summaryrefslogtreecommitdiff
AgeCommit message (Collapse)AuthorFilesLines
2020-08-10radeon/vcn: fix jpeg decode for navi10Thong Thai1-1/+1
Fixes an issue where the JPEG decode would timeout when decoding certain JPEG files. Signed-off-by: Thong Thai <thong.thai@amd.com> Reviewed-by: Boyuan Zhang <boyuan.zhang@amd.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6249>
2020-08-10radv: Do not consider layouts fast-clearable on compute queue.Bas Nieuwenhuizen1-1/+2
We cannot decompress from the compute queue. While I'm pretty sure VK_IMAGE_LAYOUT_COLOR_ATTACHMENT_OPTIMAL is only useful on the graphics queue, I cannot find a VU that prevents the transition from happening on another queue, so we need to be careful here. This patch ensures we do the decompression on the barrier that changes the queue ownership. Another problem was that DCC images were considered fast-clearable when not DCC compressed, which resulted in a mess with concurrent queue ownership. Cc: <mesa-stable@lists.freedesktop.org> Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3387 Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6252>
2020-08-10radv: Add forcecompress debug flag.Bas Nieuwenhuizen4-11/+26
Enables DCC/HTILE/CMASK/FMASK when supported, not just when we think it is beneficial. This is helpful to detect compression bugs with CTS. Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6252>
2020-08-10intel/perf: export performance counters sorted by [group|set] and nameMarcin Ślusarz1-7/+67
It's a lot easier to deal with them in RenderDoc when they are in some meaningful order. Signed-off-by: Marcin Ślusarz <marcin.slusarz@intel.com> Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5788>
2020-08-10intel/perf: split load_oa_metricsMarcin Ślusarz1-12/+18
Move oa_metrics_available out of load_oa_metrics and call build_unique_counter_list outside. This change is a preparation for the next patch. It should not have any functional impact. Signed-off-by: Marcin Ślusarz <marcin.slusarz@intel.com> Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5788>
2020-08-10intel/perf: fix performance counters availability after glFinishMarcin Ślusarz5-16/+19
Currently Linux kernel gathers performance counters at fixed intervals (~5-10ms), so if application uses AMD_performance_monitor extension and immediately after glFinish() asks GL driver for HW performance counter values it might not get any data (values == 0). Fix this by moving the "read counters from kernel" code from "is query ready" to "get counter values" callback with a loop around it. Unfortunately it means that the "read counters from kernel" code can spin for up to 10ms. Ideally kernel should gather performance counters whenever we ask it for counter values, but for now we have deal with what we have. Signed-off-by: Marcin Ślusarz <marcin.slusarz@intel.com> Cc: <mesa-stable@lists.freedesktop.org> Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5788>
2020-08-10intel/perf: streamline error handling in read_oa_samples_untilMarcin Ślusarz1-12/+16
No functional changes. Signed-off-by: Marcin Ślusarz <marcin.slusarz@intel.com> Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5788>
2020-08-10intel/perf: fix how pipeline stats are storedMarcin Ślusarz1-1/+1
It matters only when counters are not ordered by offset. Signed-off-by: Marcin Ślusarz <marcin.slusarz@intel.com> Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5788>
2020-08-10intel/perf: fix calculation of used counter spaceMarcin Ślusarz1-1/+3
It matters only when counters are not ordered by offset. Signed-off-by: Marcin Ślusarz <marcin.slusarz@intel.com> Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5788>
2020-08-10radv: report a better error message when QueueWaitIdle() failedSamuel Pitoiset1-2/+20
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6230>
2020-08-10radv: report errors back to the application via VK_EXT_debug_reportSamuel Pitoiset2-9/+26
Help for debugging. Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6230>
2020-08-10radv: rework the error function helpers a bitSamuel Pitoiset2-8/+28
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6230>
2020-08-10radv: report the spirv-nir logs back to the applicationSamuel Pitoiset1-0/+39
Via VK_EXT_debug_report to help debugging various SPIRV->NIR issues. Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6223>
2020-08-10radv: Fix assert that is too strict.Bas Nieuwenhuizen1-2/+2
The added assert fails on MSAA images if we disable FMASK .... Reordered things. Fixes: c6aadbae715 "radv: Don't use both DCC and CMASK for single sample images." Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3385 Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6232>
2020-08-10radeon/radeon_vce: fix out of target bitrate in CBR mode (H.264)Louis Li1-1/+11
StoneyRidge may not comply to required target bitrate when generating H.264 stream in CBR mode. Signed-off-by: Louis Li <Ching-shih.Li@amd.com> Reviewed-by: Leo Liu <leo.liu@amd.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4384>
