On Thu, Nov 07, 2013 at 06:08:16PM -0600, Aaron Watry wrote:
> Prevents a memory leak.
> ---
> src/gallium/drivers/radeon/radeon_llvm_emit.c | 3 +++
> 1 file changed, 3 insertions(+)
>
> diff --git a/src/gallium/drivers/radeon/radeon_llvm_emit.c
> b/src/gallium/drivers/radeon/radeon_llvm_emit.c
On Mon, Nov 11, 2013 at 03:54:48PM -0800, Matt Turner wrote:
> ---
Reviewed-by: Tom Stellard
> src/gallium/state_trackers/clover/Makefile.sources | 1 -
> 1 file changed, 1 deletion(-)
>
> diff --git a/src/gallium/state_trackers/clover/Makefile.sources
> b/src/gallium/sta
From: Tom Stellard
This fixes build failures with the gold linker.
---
src/gallium/targets/egl-static/Makefile.am | 2 +-
src/gallium/targets/egl-static/egl.link | 2 +-
src/gallium/targets/pipe-loader/Makefile.am | 2 +-
src/gallium/targets/pipe-loader/pipe.link | 2 +-
4 files changed
UseCount)
> >+return LastUseCount <= TII->getMaxAlusPerClause();
> >+ llvm_unreachable("Clause local register live at end of clause.");
> >+}
> >+return true;
> >+ }
>
> This function does not check if current clause can hold all con
On Wed, Nov 13, 2013 at 12:29:31PM -0500, Alex Deucher wrote:
> Update additional register fields.
>
> Signed-off-by: Alex Deucher
Should we CC: mesa-stable on these?
> ---
> src/gallium/drivers/radeonsi/radeonsi_pipe.c | 2 ++
> src/gallium/drivers/radeonsi/si_state.c | 4
On Wed, Nov 13, 2013 at 12:27:05PM -0500, Alex Deucher wrote:
> Signed-off-by: Alex Deucher
Reviewed-by: Tom Stellard
Now that we have compute support for Sea Islands, we will also need to
add the processor to clang. I can take care of this.
-Tom
> ---
> lib/Target/R600/Processo
From: Tom Stellard
v2:
- Use clGetDeviceIDs to query devices.
CC: "10.0"
---
src/gallium/state_trackers/clover/api/context.cpp | 12 +---
1 file changed, 9 insertions(+), 3 deletions(-)
diff --git a/src/gallium/state_trackers/clover/api/context.cpp
b/src/gallium/stat
From: Tom Stellard
We need to do this until function calls are supported.
https://bugs.freedesktop.org/show_bug.cgi?id=64225
CC: "10.0"
---
src/gallium/drivers/radeon/radeon_llvm_util.c | 24 ++--
1 file changed, 22 insertions(+), 2 deletions(-)
diff --git a/s
On Thu, Nov 14, 2013 at 11:38:06AM -0600, Aaron Watry wrote:
> On Thu, Nov 14, 2013 at 10:29 AM, Tom Stellard wrote:
> > From: Tom Stellard
> >
> > We need to do this until function calls are supported.
> >
> > https://bugs.freedesktop.org/show_b
On Wed, Nov 13, 2013 at 03:13:55PM -0500, Alex Deucher wrote:
> On Wed, Nov 13, 2013 at 1:12 PM, Tom Stellard wrote:
> > On Wed, Nov 13, 2013 at 12:27:05PM -0500, Alex Deucher wrote:
> >> Signed-off-by: Alex Deucher
> >
> > Reviewed-by: Tom Stellard
> >
>
On Wed, Nov 06, 2013 at 04:49:18PM -0600, Aaron Watry wrote:
> Turns out that I don't have commit access to Mesa, just piglit. Feel
> free to push if they look good.
