Jason Ekstrand [Thu, 1 Jun 2017 00:53:34 +0000 (17:53 -0700)]
i965/tex: Use blorp texture upload for all CCS_E textures
This improves the FillTex benchmark in GLBench 2.7 by 30% on my Broxton.
On Ken's Broxton which only has single-channel ram, it improves by 210%.
v2 (Ken): Check mt->aux_usage == ISL_AUX_USAGE_CCS_E rather than using
intel_miptree_is_lossless_compressed().
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Jason Ekstrand [Tue, 6 Jun 2017 16:58:07 +0000 (09:58 -0700)]
i965: Use blorp instead of meta for PBO texture uploads
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Jason Ekstrand [Sun, 27 Nov 2016 15:48:05 +0000 (17:48 +0200)]
i965: Add blorp-based texture upload and download paths
v1 (Topi Pohjolainen): original patch.
v2 (Topi Pohjolainen):
- Fix return value (s/MESA_FORMAT_NONE/false/) (Anuj)
- Move _mesa_tex_format_from_format_and_type() just
in the end avoiding additional if-block (Anuj)
- Explain better the array alignment restriction (Anuj)
- Do not bail out in case of gl_pixelstore_attrib::ImageHeight,
it is handled by _mesa_image_offset() automatically (Ken).
- Support 1D_ARRAY by flipping depth, width and y, z (Ken).
v3 (Topi Pohjolainen):
- Contrary to v2, do not try to handle
gl_pixelstore_attrib::ImageHeight. Currently there are no
tests in piglit or cts for it. One could possibly copy or
modify tests/texturing/texsubimage.c. There, however, seems
to be number of corner cases to consider. Moreover, current
meta path applies the packing height for both source and
targets when determining the offset. This would probably
require re-visiting also.
v4 (Topi Pohjolainen): Rebased on top of merged drm-bacon
v5 (Jason Ekstrand):
- Move to brw_blorp.c
- Significant refactoring
- Fixed 1-D array textures
- Simplified handling of PBOs vs. CPU data.
- Handle gl_pixelstore_attrib::ImageHeight. It turns out there are
piglit tests that cover this. The original version was failing them
because of an error in the way it handled 1-D array textures.
- Add support for texture download
v6 (Kenneth Graunke): Rebase fixes:
- Use intel_miptree_check_level_layer instead of deleted fields
- Update for mesa_format_supports_render[] rename.
- Pass 'false' (read-only) to intel_bufferobj_buffer
v7 (Kenneth Graunke):
- Fix brw_blorp_download_miptree to pass 'false' (not read only) for
the destination buffer (caught by Chris Wilson).
- Fix blorp_get_client_bo to pass intel_bufferobj_buffer !read_only
for the 'writable' parameter instead of 'false' (caught by Jason).
- Support GL_BGR, GL_BGRA, GL_BGRA_INTEGER, GL_BGR_INTEGER, allowing
us to use this for ReadPixels on the window system buffer (caught
by Chris Wilson).
- Fix y-flipping bugs in download path (exposed by BGRA support).
- Fix false vs. NULL return value in blorp_get_client_bo.
Signed-off-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Kenneth Graunke [Thu, 12 Oct 2017 03:33:25 +0000 (20:33 -0700)]
i965: Refactor y-flipping coordinate transform.
I want to reuse it for the BLORP download path.
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Jason Ekstrand [Thu, 1 Jun 2017 00:04:13 +0000 (17:04 -0700)]
i965/tex: Check if there is data to upload up-front
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Jason Ekstrand [Thu, 15 Jun 2017 05:28:25 +0000 (22:28 -0700)]
i965/barrier: Do the correct flushes for framebuffer access
Framebuffer access includes framebuffer reads so we need to invalidate
the texture cache. We do not, however, need to flush the depth cache
because you cannot do bind a depth texture as an image.
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Jason Ekstrand [Thu, 15 Jun 2017 05:27:20 +0000 (22:27 -0700)]
i965/barrier: Do the correct flushes for texture updates
Texture uploads and downloads may go through the render pipe which may
result in texturing from or rendering to the texture or the PBO. We
need to flush accordingly.
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Eric Anholt [Thu, 12 Oct 2017 22:45:11 +0000 (15:45 -0700)]
include: Revert out the update of the Khronos GLX extension header.
They made a mistake in the MESA_swap_control XML, which I'm pursuing in
their github. Until then, we can just back this piece out.