2020-08-09r600: Enable compute shaders for NIR code pathGert Wollny1-5/+1
There are still regessions compared to TGSI, but there are also many fixes. Signed-off-by: Gert Wollny <gert.wollny@collabora.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6025>
2020-08-09r600/sfn: Force a minimum of 4 GPRs, it seems to fix atomicsGert Wollny1-0/+2
This fixes spec@arb_compute_shader@execution@atomic-counter on HD 5450 Signed-off-by: Gert Wollny <gert.wollny@collabora.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6025>
2020-08-09r600/sfn: handle querying SSBO sizeGert Wollny2-0/+29
Signed-off-by: Gert Wollny <gert.wollny@collabora.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6025>
2020-08-09r600/sfn: Correct ssbo instruction handlingGert Wollny2-7/+38
Signed-off-by: Gert Wollny <gert.wollny@collabora.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6025>
2020-08-09r600/sfn: correct allocating and emitting of atomicsGert Wollny3-27/+23
Signed-off-by: Gert Wollny <gert.wollny@collabora.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6025>
2020-08-09r600/sfn: Add a mapping table for atomicsGert Wollny3-0/+14
Signed-off-by: Gert Wollny <gert.wollny@collabora.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6025>
2020-08-09r600/sfn: add r600 specific lowering pass for atomics and use itGert Wollny1-0/+133
v2: rebase to use global variable lists Signed-off-by: Gert Wollny <gert.wollny@collabora.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6025>
2020-08-09r600/sfn: Sort uniforms by binding and offsetGert Wollny1-0/+28
This is required to get atomics right. v2: rebase to use global variable lists Signed-off-by: Gert Wollny <gert.wollny@collabora.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6025>
2020-08-09r600: Set PIPE_CAP_NIR_ATOMICS_AS_DEREF to trueGert Wollny1-0/+1
Signed-off-by: Gert Wollny <gert.wollny@collabora.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6025>
2020-08-09gallium + mesa/st: Add PIPE_CAP_NIR_ATOMICS_AS_DEREF and use itGert Wollny4-2/+8
This cap is useful for drivers that support hardware atomics and need special handling to resolve their addresses. Signed-off-by: Gert Wollny <gert.wollny@collabora.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6025>
2020-08-08meson: bump required glvnd versionEric Engestrom3-3/+3
https://github.com/KhronosGroup/EGL-Registry/pull/95 has moved a couple of extensions defines and functions to the upstream `eglext.h`, but when 9a74746bd1f3bd28d4c4 sync'ed these files we broke compilation of apps that require these symbols on systems that don't have the updated Khronos headers. On non-GLVND builds, we still provide these headers, so everything's fine, but on GLVND builds the Khronos headers are external so we need to make sure we have a libglvnd version that's recent enough. Fixes: 9a74746bd1f3bd28d4c4 ("EGL: sync headers with Khronos") Signed-off-by: Eric Engestrom <eric@engestrom.ch> Acked-by: Daniel Stone <daniels@collabora.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6069>
2020-08-08driconf: fix force_gl_vendor descriptionEric Engestrom1-1/+1
The option is not a toggle to "allow GPU vendor to be overridden", it *is* the override. Fixes: dca119f12c291d7665d7 ("mesa/gallium: add dric option to allow overriding GL vendor string") Signed-off-by: Eric Engestrom <eric@engestrom.ch> Reviewed-by: Marek Olšák <marek.olsak@amd.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6207>
2020-08-08egl/entrypoint-check: add check that GLVND and plain EGL have the same ↵Eric Engestrom1-0/+42
entrypoints Cc: mesa-stable Signed-off-by: Eric Engestrom <eric@engestrom.ch> Reviewed-by: Emil Velikov <emil.velikov@collabora.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4448>
2020-08-08egl/entrypoint-check: split sort-check into a functionEric Engestrom1-11/+16
Cc: mesa-stable Signed-off-by: Eric Engestrom <eric@engestrom.ch> Reviewed-by: Emil Velikov <emil.velikov@collabora.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4448>
2020-08-08Correct a typo in threads_win32.hFelix Yan1-1/+1
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6238>
2020-08-08pick-ui: specify git commands in "resolve cherry pick" messageEric Engestrom1-2/+2
Cc: mesa-stable Signed-off-by: Eric Engestrom <eric@engestrom.ch> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6134>
2020-08-08zink: Fix 32-bit compilationJoshua Ashton1-2/+2
`sizeof(void*) != sizeof(VkShaderModule)` on x86 hence this fails with `-Werror=int-conversion` Fixes: 0f059d550bd "zink: split up creating zink_shader objects and VkShaderModule objects" Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6239>
2020-08-08i965: add support for force_gl_vendorTimothy Arceri2-0/+6
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3363 Reviewed-by: Danylo Piliaiev <danylo.piliaiev@globallogic.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6198>
2020-08-07freedreno/ir3: don't install ir3_compiler cmdline toolRob Clark1-1/+1