>
> I decided to have some fun and hooked valgrind up to my SI while running
> a few OpenCL tests in piglit. This is the first batc
From: Tom Stellard
Global buffers do not have an associate cs_buf handle, so
we can't copy them using r600_copy_buffer()
https://bugs.freedesktop.org/show_bug.cgi?id=64226
CC: "10.0"
---
src/gallium/drivers/r600/r600_blit.c | 32 +++-
1 file changed
From: Tom Stellard
The spec allows clGetProgramInfo() to return information about either
the devices associated with the program or the devices associated
with the context. If there are no devices associated with the program,
then we return devices associated with the context.
https
From: Tom Stellard
We need to do this until function calls are supported.
v2:
- Fix loop conditional
https://bugs.freedesktop.org/show_bug.cgi?id=64225
CC: "10.0"
---
src/gallium/drivers/radeon/radeon_llvm_util.c | 22 --
1 file changed, 20 insertions(+), 2
From: Tom Stellard
https://bugs.freedesktop.org/show_bug.cgi?id=69321
CC: "10.0"
---
src/gallium/drivers/r600/evergreen_compute.c | 4
src/gallium/drivers/r600/r600_hw_context.c | 4 +++-
src/gallium/drivers/r600/r600_pipe.h | 10 ++
3 files changed, 17
From: Tom Stellard
NOTE: This is a candidate for the 3.4 branch.
---
lib/Target/R600/AMDGPUISelLowering.cpp | 1 +
test/CodeGen/R600/fabs.ll | 36 --
2 files changed, 35 insertions(+), 2 deletions(-)
diff --git a/lib/Target/R600
On Tue, Jun 10, 2014 at 02:57:41PM +0100, Emil Velikov wrote:
> On 10/06/14 03:25, Michel Dänzer wrote:
> > From: Michel Dänzer
> >
> > LLVM is enabled by default for some architectures, but the test was failing
> > before that.
> >
> Thanks for fixing my silly mistake Michel. Would you mind CC-
On Tue, Jun 10, 2014 at 12:57:31AM +0200, thomashellan...@gmail.com wrote:
> From: Thomas Helland
>
For the series:
Reviewed-by: Tom Stellard
Do these patches make any measurable improvement in compile time?
-Tom
> This series removes some unused includes in the glsl-directory.
>
On Sat, Jun 07, 2014 at 01:24:39PM -0700, Greg Fischer wrote:
> LunarG, with support from Valve, announces the GlassyMesa project, an
> effort to bring the LLVM compiler infrastructure to Mesa.
>
This is very interesting. Have you done any testing with any of the
Gallium drivers?
How difficult
On Fri, May 30, 2014 at 05:31:10PM +0200, Bruno Jiménez wrote:
> ---
> src/gallium/docs/source/screen.rst | 2 ++
> src/gallium/include/pipe/p_defines.h | 3 ++-
> 2 files changed, 4 insertions(+), 1 deletion(-)
Reviewed-by: Tom Stellard
>
> diff --git a/src/gallium/docs
On Fri, May 30, 2014 at 05:31:12PM +0200, Bruno Jiménez wrote:
Reviewed-by: Tom Stellard
> ---
> src/gallium/state_trackers/clover/api/device.cpp | 2 +-
> src/gallium/state_trackers/clover/core/device.cpp | 6 ++
> src/gallium/state_trackers/clover/core/device.hpp | 1
On Thu, Jun 05, 2014 at 08:39:29PM +0200, Bruno Jimenez wrote:
>
> With a couple of changes, it applied cleanly to 3.14.5 (Arch's stable).
> And with the attached patch as #2 for my series I can get the correct
> number of compute units for my CEDAR.
>
> But I don't know how or where I should add
On Tue, Jun 10, 2014 at 08:36:05PM +0200, Bruno Jimenez wrote:
> On Tue, 2014-06-10 at 14:10 -0400, Tom Stellard wrote:
> > On Thu, Jun 05, 2014 at 08:39:29PM +0200, Bruno Jimenez wrote:
> > >
> > > With a couple of changes, it applied cleanly to 3.14.5 (Arch&#x
On Mon, May 19, 2014 at 06:14:50PM +0200, Bruno Jiménez wrote:
> Hi,
>
> Firstly, I shall introduce myself (at least more formally than just
> sending some patches). My name is Bruno Jiménez, I'm studying
> physics at Zaragoza's University (Spain) and I am participating in
> this year's Google Sum
On Wed, Jun 11, 2014 at 05:28:01PM +0200, Bruno Jiménez wrote:
> That commit made possible that the items could be one just
> after the other when their size was a multiple of ITEM_ALIGNMENT.