Tested-by: Mark Janes <mark.a.janes@intel.com>
Reviewed-by: Mark Janes <mark.a.janes@intel.com>
Kenneth Graunke [Sat, 9 Sep 2017 07:20:26 +0000 (00:20 -0700)]
i965: Ignore GL_SKIP_DECODE_EXT for textures accessed via texelFetch().
The GL_EXT_texture_sRGB_decode spec says:
"The conversion of sRGB color space components to linear color space is
always performed if the texel lookup function is one of the texelFetch
builtin functions.
Otherwise, if the texel lookup function is one of the texture builtin
functions or one of the texture gather functions, the conversion of sRGB
color space components to linear color space is controlled by the
TEXTURE_SRGB_DECODE_EXT parameter.
If the TEXTURE_SRGB_DECODE_EXT parameter is DECODE_EXT, the conversion
of sRGB color space components to linear color space is performed.
If the TEXTURE_SRGB_DECODE_EXT parameter is SKIP_DECODE_EXT, the value
is returned without decoding. However, if the texture is also accessed
with a texelFetch function, then the result of texture builtin functions
and/or texture gather functions may be returned with decoding or without
decoding."
This patch makes i965 force sRGB decoding for any textures accessed via
texelFetch(). If textures are accessed via texelFetch() and a regular
texture access function, this will affect the other ones too - which is
fine - it's undefined according to the last paragraph quoted.
We could make both work, but we'd have to emit multiple SURFACE_STATEs,
and have two binding table sections, like we do for texture gather hacks
on older platforms.
Fixes the following Android O CTS test:
dEQP-GLES31.functional.srgb_texture_decode.skip_decode.srgba8.texel_fetch
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Kenneth Graunke [Wed, 11 Oct 2017 07:18:38 +0000 (00:18 -0700)]
meta: Unset the textures_used_by_txf bitfield.
Drivers that use Meta are happily using blitting data using texelFetch
and GL_SKIP_DECODE_EXT, but the GL_EXT_texture_sRGB spec unfortunately
makes GL_SKIP_DECODE_EXT not necessarily work with texelFetch.
As a hack, just unset the texture_used_by_txf bitfield so we can
continue with the old desired behavior.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Kenneth Graunke [Sat, 9 Sep 2017 07:19:57 +0000 (00:19 -0700)]
nir: Make nir_shader_gather_info() track texelFetch texture accesses.
For TGSI-based drivers, st_glsl_to_tgsi records this information.
For NIR-based drivers, nir_shader_gather_info() will do so.
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Kenneth Graunke [Sat, 9 Sep 2017 07:19:57 +0000 (00:19 -0700)]
compiler: Move gl_program::TexelFetchSamplers to shader_info.
I'd like to put this sort of metadata in the shader_info structure,
rather than adding more things to gl_program.
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Dave Airlie [Thu, 12 Oct 2017 04:10:53 +0000 (05:10 +0100)]
radv: take unsafe_math and sisched into account when hashing shaders.
We want to generate different variants for sisched and unsafe_math
shader variants, so add them to the hash key.
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Dave Airlie [Wed, 11 Oct 2017 23:32:14 +0000 (09:32 +1000)]
mesa/bufferobj: fix atomic offset/size get
When I realigned the bufferobj code, I didn't see the getters
were different, realign the getters to work the same as ssbo.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103214
Fixes: 65d3ef7cd (mesa: align atomic buffer handling code with ubo/ssbo (v1.1))
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Tested-by: Mark Janes <mark.a.janes@intel.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Marek Olšák [Thu, 12 Oct 2017 20:27:20 +0000 (22:27 +0200)]
relnotes: document EGL_ANDROID_native_fence_sync on radeonsi
Eric Anholt [Wed, 11 Oct 2017 16:54:47 +0000 (09:54 -0700)]
include: Update GL headers from khronos opengl registry.
Taken from their
c6a99aff31874697741a08cbc8a3488606ce59c7, keeping the
BUILDING_MESA hunk in place.
Reviewed-by: Daniel Stone <daniels@collabora.com>
Acked-by: Kenneth Graunke <kenneth@whitecape.org>
Eric Anholt [Wed, 11 Oct 2017 16:50:13 +0000 (09:50 -0700)]
mapi: Update extension number of MESA_tile_raster_order.
Reviewed-by: Daniel Stone <daniels@collabora.com>
Acked-by: Kenneth Graunke <kenneth@whitecape.org>
Eric Anholt [Tue, 10 Oct 2017 20:56:55 +0000 (13:56 -0700)]
broadcom/vc5: Remove the u_resource_vtbl usage.
Like for vc4, this was just a wasted indirection.
