summaryrefslogtreecommitdiffstats
path: root/src/amd
Commit message (Collapse)AuthorAgeFilesLines
* radeonsi: set the convergent attribute where neededMarek Olšák2017-03-061-2/+6
| | | | Reviewed-by: Dave Airlie <[email protected]>
* gallivm,ac: add LP_FUNC_ATTR_CONVERGENTMarek Olšák2017-03-062-0/+2
| | | | Reviewed-by: Dave Airlie <[email protected]>
* radeonsi: fix LLVM 3.9 - don't use non-matching attributes on declarationsMarek Olšák2017-03-061-3/+3
| | | | | | | | | Call site attributes are used since LLVM 4.0. This also reverts commit b19caecbd6f310c1663b0cfe483d113ae3bd5fe2 "radeon/ac: fix intrinsic version check", because this is the correct fix. Reviewed-by: Dave Airlie <[email protected]>
* radv: Use the new L2 writeback flag.Bas Nieuwenhuizen2017-03-062-6/+6
| | | | | Signed-off-by: Bas Nieuwenhuizen <[email protected]> Reviewed-by: Dave Airlie <[email protected]>
* radv: Add L2 writeback.Bas Nieuwenhuizen2017-03-062-34/+54
| | | | | Signed-off-by: Bas Nieuwenhuizen <[email protected]> Reviewed-by: Dave Airlie <[email protected]>
* radv/ac: use bitfield extract new intrinsics.Dave Airlie2017-03-061-7/+4
| | | | | Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv/ac: move to new kill build.Dave Airlie2017-03-061-5/+2
| | | | | Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv/ac: move to using new export intrinsics.Dave Airlie2017-03-061-93/+86
| | | | | | | This uses the new code in build to do exports. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv/ac: switch to new intrinsics for pkrtz and clamp.Dave Airlie2017-03-061-5/+2
| | | | | Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: drop Z24 support.Dave Airlie2017-03-051-3/+0
| | | | | | | | | This isn't exposed in -pro, the hw docs say it is deprecated, so let's not bother with it. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Cc: "13.0 17.0" <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: use VK_NULL_HANDLE for handlesGrazvydas Ignotas2017-03-062-5/+5
| | | | | | | Avoids warnings on 32bit. Signed-off-by: Grazvydas Ignotas <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* radv: check for upload alloc failureGrazvydas Ignotas2017-03-061-3/+4
| | | | | | | | Mainly to avoid gcc's complains about uninitialized ptr and offset use later in that code. Signed-off-by: Grazvydas Ignotas <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* radv: don't use uninitialized value on failureGrazvydas Ignotas2017-03-061-1/+1
| | | | | | | Mainly to avoid a warning. Signed-off-by: Grazvydas Ignotas <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* radv: avoid casting warnings on 32bitGrazvydas Ignotas2017-03-062-3/+5
| | | | | | | Use the same helpers as for other handle<->pointer conversions. Signed-off-by: Grazvydas Ignotas <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* radv/amdgpu: Add some debug flags.Bas Nieuwenhuizen2017-03-066-16/+52
| | | | | Signed-off-by: Bas Nieuwenhuizen <[email protected]> Reviewed-by: Dave Airlie <[email protected]>
* radv: Cache command buffers in command pool.Bas Nieuwenhuizen2017-03-062-48/+84
| | | | | | | | | | | So that we don't keep allocating BOs for the IBs and upload buffers. We run some risk of memory increase with e.g. a bimodal size distribution of command buffers, but I haven't noticed a significant increase with dota2 and talos. Signed-off-by: Bas Nieuwenhuizen <[email protected]> Reviewed-by: Dave Airlie <[email protected]>
* radeon/ac: fix intrinsic version checkDave Airlie2017-03-061-1/+1
| | | | | | | Reported-by: [email protected] Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=100068 Signed-off-by: Dave Airlie <[email protected]>
* radv: Merge fast clear flushes.Bas Nieuwenhuizen2017-03-051-13/+35