> But compute_memory_prealloc_chunk still looked to leave a gap
> between items. Resulting in that we got a
On Fri, May 30, 2014 at 05:31:09PM +0200, Bruno Jiménez wrote:
> This series allows clover to answer the query for the number of
> max compute units of the devices.
>
> The data has been extracted from:
> AMD Accelerated Parallel Processing OpenCL Programming Guide (rev 2.7)
> Appendix D: Device P
Some apps will abort if they detect 0 compute units. This fixes
crashes in some OpenCV tests.
---
src/gallium/drivers/radeon/r600_pipe_common.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/src/gallium/drivers/radeon/r600_pipe_common.c
b/src/gallium/drivers/radeon/r600_pipe
We were serializing the binaries once when clGetProgramInfo was called
with CL_PROGRAM_BINARY_SIZES and then again when it was called with
CL_PROGRAM_BINARIES. This was slowing down some OpenCV tests which were
building binary kernel caches.
This improves the run-time of OpenCV's OCL_ImgProc/CvtC
On Fri, Jun 13, 2014 at 10:35:30PM +0200, Bruno Jiménez wrote:
> This patch changes completely the way buffers are added to the
> compute_memory_pool. Before this, whenever we were going to
> map a buffer or write to or read from it, it would get placed
> into the pool. Now, every unallocated buffe
On Fri, Jun 13, 2014 at 10:35:31PM +0200, Bruno Jiménez wrote:
> These statuses will help track whether the items are mapped
> or if they should be promoted to or demoted from the pool
> ---
> src/gallium/drivers/r600/compute_memory_pool.h | 7 ++-
> src/gallium/drivers/r600/evergreen_compute
On Fri, Jun 13, 2014 at 10:35:32PM +0200, Bruno Jiménez wrote:
> Now we will have a list with the items that are in the pool
> (item_list) and the items that are outside it (unallocated_list)
Reviewed-by: Tom Stellard
> ---
> src/gallium/drivers/r600/compute_memory
On Sun, Jun 15, 2014 at 01:08:14PM +0200, Francisco Jerez wrote:
> Tom Stellard writes:
>
> > We were serializing the binaries once when clGetProgramInfo was called
> > with CL_PROGRAM_BINARY_SIZES and then again when it was called with
> > CL_PROGRAM_BINARIES. This was
On Fri, Jun 13, 2014 at 10:35:33PM +0200, Bruno Jiménez wrote:
Reviewed-by: Tom Stellard
> ---
> src/gallium/drivers/r600/compute_memory_pool.c | 140
> +++--
> src/gallium/drivers/r600/compute_memory_pool.h | 5 +
> 2 files changed, 87 insertions(+
d with a kernel (from the item we have
> just added to the pool) without problems.
Reviewed-by: Tom Stellard
> ---
> src/gallium/drivers/r600/compute_memory_pool.c | 14 ++
> 1 file changed, 10 insertions(+), 4 deletions(-)
>
> diff --git a/src/gallium/drivers/r6
On Fri, Jun 13, 2014 at 10:35:35PM +0200, Bruno Jiménez wrote:
> This function will be used when we want to map an item
> that it's already in the pool.
> ---
> src/gallium/drivers/r600/compute_memory_pool.c | 45
> ++
> src/gallium/drivers/r600/compute_memory_pool.h | 3
On Fri, Jun 13, 2014 at 10:35:36PM +0200, Bruno Jiménez wrote:
> With this we can assure that mapped buffers will never change
> its position when relocating the pool.
>
> This patch should finally solve the mapping bug.
> ---
> src/gallium/drivers/r600/evergreen_compute.c | 10 --
> 1 fi
On Fri, Jun 13, 2014 at 10:35:37PM +0200, Bruno Jiménez wrote:
> ---
> src/gallium/drivers/r600/compute_memory_pool.c | 158
> -
> 1 file changed, 78 insertions(+), 80 deletions(-)
>
There are double linked list helper functions in gallium util, which we
should use rathe
On Fri, Jun 13, 2014 at 10:35:38PM +0200, Bruno Jiménez wrote:
> All the *Enqueue* functions that read/write buffers (except
> clEnqueueCopyBuffer) would map the associated resource, making
> it to be demoted if it was in the pool.
