Re: [Mesa-dev] [RFC PATCH 0/6] r600: speed up tesselation shaders

On 29 December 2017 at 16:38, Dave Airlie wrote: > On 11 December 2017 at 22:49, Gert Wollny wrote: >> Am Freitag, den 08.12.2017, 16:30 +1000 schrieb Dave Airlie: >>> [snip] >>> >>> So I haven't commited these yet, because I wanted to see if I could >>>

Re: [Mesa-dev] [RFC PATCH 0/6] r600: speed up tesselation shaders

On 11 December 2017 at 22:49, Gert Wollny wrote: > Am Freitag, den 08.12.2017, 16:30 +1000 schrieb Dave Airlie: >> [snip] >> >> So I haven't commited these yet, because I wanted to see if I could >> get sb to work. > Well, it was very much work in progress, I didn't expect

Re: [Mesa-dev] [PATCH 0/6] r600g/state_trackers small cleanups

I forgot to tell: there's actually lots of warnings for Wsign-compare, so if anybody wanted, it's something to look at. I fixed only as much of the code as I had a mood for :Ь В письме от пятница, 29 декабря 2017 г. 8:32:26 MSK пользователь Konstantin Kharlamov написал: > Mostly a quick run

[Mesa-dev] [PATCH 1/6] r600g: do not use "fast-clear" for small textures

Ported from radeonsi. Improves windowed glxgears ran as vblank_mode=0 glxgears -info -geometry 0+0+512+512 from ≈2270 FPS to ≈2360 FPS. Tested with AMD TURKS. Signed-off-by: Konstantin Kharlamov --- src/gallium/drivers/r600/r600_texture.c | 10 ++ 1 file

[Mesa-dev] [PATCH 6/6] r600g: fix unused variable warning

Signed-off-by: Konstantin Kharlamov --- src/gallium/drivers/r600/r600_state_common.c | 1 - 1 file changed, 1 deletion(-) diff --git a/src/gallium/drivers/r600/r600_state_common.c b/src/gallium/drivers/r600/r600_state_common.c index ec8945f084..dc5cc0ad2e 100644 ---

[Mesa-dev] [PATCH 2/6] r600g: constify some variables

Just a nice hint for both peoples and compilers. Signed-off-by: Konstantin Kharlamov --- src/gallium/drivers/r600/cayman_msaa.c | 2 +- src/gallium/drivers/r600/evergreen_state.c | 2 +- src/gallium/drivers/r600/r600_query.c | 2 +-

[Mesa-dev] [PATCH 5/6] r600g: some -Wsign-compare fixes

Signed-off-by: Konstantin Kharlamov --- src/gallium/drivers/r600/eg_debug.c | 6 +++--- src/gallium/drivers/r600/evergreen_state.c | 6 +++--- src/gallium/drivers/r600/r600_isa.c | 6 +++--- src/gallium/drivers/r600/r600_pipe.h | 2 +-

[Mesa-dev] [PATCH 0/6] r600g/state_trackers small cleanups

Mostly a quick run with -Wsign-compare. I didn't see any real problems though except for the changes at r600_isa.c where a unsigned been compared with -1. No changes in piglit except for two unstable tests for me: dlist and multiple-texture-reading. Regarding how did I manage to run piglit given

[Mesa-dev] [PATCH 4/6] st/glx: constify some variables

Just a nice hint for both peoples and compilers. Signed-off-by: Konstantin Kharlamov --- src/gallium/state_trackers/glx/xlib/glx_getproc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/gallium/state_trackers/glx/xlib/glx_getproc.c

[Mesa-dev] [PATCH 3/6] st/nine: constify some variables

Just a nice hint for both peoples and compilers. Signed-off-by: Konstantin Kharlamov --- src/gallium/state_trackers/nine/nine_pipe.h | 2 +- src/gallium/state_trackers/nine/nine_shader.c | 10 +- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git

Re: [Mesa-dev] [PATCH 9/9] radv: Enable DCC with transfers.