| | | | | | | | Don't flush multiple times if we clear multiple attachments. Also allows doing the depth clear in parallel with the fast color clears. Signed-off-by: Bas Nieuwenhuizen <[email protected]> Reviewed-by: Dave Airlie <[email protected]>
* radv: use enum_to_str util functions.Emil Velikov2017-03-042-34/+5
| | | | | | | | | Port of e9dcb17962f7e58a81c93bae7bd33885675b1043 vulkan/util: Add generator for enum_to_str functions Cc: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Emil Velikov <[email protected]> Reviewed-by: Eric Engestrom <[email protected]>
* ac: normalize build helper namesMarek Olšák2017-03-033-283/+282
| | | | | | s/emit/build/ Reviewed-by: Dave Airlie <[email protected]>
* ac: replace SI.vs.load.input with amdgcn.buffer.load.formatMarek Olšák2017-03-031-0/+20
| | | | Reviewed-by: Dave Airlie <[email protected]>
* radeonsi: move SI.vs.load.input building into amd/commonMarek Olšák2017-03-032-0/+23
| | | | Reviewed-by: Dave Airlie <[email protected]>
* ac: replace llvm.SI.tbuffer.store with llvm.amdgcn.buffer.store if ADD_TID=0Marek Olšák2017-03-033-4/+62
| | | | | | | | ADD_TID doesn't work. Needs more investigation. v2: remove leftover dead code Reviewed-by: Dave Airlie <[email protected]> (v1)
* ac: remove offen parameter from ac_build_buffer_store_dwordMarek Olšák2017-03-033-10/+8
| | | | Reviewed-by: Dave Airlie <[email protected]>
* radeonsi: merge and simplify tbuffer_store functionsMarek Olšák2017-03-033-74/+38
| | | | Reviewed-by: Dave Airlie <[email protected]>
* radeonsi: replace AMDGPU.bfe.* with amdgcn.*bfeMarek Olšák2017-03-032-0/+29
| | | | Reviewed-by: Dave Airlie <[email protected]>
* radeonsi: move kill intrinsic building into amd/commonMarek Olšák2017-03-032-0/+17
| | | | | | just a cleanup Reviewed-by: Dave Airlie <[email protected]>
* radeonsi: set readnone on reads from read-only memoryMarek Olšák2017-03-032-3/+11
|
* radeonsi: replace SI.packf16 with amdgcn.cvt.pkrtzMarek Olšák2017-03-032-0/+20
|
* ac: replace old image intrinsics with new onesMarek Olšák2017-03-031-0/+80
| | | | Reviewed-by: Dave Airlie <[email protected]>
* radeonsi: move image intrinsic building to amd/commonMarek Olšák2017-03-032-0/+97
| | | | Reviewed-by: Dave Airlie <[email protected]>
* ac: replace SI.export with amdgcn.exp.*Marek Olšák2017-03-031-0/+31
| | | | Reviewed-by: Dave Airlie <[email protected]>
* radeonsi: move llvm.SI.export building to amd/commonMarek Olšák2017-03-032-0/+26
| | | | Reviewed-by: Dave Airlie <[email protected]>
* ac: unify build_type_name_for_intr functionsMarek Olšák2017-03-033-38/+42
| | | | Reviewed-by: Dave Airlie <[email protected]>
* gallivm, ac: add writeonly and inaccessiblememonly attributesMarek Olšák2017-03-032-0/+4
| | | | Reviewed-by: Dave Airlie <[email protected]>
* amd/common: Fix build with new ac_add_function_attr()Tobias Klausmann2017-03-013-3/+5
| | | | | | | | | | | | | Fix usage of ac_add_function_attr() and make it known! common/ac_nir_to_llvm.c: In function 'create_llvm_function': common/ac_nir_to_llvm.c:265:4: error: implicit declaration of function 'ac_add_function_attr' [-Werror=implicit-function-declaration] ac_add_function_attr(main_function, i + 1, AC_FUNC_ATTR_BYVAL); ^~~~~~~~~~~~~~~~~~~~ Signed-off-by: Tobias Klausmann <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* gallivm,ac: add function attributes at call sites instead of declarationsMarek Olšák2017-03-014-48/+86
| | | | | | | | | | | | | | | | They can vary at call sites if the intrinsic is NOT a legacy SI intrinsic. We need this to force readnone or inaccessiblememonly on some amdgcn intrinsics. This is only used with LLVM 4.0 and later. Intrinsics only used with LLVM <= 3.9 don't need the LEGACY flag. gallivm and ac code is in the same patch, because splitting would be more complicated with all the LEGACY uses all over the place. v2: don't change the prototype of lp_add_function_attr. Reviewed-by: Jose Fonseca <[email protected]> (v1)