>
> But we possitively know that this transfer will end before
po
On Thu, Jun 12, 2014 at 02:11:10AM +0200, Marek Olšák wrote:
> From: Marek Olšák
>
> This adds a new type of intrinsic and SDNode: SampleRaw.
> All fields of the MIMG opcodes are exposed and can be set by Mesa,
> even DMASK. All GATHER4 variants are added and there are a lot of them.
>
> v2: doc
On Thu, Jun 12, 2014 at 02:11:11AM +0200, Marek Olšák wrote:
> From: Marek Olšák
>
LGTM.
> ---
> test/CodeGen/R600/llvm.SI.gather4.ll | 508
> +++
> 1 file changed, 508 insertions(+)
> create mode 100644 test/CodeGen/R600/llvm.SI.gather4.ll
>
> diff --git a/t
o do that
was by replacing the intrinsic with an SDNode.
-Tom
> Marek
>
> On Mon, Jun 16, 2014 at 5:45 PM, Tom Stellard wrote:
> > On Thu, Jun 12, 2014 at 02:11:10AM +0200, Marek Olšák wrote:
> >> From: Marek Olšák
> >>
> >> This adds a new type of in
This is for reporting whether or not double precision floating-point
operations are supported.
---
src/gallium/auxiliary/gallivm/lp_bld_limits.h | 2 ++
src/gallium/auxiliary/tgsi/tgsi_exec.h| 2 ++
src/gallium/docs/source/screen.rst| 2 ++
src/gallium/drivers/r300/r300_screen.
From: Matt Arsenault
---
src/gallium/state_trackers/clover/api/device.cpp | 11 +--
src/gallium/state_trackers/clover/core/device.cpp | 24 +++
src/gallium/state_trackers/clover/core/device.hpp | 3 +++
3 files changed, 36 insertions(+), 2 deletions(-)
diff --git a
---
src/gallium/state_trackers/clover/api/device.cpp | 4 +++-
src/gallium/state_trackers/clover/core/device.cpp | 6 ++
src/gallium/state_trackers/clover/core/device.hpp | 1 +
3 files changed, 10 insertions(+), 1 deletion(-)
diff --git a/src/gallium/state_trackers/clover/api/device.cpp
b/
An LLVMContext should only be accessed by a single and using the global
context was causing crashes in multi-threaded environments. Now we use
a separate context for each compile.
---
src/gallium/state_trackers/clover/llvm/invocation.cpp | 15 +--
1 file changed, 9 insertions(+), 6 de
From: Matt Arsenault
If there were only warnings, they would not be added to the log.
Also fixes valgrind use after free errors.
---
src/gallium/state_trackers/clover/core/compiler.hpp | 3 ++-
src/gallium/state_trackers/clover/core/error.hpp | 2 +-
src/gallium/state_trackers/clover/co
some error handling to
util_dlopen, so that it prints an error message when it fails to load a
shared object.
Other than that, it's hard to review a series like this, but I'll
give it an:
Acked-by: Tom Stellard
Since I like the general approach.
-Tom
> In a nutshell:
> - Convert o
On Wed, Jun 18, 2014 at 09:54:28AM +1000, Dave Airlie wrote:
> On 18 June 2014 05:08, Roland Scheidegger wrote:
> > This looks ok to me though since tgsi currently doesn't have any double
> > opcodes (well the docs have them...) it doesn't really apply to most
> > drivers (at least I assume you do
We were printing messages for all diagnostic types, which was
spamming the console for some OpenCL programs.
---
src/gallium/drivers/radeon/radeon_llvm_emit.c | 6 --
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/src/gallium/drivers/radeon/radeon_llvm_emit.c
b/src/gallium/driv
On Thu, Jun 19, 2014 at 03:53:42PM +0900, Michel Dänzer wrote:
> From: Michel Dänzer
>
I just pushed this patch to fix the regressions. We can update the
other intrinsics in a follow on patch.
We also need to change RSQ to use llvm.AMDGPU.rsq.clamped once
http://lists.cs.uiuc.edu/pipermail/llv
On Thu, Jun 19, 2014 at 10:21:32AM -0400, Jan Vesely wrote:
> The important part is the change of the condition to <= 0. Otherwise the loop
> gets stuck never actually growing the pool.