Eric Anholt [Wed, 11 Oct 2017 17:32:25 +0000 (10:32 -0700)]
mesa: Disallow GL_RED/GL_RG with half-floats on GLES2.
Sure, you'd think that the combination of GL_OES_texture_half_float and
GL_EXT_texture_rg would mean that GL_RG16F exists, but it doesn't.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103227
Fixes: c16a7443e999 ("mesa: Expose GL_OES_required_internalformat on GLES contexts.")
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Tue, 12 Sep 2017 18:17:31 +0000 (20:17 +0200)]
radeonsi: implement sync_file import/export
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Tue, 12 Sep 2017 18:13:06 +0000 (20:13 +0200)]
winsys/amdgpu: implement sync_file import/export
syncobj is used internally for interactions with command submission.
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Tue, 12 Sep 2017 18:06:37 +0000 (20:06 +0200)]
ac: add radeon_info::has_sync_file
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Eric Anholt [Thu, 12 Oct 2017 00:40:35 +0000 (17:40 -0700)]
broadcom/vc5: Don't pair VPMSETUP with other peripheral access.
The specs don't say you can't, but pairing it with an SFU write on the
7268 breaks all our simple shader tests using gl_MVP * gl_Vertex.
Eric Anholt [Thu, 12 Oct 2017 00:15:10 +0000 (17:15 -0700)]
broadcom/vc5: Fix inclusion of FS flag bits in dumping the FS address.
Marek Olšák [Mon, 9 Oct 2017 16:56:22 +0000 (18:56 +0200)]
st/dri: implement __DRIimageExtension::validateUsage properly
Reviewed-by: Daniel Stone <daniels@collabora.com>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Mon, 9 Oct 2017 16:44:50 +0000 (18:44 +0200)]
gallium: add pipe_screen::check_resource_capability
This is optional (and no CAP).
Implemented by radeonsi, ddebug, rbug, trace.
Reviewed-by: Daniel Stone <daniels@collabora.com>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Mon, 9 Oct 2017 16:42:48 +0000 (18:42 +0200)]
ac/surface: add ac_surface::is_displayable
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Mon, 9 Oct 2017 16:31:12 +0000 (18:31 +0200)]
amd/addrlib: add Addr2IsValidDisplaySwizzleMode
Some "standard" (_S) swizzle modes are displayable on Raven,
even though the micro tile mode says it's not displayable.
Expose the addrlib function to the driver.
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
tournier.elie [Thu, 12 Oct 2017 11:24:10 +0000 (12:24 +0100)]
meson: fix typo in isl
Signed-off-by: Elie Tournier <elie.tournier@collabora.com>
Reviewed-by: Antia Puentes <apuentes@igalia.com>
Reviewed-by: Dylan Baker <dylan@pnwbakers.com>
Rob Herring [Wed, 11 Oct 2017 22:46:10 +0000 (17:46 -0500)]
Android: disable i9x5 drivers on non-x86 builds
The i965 driver has become dependent on x86 specific compiler builtin
functions, so ensure it's disabled for non-x86 builds.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Signed-off-by: Rob Herring <robh@kernel.org>
Wladimir J. van der Laan [Sat, 30 Sep 2017 08:11:32 +0000 (10:11 +0200)]
etnaviv: Do GC3000 resolve-in-place when possible
If an RS blit is done with source exactly the same as destination, and
the hardware supports this, do an in-place resolve. This only fills in
tiles that have not been rendered to using information from the TS.
This is the same as the blob does and potentially saves significant
bandwidth when doing i.MX6qp scanout using PRE, and when rendering to
textures (though here using sampler TS would be even better).
Signed-off-by: Wladimir J. van der Laan <laanwj@gmail.com>
Reviewed-by: Lucas Stach <l.stach@pengutronix.de>
Eric Engestrom [Mon, 25 Sep 2017 21:04:24 +0000 (22:04 +0100)]
egl_haiku: drop haiku_egl_driver struct
The struct only contained the one field we're interested in.
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Eric Engestrom [Thu, 12 Oct 2017 13:26:47 +0000 (14:26 +0100)]
egl: remove left over _EGLMain_t
Fixes: b174a1ae720cb404738c "egl: Simplify the "driver" interface"
Cc: Adam Jackson <ajax@redhat.com>
Signed-off-by: Eric Engestrom <eric.engestrom@imgtec.com>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Eric Engestrom [Mon, 25 Sep 2017 21:39:24 +0000 (22:39 +0100)]
egl: drop memset(0) of calloc'ed memory
`_EGLDriver *drv` is a freshly calloc()'ed object, memset(0)'ing some of
it is a no-op.
