Reviewed-by: Bruce Cherniak
> On May 11, 2017, at 12:59 PM, Tim Rowley wrote:
>
> This change fixes the build break with llvm-svn.
>
> r301981 of llvm-svn made add/remove of function attributes
> use AttrBuilder instead of AttributeList.
>
> Tested with llvm-3.9, llvm-4.0, llvm-svn.
> ---
>
Reviewed-by: Bruce Cherniak
> On Nov 13, 2017, at 8:03 PM, Tim Rowley wrote:
>
> Speed up avx512 platforms; fixes performance regression caused
> by swithc to simdlib.
>
> Cc: mesa-sta...@lists.freedesktop.org
> ---
> .../drivers/swr/rasterizer/common/simdlib_512_avx512.inl | 12 +
Reviewed-by: Bruce Cherniak
> On Nov 13, 2017, at 8:03 PM, Tim Rowley wrote:
>
> Speed up simd16 frontend (default) on avx/avx2 platforms;
> fixes performance regression caused by switch to simdlib.
>
> Cc: mesa-sta...@lists.freedesktop.org
> ---
> .../swr/rasterizer/common/simdlib_512_emu.in
Reviewed-by: Bruce Cherniak
> On Nov 20, 2017, at 11:18 AM, Tim Rowley wrote:
>
> Highlights are code cleanups and more progress on simd16.
>
> Tim Rowley (10):
> swr/rast: support flexible vertex layout for DS output
> swr/rast: Widen fetch shader to SIMD16
> swr/rast: Code style change (N
Reviewed-by: Bruce Cherniak
> On Jun 15, 2017, at 1:37 PM, Tim Rowley wrote:
>
> Highlights include: jit cache (disabled currently), work in progress
> to shrink the vertex structure used in the frontend, and refactoring
> to speed recompiles if simdintrin.h is changed.
>
> Tim Rowley (16):
>
> On Jun 22, 2017, at 2:23 AM, Michel Dänzer wrote:
>
> On 13/06/17 01:55 AM, Marek Olšák wrote:
>> From: Marek Olšák
>
> This broke piglit spec@glsl-1.20@execution@clipping@fixed-clip-enables
> on my Kaveri:
I am seeing this same regression on llvmpipe and swr renderers. Anyone else?
(bisec
ts/spec/glsl-1.20/execution/clipping/fixed-clip-enables.shader_test -auto
-fbo
Regards,
Bruce
> Marek
>
> On Fri, Jun 23, 2017 at 9:16 PM, Cherniak, Bruce
> wrote:
>>
>>> On Jun 22, 2017, at 2:23 AM, Michel Dänzer wrote:
>>>
>>> On 13/06/17 01:5
Reviewed-by: Bruce Cherniak
> On Jun 26, 2017, at 9:34 AM, Eric Engestrom wrote:
>
> On Monday, 2017-06-26 09:03:13 -0500, Tim Rowley wrote:
>> Some combinations of c++ compilers and standard libraries had problems
>> with the string::replace code we were using previously.
>>
>> This should fi
Back in February, I submitted a patch for review to address an a crash in
GALLIUM_TRACE.
It never got a review, and I forgot to follow up on it. Is this a correct fix
and useful to anyone
else?
Thanks,
Bruce
From patchwork Wed Feb 1 20:20:38 2017
Content-Type: text/plain; charset="utf-
this a valid fix? It prevents a crash that happens on occasion
while running
GALLIUM_TRACE.
I too would be interested in learning how to replay traces. Would be very
handy.
Thanks,
Bruce
> Marek
>
> On Mon, Jun 26, 2017 at 6:28 PM, Cherniak, Bruce
> wrote:
>> Back in Feb
Reviewed-by: Bruce Cherniak
> On Jun 27, 2017, at 1:09 PM, Tim Rowley wrote:
>
> Highlights include splitting the heavily templated files into multiple
> chunks to speed compile (2x for a large machine), and switching the
> simd intrinsic usage from a macro-based header to a more c++ feeling
>
Reviewed-by: Bruce Cherniak
> On Jun 29, 2017, at 10:07 AM, Tim Rowley wrote:
>
> Reduces the memory footprint of the frontend processing by packing
> vertices.
> ---
> src/gallium/drivers/swr/swr_draw.cpp | 6 --
> 1 file changed, 4 insertions(+), 2 deletions(-)
>
> diff --git a/src/galliu
Reviewed-by: Bruce Cherniak
> On Jun 30, 2017, at 11:52 AM, Tim Rowley wrote:
>
> Tag pStat field in swr_draw_context structure so gen_llvm_types.py
> can deal with the actual structure type instead of using void.