>
> The change in the aux-need calculation guarantees max 2 iterations, and
> avoids wasting memory in case a sm
On Thu, Jun 19, 2014 at 11:22:28AM -0400, Jan Vesely wrote:
> On Thu, 2014-06-19 at 17:12 +0200, Bruno Jimenez wrote:
> > Hi,
> >
> > To which failure are you refering? Could you please send me a
> > test/program that I can try to track this down?
>
> well, the compute_memory_finalize_pending() f
On Wed, Jun 18, 2014 at 05:01:50PM +0200, Bruno Jiménez wrote:
> Hi,
>
> This is my second attempt to fix the mapping bug adding all the
> suggestions that Tom Stellard sent, and, so far, it seems that
> it is resolved.
>
> This series changes completely how OpenCL buffers
On Fri, Jun 20, 2014 at 07:14:43PM -0500, Aaron Watry wrote:
> Signed-off-by: Aaron Watry
Reviewed-by: Tom Stellard
> ---
> src/gallium/auxiliary/gallivm/lp_bld_debug.cpp | 4 +++-
> 1 file changed, 3 insertions(+), 1 deletion(-)
>
> diff --git a/src/gallium/auxiliary/galliv
On Sat, Jun 21, 2014 at 06:33:17PM +0200, Francisco Jerez wrote:
> Tom Stellard writes:
>
> > From: Matt Arsenault
> >
> > If there were only warnings, they would not be added to the log.
> > Also fixes valgrind use after free errors.
> > ---
> &g
On Sun, Jun 22, 2014 at 04:05:49PM +0200, Francisco Jerez wrote:
> Bruno Jimenez writes:
>
> > On Sat, 2014-06-21 at 17:39 +0200, Francisco Jerez wrote:
> >[...]
> >> The implementation of PIPE_TRANSFER_MAP_DIRECTLY introduced in PATCH 10
> >> has somewhat worrying semantics: A mapping with this
ks!
-Tom
> > Sorry for any inconvenience this may have caused.
>
> no worries, none caused
>
> >
> > > This fixes crashes and assertion failures in two gegl tests.
> > >
> > > Signed-off-by: Jan Vesely
> > > CC: Bruno Jimenez
> >
https://bugs.freedesktop.org/show_bug.cgi?id=80015
CC: "10.1 10.2"
---
src/gallium/drivers/radeon/radeon_setup_tgsi_llvm.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/src/gallium/drivers/radeon/radeon_setup_tgsi_llvm.c
b/src/gallium/drivers/radeon/radeon_setup_tgsi_llvm.
v2:
- Report correct values for CL_DEVICE_NATIVE_VECTOR_WIDTH_DOUBLE and
CL_DEVICE_PREFERRED_VECTOR_WIDTH_DOUBLE.
- Only define cl_khr_fp64 if the extension is supported.
- Remove trailing space from extension string.
- Rename device query function from cl_khr_fp86() to has_doubles().
-
From: Francisco Jerez
---
src/gallium/state_trackers/clover/api/kernel.cpp | 4 +++-
src/gallium/state_trackers/clover/util/compat.hpp | 8
2 files changed, 7 insertions(+), 5 deletions(-)
diff --git a/src/gallium/state_trackers/clover/api/kernel.cpp
b/src/gallium/state_trackers/clov
This is for reporting whether or not double precision floating-point
operations are supported.
Reviewed-by: Francisco Jerez
---
src/gallium/auxiliary/gallivm/lp_bld_limits.h | 2 ++
src/gallium/auxiliary/tgsi/tgsi_exec.h| 2 ++
src/gallium/docs/source/screen.rst| 2 ++
src/ga
From: Matt Arsenault
v2:
-Fix indentation
---
src/gallium/state_trackers/clover/api/device.cpp | 11 +--
src/gallium/state_trackers/clover/core/device.cpp | 24 +++
src/gallium/state_trackers/clover/core/device.hpp | 3 +++
3 files changed, 36 insertions(+), 2 del
From: Matt Arsenault
If there were only warnings, they would not be added to the log.
Also fixes valgrind use after free errors.
v2:
- Use compat::string.
---
src/gallium/state_trackers/clover/core/compiler.hpp | 3 ++-
src/gallium/state_trackers/clover/core/error.hpp | 4 ++--
src/g
On Tue, Jun 17, 2014 at 01:51:10AM +0200, Marek Olšák wrote:
> Since LLVM 3.5 will be released in August and my radeon patches adding
Which LLVM patches are required for ARB_draw_indirect?