For the series: Tested-by: Dieter Nützel on RX580 with 'smoketest' somewhat faster 'F1 2017' little bit slower BTW You dropped all my tb last time. Dieter Am 29.12.2017 03:06, schrieb Bas Nieuwenhuizen: Before this DCC was in practice disabled for most games. This

Re: [Mesa-dev] [PATCH 2/3] nir: Add a helper to get the uvec4 type.

Sure. Rb On December 28, 2017 19:56:55 Eric Anholt wrote: I needed this in the vc5 compiler. --- src/compiler/nir_types.cpp | 6 ++ src/compiler/nir_types.h | 1 + 2 files changed, 7 insertions(+) diff --git a/src/compiler/nir_types.cpp b/src/compiler/nir_types.cpp

[Mesa-dev] [PATCH 9/9] radv: Enable DCC with transfers.

Before this DCC was in practice disabled for most games. This enables practical DCC use. Expect a 5-10% perf increase on a bunch of games on vega @ 4k. --- src/amd/vulkan/radv_image.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/src/amd/vulkan/radv_image.c

[Mesa-dev] [PATCH 1/9] radv: Don't enable DCC / TC compat HTILE for storage images.

We don't get a layout when binding to a descriptor set, but can assume that the LAYOUT is GENERAL. For DCC stores with the DCC bits set will result in a hang, so better be safe than sorry. --- src/amd/vulkan/radv_image.c | 11 ++- 1 file changed, 6 insertions(+), 5 deletions(-) diff

[Mesa-dev] [PATCH 2/9] radv: Add GFX DCC decompress.

--- src/amd/vulkan/radv_meta_fast_clear.c | 94 ++- src/amd/vulkan/radv_private.h | 1 + 2 files changed, 83 insertions(+), 12 deletions(-) diff --git a/src/amd/vulkan/radv_meta_fast_clear.c b/src/amd/vulkan/radv_meta_fast_clear.c index

[Mesa-dev] [PATCH 6/9] radv: Don't init DCC metadata during FS resolve.

It should already be valid there + the RB will update it during rendering. --- src/amd/vulkan/radv_meta_resolve_fs.c | 5 - 1 file changed, 5 deletions(-) diff --git a/src/amd/vulkan/radv_meta_resolve_fs.c b/src/amd/vulkan/radv_meta_resolve_fs.c index 798129ec854..99314d94e53 100644 ---

[Mesa-dev] [PATCH 4/9] radv: Add compute DCC decompress.

We do an in place copy where we read compressed and write decompressed. By doing this in sizes that cover entire DCC blocks and waiting for all reads in the block before starting to write we avoid corruption. In the end we clear the DCC metadata to 0x. --- src/amd/vulkan/radv_meta.h

[Mesa-dev] [PATCH 3/9] radv: Use the meta fast clear destructor on construction failure.

Simplifies failure paths. The caller already calls radv_device_finish_meta_fast_clear_flush_state on failure. --- src/amd/vulkan/radv_meta_fast_clear.c | 9 +++-- 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/src/amd/vulkan/radv_meta_fast_clear.c

[Mesa-dev] [PATCH 7/9] radv: Disable DCC for GENERAL layout and compute transfer dest.

Apps can use this for render feedback loops, where things are defined if they render each pixel only once. However, DCC fails here, as the level of coherence is a block not a pixel, so disable it. This is also going to help implementing other stuff. Even if we optimize this later to only happen

[Mesa-dev] [PATCH 5/9] radv: Make color meta operations layout aware.

For fast clear eliminate and decompressions, we always use the most compressed format. For clears, the code already creates a renderpass on demand with the exact same layout as specified. Otherwise we start distinguishing between GENERAL and TRANSFER_DST_OPTIMAL. ---

[Mesa-dev] [PATCH 8/9] radv: Decompress copy destination if formats are incompatible.

