summaryrefslogtreecommitdiffstats
path: root/src/gallium/drivers/radeon
Commit message (Collapse)AuthorAgeFilesLines
* radeonsi: rework RB+ for StoneyMarek Olšák2016-02-022-6/+2
| | | | | | | | | | | | | | | This fixes it. States which also need to be taken into account: - SPI color formats - each down-conversion format supports only a limited set of SPI formats - whether MSAA resolving and logic op are enabled These need special handling: - blending - disabled channels Reviewed-by: Nicolai Hähnle <[email protected]>
* radeonsi: Add option for SI schedulerAxel Davy2016-01-282-0/+2
| | | | | | | | | | Add a debug option to select the LLVM SI Machine Scheduler. R600_DEBUG=sisched Signed-off-by: Axel Davy <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]> Reviewed-by: Nicolai Hähnle <[email protected]> Reviewed-by: Marek Olšák <[email protected]>
* r600,compute: Plug few memory leaksJan Vesely2016-01-262-0/+23
| | | | | | | | | | | v2: drop inline keyword drop radeon_llvm_dispose_kernel_module wrapper v3: move definitions to .c file use in radeonsi Signed-off-by: Jan Vesely <[email protected]> Signed-off-by: Marek Olšák <[email protected]>
* radeonsi: change LLVM intrinsics for BREV, CLAMP, EX2Marek Olšák2016-01-221-3/+6
| | | | | | | Requested by Matt Arsenault. Reviewed-by: Tom Stellard <[email protected]> Reviewed-by: Nicolai Hähnle <[email protected]>
* gallium/radeon: rename max_compute_units -> num_good_compute_unitsMarek Olšák2016-01-222-3/+3
| | | | | | radeon sets this correctly, but not amdgpu Reviewed-by: Nicolai Hähnle <[email protected]>
* radeonsi: use all SPI color formatsMarek Olšák2016-01-221-1/+5
| | | | | | | | | because not using SPI_SHADER_32_ABGR doubles fill rate. We should also get optimal performance if alpha isn't needed or blending isn't enabled. Reviewed-by: Nicolai Hähnle <[email protected]>
* radeonsi: use SPI_SHADER_COL_FORMAT fields instead of export_16bpcMarek Olšák2016-01-221-0/+1
| | | | | | | | | | | | | This does change the behavior slightly: If a shader writes COLOR[i] and that color buffer isn't bound, the shader will export MRT_NULL instead and discard the IR tree that calculates the output. The only exception is alpha-to-coverage, which requires an alpha export. v2: - update a comment about 16BPC - account for MRTZ when when fixing alpha-test/kill Reviewed-by: Nicolai Hähnle <[email protected]>
* gallium/radeon: Rename do_invalidate_resource to invalidate_bufferMichel Dänzer2016-01-181-4/+6
| | | | | | | And only call it from r600_invalidate_resource for buffer resources. Reviewed-by: Nicolai Hähnle <[email protected]> Reviewed-by: Marek Olšák <[email protected]>
* gallium/radeon: do not reallocate user memory buffersNicolai Hähnle2016-01-142-8/+31
| | | | | | | | | The whole point of AMD_pinned_memory is that applications don't have to map buffers via OpenGL - but they're still allowed to, so make sure we don't break the link between buffer object and user memory unless explicitly instructed to. Reviewed-by: Marek Olšák <[email protected]>
* gallium/radeon: implement PIPE_CAP_INVALIDATE_BUFFERNicolai Hähnle2016-01-143-7/+20
| | | | Reviewed-by: Marek Olšák <[email protected]>