* gallivm,ac: remove unused FUNC_ATTR_LAST enumsMarek Olšák2017-03-011-1/+0
| | | | Reviewed-by: Jose Fonseca <[email protected]>
* radv: fix txs for sampler buffersDave Airlie2017-03-011-1/+1
| | | | | | | | | I messed this up when I wrote it, this fixes: dEQP-VK.memory.pipeline_barrier.*uniform_texel_buffer.* Reviewed-by: Bas Nieuwenhuizen <[email protected]> Cc: "17.0" <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* amd/common: fix ASICREV_IS_POLARIS11_M for Polaris12Marek Olšák2017-02-281-1/+1
| | | | | | Cc: 17.0 <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Dave Airlie <[email protected]>
* radv: Don't allocate space for unused immutable samplers.Bas Nieuwenhuizen2017-02-281-9/+14
| | | | | Signed-off-by: Bas Nieuwenhuizen <[email protected]> Reviewed-by: Dave Airlie <[email protected]>
* radv/ac: Use constants for immutable samplers.Bas Nieuwenhuizen2017-02-281-0/+16
| | | | | Signed-off-by: Bas Nieuwenhuizen <[email protected]> Reviewed-by: Dave Airlie <[email protected]>
* radv: Detect if all immutable samplers for a binding are equal.Bas Nieuwenhuizen2017-02-282-0/+6
| | | | | | | We can then use constants for indexed loads. Signed-off-by: Bas Nieuwenhuizen <[email protected]> Reviewed-by: Dave Airlie <[email protected]>
* radv: Store the immutable samplers as uint32_t[4].Bas Nieuwenhuizen2017-02-282-10/+6
| | | | | | | So we don't need to know about radv_sampler in ac_nir_to_llvm. Signed-off-by: Bas Nieuwenhuizen <[email protected]> Reviewed-by: Dave Airlie <[email protected]>
* radeon/ac: make ac_shader_binary_config_start() available externallyTimothy Arceri2017-02-282-1/+8
| | | | | | | | The read config functions are different for r600 and radeonsi so we can't just share the one in amd common. So just share this instead. Reviewed-by: Marek Olšák <[email protected]>
* radeon/ac: add llvm_ir_string to ac_shader_binary structTimothy Arceri2017-02-281-0/+1
| | | | Reviewed-by: Marek Olšák <[email protected]>
* radv: fix depth format in blit2d.Dave Airlie2017-02-281-2/+5
| | | | | | | | | | | | | For blitting we need to use the depth or stencil format, never the combined. This fixes: dEQP-VK.texture.shadow.2d.nearest.less_or_equal_d32_sfloat_s8_uint and a few others. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Cc: "13.0 17.0" <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv/formats: add fast clear for 8-bit signed ints.Dave Airlie2017-02-281-0/+16
| | | | | | | These formats are used by some CTS tests, may as well fill them in. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: Use correct size for availability flag.Bas Nieuwenhuizen2017-02-271-2/+5
| | | | | | | | | | Per spec, VK_QUERY_RESULT_64_BIT specifies the integer size and the availability flag is an integer. We apparently handled this correctly already for the copy to buffer case. Signed-off-by: Bas Nieuwenhuizen <[email protected]> Reviewed-by: Dave Airlie <[email protected]> Cc: 13.0 17.0 <[email protected]>
* radv: Only use PKT3_OCCLUSION_QUERY when it doesn't hang.Bas Nieuwenhuizen2017-02-271-20/+45
| | | | | | | | | | | | | PKT3_OCCLUSION_QUERY hangs when used in a nested IB. This only calls it when in a primary command buffer and we change GetQueryPoolResults to not need it. CmdCopyQueryPoolResults still needs it so we break that behavior for secondary command buffers. However, that would hang already and using an unitialized value is better than a hang. Signed-off-by: Bas Nieuwenhuizen <[email protected]> Reviewed-by: Dave Airlie <[email protected]> Cc: 13.0 17.0 <[email protected]>
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-23 17:17:52 +0000