If both source and destination are DCC compressed, and their formats are not compatible, we need to decompress one of them to make sure we can do reinterpretation (which needs src format == dst format) . --- src/amd/vulkan/radv_meta_copy.c | 27 +-- 1 file changed, 25

[Mesa-dev] [PATCH 2/3] nir: Add a helper to get the uvec4 type.

I needed this in the vc5 compiler. --- src/compiler/nir_types.cpp | 6 ++ src/compiler/nir_types.h | 1 + 2 files changed, 7 insertions(+) diff --git a/src/compiler/nir_types.cpp b/src/compiler/nir_types.cpp index 377de0c9c7bd..cbdd452dc813 100644 --- a/src/compiler/nir_types.cpp +++

[Mesa-dev] [PATCH 3/3] util: use zlib's CRC32 implementaion for larger buffers

zlib provides a faster slice-by-4 CRC32 implementation than the traditional single byte lookup one used by mesa. As most supported platforms now link zlib unconditionally, we can easily use it. For small buffers the old implementation is still used as it's faster with cold cache (first call), as

[Mesa-dev] [PATCH 1/3] nir: Add a lowering pass for gl_FragColor to glFragData[] writes.

For VC5, the shader needs to have the appropriate base type for the variable in the render target write, and gallium's FS_COLOR0_WRITES_ALL_CBUFS (used for glClearBufferiv) doesn't give you that information. This pass lets the backend decide what types to explode the gl_FragColor write out to.

[Mesa-dev] [PATCH 1/3] android,configure,meson: define HAVE_ZLIB

The next change wants to use some optional zlib functionality, however not all platforms currently use zlib. Based on earlier Jordan Justen's patches and their review feedback. Signed-off-by: Grazvydas Ignotas --- Android.common.mk | 1 + configure.ac | 1 + meson.build

[Mesa-dev] [PATCH 2/3] util/crc32: don't drop the const qualifier

Signed-off-by: Grazvydas Ignotas --- src/util/crc32.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/util/crc32.c b/src/util/crc32.c index 44d637c..f2e01c6 100644 --- a/src/util/crc32.c +++ b/src/util/crc32.c @@ -109,11 +109,11 @@ util_crc32_table[256]

[Mesa-dev] [PATCH 3/3] broadcom/vc5: Use the new glFragColor lowering pass.

This fixes dEQP-GLES3.functional.fbo.color.clear.r16i and friends, by making sure we do an integer TLB store instead of float. --- src/broadcom/compiler/nir_to_vir.c| 5 + src/broadcom/compiler/v3d_compiler.h | 6 ++ src/broadcom/compiler/vir.c | 13 +

[Mesa-dev] [PATCH] radv/gfx9: use correct swizzle parameter to work out border swizzle.

From: Dave Airlie This should fix: dEQP-VK.pipeline.sampler.view_type.*.format.b4g4r4a4_unorm_pack16.address_modes.all_mode_clamp_to_border_opaque_black and a few others in that area. Fixes: b11c4a5546 (radv: add texture descriptor/fmask/cmask support for GFX9)

[Mesa-dev] [PATCH] radv/gfx9: use a bigger hammer to flush cb/db caches.

From: Dave Airlie amdvlk is probably more subtle than this but it never uses the inv cb/db variants, we fail some CTS tests without this. Fixes: dEQP-VK.renderpass.dedicated_allocation.formats.d32_sfloat_s8_uint.input*. Fixes: c2fbeb7ca05 (radv: add GFX9 cache flushing

[Mesa-dev] [PATCH] radv/gfx9: fix block compression texture views.