* gallium/radeon: reset valid_buffer_range on PIPE_TRANSFER_DISCARD_WHOLE_RESOURCENicolai Hähnle2016-01-141-0/+3
| | | | | | | This accomodates a streaming pattern where the discard flag is set when the application wraps back to the beginning of the buffer. Reviewed-by: Marek Olšák <[email protected]>
* gallium/radeon: dump LLVM module outside of radeon_llvm_compileMarek Olšák2016-01-032-4/+3
| | | | | Reviewed-by: Edward O'Callaghan <[email protected]> Reviewed-by: Nicolai Hähnle <[email protected]>
* gallium/radeon: always add +DumpCode to the LLVM target machine for LLVM <= 3.5Marek Olšák2016-01-032-4/+3
| | | | | | | It's the same behavior that we use for later LLVM. Reviewed-by: Edward O'Callaghan <[email protected]> Reviewed-by: Nicolai Hähnle <[email protected]>
* gallium/radeon: r600_can_dump_shader should get TGSI processor type directlyMarek Olšák2016-01-032-7/+3
| | | | | Reviewed-by: Edward O'Callaghan <[email protected]> Reviewed-by: Nicolai Hähnle <[email protected]>
* gallium/radeon: send LLVM diagnostics as debug messagesNicolai Hähnle2016-01-021-15/+46
| | | | | | | | | | | | | Diagnostics sent during code generation and the every error message reported by LLVMTargetMachineEmitToMemoryBuffer are disjoint reporting mechanisms. We take care of both and also send an explicit message indicating failure at the end, so that log parsers can more easily tell the boundary between shader compiles. Removed an fprintf that could never be triggered. Reviewed-by: Edward O'Callaghan <[email protected]> Reviewed-by: Marek Olšák <[email protected]>
* gallium/radeon: pass pipe_debug_callback into radeon_llvm_compile (v2)Nicolai Hähnle2016-01-022-3/+7
| | | | | | | This will allow us to send shader debug info via the context's debug callback. Reviewed-by: Edward O'Callaghan <[email protected]> (v1) Reviewed-by: Marek Olšák <[email protected]>
* gallium/radeon: implement set_debug_callbackNicolai Hähnle2016-01-022-0/+14
| | | | | Reviewed-by: Edward O'Callaghan <[email protected]> Reviewed-by: Marek Olšák <[email protected]>
* u_upload_mgr: allow specifying PIPE_USAGE_* for the upload bufferMarek Olšák2016-01-021-1/+1
| | | | Reviewed-by: Nicolai Hähnle <[email protected]>
* u_upload_mgr: remove alignment parameter from u_upload_createMarek Olšák2016-01-021-1/+1
| | | | Reviewed-by: Nicolai Hähnle <[email protected]>
* u_upload_mgr: pass alignment to u_upload_alloc manuallyMarek Olšák2016-01-022-2/+2
| | | | | | | | | | The fixed alignment of u_upload_mgr will go away. This is the first step. The motivation is that one u_upload_mgr can have multiple users, each allocating from the same buffer, but requiring a different alignment. Reviewed-by: Nicolai Hähnle <[email protected]>
* gallium/radeon: fix regression in a number of driver queriesNicolai Hähnle2015-12-211-3/+3
| | | | | | | | This rather silly mistake was introduced by commit 01910676. Cc: "11.1" <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Marek Olšák <[email protected]>
* gallium/radeon: only dispose locally created target machine in ↵Nicolai Hähnle2015-12-181-2/+3
| | | | | | | | | radeon_llvm_compile Unify the cleanup paths of the function rather than duplicating code. Cc: "11.0 11.1" <[email protected]> Reviewed-by: Michel Dänzer <[email protected]>
