx] [PATCH] Runtime: set the sub slice according to kernel pooled EU configure.

LGTM Ruiling > -Original Message- > From: Intel-gfx [mailto:intel-gfx-boun...@lists.freedesktop.org] On Behalf Of > Yang Rong > Sent: Wednesday, June 15, 2016 4:20 PM > To: beignet@lists.freedesktop.org; intel-...@lists.freedesktop.org; > arun.siluv...@linux.intel.com > Subject:

Re: [Beignet] [PATCH] GBE: fix a patch JMPI assert.

I am ok with this patch. Thanks! Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Yang Rong > Sent: Thursday, May 26, 2016 1:29 PM > To: beignet@lists.freedesktop.org > Cc: Yang, Rong R > Subject: [Beignet]

Re: [Beignet] [PATCH] Runtime: Use uanme to get kernel architecture.

> -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Yang Rong > Sent: Thursday, May 26, 2016 1:17 PM > To: beignet@lists.freedesktop.org > Cc: Yang, Rong R > Subject: [Beignet] [PATCH] Runtime: Use uanme to get kernel

Re: [Beignet] [PATCH 2/2] CMake: use CHECK_LIBRARY_EXISTS to check the function instead of version.

The patchset LGTM Thanks! Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Yang Rong > Sent: Wednesday, June 15, 2016 4:14 PM > To: beignet@lists.freedesktop.org > Cc: Yang, Rong R > Subject: [Beignet]

Re: [Beignet] [PATCH 2/2] Runtime: fix caffe segmentation fault when exit.

> -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Yang Rong > Sent: Tuesday, June 21, 2016 12:15 AM > To: beignet@lists.freedesktop.org > Cc: Yang, Rong R > Subject: [Beignet] [PATCH 2/2] Runtime: fix caffe

Re: [Beignet] [PATCH 2/2] GBE: warning when the GEN binary version mismatch.

>}; > - > +#define GEN_BINARY_VERSION 1 >static const unsigned char > gen_binary_header[GBHI_MAX][GEN_BINARY_HEADER_LENGTH]= \ > - {{0, 'G','E', 'N', 'C', 'B', > 'Y', 'T'}, > - {0, 'G','E', 'N', 'C',

Re: [Beignet] [PATCH] Building unit tests on Fedora 24

> -Original Message- > From: Michael Eiler [mailto:eiler.m...@gmail.com] > Sent: Wednesday, June 15, 2016 3:36 AM > To: beignet@lists.freedesktop.org > Subject: [PATCH] Building unit tests on Fedora 24 > > Hi, > > I tried to compile beignet on Fedora 24 and noticed that some unit >

Re: [Beignet] Pointer load/store - obsolete documentation?

> -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Rebecca N. Palmer > Sent: Friday, June 10, 2016 5:40 AM > To: beignet@lists.freedesktop.org > Subject: [Beignet] Pointer load/store - obsolete documentation? > > The documentation says "an

Re: [Beignet] [PATCH 4/5] Backend: Optimization internal math, use mad

The first four patches look good. But personally I don't think the 5th patch is proper for merge, although I am not good at copyright topics. Thanks! Ruiling ___ Beignet mailing list Beignet@lists.freedesktop.org

Re: [Beignet] [PATCH 4/8] OCL20: handle device enqueue helper functions in the backend.

> diff --git a/backend/src/llvm/llvm_gen_backend.cpp > b/backend/src/llvm/llvm_gen_backend.cpp > index 1c41207..033e7de 100644 > --- a/backend/src/llvm/llvm_gen_backend.cpp > +++ b/backend/src/llvm/llvm_gen_backend.cpp > @@ -1474,9 +1474,6 @@ namespace gbe >return; > } > if

Re: [Beignet] [PATCH 1/3] Benchmark: Evaluate math performance on intervals

> -Original Message- > From: Lupescu, Grigore > Sent: Wednesday, May 4, 2016 3:06 PM > To: Song, Ruiling <ruiling.s...@intel.com>; beignet@lists.freedesktop.org > Subject: RE: [Beignet] [PATCH 1/3] Benchmark: Evaluate math performance on > intervals >