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Eric Engestrom [Tue, 26 Sep 2017 12:13:39 +0000 (13:13 +0100)]
egl: replace _egl_driver->Unload() callback with a simple free()
Bonus: fixes a memleak on haiku when unloading the driver
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Dave Airlie [Thu, 12 Oct 2017 04:24:41 +0000 (14:24 +1000)]
radv: don't crash if cache is disabled.
If you set MESA_GLSL_CACHE_DISABLE, radv crashed.
Fixes: fd24be134f (radv: make use of on-disk cache)
Signed-off-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Samuel Pitoiset [Thu, 5 Oct 2017 13:51:20 +0000 (15:51 +0200)]
radv: use CLEAR_STATE for initializing some registers
Based on RadeonSI.
This improves some Vulkan demos by +1% to +3%.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Samuel Pitoiset [Thu, 5 Oct 2017 12:55:24 +0000 (14:55 +0200)]
radv: add has_clear_state and enable it on CIK+ only
This will allow us to emit the CLEAR_STATE packet instead
of a bunch of useless packets when doing CS initialization.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Samuel Pitoiset [Thu, 5 Oct 2017 13:13:19 +0000 (15:13 +0200)]
radv: do not set registers for merged ES-GS on GFX9
Based on RadeonSI.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Samuel Pitoiset [Thu, 5 Oct 2017 12:43:05 +0000 (14:43 +0200)]
radv: move the raster config emission in si_set_raster_config()
Similar to RadeonSI, also only call this function for <= VI.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Nicolai Hähnle [Tue, 3 Oct 2017 13:02:22 +0000 (15:02 +0200)]
radeonsi: add support for PIPE_FORMAT_{X1,A1}R5G5B5_UNORM
Fixes dEQP-EGL.functional.image.modify.tex_rgb5_a1_tex_subimage_rgba8
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Nicolai Hähnle [Tue, 3 Oct 2017 13:00:24 +0000 (15:00 +0200)]
gallium: add tests for PIPE_FORMAT_{X1,A1}B5G5R5_UNORM formats
This is a left-over from my version of adding the new format
after rebasing on Eric's version.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Dave Airlie [Wed, 11 Oct 2017 00:45:50 +0000 (10:45 +1000)]
include/drm-uapi: clarify when headers can be updated.
Clarify when headers can be updated here.
Reviewed-by: Gurchetan Singh<gurchetansingh@chromium.org>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Wed, 11 Oct 2017 04:10:37 +0000 (15:10 +1100)]
radv: remove duplicate line of code
The same line of code is a few lines above.
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Timothy Arceri [Wed, 11 Oct 2017 01:10:31 +0000 (12:10 +1100)]
radv: make use of on-disk cache
If the app provided in-memory pipeline cache doesn't yet contain
what we are looking for, or it doesn't provide one at all then we
fallback to the on-disk cache.
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Timothy Arceri [Wed, 11 Oct 2017 01:00:27 +0000 (12:00 +1100)]
radv: create on-disk shader cache
This is the drivers on-disk cache intended to be used as a
fallback as opposed to the pipeline cache provided by apps.
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Timothy Arceri [Wed, 11 Oct 2017 00:59:20 +0000 (11:59 +1100)]
radv: remove duplicate debug_flags field
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Lionel Landwerlin [Wed, 11 Oct 2017 16:24:37 +0000 (17:24 +0100)]
anv: intel: use anv_image's computed size for importing a BO
Rather than relying on size = stride * height, we can rely on
anv_image's total size.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Acked-by: Daniel Stone <daniels@collabora.com>
Lionel Landwerlin [Wed, 11 Oct 2017 16:21:53 +0000 (17:21 +0100)]
anv: bo_cache: allow importing a BO larger than needed
It's not a problem if a BO has been allocated larger than we need it
to be.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=102940
Fixes: 818b857914 ("anv: Use the BO cache for DeviceMemory allocations")
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Daniel Stone <daniels@collabora.com>
Cc: mesa-stable@lists.freedesktop.org
Nicolai Hähnle [Fri, 6 Oct 2017 18:28:43 +0000 (20:28 +0200)]
st/glsl_to_tgsi: the second destination doesn't support relative addressing
It's not used -- DFRACEXP gets array indexes of its exponent out-parameter
lowered earlier -- and it wouldn't have worked correctly anyway when both
dst and dst1 use relative addressing.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Nicolai Hähnle [Fri, 6 Oct 2017 18:27:40 +0000 (20:27 +0200)]
st/glsl_to_tgsi: fix DFRACEXP with only one destination
Replace the undefined destination by a new temporary register.