>
> Code cleanup, no functional change.
> ---
> src/gallium/drivers/swr/swr_con
On Jul 4, 2017, at 9:40 AM, Jose Fonseca
mailto:jfons...@vmware.com>> wrote:
On 29/06/17 11:02, Michel Dänzer wrote:
On 29/06/17 01:54 AM, Cherniak, Bruce wrote:
On Jun 26, 2017, at 2:10 PM, Marek Olšák
mailto:mar...@gmail.com>> wrote:
In my opinion, dumping resources isn'
Reviewed-by: Bruce Cherniak
> On Jul 6, 2017, at 11:26 AM, Tim Rowley wrote:
>
> Define these in terms of setzero for ancient gcc versions which don't
> have the undefined intrinsics.
>
> Cc: mesa-sta...@lists.freedesktop.org
> ---
> src/gallium/drivers/swr/rasterizer/common/os.h | 6 ++
>
Reviewed-by: Bruce Cherniak
> On Jul 6, 2017, at 11:26 AM, Tim Rowley wrote:
>
> ---
> src/gallium/drivers/swr/rasterizer/jitter/fetch_jit.cpp | 2 --
> src/gallium/drivers/swr/rasterizer/jitter/streamout_jit.cpp | 2 --
> 2 files changed, 4 deletions(-)
>
> diff --git a/src/gallium/drivers/
Reviewed-by: Bruce Cherniak
> On Jul 6, 2017, at 11:26 AM, Tim Rowley wrote:
>
> ---
> src/gallium/drivers/swr/rasterizer/common/simdlib_256_avx.inl | 6 +-
> 1 file changed, 5 insertions(+), 1 deletion(-)
>
> diff --git a/src/gallium/drivers/swr/rasterizer/common/simdlib_256_avx.inl
> b/s
Reviewed-by: Bruce Cherniak
> On Jul 6, 2017, at 1:55 PM, Tim Rowley wrote:
>
> Cacheline alignment of SWR_STATS to prevent sharing of cachelines
> between threads (performance).
>
> Gets rid of gcc-7.1 warning about using c++17's over-aligned new
> feature.
>
> Cc: mesa-sta...@lists.freedesk
Reviewed-by: Bruce Cherniak
> On Jul 7, 2017, at 4:25 PM, Tim Rowley wrote:
>
> Use the SWR rasterizer API through the table returned from
> SwrGetInterface rather than referencing the functions directly.
> This will allow us to move to a model of having the driver dynamically
> load the appro
Reviewed-by: Bruce Cherniak
> On Jul 11, 2017, at 9:52 AM, Tim Rowley wrote:
>
> From: George Kyriazis
>
> Needed to expose SwrGetInterface
> ---
> src/gallium/drivers/swr/rasterizer/common/os.h | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/src/gallium/drivers/swr/
Reviewed-by: Bruce Cherniak
> On Jul 12, 2017, at 10:38 AM, Tim Rowley wrote:
>
> Highlights are read-only render targets and simd16 fixes.
>
> Tim Rowley (6):
> swr/rast: Support render target mask instead of render target count
> swr/rast: Add support for read-only render targets
> swr/r
Reviewed-by: Bruce Cherniak
> On Dec 5, 2017, at 10:50 AM, George Kyriazis
> wrote:
>
> gen_BackendPixelRate*.cpp depends on gen_ar_eventhandler.hpp.
> Fix missing dependency.
> ---
> src/gallium/drivers/swr/SConscript | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/src/gallium/drive
Reviewed-by: Bruce Cherniak
> On Dec 14, 2017, at 3:34 PM, Tim Rowley wrote:
>
> Highlights include simd16 work, thread pool initialization rework,
> and code cleanup.
>
> Tim Rowley (20):
> swr/rast: Remove unneeded copy of gather mask
> swr/rast: Binner fixes for viewport index offset han
> On Dec 17, 2017, at 10:23 AM, Andres Gomez wrote:
>
> Bruce, this depends on ead0dfe31ec7 which didn't make it for the 17.2
> queue so I will be leaving out from there.
Hi Andres, it is fine to leave out for 17.2, that branch is fine.
We would like this in 17.3 stable, however. 17.3.0 contai
This change only affects the client buffer case (swr_user_vbuf_range), not VBOs.