From: Dave Airlie This ports a fix from amdvlk, to fix the sizing for mip levels when block compressed images are viewed using uncompressed views. Fixes: dEQP-VK.image.texel_view_compatible.graphic.extended*bc* Fixes: e38685cc62e 'Revert "radv: disable support for VEGA for

[Mesa-dev] [PATCH 2/3] radv/gfx9: fix 3d image clears on compute queues

From: Dave Airlie This fixes some of the broken: dEQP-VK.synchronization.op.multi_queue.*64x64x8* tests. Fixes: e38685cc62e 'Revert "radv: disable support for VEGA for now."' Signed-off-by: Dave Airlie --- src/amd/vulkan/radv_meta_bufimage.c | 73

[Mesa-dev] [PATCH 1/3] radv/gfx9: fix 3d image to image transfers on compute queues.

From: Dave Airlie This fixes some of the broken: dEQP-VK.synchronization.op.multi_queue.*64x64x8* tests. Fixes: e38685cc62e 'Revert "radv: disable support for VEGA for now."' Signed-off-by: Dave Airlie --- src/amd/vulkan/radv_meta_bufimage.c | 75

[Mesa-dev] [PATCH 3/3] radv/gfx9: fix buffer to image for 3d images on compute queues

From: Dave Airlie This fixes some of the broken: dEQP-VK.synchronization.op.multi_queue.*64x64x8* tests. Fixes: e38685cc62e 'Revert "radv: disable support for VEGA for now."' Signed-off-by: Dave Airlie --- src/amd/vulkan/radv_meta_bufimage.c | 62

Re: [Mesa-dev] [PATCH] radv: enable denorms for 64-bit and 16-bit floats

On 12/28/2017 11:08 PM, Matt Arsenault wrote: On Dec 28, 2017, at 16:55, Samuel Pitoiset wrote: Similar to RadeonSI. This fixes: dEQP-VK.image.texel_view_compatible.graphic.basic.attachment_read.bc*r16g16b16a16_sfloat

Re: [Mesa-dev] [PATCH] radv: enable denorms for 64-bit and 16-bit floats

> On Dec 28, 2017, at 16:55, Samuel Pitoiset wrote: > > Similar to RadeonSI. > > This fixes: > dEQP-VK.image.texel_view_compatible.graphic.basic.attachment_read.bc*r16g16b16a16_sfloat > dEQP-VK.image.extended_usage_bit.attachment_write.r16_sfloat > > Signed-off-by:

[Mesa-dev] [PATCH] radv: enable denorms for 64-bit and 16-bit floats

Similar to RadeonSI. This fixes: dEQP-VK.image.texel_view_compatible.graphic.basic.attachment_read.bc*r16g16b16a16_sfloat dEQP-VK.image.extended_usage_bit.attachment_write.r16_sfloat Signed-off-by: Samuel Pitoiset --- src/amd/common/ac_nir_to_llvm.c | 14

[Mesa-dev] [Bug 104351] X Error of failed request: BadAlloc (insufficient resources for operation)

https://bugs.freedesktop.org/show_bug.cgi?id=104351 Emil Velikov changed: What|Removed |Added Resolution|--- |DUPLICATE

[Mesa-dev] Buffer update assert with multiple contexts.

I'm hitting this assert in radeonsi: si_descriptors.c:1414: si_desc_reset_buffer_offset: Assertion `old_buf_va <= old_desc_va' failed. It seems to happen when a buffer is updated after being bound (as a uniform buffer) on multiple contexts in a sharing group. If it's bound on context A and B,

Re: [Mesa-dev] [PATCH] svga: update SVGA_NEW_ flags for updating sampler state

Looks good. Reviewed-by: Charmaine Lee From: Brian Paul Sent: Thursday, December 28, 2017 11:09:34 AM To: mesa-dev@lists.freedesktop.org Cc: Neha Bhende; Charmaine Lee Subject: [PATCH] svga: update SVGA_NEW_

[Mesa-dev] [PATCH] svga: update SVGA_NEW_ flags for updating sampler state

The SVGA_NEW_FS flag is needed since we now examine the fragment shader's fs_shadow_compare_units flags. The SVGA_NEW_TEXTURE_FLAGS flag is not needed since it's only for pre-VGPU10. No piglit changes. This doesn't fix any known issues but it could pop up somewhere. Suggested by Charmaine. ---