Re: [Beignet] [PATCH 1/3] Benchmark: Evaluate math performance on intervals

> -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Grigore Lupescu > Sent: Monday, May 2, 2016 3:04 AM > To: beignet@lists.freedesktop.org > Subject: [Beignet] [PATCH 1/3] Benchmark: Evaluate math performance on > intervals > > From:

Re: [Beignet] [PATCH] GBE: try to avoid bank conflict in register allocator.

I have fix them and send v2. Thanks! > -Original Message- > From: Luo, Xionghu > Sent: Wednesday, April 27, 2016 3:18 PM > To: Song, Ruiling <ruiling.s...@intel.com>; beignet@lists.freedesktop.org > Cc: Song, Ruiling <ruiling.s...@intel.com> > Subject:

Re: [Beignet] [PATCH OCL20] Runtime: Add new param_name to clGetProgramBuildInfo

Hi Xiuli, I have made such modification in my local machine. I have just send it out to the mail list. I think we need to make a small wrapper for interp_program_get_global_constant_size(program->opaque); And I also add a minor check against is_built to make sure the program was built

Re: [Beignet] [PATCH OCL20 v2] Backend: Refine typedef of ptrint_t

It's OK for me. Thanks! Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Xiuli Pan > Sent: Friday, March 25, 2016 3:58 PM > To: beignet@lists.freedesktop.org > Cc: Pan, Xiuli > Subject: [Beignet] [PATCH OCL20

Re: [Beignet] [PATCH 3/7] GBE: add ocl 2.0 work_group_barrier support.

an > Sent: Tuesday, April 5, 2016 1:33 PM > To: Song, Ruiling <ruiling.s...@intel.com> > Cc: beignet@lists.freedesktop.org > Subject: Re: [Beignet] [PATCH 3/7] GBE: add ocl 2.0 work_group_barrier > support. > > Hi Ruiling, > > The patch set LGTM, only a small probl

Re: [Beignet] [PATCH 1/7] GBE: Fix type mismatch bug.

Please help review this version, I just rebased to latest ocl2.0 branch. You can skip previous version of these patches. Thanks! Ruiling > -Original Message- > From: Song, Ruiling > Sent: Friday, April 1, 2016 2:53 PM > To: beignet@lists.freedesktop.org > Cc: Song, Rui

Re: [Beignet] clCreateFromGLTexture working?

Beignet previously support a mesa version. But as mesa changes, things may not work correct now. So we disable the mesa extension in below commit. commit 47ebe2e96c777d9fd2ba07cef0e681eaff243fa1 Author: Zhigang Gong Date: Fri Dec 5 10:19:21 2014 +0800 CL: Don't

Re: [Beignet] [PATCH] Backend: Clang now support static, fix now

Hi Xiuli, The patch is OK for me. I would like this to be merged into OCL20 branch first. Have you done some test against master branch? I just want to make sure it does not break anything in OpenCL 1.2. Thanks! Ruiling > -Original Message- > From: Beignet

Re: [Beignet] [PATCH] Libocl: change prototype of math built-in for OCL2.0 spec

LGTM Thanks! Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Xiuli Pan > Sent: Tuesday, March 22, 2016 12:38 PM > To: beignet@lists.freedesktop.org > Cc: Pan, Xiuli > Subject: [Beignet] [PATCH] Libocl:

Re: [Beignet] [Patch v2 2/2] [OCL20] atomic_flag_test_and_set function fix.

> -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > xionghu@intel.com > Sent: Friday, March 11, 2016 11:42 PM > To: beignet@lists.freedesktop.org > Cc: Luo, Xionghu > Subject: [Beignet] [Patch v2 2/2] [OCL20]

Re: [Beignet] [PATCH v2 1/8] [OCL20] runtime: fix gcc build error.