-Tom
> ARB_draw_indirect depend on it, I will commit ARB_draw_indirect
> support for Gallium with softpipe
into LLVM 3.4.2, which was released last week, so
you don't have to wait until LLVM 3.5.
-Tom
> Marek
>
> On Fri, Jun 27, 2014 at 5:26 PM, Tom Stellard wrote:
> > On Tue, Jun 17, 2014 at 01:51:10AM +0200, Marek Olšák wrote:
> >> Since LLVM 3.5 will be released i
On Wed, Jul 02, 2014 at 06:29:25PM +0200, Laurent Carlier wrote:
> Le mercredi 25 juin 2014, 11:58:47 Michel Dänzer a écrit :
> > On 25.06.2014 09:15, Tom Stellard wrote:
> > > https://bugs.freedesktop.org/show_bug.cgi?id=80015
> > >
> > > CC: "10.1 1
On Thu, Jun 26, 2014 at 04:15:39PM +0200, Francisco Jerez wrote:
> Tom Stellard writes:
>
> > v2:
> > - Report correct values for CL_DEVICE_NATIVE_VECTOR_WIDTH_DOUBLE and
> > CL_DEVICE_PREFERRED_VECTOR_WIDTH_DOUBLE.
> > - Only define cl_khr_fp64
v2:
- Report correct values for CL_DEVICE_NATIVE_VECTOR_WIDTH_DOUBLE
and CL_DEVICE_PREFERRED_VECTOR_WIDTH_DOUBLE.
- Only define cl_khr_fp64 if the extension is supported.
- Remove trailing space from extension string.
- Rename device query function from cl_khr_fp86() to
has_doubles(
---
src/gallium/state_trackers/clover/api/device.cpp | 3 +--
src/gallium/state_trackers/clover/core/device.cpp | 6 ++
src/gallium/state_trackers/clover/core/device.hpp | 1 +
3 files changed, 8 insertions(+), 2 deletions(-)
diff --git a/src/gallium/state_trackers/clover/api/device.cpp
b/s
On Thu, Jul 03, 2014 at 01:12:07AM +0200, Francisco Jerez wrote:
> Tom Stellard writes:
>
> > On Thu, Jun 26, 2014 at 04:15:39PM +0200, Francisco Jerez wrote:
> >> Tom Stellard writes:
> >>
> >> > v2:
> >> > - Report corre
data !{metadata !"work_group_size_hint", i32 4, i32 1, i32 1}
>
> Attempting to get the kernel without the correct number of attributes led
> to memory corruption and luxrays crashing out.
>
> Fixes the cl/program/execute/attributes.cl piglit test.
>
Thanks for tra
On Thu, Jul 03, 2014 at 10:56:24AM -0400, Tom Stellard wrote:
> On Wed, Jul 02, 2014 at 04:34:24PM -0500, Aaron Watry wrote:
> > Previously, we were assuming that kernel metadata nodes only had 1 operand.
> >
> > Kernels which have attributes can have more than 1, e.g.:
>
On Thu, Jul 03, 2014 at 11:59:00AM -0400, Alex Deucher wrote:
> On Thu, Jul 3, 2014 at 11:46 AM, Aaron Watry wrote:
> > On Thu, Jul 3, 2014 at 9:56 AM, Tom Stellard wrote:
> >> On Wed, Jul 02, 2014 at 04:34:24PM -0500, Aaron Watry wrote:
> >>> Previously, we were
at all
> >> required built-ins/defines for luxrays are now present (at least with
> >> my own libclc tree), at least with image support disabled in luxrays.
> >>
> >> If you enable image support, I believe that it is still going to fail
> >> due to mis
On Fri, Jul 04, 2014 at 12:28:20AM +0200, Francisco Jerez wrote:
> Tom Stellard writes:
>
> > On Thu, Jul 03, 2014 at 01:12:07AM +0200, Francisco Jerez wrote:
> >> Tom Stellard writes:
> >>
> >> > On Thu, Jun 26, 2014 at 04:15:39PM +0200, Francisco
On Thu, Jul 03, 2014 at 10:33:41PM -0500, Darius Goad wrote:
> Hello. I'm trying to get my feet wet with Mesa, and I was wondering
> what some good tasks for me would be. Thanks again.