Reviewed with the caveat that the patch description be changed to remove "VBO"
Reviewed-by: Bruce Cherniak
> On Dec 15, 2017, at 10:22 AM, George Kyriazis
> wrote:
>
> Account for info.index_bias when calculating
Reviewed-by: Bruce Cherniak
> On Jan 2, 2018, at 10:57 AM, Tim Rowley wrote:
>
> LLVM api change.
>
> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=104381
> ---
> src/gallium/drivers/swr/rasterizer/jitter/JitManager.cpp | 4
> 1 file changed, 4 insertions(+)
>
> diff --git a/src/
On Dec 21, 2017, at 6:41 PM, Andres Rodriguez
mailto:andre...@gmail.com>> wrote:
Rename fences -> semaphores in preparation for upgrading fence
functionality.
This series renames the following symbols:
- pipe_fence_handle -> pipe_semaphore_handle
- fence_server_sync -> semaphore_server_sync
Reviewed-by: Bruce Cherniak
> On Jan 4, 2018, at 10:33 AM, Tim Rowley wrote:
>
> Should be 0x8000 instead of 0x800.
>
> Cc: mesa-sta...@lists.freedesktop.org
> ---
> src/gallium/drivers/swr/rasterizer/common/simdlib_128_avx512.inl | 2 +-
> src/gallium/drivers/swr/rasterizer/common/simd
Set Reviewed-by: Bruce Cherniak
> On Jan 4, 2018, at 12:58 PM, Tim Rowley wrote:
>
> Highlights include simd16 cleanup (renaming and removing old
> codepaths), fixing a potential crash with the fetch shader, and code
> cleanups.
>
> Tim Rowley (6):
> swr/rast: SIMD16 builder - cleanup naming
Reviewed-by: Bruce Cherniak
> On Jan 9, 2018, at 11:50 AM, George Kyriazis
> wrote:
>
> BuilderSWR::swr_gs_llvm_fetch_input() (and consequently
> swr_gs_llvm_fetch_input()), did not handle the case where
> is_vindex_indirect or is_aindex_direct is set.
>
> Implement it, using the code in dra
On Jan 16, 2018, at 1:40 PM, Chuck Atkins
mailto:chuck.atk...@kitware.com>> wrote:
Perhaps one can split out the .cpp and build changes somehow.
Good idea. It's easy enough to split and without the autoconf changes the
existing behavior will still be preserved so the other two builds can stil
With a minor comment change (below)
Reviewed-by: Bruce Cherniak
> On Jan 16, 2018, at 1:59 PM, Chuck Atkins wrote:
>
> Part 1 of 2 (part 1 is autoconf changes, part 2 is C++ changes)
>
> When only a single SWR architecture is being used, this allows that
> architecture to be builtin rather th
> On Jan 16, 2018, at 1:59 PM, Chuck Atkins wrote:
>
> Part 2 of 2 (part 1 is autoconf changes, part 2 is C++ changes)
>
> When only a single SWR architecture is being used, this allows that
> architecture to be builtin rather than as a separate libswrARCH.so that
> gets loaded via dlopen. Sin
Apologies for not seeing this over the holidays.
Reviewed-by: Bruce Cherniak
mailto:bruce.chern...@intel.com>>
On Jan 18, 2018, at 12:03 PM, Emil Velikov
mailto:emil.l.veli...@gmail.com>> wrote:
On 31 December 2017 at 16:55, Greg V
mailto:greg@unrelenting.technology>> wrote:
---
src/gallium/d
Thanks Chuck!
Reviewed-by: Bruce Cherniak
> On Jan 18, 2018, at 1:57 PM, Chuck Atkins wrote:
>
> Part 2 of 2 (part 1 is autoconf changes, part 2 is C++ changes)
>
> When only a single SWR architecture is being used, this allows that
> architecture to be builtin rather than as a separate libsw
Thanks Chuck!
Reviewed-by: Bruce Cherniak
> On Jan 18, 2018, at 1:57 PM, Chuck Atkins wrote:
>
> Part 1 of 2 (part 1 is autoconf changes, part 2 is C++ changes)
>
> When only a single SWR architecture is being used, this allows that
> architecture to be builtin rather than as a separate libsw
Entire set.
Reviewed-by: Bruce Cherniak
> On Jan 19, 2018, at 3:46 PM, George Kyriazis
> wrote:
>
> Also including:
> - enabling of SIMD16 VS
> - Early Rasterization implementation
>
> George Kyriazis (20):
> swr/rast: Fix one more invalid object format for windows.
> swr/rast: Added mis
Reviewed-by: Bruce Cherniak
> On Jan 19, 2018, at 5:03 PM, George Kyriazis
> wrote:
>
> For some reason llvm5 is picky about accepting a void * type in the
> case of building an argument list.
