summaryrefslogtreecommitdiff
path: root/src/amd/vulkan/radv_query.c
Commit message (Collapse)AuthorAgeFilesLines
* radv: additional query fixesAndres Rodriguez2019-09-041-7/+8
| | | | | | | | | | Make sure we read the updated data from the gpu in cases where WAIT_BIT is not set. Cc: 19.1 19.2 <mesa-stable@lists.freedesktop.org Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl> (cherry picked from commit a410823b3ede9ff3bf7f56ffca295d1b3d04dbad)
* tree-wide: replace MAYBE_UNUSED with ASSERTEDEric Engestrom2019-07-311-2/+2
| | | | | | Suggested-by: Jason Ekstrand <jason@jlekstrand.net> Signed-off-by: Eric Engestrom <eric.engestrom@intel.com> Reviewed-by: Matt Turner <mattst88@gmail.com>
* radv: fix queries with WAIT_BIT returning VK_NOT_READYradv-wait-query-fixAndres Rodriguez2019-07-271-1/+1
| | | | | | | | | | | | | | | | | When vkGetQueryPoolResults() is called with VK_QUERY_RESULT_WAIT_BIT set, the driver is supposed to wait for the query to become available before returning. Currently, radv returns once the query is indeed ready, but it returns VK_NOT_READY. It also fails to populate the results. The problem is a missing volatile in the secondary check for query availability. This patch removes the secondary check altogether since it is redundant with the preceding loop. This bug was found with an unreleased version of SteamVR. Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
* radv: allow to select DST_SEL with RELEASE_MEMSamuel Pitoiset2019-07-161-0/+2
| | | | | Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Dave Airlie <airlied@redhat.com>
* radv: rename and re-document cache flush flagsSamuel Pitoiset2019-06-251-4/+4
| | | | | | | SMEM and VMEM caches are L0 on gfx10. Ported from RadeonSI. Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
* radv: flush and invalidate CB before resetting query pools on GFX9Samuel Pitoiset2019-06-131-0/+4
| | | | | | | | | | | | We have to emit a CACHE_FLUSH_AND_INV_TS_EVENT to be sure all prior GPU work is done. While we are at it, also flush and invalidate DB. This fixes the following CTS (when the small hint is disabled): dEQP-VK.query_pool.statistics_query.reset_before_copy.* Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-By: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
* radv: fix occlusion queries on VegaMSamuel Pitoiset2019-06-121-21/+27
| | | | | | | | | | | | | | The number of render backends is 16 but the enabled mask is 0xaaaa. As noticed by Bas, allowing disabled render backends might break the OCCLUSION_QUERY packet. We don't use it yet but keep this in mind. This fixes dEQP-VK.query_pool.* and dEQP-VK.multiview.*. Cc: 19.0 19.1 <mesa-stable@lists.freedesktop.org> Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-By: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
* radv: flush pending query reset caches before copying resultsSamuel Pitoiset2019-06-031-15/+25
| | | | | | | | | | From the Vulkan spec 1.1.108: "vkCmdCopyQueryPoolResults is guaranteed to see the effect of previous uses of vkCmdResetQueryPool in the same queue, without any additional synchronization." Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
* radv: sync before resetting a pool if there is active pending queriesSamuel Pitoiset2019-05-291-0/+11
| | | | | | | | | | | Make sure to sync all previous work if the given command buffer has pending active queries. Otherwise the GPU might write queries data after the reset operation. This fixes a bunch of new dEQP-VK.query_pool.* CTS failures. Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
* radv: tidy up GetQueryPoolResults for occlusion queriesSamuel Pitoiset2019-05-271-7/+5
| | | | | | | | Just move the block that checks the availability bit into the switch like other query types. Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
* radv: do not reset query pool during creationSamuel Pitoiset2019-05-221-3/+0
| | | | | | | | | | | From the Vulkan spec 1.1.108: "After query pool creation, each query must be reset before it is used." So, the driver doesn't need to do this at creation time. Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
* radv: write availability status vkGetQueryPoolResults() when the data is not ↵Samuel Iglesias Gonsálvez2019-03-251-15/+4