It is mostly just useful to us.. and it is big since it links in nir and most of the rest of gallium. Signed-off-by: Rob Clark <robdclark@chromium.org> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6234>
2020-08-07freedreno/registers: add some missing regs to buildRob Clark1-0/+4
Needed for installed version of crashdec/cffdump. Fixes: 9c33c538981 ("freedreno/registers: install gzip'd register database") Signed-off-by: Rob Clark <robdclark@chromium.org> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6234>
2020-08-07meson/freedreno: Fix lua requirementDylan Baker1-1/+1
Freedreno needs at least Lua 5.2, but the current code will report found for 5.1, which doesn't actually work. Fixes: caa107cb8db930bc59cd557a325a6a0bc4a86565 ("freedreno/decode: move dependencies up a level") Reviewed-by: Rob Clark <robclark@freedesktop.org> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6229>
2020-08-07radeonsi: various fixes for gfx10.3Marek Olšák1-0/+2
The magic numbers fix sample shading. The bypass flag is optional. Fixes: a23802bcb9a - ac,radeonsi: start adding support for gfx10.3 Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6137>
2020-08-07radeonsi: remove the NGG hack decreasing LDS usage to deal with overflowsMarek Olšák1-7/+2
The LDS size can't overflow anymore, so we can use the correct max LDS size. Fixes: a23802bcb9a - ac,radeonsi: start adding support for gfx10.3 Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6137>
2020-08-07radeonsi: add a common function for getting the size of gs_ngg_scratchMarek Olšák3-6/+13
The next commit will use it. Fixes: a23802bcb9a - ac,radeonsi: start adding support for gfx10.3 Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6137>
2020-08-07radeonsi: don't count unusable vertices to the NGG LDS sizeMarek Olšák1-3/+11
Now we get optimal LDS usage. Fixes: a23802bcb9a - ac,radeonsi: start adding support for gfx10.3 Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6137>
2020-08-07radeonsi: fix applying the NGG minimum vertex count requirementMarek Olšák1-3/+8
The code applied the restriction too late, which could overflow LDS size, which started happening more often after the minimum vertex count was increased for Sienna. Incorporate the clamping into the previous code for rounding up the counts. Now the LDS size can never overflow, but it may use vector lanes less efficiently (max_gsprims can be decreased more), which will be addressed in the next commit. Fixes: 4ecc39e1aa1 ("radeonsi/gfx10: NGG geometry shader PM4 and upload") Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6137>
2020-08-07radeonsi: increase minimum NGG vertex count requirement per workgroup on gfx ↵Marek Olšák1-3/+4
10.3 Fixes: a23802bcb9a - ac,radeonsi: start adding support for gfx10.3 Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6137>
2020-08-07radeonsi: use the same units for esgs_ring_size and ngg_emit_sizeMarek Olšák3-3/+3
for consistency Fixes: a23802bcb9a - ac,radeonsi: start adding support for gfx10.3 Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6137>
2020-08-07radeonsi: use correct wave size in gfx10_ngg_calculate_subgroup_infoMarek Olšák1-1/+1
Fixes: 88efb63cafc ("radeonsi/gfx10: implement Wave32") Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6137>
2020-08-07Revert "radeonsi: honor a user-specified pitch on gfx10.3"Marek Olšák1-20/+6
This reverts commit c4b5fd9ab096a0bb5106b93191b13c81cc32243b. It breaks mipmapping. This is only meant to be used by OpenCL, which allows setting a user pitch for linear images. In all other cases, don't support a custom pitch. Fixes: c4b5fd9ab096a0bb51 "radeonsi: honor a user-specified pitch on gfx10.3" Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6137>
2020-08-07ac/gpu_info: set num_tiles_pipes on gfx10+ tooMarek Olšák1-1/+1
Based on PAL. Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6137>
2020-08-07radeonsi: enable ETC2 hw acceleration on Raven2Marek Olšák1-1/+1
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl> Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6213>
2020-08-07zink: pre-hash gfx-pipeline-stateAntonio Caggiano4-10/+43
Store a hash in `zink_gfx_pipeline_state` to keep track of state changes and avoid to recompute it when the state has not changed. Signed-off-by: Antonio Caggiano <antonio.caggiano@collabora.com> Reviewed-by: Mike Blumenkrantz <michael.blumenkrantz@gmail.com> Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6061>
2020-08-07zink: rename zink_gfx_program::stages to 'modules'Mike Blumenkrantz3-11/+11
we've been confusing 'stages' and 'shaders' over and over for a long time, so maybe having a totally different name will help here Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5970>
2020-08-07zink: always compile shaders in pipeline orderMike Blumenkrantz1-8/+12
in order to accurately perform slot/location mapping that's consistent across stages, we need to go through the stages in order so that we can pass each successive slot map allocation along to the next compiled stage Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5970>
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-22 00:53:33 +0000