>
> Since we don't care about the type (we ignore the argument for now),
> pick another pointer typ
> On Sep 20, 2017, at 8:13 AM, Laurent Carlier wrote:
>
> Le mardi 19 septembre 2017, 21:25:42 CEST Tim Rowley a écrit :
>> We currently don't use these instructions, and since their API
>> changed in llvm-5.0 having them in the autogen files broke the mesa
>> release tarballs which ship with gen
> On Sep 21, 2017, at 7:46 PM, Tim Rowley wrote:
>
> One piglit regression, which was a false pass:
> spec@glsl-1.50@execution@geometry@dynamic_input_array_index
> ---
> .../drivers/swr/rasterizer/core/frontend.cpp | 227 -
> src/gallium/drivers/swr/rasterizer/core/stat
+ // control header
(SWR_VTX_NUM_SLOTS * 16) * // sizeof vertex
pGS->maxNumVerts; // num verts
On Sep 23, 2017, at 9:51 PM, Cherniak, Bruce
mailto:bruce.chern...@intel.com>> wrote:
On Sep 21, 2017, at 7:46 PM, Tim Rowley
mailto:timothy.o.row...@intel.com>> wrote:
O
Reviewed-by: Bruce Cherniak
> On Sep 21, 2017, at 7:46 PM, Tim Rowley wrote:
>
> Highlights: large change in the geometry shader api, cleanups.
>
> Tim Rowley (9):
> swr/rast: Add support for R10G10B10_FLOAT_A2_UNORM pixel format
> swr/rast: New GS state/context API
> swr/rast: Fetch compi
Reviewed-by: Bruce Cherniak
> On Sep 25, 2017, at 5:28 PM, George Kyriazis
> wrote:
>
> Swr caches fb contents in tiles. Those tiles are stored on a per-context
> basis.
>
> When switching contexts that share resources we need to make sure that
> the tiles of the old context are being store
Reviewed-by: Bruce Cherniak
> On Sep 25, 2017, at 5:28 PM, George Kyriazis
> wrote:
>
> No need to check if screen->pipe != pipe, so we can just assign it. Just do
> it.
> ---
> src/gallium/drivers/swr/swr_state.cpp | 3 +--
> 1 file changed, 1 insertion(+), 2 deletions(-)
>
> diff --git a/
Reviewed-by: Bruce Cherniak
> On Oct 3, 2017, at 3:23 PM, Tim Rowley wrote:
>
> Causing a crash in ParaView waveletcontour.py test when
> _DEBUG defined due to vector aligned copy with unaligned
> address.
> ---
> src/gallium/drivers/swr/rasterizer/core/clip.h | 4 ++--
> 1 file changed, 2 inse
Reviewed-by: Bruce Cherniak
> On Oct 11, 2017, at 10:50 AM, Rowley, Timothy O
> wrote:
>
> Start building vertex shaders as simd16.
>
> Disabled by default, set USE_SIMD16_SHADERS in knobs.h to experiment.
>
> Cc: Bruce Cherniak
> ---
> src/gallium/drivers/swr/swr_screen.cpp | 6 ++
>
Reviewed-by: Bruce Cherniak
> On Jan 5, 2017, at 11:18 AM, Tim Rowley wrote:
>
> ---
> .../drivers/swr/rasterizer/common/formats.cpp | 104 ++---
> .../drivers/swr/rasterizer/common/formats.h| 4 +
> .../drivers/swr/rasterizer/core/format_traits.h| 88 +
With minor nits that patch 5 applies to Transpose16_16 (not Transform_16_16);
and patch 6 changes the function declaration 2nd-line whitespace of
OutputMerger4x2 and OutputMerger8x2 (we can fix this in a follow-on checking to
core)
Reviewed-by: Bruce Cherniak
> On Jan 5, 2017, at 5:19 PM, Ti
This comes in very handy on a SLES11 (or similar) based install.
Reviewed-by: Bruce Cherniak
> On Jan 6, 2017, at 7:27 AM, Chuck Atkins wrote:
>
> Cc: mesa-sta...@lists.freedesktop.org
> Cc: Bruce Cherniak
> Signed-of-by: Chuck Atkins
> ---
> configure.ac|
Reviewed-by: Bruce Cherniak
> On Jan 11, 2017, at 5:19 PM, George Kyriazis
> wrote:
>
> Defer delete on regular resources. This ensures that any work being done
> on the resource is completed before freeing up the resource's memory.