| | | | | | | | | | | | | | | | | | | | | available If VK_QUERY_RESULT_WITH_AVAILABILY_BIT is set and VK_QUERY_RESULT_WAIT_BIT and VK_QUERY_RESULT_PARTIAL_BIT are both not set, we need return to VK_NOT_READY only and set the availability status field for each query. From Vulkan spec: "If VK_QUERY_RESULT_WAIT_BIT and VK_QUERY_RESULT_PARTIAL_BIT are both not set then no result values are written to pData for queries that are in the unavailable state at the time of the call, and vkGetQueryPoolResults returns VK_NOT_READY. However, availability state is still written to pData for those queries if VK_QUERY_RESULT_WITH_AVAILABILITY_BIT is set." Signed-off-by: Samuel Iglesias Gonsálvez <siglesias@igalia.com> Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
* radv: don't overwrite results in VkGetQueryPoolResults() when queries are ↵Samuel Iglesias Gonsálvez2019-03-251-16/+32
| | | | | | | | | | | | | | | | | | | | | | | not available If the query is not available and VK_QUERY_RESULT_WAIT_BIT and VK_QUERY_RESULT_PARTIAL_BIT are both not set, the spec doesn't allow to modify its result. From Vulkan spec: "If VK_QUERY_RESULT_WAIT_BIT and VK_QUERY_RESULT_PARTIAL_BIT are both not set then no result values are written to pData for queries that are in the unavailable state at the time of the call, and vkGetQueryPoolResults returns VK_NOT_READY. However, availability state is still written to pData for those queries if VK_QUERY_RESULT_WITH_AVAILABILITY_BIT is set." v2: - Move VK_NOT_READY change to next patch (Samuel Pitoiset) Signed-off-by: Samuel Iglesias Gonsálvez <siglesias@igalia.com> Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
* radv: Implement VK_EXT_host_query_reset.Bas Nieuwenhuizen2019-03-181-0/+22
| | | | | Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Acked-by: Eric Engestrom <eric@engestrom.ch>
* radv: set num_components on vulkan_resource_index intrinsicLionel Landwerlin2019-03-061-6/+12
| | | | | | | | | | In 61e009d2c4e4df we changed the number of components in the vulkan_resource_index intrinsic and forgot the update Radv's code for it. Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Fixes: 61e009d2c4e4df ("spirv: Use the same types for resource indices as pointers") Reviewed-by: Samuel Pitoiset samuel.pitoiset@gmail.com
* radv/winsys: Set winsys bo priority on creation.Bas Nieuwenhuizen2019-01-291-1/+2
| | | | Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
* radv: remove old_fence parameter from si_cs_emit_write_event_eop()Samuel Pitoiset2019-01-231-2/+2
| | | | | | | | This parameter is actually useless as the immediate value can always be zero. Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
* radeonsi: correct WRITE_DATA.DST_SEL definitionsMarek Olšák2019-01-221-1/+1
| | | | Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
* nir: replace more nir_load_system_value calls with builder functionsKarol Herbst2019-01-211-2/+2
| | | | | | Signed-off-by: Karol Herbst <kherbst@redhat.com> Reviewed-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
* radv/query: Use 1-bit booleans in query shadersJason Ekstrand2018-12-191-21/+21
| | | | | | | | Fixes: 44227453ec03f "nir: Switch to using 1-bit Booleans for almost..." Reviewed-by: Rhys Perry <pendingchaos02@gmail.com> Tested-by: Rhys Perry <pendingchaos02@gmail.com> Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl> Tested-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
* radv/query: Add a nir_test_flag helperJason Ekstrand2018-12-191-15/+16
| | | | | | | | | | This is little more than an iadd_imm right now but it will help in the next commit where we refactor things further. Reviewed-by: Rhys Perry <pendingchaos02@gmail.com> Tested-by: Rhys Perry <pendingchaos02@gmail.com> Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl> Tested-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
* radv: switch from nir_bcsel to nir_b32cselRhys Perry2018-12-171-4/+4
| | | | | | Fixes: 191a1dce928 ('nir: Add 1-bit Boolean opcodes') Signed-off-by: Rhys Perry <pendingchaos02@gmail.com> Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
* radv: wait on the high 32 bits of timestamp queriesSamuel Pitoiset2018-12-051-1/+4
| | | | | | | | In case we are unlucky if the low part is 0xffffffff. Fixes: 5d6a560a29 ("radv: do not use the availability bit for timestamp queries") Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
* radv: reset pending_reset_query when flushing cachesSamuel Pitoiset2018-12-051-1/+0
| | | | | | | | | | | | | If the driver used a compute shader for resetting a query pool, it should be completed when caches are flushed. This might reduce the number of stalls if operations are done between vkCmdResetQueryPool() and vkCmdBeginQuery() (or vkCmdWriteTimestamp()). Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl> Reviewed-by: Alex Smith <asmith@feralinteractive.com>