This patchset LGTM. Thanks! Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > xionghu@intel.com > Sent: Tuesday, March 1, 2016 7:35 PM > To: beignet@lists.freedesktop.org > Cc: Luo, Xionghu > Subject:

Re: [Beignet] [PATCH] GBE: remove stacksize 64KB limitation.

Please remove the .swp files, the patch itself looks good to me. Thanks! Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Yang Rong > Sent: Tuesday, March 1, 2016 4:14 PM > To: beignet@lists.freedesktop.org > Cc: Yang, Rong R

Re: [Beignet] [PATCH v2 2/9] [OCL20] cl_mem_fence_flags definiton change from MACRO to enum

> -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > xionghu@intel.com > Sent: Thursday, February 25, 2016 12:17 AM > To: beignet@lists.freedesktop.org > Cc: Luo, Xionghu > Subject: [Beignet] [PATCH v2 2/9] [OCL20]

Re: [Beignet] Introductory questions

> -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Daniel M Gessel > Sent: Monday, February 22, 2016 7:59 PM > Cc: beignet@lists.freedesktop.org > Subject: Re: [Beignet] Introductory questions > > Thank you so much for your answers. > >

Re: [Beignet] [PATCH V2 3/3] enable byte gather for vload2/3/4/8(offset, char*) on SKL, BXT and BDW

The patchset LGTM. Thanks! Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Guo Yejun > Sent: Wednesday, February 24, 2016 4:15 AM > To: beignet@lists.freedesktop.org > Cc: Guo, Yejun > Subject: [Beignet]

Re: [Beignet] Introductory questions

> -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Daniel M Gessel > Sent: Sunday, February 21, 2016 8:13 AM > To: beignet@lists.freedesktop.org > Subject: [Beignet] Introductory questions > > Is this a good list to ask introductory

Re: [Beignet] [PATCH] Revert "GBE: disable mad for some cases."

LGTM Thanks! Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Zhigang Gong > Sent: Friday, February 19, 2016 2:08 PM > To: beignet@lists.freedesktop.org > Cc: Gong, Zhigang > Subject: [Beignet] [PATCH]

Re: [Beignet] [PATCH] GBE: remove stacksize 64KB limitation.

> -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Yang Rong > Sent: Sunday, February 14, 2016 2:42 PM > To: beignet@lists.freedesktop.org > Cc: Yang, Rong R > Subject: [Beignet] [PATCH] GBE: remove stacksize 64KB

Re: [Beignet] [PATCH V2] Backend: Add support for LLVM release 3.8

LGTM, thanks for adding 3.8 support. Thanks! Ruiling > -Original Message- > From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of > Pan Xiuli > Sent: Wednesday, January 27, 2016 2:15 PM > To: beignet@lists.freedesktop.org > Cc: Pan, Xiuli >

Re: [Beignet] MaxAtomicInlineWidth of SPIR64TargetInfo

Hi Anastasia, Do you have any comment/suggestion on this? Thanks! Ruiling From: cfe-dev [mailto:cfe-dev-boun...@lists.llvm.org] On Behalf Of Luo, Xionghu via cfe-dev Sent: Friday, January 15, 2016 12:03 PM To: 'cfe-...@lists.llvm.org' Cc: beignet@lists.freedesktop.org

Re: [Beignet] Gen 8 support

Yes, it is supported. You can have a try. Please take a look at Beignet Wiki page: http://www.freedesktop.org/wiki/Software/Beignet/ If you still have problem, you can send email to this mail list. Thanks! Ruiling From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of Andrés

Re: [Beignet] beignet git with llvm 3.7.1 + haswell (gen 7.5) failing

Yes, I agree with you. But at least as I know haswell hardware does not support double well. Hi Junyan, Can we handle it graciously? Do you have any idea? Thanks! Ruiling From: Paulo Dias [mailto:paulo.miguel.d...@gmail.com] Sent: Wednesday, January 20, 2016 8:37 PM To: Song, Ruiling

  1   2   3   4   >