> ---
> src/gallium/drivers/swr/swr_screen.cpp | 17 +---
Reviewed-by: Bruce Cherniak
> On Jan 20, 2017, at 1:44 PM, George Kyriazis
> wrote:
>
> Some query results struct contents are declared as cache line aligned.
> Use aligned malloc, and align the whole struct, to be safe.
>
> Fixes crash when compiling with clang.
>
> CC:
>
> ---
> src/gal
Reviewed-by: Bruce Cherniak
> On Jan 24, 2017, at 5:27 PM, George Kyriazis
> wrote:
>
> In swr_update_derived() update texture and sampler state on a new fragment
> shader. GALLIUM_HUD can update fs using a previously bound texture and
> sampler.
> ---
> src/gallium/drivers/swr/swr_state.cpp
Reviewed-by: Bruce Cherniak
> On Mar 27, 2017, at 1:34 PM, Tim Rowley wrote:
>
> Handle rename of llvm AttributeSet to AttributeList in the same
> fashion as ac_llvm_helper.cpp.
> ---
> src/gallium/drivers/swr/swr_shader.cpp | 24 +++-
> 1 file changed, 15 insertions(+), 9 de
Reviewed-by: Bruce Cherniak
> On Mar 27, 2017, at 1:34 PM, Tim Rowley wrote:
>
> Add CreateAlignmentAssumptionHelper to gen_llvm_ir_macros.py ignore list.
> ---
> src/gallium/drivers/swr/rasterizer/codegen/gen_llvm_ir_macros.py | 7 +++
> 1 file changed, 3 insertions(+), 4 deletions(-)
>
>
In light of dropping patch 10/10 (for now), this patch stands as-is.
Windows/SCONS build will be addressed in a followup.
This patch:
Reviewed-by: Bruce Cherniak
mailto:bruce.chern...@intel.com>>
On Mar 27, 2017, at 7:35 PM, Kyriazis, George
mailto:george.kyria...@intel.com>> wrote:
With thi
Entire set… Reviewed-by: Bruce Cherniak
> On Apr 4, 2017, at 1:16 PM, Tim Rowley wrote:
>
> Highlights include simd16 work, msaa enhancements, and removing the
> extra copy of mako we included.
>
> Tim Rowley (9):
> swr: [rasterizer core] SIMD16 Frontend WIP
> swr: [rasterizer core/memory] F
Reviewed-by: Bruce Cherniak
> On Apr 6, 2017, at 7:10 PM, Tim Rowley wrote:
>
> ---
> src/gallium/drivers/swr/swr_screen.cpp | 1 -
> src/gallium/drivers/swr/swr_shader.cpp | 1 -
> 2 files changed, 2 deletions(-)
>
> diff --git a/src/gallium/drivers/swr/swr_screen.cpp
> b/src/gallium/drivers/s
Thanks for the review. You’re correct, even though FBOs work, there are still
a number of apps that rely on msaa in the winsys buffers and we don’t want to
artificially exclude them.
> On Apr 7, 2017, at 12:54 PM, Roland Scheidegger wrote:
>
> I'm not an expert on glx, but looks alright to me
Entire set Reviewed-by: Bruce Cherniak
> On Apr 10, 2017, at 11:45 AM, Tim Rowley wrote:
>
> Highlights; compile time fix, simd16 work, code cleanup.
>
> Tim Rowley (12):
> swr: [rasterizer core] Reduce templates to speed compile
> swr: [rasterizer core] Multisample sample position setup cha
Reviewed-by: Bruce Cherniak
> On Apr 13, 2017, at 3:30 PM, George Kyriazis
> wrote:
>
> Add polygon stipple functionality to the fragment shader.
>
> Explicitly turn off polygon stipple for lines and points, since we
> do them using tris.
> ---
> src/gallium/drivers/swr/swr_context.h | 4 ++
Reviewed-by: Bruce Cherniak
> On Apr 13, 2017, at 1:41 PM, Tim Rowley wrote:
>
> ---
> src/gallium/docs/source/drivers/openswr.rst | 2 +-
> src/gallium/docs/source/drivers/openswr/usage.rst | 9 +++--
> 2 files changed, 4 insertions(+), 7 deletions(-)
>
> diff --git a/src/gallium/docs
Reviewed-by: Bruce Cherniak
> On Apr 14, 2017, at 2:03 PM, Tim Rowley wrote:
>
> v2: add back scons section, mention additional built swr libraries
> ---
> src/gallium/docs/source/drivers/openswr.rst | 2 +-
> src/gallium/docs/source/drivers/openswr/usage.rst | 16 +++-
> 2 fil
Reviewed-by: Bruce Cherniak
> On Apr 19, 2017, at 8:41 AM, Tim Rowley wrote:
>
> Build VS with alternating output for the current simd16 fe double-pump
> of a simd8 shader.