Cleanup merge_two_dsts while we're at it.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Nicolai Hähnle [Fri, 6 Oct 2017 15:14:46 +0000 (17:14 +0200)]
st/glsl_to_tgsi: fix indirect access to 64-bit integer
Make sure we actually allocate two adjacent TGSI temporaries. The
current code fails e.g. when an arithmetic operation has two
operands with indirect accesses.
I will send out a new piglit test
(arb_gpu_shader_int64/execution/indirect-array-two-accesses.shader_test)
Cc: mesa-stable@lists.freedesktop.org
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Nicolai Hähnle [Thu, 5 Oct 2017 17:25:48 +0000 (19:25 +0200)]
st/mesa: don't assign prog->ShadowSamplers
It's not used, and the assignment for the TGSI case was incorrect
for sampler arrays.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Nicolai Hähnle [Thu, 5 Oct 2017 17:39:33 +0000 (19:39 +0200)]
st/glsl_to_tgsi: ignore GL_TEXTURE_SRGB_DECODE_EXT for samplers used with texelFetch*()
See the comment for the relevant spec quote.
Fixes dEQP-GLES31.functional.srgb_texture_decode.skip_decode.srgba8.texel_fetch
v2: note the interaction between ARB_bindless_texture and EXT_texture_sRGB_decode
as a TODO
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Nicolai Hähnle [Thu, 5 Oct 2017 12:08:04 +0000 (14:08 +0200)]
st/mesa: store state that affects sampler views per context
This fixes sequences like:
1. Context 1 samples from texture with sRGB decode enabled
2. Context 2 samples from texture with sRGB decode disabled
3. Context 1 samples from texture with sRGB decode disabled
Previously, step 3 would see the prev_sRGBDecode value from context 2
and would incorrectly use the old sampler view with sRGB decode enabled.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Tim Rowley [Tue, 10 Oct 2017 16:08:29 +0000 (11:08 -0500)]
swr: simd16 shaders work in progress
Start building vertex shaders as simd16.
Disabled by default, set USE_SIMD16_SHADERS in knobs.h to experiment.
Reviewed-by: Bruce Cherniak <bruce.cherniak@intel.com>
Tim Rowley [Tue, 10 Oct 2017 16:07:11 +0000 (11:07 -0500)]
gallium: allow 512-bit vectors
Increase the max allowed vector size from 256 to 512.
No piglit llvmpipe regressions running on avx2.
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Kenneth Graunke [Tue, 10 Oct 2017 17:19:21 +0000 (10:19 -0700)]
i965: Drop brw_bo_alloc in ARB_indirect_parameters implementation.
The original implementation allocated a new BO here, but we decided to
switch to intel_upload_space, which returns a reference to the current
upload BO. We accidentally kept the brw_bo_alloc, even though it's no
longer necessary - intel_upload_space will immediately unreference it,
causing us to allocate and immediately free a buffer.
Reviewed-by: Plamena Manolova <plamena.manolova@intel.com>
Kenneth Graunke [Sun, 30 Jul 2017 23:15:56 +0000 (16:15 -0700)]
i965: Allow mapped VBOs during drawing in non-debug contexts.
Section 6.3.2 of the GL 4.5 spec says:
"Any GL command which attempts to read from, write to, or change
the state of a buffer object may generate an INVALID_OPERATION error
if all or part of the buffer object is mapped ... However, only
commands which explicitly describe this error are required to do so.
If an error is not generated, such commands will have undefined
results and may result in GL interruption or termination."
Setting this flag allows us to skip walking over the buffer bindings
for every enabled vertex attribute (_mesa_all_buffers_are_unmapped).
Improves performance in GFXBench4's gl_driver2_off microbenchmark by
3.05797% +/- 0.709031% (n=33) on Apollolake.
This breaks KHR-*.draw_elements_base_vertex_tests.invalid_mapped_bos,
but that test is invalid and has been removed from the upstream CTS.
Reviewed-by: Eric Anholt <eric@anholt.net>
Dylan Baker [Tue, 10 Oct 2017 21:50:53 +0000 (14:50 -0700)]
meson: fix glx test
That requires a generated header that was rolled into a loop.
fixes:
a47c525f3281a27 ("meson: build glx")
Signed-off-by: Dylan Baker <dylanx.c.baker@intel.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Ilia Mirkin [Wed, 11 Oct 2017 03:50:06 +0000 (23:50 -0400)]
nv50,nvc0: fix push hint logic in presence of a start offset
Previously buffer offsets were passed in explicitly as an offset, which
had to be added to the resource address. Now they are passed in via an
increased 'start' parameter. As a result, we were double-adding the
start offset in this kind of situation.