>
What hardware do you have? What are you interested in working on?
-Tom
> - Darius Goad
> __
On Fri, Jul 04, 2014 at 12:28:05PM +0200, Francisco Jerez wrote:
> Tom Stellard writes:
>
> > On Fri, Jul 04, 2014 at 12:28:20AM +0200, Francisco Jerez wrote:
> >> Tom Stellard writes:
> >>
> >> > On Thu, Jul 03, 2014 at 01:12:07AM +0200, Francisco
On Fri, Jul 04, 2014 at 05:25:42PM +0200, Francisco Jerez wrote:
> Tom Stellard writes:
>
> > On Fri, Jul 04, 2014 at 12:28:05PM +0200, Francisco Jerez wrote:
> >> Tom Stellard writes:
> >>
> >> > On Fri, Jul 04, 2014 at 12:28:20AM +0200, Francisco
On Thu, Jul 03, 2014 at 06:26:04PM +0200, Marek Olšák wrote:
> From: Marek Olšák
Reviewed-by: Tom Stellard
>
> It was conflicting with def TEX_SHADOW_ARRAY, which also handles them.
> ---
> lib/Target/R600/R600Instructions.td | 2 +-
> 1 file changed, 1 insertion(+), 1 del
On Tue, Jul 08, 2014 at 03:37:02AM +0200, Marek Olšák wrote:
> From: Marek Olšák
>
> Needed by ARB_draw_indirect.
I think we should come up with a rule for how long we should support
older versions of LLVM. Do you have any thoughts about this? I was
thinking we could have each Mesa release sup
On Tue, Jul 08, 2014 at 01:37:02AM +0200, Marek Olšák wrote:
> From: Marek Olšák
>
> This is a follow-up to the commit which adds texture fetches with offsets.
Will this still work with LLVM 3.4.2 ?
-Tom
> ---
> src/gallium/drivers/radeonsi/si_shader.c | 29 -
> 1
On Tue, Jul 08, 2014 at 01:37:03AM +0200, Marek Olšák wrote:
> From: Marek Olšák
Reviewed-by: Tom Stellard
>
> ---
> src/gallium/drivers/radeonsi/si_blit.c| 2 +-
> src/gallium/drivers/radeonsi/si_descriptors.c | 12 +-
> src/gallium/drivers/radeonsi/si_
> This should make growing the pool faster, and we can also save
> 64KB of memory that were allocated for the 'shadow', even if they
> weren't used.
Reviewed-by: Tom Stellard
> ---
> src/gallium/drivers/r600/compute_memory_pool.c | 61
> ++
On Fri, Jul 11, 2014 at 10:20:54AM +0200, Bruno Jiménez wrote:
> v2: Add information about the item's starting point and size
Reviewed-by: Tom Stellard
> ---
> src/gallium/drivers/r600/compute_memory_pool.c | 9 +
> 1 file changed, 9 insertions(+)
>
> diff --gi
On Fri, Jul 11, 2014 at 01:00:34AM +0200, Marek Olšák wrote:
> I have just tested it and it works with LLVM 3.4.2.
>
Ok, thanks.
Both patches are:
Reviewed-by: Tom Stellard
> Marek
>
> On Thu, Jul 10, 2014 at 5:11 PM, Tom Stellard wrote:
> > On Tue, Jul 08, 2014 at 01
We were trying to print the error message after disposing the
message object.
---
src/gallium/drivers/radeon/radeon_llvm_emit.c | 11 ---
1 file changed, 4 insertions(+), 7 deletions(-)
diff --git a/src/gallium/drivers/radeon/radeon_llvm_emit.c
b/src/gallium/drivers/radeon/radeon_llvm_em
---
src/gallium/auxiliary/util/u_math.h | 22 ++
src/gallium/drivers/radeonsi/si_shader.c | 8 +---
2 files changed, 23 insertions(+), 7 deletions(-)
diff --git a/src/gallium/auxiliary/util/u_math.h
b/src/gallium/auxiliary/util/u_math.h
index b9ed197..cd3cf04 100644
The is used for programs that have arrays of constants that
are accessed using dynamic indices. The shader will compute
the base address of the constants and then access them using
SMRD instructions.