> ---
> src/gallium/drivers/swr/swr_shader.cpp | 30 +-
> 1 file changed, 25 insertions(+), 5
Reviewed-by: Bruce Cherniak
(and thanks for not emailing such a huge patch)
> On Jun 8, 2018, at 3:01 PM, Alok Hota wrote:
>
> Sorry for the large patch - the changes are all whitespace and code
> formatting for the swr driver and its rasterizer.
> The patch file itself is available on Github
> On Jun 18, 2018, at 9:23 AM, Juan A. Suarez Romero
> wrote:
>
> RADV now requires LLVM 5.0 or greater, and thus we can't build dist
> tarball because swr requires LLVM 4.0.
>
> Let's bump required LLVM to 5.0 in swr too.
Sorry, I didn't see this sooner. We are fine with bumping the swr min
Reviewed-by: Bruce Cherniak
> On Jun 19, 2018, at 10:03 AM, Alok Hota wrote:
>
> These code changes were made in between some of the formatting changes.
> Unforunately we do have another formatting patch coming in after this,
> but I will keep that separate.
>
> These patches are primarily foc
Reviewed-by: Bruce Cherniak
> On Jun 22, 2018, at 9:11 AM, Alok Hota wrote:
>
> ---
> .../swr/rasterizer/jitter/JitManager.cpp | 133 ++--
> .../swr/rasterizer/jitter/builder_gfx_mem.cpp | 90 +
> .../swr/rasterizer/jitter/builder_gfx_mem.h | 101 +-
> .../jitter/f
Reviewed-by: Bruce Cherniak
> On Jun 25, 2018, at 9:52 AM, Alok Hota wrote:
>
> ---
> .../swr/rasterizer/jitter/builder_gfx_mem.cpp | 13 +
> .../drivers/swr/rasterizer/jitter/builder_gfx_mem.h | 6 ++
> 2 files changed, 19 insertions(+)
>
> diff --git a/src/gallium/driver
v2 Reviewed-by: Bruce Cherniak
> On Jun 25, 2018, at 9:52 AM, Alok Hota wrote:
>
> These code changes were made in between some of the formatting changes.
> Unforunately we do have another formatting patch coming in after this,
> but I will keep that separate.
>
> These patches are primarily
Reviewed-by: Bruce Cherniak
> On Jun 28, 2018, at 2:17 PM, Alok Hota wrote:
>
> Sorry for the churn on these patches. They had to be split in three due
> to some code change in between a mass formatting change. Anyway this
> patch contains only formatting changes for the files that were update
Entire patch set Reviewed-by: Bruce Cherniak
> On Apr 17, 2018, at 8:31 PM, George Kyriazis
> wrote:
>
>
> Lots of SWR-specifc changes, including:
> - work for 16-wide simd operation across all avx flavors
> - separate avx instrinsics into a separate x86 lowering pass
> - stats work
> - mis
Reviewed-by: Bruce Cherniak
> On Apr 25, 2018, at 2:21 PM, George Kyriazis
> wrote:
>
> Misc changes. Include:
> - fix KNL behavior with LLVm 6.0.0
> - fix byte offset for non-indexed draws
> - fix 64-bit float handling with code generator
> - misc cleanup
>
> George Kyriazis (21):
> swr/r
Reviewed-by: Bruce Cherniak
> On May 4, 2018, at 1:40 PM, George Kyriazis wrote:
>
> Misc OpenSWR changes
>
> George Kyriazis (7):
> swr/rast: Change formatting
> swr/rast: Use binner topology to assemble backend attributes
> swr/rast: Add constant initializer for uint64_t
> swr/rast: Add
On May 14, 2018, at 8:59 AM, Alexandre
mailto:alexandre.gauthier-foic...@inria.fr>>
wrote:
Hello,
Sorry for the inconvenience if this message is not appropriate for this mailing
list.
The following is a question for developers of the swr driver of gallium.