* radv: Flush before vkCmdWriteTimestamp() if neededAlex Smith2018-12-051-11/+19
| | | | | | | | | | | As done for vkCmdBeginQuery() already. Prevents timestamps from being overwritten by previous vkCmdResetQueryPool() calls if the shader path was used to do the reset. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108925 Fixes: a41e2e9cf5 ("radv: allow to use a compute shader for resetting the query pool") Signed-off-by: Alex Smith <asmith@feralinteractive.com> Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
* nir: replace nir_load_system_value calls with appropiate builder functionsKarol Herbst2018-11-141-4/+4
| | | | | | | | | this helps reduce the overall code changes when a bit_size parameter is added to nir_load_system_value Reviewed-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Eric Anholt <eric@anholt.net> Signed-off-by: Karol Herbst <kherbst@redhat.com>
* radv: disable conditional rendering for vkCmdCopyQueryPoolResults()Samuel Pitoiset2018-11-071-0/+10
| | | | | | | | | VK_EXT_conditional_rendering says that copy commands should not be affected by conditional rendering. Cc: 18.2 18.3 <mesa-stable@lists.freedesktop.org> Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Dave Airlie <airlied@redhat.com>
* radv: allocate enough space in CS when copying query results with computeSamuel Pitoiset2018-11-071-0/+4
| | | | | Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Dave Airlie <airlied@redhat.com>
* radv: more use of radv_cp_wait_mem()Samuel Pitoiset2018-11-051-22/+9
| | | | | Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Dave Airlie <airlied@redhat.com>
* radv: replace si_emit_wait_fence() with radv_cp_wait_mem()Samuel Pitoiset2018-11-051-1/+2
| | | | | Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Dave Airlie <airlied@redhat.com>
* radv: add missing TFB queries support to CmdCopyQueryPoolsResults()Samuel Pitoiset2018-11-051-0/+277
| | | | | | | Cc: 18.3 <mesa-stable@lists.freedesktop.org> Fixes: b4eb029062a ("radv: implement VK_EXT_transform_feedback") Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Dave Airlie <airlied@redhat.com>
* radv: remove useless sync after copying query results with computeSamuel Pitoiset2018-11-051-4/+0
| | | | | | | | | | | | | | | The spec says: "vkCmdCopyQueryPoolResults is considered to be a transfer operation, and its writes to buffer memory must be synchronized using VK_PIPELINE_STAGE_TRANSFER_BIT and VK_ACCESS_TRANSFER_WRITE_BIT before using the results." VK_PIPELINE_STAGE_TRANSFER_BIT will wait for compute to be idle, while VK_ACCESS_TRANSFER_WRITE_BIT will invalidate both L1 vector caches and L2. So, it's useless to set those flags internally. Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
* radv: use WAIT_REG_MEM_GREATER_OR_EQUAL instead of a magic valueSamuel Pitoiset2018-10-311-1/+1
| | | | | Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Dave Airlie <airlied@redhat.com>
* radv: use pool->stride when calling radv_query_shader()Samuel Pitoiset2018-10-311-2/+2
| | | | | | | Not needed to recompute the stride. Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Dave Airlie <airlied@redhat.com>
* radv: implement VK_EXT_transform_feedbackSamuel Pitoiset2018-10-291-10/+101
| | | | | | | | This implementation should work and potential bugs can be fixed during the release candidates window anyway. Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Dave Airlie <airlied@redhat.com>
* ac: correct PKT3_COPY_DATA definitionsMarek Olšák2018-10-061-4/+4
|
* radv: fix resetting the pool for timestamp queriesSamuel Pitoiset2018-10-041-7/+5
| | | | | | | | | | | Since the driver no longer uses the availability bit for timestamp queries it shouldn't reset it. Instead, it should reset the query values to UINT32_MAX. This fixes VM faults. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108164 Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Tested-by: Józef Kucia <joseph.kucia@gmail.com> Reviewed-by: Dave Airlie <airlied@redhat.com>
* radv: do not use the availability bit for timestamp queriesSamuel Pitoiset2018-09-281-30/+27
| | | | | | | | | | | It's unnecessary because we can just check if the timestamp is to different to the default value when a pool is created or resetted. Instead of waiting for the availability bit to be 1, we have to emit a not equal WAIT_REG_MEM for checking if the timestamp is ready. Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Dave Airlie <airlied@redhat.com>
* radv: Add on-demand compilation of built-in shaders.Bas Nieuwenhuizen2018-08-141-5/+27