* configure.ac: use pkg-config for libelfJonathan Gray2015-12-171-2/+3
| | | | | | | | | | | | | Use PKG_CHECK_MODULES to get the flags to link libelf v2: keep AC_CHECK_LIB as a fallback for elfutils provided libelf that doesn't install a pkg-config file. Signed-off-by: Jonathan Gray <[email protected]> Reviewed-by: Michel Dänzer <[email protected]> Tested-by: Michel Dänzer <[email protected]> Cc: "11.0 11.1" <[email protected]> Reviewed-by: Emil Velikov <[email protected]>
* gallium/radeon: remove unnecessary test in r600_pc_query_add_resultNicolai Hähnle2015-12-151-3/+0
| | | | | | | This test is a left-over of the initial development. It is unneeded and misleading, so let's get rid of it. Reviewed-by: Edward O'Callaghan <[email protected]>
* gallium/radeon: remove radeon_winsys_cs_handleMarek Olšák2015-12-1115-69/+60
| | | | | | | | "radeon_winsys_cs_handle *cs_buf" is now equivalent to "pb_buffer *buf". Reviewed-by: Nicolai Hähnle <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]> Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: implement fast stencil clearMarek Olšák2015-12-111-0/+2
| | | | Reviewed-by: Alex Deucher <[email protected]>
* gallium/radeon: fix Hyper-Z hangs by programming PA_SC_MODE_CNTL_1 correctlyMarek Olšák2015-12-112-3/+11
| | | | | | | | | | This is the recommended setting according to hw people and it makes Hyper-Z stable. Just the two magic states. This fixes Evergreen, Cayman, SI, CI, VI (using the Cayman code). Cc: 11.0 11.1 <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
* radeonsi: implement RB+ for Stoney (v2)Marek Olšák2015-12-113-0/+10
| | | | | | v2: fix dual source blending Reviewed-by: Alex Deucher <[email protected]>
* Revert "radeonsi: disable DCC on Stoney"Marek Olšák2015-12-111-4/+0
| | | | | | | | | | | This reverts commit 32f05fadbbdf2a3fb60055e610bbbdcd82dd3ce5. It turned out the problem with Stoney was caused by incorrect handling of a non-power-two VRAM size in the kernel driver. This is an optional BIOS setting and can be worked around by choosing a different VRAM size in the BIOS. Cc: 11.1 <[email protected]>
* radeonsi: disable DCC on StoneyMarek Olšák2015-12-071-0/+4
| | | | | Cc: 11.1 <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
* gallium/drivers: Sanitize NULL checks into canonical formEdward O'Callaghan2015-12-063-6/+6
| | | | | | | | | | Use NULL tests of the form `if (ptr)' or `if (!ptr)'. They do not depend on the definition of the symbol NULL. Further, they provide the opportunity for the accidental assignment, are clear and succinct. Signed-off-by: Edward O'Callaghan <[email protected]> Signed-off-by: Marek Olšák <[email protected]>
* gallium/radeon*: Remove useless castsEdward O'Callaghan2015-12-061-1/+1
| | | | | | | | These are unnecessary and are likely just left overs from prior work. Signed-off-by: Edward O'Callaghan <[email protected]> Signed-off-by: Marek Olšák <[email protected]>
* radeonsi: fix Fiji for LLVM <= 3.7Marek Olšák2015-12-031-1/+2
| | | | | Cc: 11.0 11.1 <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
* radeonsi: fix occlusion queries on FijiMarek Olšák2015-12-031-2/+2
| | | | Tested.