This condition was triggered by piglit's draw-elements test which has a
requisite glMultiDrawElements in combination with a small enough number
of vertices to go through the immediate push path.
Fixes: 330d0607ed6 ("gallium: remove pipe_index_buffer and set_index_buffer")
Reported-by: Karol Herbst <karolherbst@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Cc: mesa-stable@lists.freedesktop.org
Kenneth Graunke [Sat, 9 Sep 2017 07:18:39 +0000 (00:18 -0700)]
i965: Make brw_update_texture_surface static.
Trivial. It's not used in other files.
Rob Herring [Tue, 10 Oct 2017 22:01:29 +0000 (17:01 -0500)]
Android: fix build break from r600/radeon split
Commit
06bfb2d28f7a ("r600: fork and import gallium/radeon") broke the
Android build:
external/mesa3d/src/gallium/drivers/radeon/r600_pipe_common.c:43:10: fatal error: 'llvm-c/TargetMachine.h' file not found
^~~~~~~~~~~~~~~~~~~~~~~~
Update the Android makefiles so that drivers/radeon is only built when
radeonsi (and therefore LLVM) is enabled.
Fixes: 06bfb2d28f7a (r600: fork and import gallium/radeon)
Acked-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Rob Herring <robh@kernel.org>
Rob Herring [Fri, 15 Sep 2017 13:50:09 +0000 (08:50 -0500)]
Android: move libraries to /vendor
As part of Treble project in Android O, all the device specific files have
to be located in a separate vendor partition. This is done by setting
LOCAL_PROPRIETARY_MODULE (the name is misleading). This change will not
break existing platforms without a vendor partition as it will just move
files to /system/vendor.
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Signed-off-by: Rob Herring <robh@kernel.org>
Kenneth Graunke [Tue, 10 Oct 2017 08:02:44 +0000 (01:02 -0700)]
i965: Fix output register sizes when multiple variables share a slot.
ARB_enhanced_layouts allows multiple output variables to share the same
location - and these variables may not have the same sizes. For
example, consider these output variables:
// consume X/Y/Z components of 6 vectors
layout(location = 0) out vec3 a[6];
// consumes W component of the first vector
layout(location = 0, component = 3) out float b;
Looking at the first declaration, we see that VARYING_SLOT_VAR0 needs 24
components worth of space (vec3 padded out to a vec4, 4 * 6 = 24). But
looking at the second declaration, we would think that VARYING_SLOT_VAR0
needs only 4 components of space (a single float padded out to a vec4).
nir_setup_outputs() only considered the space requirements of the first
declaration it happened to see, so if 'float b' came first, it would
underallocate the output register space, causing brw_fs_validator.cpp
to assert fail about inst->dst.offset exceeding the register size.
Fixes Piglit's tests/spec/arb_enhanced_layouts/execution/component-layout/
vs-to-fs-array-interleave-single-location.shader_test.
Thanks to Tim Arceri for finding this bug and writing a test!
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Dave Airlie [Tue, 10 Oct 2017 23:48:21 +0000 (09:48 +1000)]
nir: bump loop unroll limit to 96.
With the ssao demo from Vulkan demos:
radv/rx480: 440->440fps
anv/haswell: 24->34 fps
The demo does a 0->32 loop across a ubo with 32 members.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Dave Airlie [Tue, 10 Oct 2017 23:45:44 +0000 (09:45 +1000)]
anv: fix assert in wsi image code.
This assert was firing just running demos.
Jason said it should be this.
Fixes: 6c7720ed78 (anv/wsi: Allocate enough memory for the entire image)
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Dave Airlie [Fri, 15 Sep 2017 03:14:56 +0000 (13:14 +1000)]
mesa/st: fix atomic buffer sizing to align with ssbo.
This respects the size from the range setting like ssbo.
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Dave Airlie [Fri, 15 Sep 2017 03:13:20 +0000 (13:13 +1000)]
mesa/bufferobj: consolidate some buffer binding code.
These paths are again 90% the same, consolidate them into
one.
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Dave Airlie [Fri, 15 Sep 2017 02:55:50 +0000 (12:55 +1000)]
mesa/bufferobj: consolidate some codepaths between ubo/ssbo/atomics.
These are 90% the same code, consolidate them into a couple of
common codepaths.