I am the main developer of a motio
Patchset (1/7)
Reviewed-by: Bruce Cherniak
> On May 23, 2018, at 2:58 PM, Alok Hota wrote:
>
> SCATTERPS previously assumed it was being used with an existing basic
> block
> ---
> .../drivers/swr/rasterizer/jitter/builder_mem.cpp | 29 +++---
> 1 file changed, 20 insertions(+)
Entire patchset: 1-7 (What I meant to say in the first place)
Reviewed-by: Bruce Cherniak
> On May 24, 2018, at 11:13 AM, Cherniak, Bruce
> wrote:
>
> Patchset (1/7)
> Reviewed-by: Bruce Cherniak
>
>> On May 23, 2018, at 2:58 PM, Alok Hota wrote:
>>
>
V2: Good catch!
Reviewed-by: Bruce Cherniak
> On May 25, 2018, at 10:19 AM, Alok Hota wrote:
>
> Version 2 makes a small change to swr_loader.cpp to include the new InitMemory
> header, which fixes a compile error on single-architecture builds.
>
> Alok Hota (7):
> swr/rast: Added in-place b
Hello and apologies for such a delayed response — we were quite busy with the
SC’18
supercomputing conference.
On Oct 17, 2018, at 3:37 PM, Roland Scheidegger
mailto:srol...@vmware.com>> wrote:
Am 17.10.18 um 19:15 schrieb Gert Wollny:
Dear all,
we are looking into doing a CI for virglrenderer
Reviewed-by: Bruce Cherniak
> On Feb 27, 2018, at 2:12 PM, George Kyriazis
> wrote:
>
> v2 is a merged patchset of the following email threads:
> <1519312447-27403-1-git-send-email-george.kyria...@intel.com>
> <1519317122-3529-1-git-send-email-george.kyria...@intel.com>
>
> The cc to mesa-st
Reviewed-by: Bruce Cherniak
> On Feb 28, 2018, at 1:16 PM, George Kyriazis
> wrote:
>
> Populate pLastIndex, even for the non-indexed case. An zero pLastIndex
> can cause the index offsets inside the fetcher to have non-sensical values
> that can be either very large positive or very large n
patch set (1 through 9) Reviewed-by: Bruce Cherniak
> On Mar 7, 2018, at 7:32 PM, George Kyriazis wrote:
>
> ---
> src/gallium/drivers/swr/rasterizer/jitter/builder_mem.cpp | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/src/gallium/drivers/swr/rasterizer/jitter/builder_mem.cpp
> b/s
We don't currently build SWR on OS X, I've had difficulty building Mesa on OS X
in general.
But, I'd be very interesting in learning. Thanks for the patch.
Reviewed-by: Bruce Cherniak
> On Mar 14, 2018, at 6:19 PM, Jeremy Huddleston Sequoia
> wrote:
>
> From: Apple SWE
>
> sched_yield is
Code looks good. I'm not able to test it, but it's isolated within #defined(
__APPLE__).
Thanks for the contribution.
Reviewed-by: Bruce Cherniak
> On Mar 14, 2018, at 6:19 PM, Jeremy Huddleston Sequoia
> wrote:
>
> From: Apple SWE
>
> The implementation for bootstrapping SWR on Darwin t
On Jan 24, 2018, at 11:43 AM, Emil Velikov
mailto:emil.l.veli...@gmail.com>> wrote:
On 24 January 2018 at 15:30, George Kyriazis
mailto:george.kyria...@intel.com>> wrote:
LLVM 3.9 was not taken into in initial check-in.
In addition to Emil's comments, please correct commit message to make sens
v2 is Reviewed-by: Bruce Cherniak
> On Jan 24, 2018, at 2:43 PM, George Kyriazis
> wrote:
>
> LLVM 3.9 was not taken into account in initial check-in.
>
> Fixes: 01ab218bbc ("swr/rast: Initial work for debugging support.")
> cc: mesa-sta...@lists.freedesktop.org
> Bugzilla: https://bugs.free
Series Reviewed-by: Bruce Cherniak
> On Jan 24, 2018, at 9:31 AM, George Kyriazis
> wrote:
>
> Early Rasterization did not initially work with USE_SIMD16_FRONTEND=0.
> Fix it so it works there, too. Please note that the default setting
> is USE_SIMD16_FRONTEND=1.
> ---
> .../drivers/swr/rast
Reviewed-by: Bruce Cherniak
> On Jan 24, 2018, at 2:50 PM, George Kyriazis
> wrote:
>
> Modify DumpToFile to only dump the function, not the entire module.
> Reduces file sizes and speeds up the dumping.