| | | | | | | | | | | | | | | | | | | | | | | | | In environments where we cannot cache, e.g. Android (no homedir), ChromeOS (readonly rootfs) or sandboxes (cannot open cache), the startup cost of creating a device in radv is rather high, due to compiling all possible built-in pipelines up front. This meant depending on the CPU a 1-4 sec cost of creating a Device. For CTS this cost is unacceptable, and likely for starting random apps too. So if there is no cache, with this patch radv will compile shaders on demand. Once there is a cache from the first run, even if incomplete, the driver knows that it can likely write the cache and precompiles everything. Note that I did not switch the buffer and itob/btoi compute pipelines to on-demand, since you cannot really do anything in Vulkan without them and there are only a few. This reduces the CTS runtime for the no caches scenario on my threadripper from 32 minutes to 8 minutes. Reviewed-by: Dave Airlie <airlied@redhat.com>
* nir: cleanup oversized arrays in nir_swizzle callsKarol Herbst2018-07-131-4/+2
| | | | | | | | | | There are no fixed sized array arguments in C, those are simply pointers to unsized arrays and as the size is passed in anyway, just rely on that. where possible calls are replaced by nir_channel and nir_channels. Reviewed-by: Jason Ekstrand <jason@jlekstrand.net> Signed-off-by: Karol Herbst <kherbst@redhat.com>
* radv: get rid of buffer object prioritiesSamuel Pitoiset2018-07-121-4/+4
| | | | | | | | | We mostly use the same priority for all buffer objects, so I don't think that matter much. This should reduce CPU overhead a little bit. Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
* radv: emit a dummy ZPASS_DONE to prevent GPU hangs on GFX9Samuel Pitoiset2018-07-121-3/+6
| | | | | | | | | | A ZPASS_DONE or PIXEL_STAT_DUMP_EVENT (of the DB occlusion counters) must immediately precede every timestamp event to prevent a GPU hang on GFX9. Cc: 18.1 <mesa-stable@lists.freedesktop.org> Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
* radv: remove unused 'predicated' parameter from some functionsSamuel Pitoiset2018-06-271-5/+2
| | | | | | | It's always false. Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Dave Airlie <airlied@redhat.com>
* radv: emit PIPELINESTAT_{START,STOP} events for pipeline stats queriesSamuel Pitoiset2018-06-261-0/+11
| | | | | | | | | Ported from RadeonSI. This appears to fix some random fails with: dEQP-VK.query_pool.statistics_query.* Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
* radv: use EOP_DATA_SEL_* instead of magic numbersSamuel Pitoiset2018-06-211-3/+6
| | | | | Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
* amd,radeonsi: rename radeon_winsys_cs -> radeon_cmdbufMarek Olšák2018-06-191-5/+5
| | | | Acked-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
* radv: Add option to print errors even in optimized builds.Bas Nieuwenhuizen2018-05-311-3/+3
| | | | | | | | | | | Errors are not that common of a case so we can eat a slight perf hit in having to call a function and do a runtime check. In turn this makes debugging random errors happening for end users easier, because they don't have to have a debug build on hand. Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com> Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
* radv: Fix multiview queries.Bas Nieuwenhuizen2018-05-141-19/+20
| | | | | | | | | | | | | | | | | This moves the extra queries to after the main query ended, instead of doing it after the begin and hence doing nesting. We also emit only (view count - 1) extra queries, as the main query is already there for the first view. This fixes the CTS occasionally getting stuck in dEQP-VK.multiview.queries* waiting on results. Fixes: 32b4f3c38dc "radv/query: handle multiview queries properly. (v3)" CC: 18.1 <mesa-stable@lists.freedesktop.org> Reviewed-by: Dave Airlie <airlied@redhat.com> Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
* radv: only disable out-of-order rast for perfect occlusion queriesSamuel Pitoiset2018-05-021-2/+2
| | | | | Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
* radv: only enable PERFECT_ZPASS_COUNTS for precision occlusion queriesSamuel Pitoiset2018-04-061-5/+31
| | | | | | | | | | This unnecessary when the precision bit flag is not set, and this might hurt performance. The Vulkan explains that not setting VK_QUERY_CONTROL_PRECISE_BIT might be more efficient on some implementations. Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
View Lorry Controller Status