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Dave Airlie [Fri, 15 Sep 2017 02:43:55 +0000 (12:43 +1000)]
mesa: rename various buffer bindings to one struct.
One binding to bind them all, these are all the same thing.
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Dave Airlie [Fri, 15 Sep 2017 02:38:18 +0000 (12:38 +1000)]
mesa: align atomic buffer handling code with ubo/ssbo (v1.1)
this adds automatic size support to the atomic buffer code,
but also realigns the code to act like the ubo/ssbo code.
v1.1:
add missing blank lines.
reindent one block properly.
check for NullBufferObj.
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Kenneth Graunke [Sat, 7 Oct 2017 07:14:34 +0000 (00:14 -0700)]
i965: Don't try to decode types for non-existent src1.
KHR-GL45.shader_ballot_tests.ShaderBallotBitmasks has a MOV that hits
this validation path. MOVs don't have a src1 file, but calling
brw_inst_src1_type() was tripping on src1.file being BRW_IMMEDIATE_VALUE
and the hw_type being something invalid for immediates.
To work around this, just pretend src1 is src0 if there isn't a src1.
Fixes: 2572c2771d0cab0b9bc489d354ede44dfc88547b (i965: Validate "Special
Requirements for Handling Double Precision Data Types")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=102680
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Karol Herbst [Wed, 16 Aug 2017 18:32:42 +0000 (20:32 +0200)]
main/format: skip format conversion if src and dst format are equal
Fixes 'KHR-GL45.copy_image.functional' on Nouveau and i965.
v2: (by Kenneth Graunke)
Rewrite patch according to Jason Ekstrand's review feedback.
This makes it handle differing strides, which i965 needed.
Signed-off-by: Karol Herbst <karolherbst@gmail.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Jason Ekstrand [Sat, 7 Oct 2017 04:11:59 +0000 (21:11 -0700)]
mesa: Make _mesa_get_format_bytes handle array formats.
This is easier than making callers handle a bunch of special cases.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Bas Nieuwenhuizen [Sun, 8 Oct 2017 19:58:23 +0000 (21:58 +0200)]
radv: Only set the MTYPE flags on GFX9+.
Older kernels fail the va_op with this flag set. If the kernel
supports GFX9 usefully, it will also support this flag.
Fixes: e8d57802fea "radv/gfx9: allocate events from uncached VA space"
Reviewed-by: Dave Airlie <airlied@redhat.com>
Kenneth Graunke [Fri, 6 Oct 2017 03:31:01 +0000 (20:31 -0700)]
i965: Disable auxiliary buffers when there are self-dependencies.
Jason and I investigated several OpenGL CTS failures where the tests
bind the same texture for rendering and texturing, at the same time.
This has defined results as long as the reads happen before writes,
or the regions are non-overlapping. Normally, this just works out.
However, CCS can cause problems. If the shader is reading one set of
pixels, and writing to different pixels that are adjacent, they may end
up being covered by the same CCS block. So rendering may be writing a
CCS block, while the sampler is trying to read it. Corruption ensues.
Disabling CCS is unfortunate, but safe.
Fixes several KHR-GL45.texture_barrier.* subtests.
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Dave Airlie [Mon, 9 Oct 2017 20:27:40 +0000 (06:27 +1000)]
r600: cleanup llvm ir target selection.
Only r600 target used now for compute IR.
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Dave Airlie [Mon, 9 Oct 2017 20:27:10 +0000 (06:27 +1000)]
r600: drop tc_L2_dirty bit, this was SI only.
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Dave Airlie [Tue, 10 Oct 2017 03:23:40 +0000 (13:23 +1000)]
radeonsi: lower ffma in nir to mad.
This lowers ffma to a * b + c.
This seems like it should keep Marek happiest, so
we'd never get to the fma instruction emission code.
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Dave Airlie [Tue, 3 Oct 2017 20:33:02 +0000 (06:33 +1000)]
radv: lower ffma in nir.
So it appears the Vulkan SPIR-V fma opcode can be equivalent to a
mad operation, and the fma hw opcode on AMD hw is issued like a double
opcode so is slower. Also the radeonsi stack does this.
This appears to improve performance on a number of games from Feral,
and thanks to Feral for noticing the problem.
I'm reposting this one as Marek indicated he thinks this is what
we should be doing on AMD hw.