---
src/gallium/drivers/radeon/r600_pipe_common.h | 5 +
src/gallium/drivers/radeon/radeon_e
Also change the wait parameter from false to true.
---
I'm really not sure what is correct here, but this patch fixes event profiling
on SI.
src/gallium/state_trackers/clover/core/timestamp.cpp | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/src/gallium/state_trackers/clov
We use PIPE_QUERY_TIMESTAMP for profiling events, and gallium specifies
that the timestamp be in nanoseconds.
---
src/gallium/state_trackers/clover/api/device.cpp | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/src/gallium/state_trackers/clover/api/device.cpp
b/src/gallium/
v2:
- Move the end_query() call into the timestamp constructor.
- Still pass false as the wait parameter to get_query_result().
---
src/gallium/state_trackers/clover/core/timestamp.cpp | 1 +
1 file changed, 1 insertion(+)
diff --git a/src/gallium/state_trackers/clover/core/timestamp.cpp
b/s
e faster but possibly less accurate code.
>
> Piglit didn't indicate any regressions.
Both patches are:
Reviewed-by: Tom Stellard
> ---
> src/gallium/drivers/radeon/radeon_llvm_emit.c | 5 +
> 1 file changed, 5 insertions(+)
>
> diff --git a/src/gallium/drivers/rade
On Wed, Jul 16, 2014 at 11:12:42PM +0200, Bruno Jiménez wrote:
> Hi,
>
> This series finally adds support for defragmenting the pool for
> OpenCL buffers in the r600g driver. It is mostly a rewritten of
> the series that I wrote some months ago.
>
> For defragmenting the pool I have thought of tw
---
src/gallium/drivers/radeonsi/si_compute.c | 7 ++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/src/gallium/drivers/radeonsi/si_compute.c
b/src/gallium/drivers/radeonsi/si_compute.c
index 3a9f00f..a7d61e7 100644
--- a/src/gallium/drivers/radeonsi/si_compute.c
+++ b/src/gal
---
src/gallium/winsys/radeon/drm/radeon_drm_winsys.c | 6 ++
src/gallium/winsys/radeon/drm/radeon_winsys.h | 2 ++
2 files changed, 8 insertions(+)
diff --git a/src/gallium/winsys/radeon/drm/radeon_drm_winsys.c
b/src/gallium/winsys/radeon/drm/radeon_drm_winsys.c
index 576fea5..7cda70a 1
The scratch buffer will be used for private memory and also register
spilling.
---
src/gallium/drivers/radeonsi/si_compute.c | 85 ++-
src/gallium/drivers/radeonsi/si_shader.c | 5 ++
src/gallium/drivers/radeonsi/si_shader.h | 2 +
3 files changed, 90 insertions(+),
The is used for programs that have arrays of constants that
are accessed using dynamic indices. The shader will compute
the base address of the constants and then access them using
SMRD instructions.
---
src/gallium/drivers/radeon/r600_pipe_common.h | 5 +
src/gallium/drivers/radeon/radeon_e
v2:
- Preserve word boundaries.
---
src/gallium/auxiliary/util/u_math.h | 17 +
1 file changed, 17 insertions(+)
diff --git a/src/gallium/auxiliary/util/u_math.h
b/src/gallium/auxiliary/util/u_math.h
index b9ed197..5de181a 100644
--- a/src/gallium/auxiliary/util/u_math.h
+++ b/
---
src/gallium/drivers/radeonsi/si_descriptors.c | 4 +---
src/gallium/drivers/radeonsi/si_shader.c | 8 +---
2 files changed, 2 insertions(+), 10 deletions(-)
diff --git a/src/gallium/drivers/radeonsi/si_descriptors.c
b/src/gallium/drivers/radeonsi/si_descriptors.c
index 38ad077..41c1
---
src/gallium/drivers/r600/evergreen_compute.h | 13 -
src/gallium/drivers/radeon/r600_pipe_common.h | 5 +
src/gallium/drivers/radeonsi/si_compute.c | 5 +
3 files changed, 10 insertions(+), 13 deletions(-)
diff --git a/src/gallium/drivers/r600/evergreen_compute.h
b
201 - 300 of 1703 matches
Mail list logo