Re: [Mesa-dev] [PATCH 4/4] anv/device: Mark all state buffers as needing capture

Thanks! I've pushed the last 3. I'll let the debate continue on 1/4. :-) On Thu, Dec 28, 2017 at 9:25 AM, Lionel Landwerlin < lionel.g.landwer...@intel.com> wrote: > Reviewed-by: Lionel Landwerlin > > > On 27/12/17 20:58, Jason Ekstrand wrote: > >> Previously,

Re: [Mesa-dev] Allocator Nouveau driver, Mesa EXT_external_objects, and DRM metadata import interfaces

(Adding dri-devel back, and trying to respond to some comments from the different forks) James Jones wrote: > Your worst case analysis above isn't far off from our HW, give or take > some bits and axes here and there. We've started an internal discussion > about how to lay out all the bits we

Re: [Mesa-dev] [PATCH 4/4] anv/device: Mark all state buffers as needing capture

Reviewed-by: Lionel Landwerlin On 27/12/17 20:58, Jason Ekstrand wrote: Previously, we were flagging the instruction state buffer for capture but not surface state or dynamic state. We want those captured too. --- src/intel/vulkan/anv_device.c | 6 +++--- 1

Re: [Mesa-dev] [PATCH 3/4] intel/aubinator: Gracefully handle dynamic state not being available

Reviewed-by: Lionel Landwerlin On 27/12/17 20:58, Jason Ekstrand wrote: Some older versions of the Vulkan driver didn't properly tag dynamic state as needing to be captured. Also, this prevents crashes when looking at dumps on older kernels. ---

Re: [Mesa-dev] [PATCH 2/4] intel/aubinator: Free section data last

Good catch! Reviewed-by: Lionel Landwerlin On 27/12/17 20:58, Jason Ekstrand wrote: We were walking the sections, printing the batches, and then freeing them in one pass. If the batch happens to reference any earlier sections (which it almost certainly will

Re: [Mesa-dev] [PATCH] svga: check for null fs pointer in update_samplers()

Looks good. Reviewed-by: Neha Bhende From: Brian Paul Sent: Thursday, December 28, 2017 8:19:24 AM To: mesa-dev@lists.freedesktop.org Cc: Charmaine Lee; Neha Bhende Subject: [PATCH] svga: check for null fs pointer in

Re: [Mesa-dev] [PATCH] svga: check for null fs pointer in update_samplers()

Reviewed-by: Charmaine Lee From: Brian Paul Sent: Thursday, December 28, 2017 8:19:24 AM To: mesa-dev@lists.freedesktop.org Cc: Charmaine Lee; Neha Bhende Subject: [PATCH] svga: check for null fs pointer in

[Mesa-dev] [PATCH] svga: check for null fs pointer in update_samplers()

This can happen when there's no active fragment shader, such as when using transform feedback. This wasn't hit by any Piglit test but is hit by Daniel Rákos' Nature demo. VMware bug 2026189. --- src/gallium/drivers/svga/svga_state_sampler.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

[Mesa-dev] [Bug 93551] Divinity: Original Sin Enhanced Edition(Native) crash on start

https://bugs.freedesktop.org/show_bug.cgi?id=93551 --- Comment #47 from Robert G. Brown --- Installed the shim for Fedora 25, XFCE, and Steam. It worked. Upgraded to F26 (it no longer worked) and then to F27 (and it still no longer works). I've played with it a fair bit,

Re: [Mesa-dev] [PATCH 2/3] radv/radeonsi: set dcc min uncompressed properly for APUs.