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Cc: "17.2" <mesa-stable@lists.freedesktop.org>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Alex Smith [Tue, 10 Oct 2017 16:00:09 +0000 (17:00 +0100)]
radv: Add R16G16B16A16_SNORM fast clear support
Signed-off-by: Alex Smith <asmith@feralinteractive.com>
Cc: "17.2" <mesa-stable@lists.freedesktop.org>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Eric Anholt [Tue, 10 Oct 2017 18:19:23 +0000 (11:19 -0700)]
broadcom/vc5: Fix handling of 5551 textures using the new gallium format.
Like vc4, we have the alpha in the low bit. Fixes a bunch of piglit
texwrap failures.
Eric Anholt [Fri, 6 Oct 2017 00:18:34 +0000 (17:18 -0700)]
broadcom/vc5: Set the RCL's MSAA mode to match the BCL's MSAA state.
Eric Anholt [Thu, 5 Oct 2017 22:50:59 +0000 (15:50 -0700)]
braodcom/vc5: Set up clear color for higher-bpp formats.
Fixes arb_color_buffer_float-clear
Eric Anholt [Thu, 5 Oct 2017 22:40:18 +0000 (15:40 -0700)]
broadcom/vc5: Set up per-MRT clear colors.
Fixes fbo-mrt-alphatest.
Eric Anholt [Thu, 5 Oct 2017 22:19:49 +0000 (15:19 -0700)]
broadcom/vc5: Fix blendfactor zero handling.
I cut the line out to move it up to the top, when putting "0" in the
switch made the compiler complain that that wasn't a valid enum.
Eric Anholt [Wed, 4 Oct 2017 23:42:55 +0000 (16:42 -0700)]
broadcom/vc5: Fix Rendering Mode Common Config's color store bitmask.
This controls the RTs that get stored by the default resolved store, the
same way that the extended resolved store packet has a RT bitmask.
Eric Anholt [Tue, 3 Oct 2017 00:21:23 +0000 (17:21 -0700)]
broadcom/vc5: Add support for f32 render targets.
The TLB write code is getting ugly and needs a refactoring (that will
hopefully handle TLBU uniform coalescing as well).
Eric Anholt [Tue, 3 Oct 2017 00:05:24 +0000 (17:05 -0700)]
broadcom/vc5: Fix color masks for non-independent blending.
This gets fbo-mrt-alphatest working except for the second RT's clear color.
Eric Anholt [Mon, 2 Oct 2017 23:55:04 +0000 (16:55 -0700)]
broadcom/vc5: Make the BCL's number of render targets setup match the RCL.
Eric Anholt [Mon, 2 Oct 2017 23:54:09 +0000 (16:54 -0700)]
braodcom/vc5: Fix tile size setup for MRTs.
We need to divide the TLB in two for the 2nd color buffer, and again if
the 3rd or 4th are present.
Eric Anholt [Mon, 2 Oct 2017 23:43:33 +0000 (16:43 -0700)]
broadcom/vc5: Start hooking up multiple render targets support.
We now emit as many TLB color writes as there are color buffers.
Eric Anholt [Mon, 2 Oct 2017 21:09:56 +0000 (14:09 -0700)]
broadcom/vc5: Add support for GL_EXT_provoking_vertex.
The bit was missing from the spec, but it's there in the simulator. Fixes
the piglit clipflat test.
Eric Anholt [Mon, 2 Oct 2017 19:20:35 +0000 (12:20 -0700)]
braodcom/vc5: Find the actual first TF output for our TF spec.
This doesn't yet support PSIZ, but gets us at least some of TF working.
Eric Anholt [Mon, 2 Oct 2017 20:02:32 +0000 (13:02 -0700)]
broadcom/vc5: Fix translation of transform feedback's output_register field.
It's a NIR driver_location, not a slot offset.
Eric Anholt [Mon, 2 Oct 2017 19:17:30 +0000 (12:17 -0700)]
broadcom/vc5: Mark our primitives as needing TF processing.
The TF enable state appears to stick around until the next TF enable
packet is sent, so we only want to request TF when the shader is using it.
Eric Anholt [Mon, 2 Oct 2017 19:05:30 +0000 (12:05 -0700)]
broadcom/vc5: Fix setup of TF dword output count.
I missed the "- 1" when reading the spec.
Eric Anholt [Mon, 2 Oct 2017 18:41:57 +0000 (11:41 -0700)]
broadcom/vc5: Fix up a comment from vc4 about the predraw texture setup.
Eric Anholt [Sat, 30 Sep 2017 23:48:44 +0000 (16:48 -0700)]
broadcom/vc5: Flush the job when mapping a transform feedback buffer.
We will want something fancier for reusing a TF output within the same
frame, but we at least need this in order for piglit tests to work.