* radeonsi: print framebuffer info into ddebug logsMarek Olšák2015-12-032-2/+2
| | | | Reviewed-by: Michel Dänzer <[email protected]>
* gallium/radeon: print more info about HTILEMarek Olšák2015-12-032-2/+17
| | | | Reviewed-by: Michel Dänzer <[email protected]>
* gallium/radeon: print more info about CMASKMarek Olšák2015-12-032-3/+16
| | | | Reviewed-by: Michel Dänzer <[email protected]>
* gallium/radeon: rename fmask::pitch -> pitch_in_pixelsMarek Olšák2015-12-032-4/+4
| | | | Reviewed-by: Michel Dänzer <[email protected]>
* gallium/radeon: print more information about texturesMarek Olšák2015-12-031-5/+43
| | | | Reviewed-by: Michel Dänzer <[email protected]>
* gallium/radeon: move printing texture info into a separate functionMarek Olšák2015-12-031-41/+51
| | | | Reviewed-by: Michel Dänzer <[email protected]>
* gallium/radeon: remove unused r600_texture::pitch_overrideMarek Olšák2015-12-032-2/+0
| | | | Reviewed-by: Michel Dänzer <[email protected]>
* gallium/radeon: remove DBG_TEXMIPMarek Olšák2015-12-033-4/+2
| | | | | | we don't need 2 flags for dumping texture info Reviewed-by: Michel Dänzer <[email protected]>
* radeon: only suspend queries on flush if they haven't been suspended yetNicolai Hähnle2015-11-282-2/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | Non-timer queries are suspended during blits. When the blits end, the queries are resumed, but this resume operation itself might run out of CS space and trigger a flush. When this happens, we must prevent a duplicate suspend during preflush suspend, and we must also prevent a duplicate resume when the CS flush returns back to the original resume operation. This fixes a regression that was introduced by: commit 8a125afa6e88a3eeddba8c7fdc1a75c9b99d5489 Author: Nicolai Hähnle <[email protected]> Date: Wed Nov 18 18:40:22 2015 +0100 radeon: ensure that timing/profiling queries are suspended on flush The queries_suspended_for_flush flag is redundant because suspended queries are not removed from their respective linked list. Reviewed-by: Marek Olšák <[email protected]> Reported-by: Axel Davy <[email protected]> Cc: "11.1" <[email protected]> Tested-by: Axel Davy <[email protected]> Reviewed-by: Marek Olšák <[email protected]>
* radeon: use PIPE_DRIVER_QUERY_FLAG_DONT_LIST for perfcountersNicolai Hähnle2015-11-261-0/+2
| | | | | | | | Since the query names are not very enlightening, and there are thousands of them, GALLIUM_HUD=help should only show the first and last query name for each hardware block. Reviewed-by: Marek Olšák <[email protected]>
* radeon: delay the generation of driver query names until first useNicolai Hähnle2015-11-262-96/+106
| | | | | | | This shaves a bit more time off the startup of programs that don't actually use performance counters. Reviewed-by: Marek Olšák <[email protected]>
* radeonsi: implement AMD_performance_monitor for CIK+Nicolai Hähnle2015-11-256-3/+784
| | | | | | | | | | | | | | | | | | Expose most of the performance counter groups that are exposed by Catalyst. Ideally, the driver will work with GPUPerfStudio at some point, but we are not quite there yet. In any case, this is the reason for grouping multiple instances of hardware blocks in the way it is implemented. The counters can also be shown using the Gallium HUD. If one is interested to see how work is distributed across multiple shader engines, one can set the environment variable RADEON_PC_SEPARATE_SE=1 to obtain finer-grained performance counter groups. Part of the implementation is in radeon because an implementation for older hardware would largely follow along the same lines, but exposing a different set of blocks which are programmed slightly differently. Reviewed-by: Marek Olšák <[email protected]>
* radeon: scale query buffer size to result sizeNicolai Hähnle2015-11-251-1/+1
| | | | | | | Performance monitor queries can become very big, especially considering that instances of a block in different shader engines are queried separately. Reviewed-by: Marek Olšák <[email protected]>
* radeon: extend CIK_UCONFIG_REG_END for performance countersNicolai Hähnle2015-11-251-1/+1
| | | | Reviewed-by: Marek Olšák <[email protected]>
* radeon: add perfcounter-related EVENT_TYPEsNicolai Hähnle2015-11-251-0/+3
| | | | Reviewed-by: Marek Olšák <[email protected]>
* radeon: additional constants for WAIT_REG_MEM and EVENT_WRITE_EOPNicolai Hähnle2015-11-251-0/+8
| | | | Reviewed-by: Marek Olšák <[email protected]>
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-27 12:11:48 +0000