Reviewed-by: Marek Olšák Marek On Tue, Dec 26, 2017 at 11:19 PM, Dave Airlie wrote: > From: Dave Airlie > > This is ported from amdvlk. > > Signed-off-by: Dave Airlie > --- > src/amd/vulkan/radv_device.c

Re: [Mesa-dev] [PATCH] radeonsi: don't use fast color clear for small images even on APUs

On Thu, Dec 28, 2017 at 3:54 PM, Marek Olšák wrote: > On Thu, Dec 28, 2017 at 12:29 PM, Konstantin Kharlamov > wrote: >> I'm wondering, how is r600g different in that regard? I tried wiring up the >> code into evergreen_do_fast_color_clear(), both in this

Re: [Mesa-dev] [PATCH 3/6] amd/common: Add detection of the syncobj wait/signal/reset ioctls.

OK. I was confused because the name has_syncobj_wait suggests that it's about amdgpu_cs_syncobj_wait, not WAIT_FOR_SUBMIT. Marek On Wed, Dec 27, 2017 at 1:18 AM, Bas Nieuwenhuizen wrote: > For vulkan, I wanted this because of > > drm/syncobj: Allow wait for submit and

Re: [Mesa-dev] [PATCH] radeonsi: don't use fast color clear for small images even on APUs

On Thu, Dec 28, 2017 at 12:29 PM, Konstantin Kharlamov wrote: > I'm wondering, how is r600g different in that regard? I tried wiring up the > code into evergreen_do_fast_color_clear(), both in this state and by using > 256*256 — however FPS for me always varies around the

Re: [Mesa-dev] [PATCH 1/4] intel/aubinator: Allow for the case where the ascii85 decode fails

On December 28, 2017 08:24:03 Jason Ekstrand wrote: On December 28, 2017 01:30:11 Kenneth Graunke wrote: On Wednesday, December 27, 2017 3:13:42 PM PST Jason Ekstrand wrote: On December 27, 2017 17:06:43 Kenneth Graunke

Re: [Mesa-dev] [PATCH 1/4] intel/aubinator: Allow for the case where the ascii85 decode fails

On December 28, 2017 01:30:11 Kenneth Graunke wrote: On Wednesday, December 27, 2017 3:13:42 PM PST Jason Ekstrand wrote: On December 27, 2017 17:06:43 Kenneth Graunke wrote: > On Wednesday, December 27, 2017 12:58:12 PM PST Jason Ekstrand

[Mesa-dev] [PATCH] gallium/winsys/kms: Add support for multi-planes (v2)

v2: address comments from Tomasz Figa a) Add more check for plane size. b) Avoid duplicated mapping and leaked mapping. c) Other minor changes. Signed-off-by: Lepton Wu Change-Id: I0863f522976cc8863d6e95492d9346df35c066ec ---

Re: [Mesa-dev] [PATCH] radeonsi: don't use fast color clear for small images even on APUs

I'm wondering, how is r600g different in that regard? I tried wiring up the code into evergreen_do_fast_color_clear(), both in this state and by using 256*256 — however FPS for me always varies around the same 1420. That said, I'm seeing lots of CPU used by Xorg, glxgears, and compton — I'm

Re: [Mesa-dev] [PATCH] radv: move local bos usage to a perftest flag.

Reviewed-by: Bas Nieuwenhuizen On Thu, Dec 28, 2017 at 7:14 AM, Dave Airlie wrote: > From: Dave Airlie > > These seem mildly unstable on vega, crashing CTS in various fun ways, > and looks like leaking memory. > > Disable for

Re: [Mesa-dev] [PATCH] radv: fix pipeline statistics end query on compute queue

Please add a fixes tag. Reviewed-by: Bas Nieuwenhuizen On Thu, Dec 28, 2017 at 7:33 AM, Dave Airlie wrote: > From: Dave Airlie > > It's legal to a pipeline stat query on a compute queue, > but we'd emit the wrong packet here.

Re: [Mesa-dev] [PATCH] radv: fix events on compute queues.

Reviewed-by: Bas Nieuwenhuizen On Thu, Dec 28, 2017 at 7:29 AM, Dave Airlie wrote: > From: Dave Airlie > > The event emission wasn't sending the correct packet for gfx8 compute > queues, which explains why it works on vega fine.