> ---
> src/gallium/drivers/swr/rasterizer/jitter/JitManager.cpp | 3 +--
> 1 file changed,
Entire set Reviewed-by: Bruce Cherniak
> On Feb 13, 2018, at 4:42 PM, George Kyriazis
> wrote:
>
> Batch patchset of SWR rasterizer-related changes
>
> George Kyriazis (31):
> swr/rast: Add missing parameter to a few gather functions
> swr/rast: Cleanup knob definitions
> swr/rast: Don't
Set looks great with a couple suggestions:
* In swr_update_derived() it seems like the GS should also depend on SWR_NEW_VS
dirty since swr_generate_gs_key() references ctx->vs->info.base.
*In swr_context.h the SWR_NEW_ALL mask should be expanded by 2-bits to account
for the new dirty flags. Or
Maybe a little cleaner working on the relnotes: “Geometry shaders on on swr”;
perhaps “Geometry shaders enabled on swr”?
With that…
Reviewed-by: Bruce Cherniak
> On Mar 3, 2017, at 2:24 PM, Tim Rowley wrote:
>
> This patch set implements geometry shaders for the swr driver.
>
> Probably sti
Reviewed-by: Bruce Cherniak
> On Mar 5, 2017, at 3:24 PM, Ilia Mirkin wrote:
>
> This makes bin/gl-3.2-layered-rendering-gl-layer-render fail only with
> 2DMS_ARRAY, which is expected given the lackluster MSAA support. However
> all the regular types pass.
>
> Signed-off-by: Ilia Mirkin
> ---
Reviewed-by: Bruce Cherniak
> On Mar 15, 2017, at 11:51 AM, Rowley, Timothy O
> wrote:
>
> General protection, and prevents us from smashing the stack
> on the first clear state validation (a7b8d50bcb). Fixes crash
> using icc.
> ---
> src/gallium/drivers/swr/swr_state.cpp | 2 ++
> 1 file cha
Looks like “patchwork” got a bit confused by v2, but the intended patch-set
applies cleanly and looks good.
Reviewed-by: Bruce Cherniak
> On Mar 16, 2017, at 2:09 PM, Tim Rowley wrote:
>
> Hightlights include: lots of simd16 work, assert rework, and autogen
> changes (scripts centralized, one
Reviewed-by: Bruce Cherniak
> On Aug 23, 2017, at 11:19 AM, Tim Rowley wrote:
>
> Only copy this value when in restart drawing mode.
>
> Eliminates valgrind errors when running trivial programs.
> ---
> src/gallium/drivers/swr/swr_draw.cpp | 5 -
> 1 file changed, 4 insertions(+), 1 deleti
Gentle bump. This fixes mesa master for Kitware's VTK testing.
> On Aug 25, 2017, at 2:59 PM, Bruce Cherniak wrote:
>
> From: Brian Paul
>
> For software drivers where we want "fake" msaa support for GL 3.x, we
> treat 1 sample as being msaa.
>
> For drivers with real msaa support, start for
Gentle bump. This fixes mesa master for Kitware's VTK testing.
> On Aug 25, 2017, at 2:59 PM, Cherniak, Bruce wrote:
>
> Accompanying patch "st/mesa: only try to create 1x msaa surfaces for
> 'fake' msaa" requires driver to report max_samples=1 to enable &q
Reviewed-by: Bruce Cherniak
> On Sep 5, 2017, at 1:57 PM, Tim Rowley wrote:
>
> Highlight is starting to unify the simd/simd16 code, removing lots of
> temporary code duplication.
>
> No piglit or vtk test regressions.
>
> Tim Rowley (8):
> swr/rast: Allow gather of floats from fetch shader
Reviewed-by: Bruce Cherniak
> On Sep 7, 2017, at 3:53 AM, Thomas Hellstrom wrote:
>
> This fixes a regression introduced with commit
> eceb6710024716433069d705fbd873d6d136c2cc:
> "mesa/st: Reduce the number of frontbuffer flush calls"
> where we, after flushing the front buffer marked it as no
>
> On Sep 7, 2017, at 5:21 AM, Eric Engestrom wrote:
>
> Signed-off-by: Eric Engestrom
> ---
> src/gallium/drivers/swr/rasterizer/memory/StoreTile.h | 10 ++
> 1 file changed, 6 insertions(+), 4 deletions(-)
>
> diff --git a/src/gallium/drivers/swr/rasterizer/memory/StoreTile.h
> b/sr
Reviewed-by: Bruce Cherniak
> On Sep 11, 2017, at 2:28 PM, Tim Rowley wrote:
>
> Mostly some api changes, plus making the cpu topology code a bit more
> robust in the face of some odd configurations seen in virtualized
> environments.
>
> No piglit or vtk ctest regressions.
>
> Tim Rowley (1
101 - 200 of 215 matches
Mail list logo
