summaryrefslogtreecommitdiffstats
path: root/src/amd
Commit message (Collapse)AuthorAgeFilesLines
* radv: fix texturesamples to handle single sample caseDave Airlie2016-11-111-2/+10
| | | | | | | | | | | | We can only read the valid samples if this is an MSAA texture, which means the type field must be 0x14 or 0x15. This fixes: dEQP-VK.glsl.texture_functions.query.texturesamples.* Cc: "13.0" <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: automake: list correct file in the EXTRA_DISTEmil Velikov2016-11-101-1/+1
| | | | | | | | | Earlier commit renamed the file radeon_icd.json{,.in} but missed one reference of the file - in EXTRA_DIST. Cc: "13.0" <[email protected]> Fixes: 0f434a68a ("radv: Suffix the radeon_icd file with the host CPU") Signed-off-by: Emil Velikov <[email protected]>
* radv: fixup botched llvm API changes.Dave Airlie2016-11-101-4/+3
| | | | | Reported-by: Jan Vesely <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* ac/nir/llvm: adopt to new LLVM attribute API.Dave Airlie2016-11-101-36/+108
| | | | | | | | Ported from corresponding changes to gallivm. tested build against 3.9 and master. Signed-off-by: Dave Airlie <[email protected]>
* radv: Suffix the radeon_icd file with the host CPUEmil Velikov2016-11-093-3/+9
| | | | | | | | | | | Port of the anv commit d96345de989 ("anv: Suffix the intel_icd file with the host CPU"). v2: s/intel_icd/radeon_icd/ in commit summary (Gražvydas) Cc: "13.0" <[email protected]> Signed-off-by: Emil Velikov <[email protected]> Reviewed-by: Dave Airlie <[email protected]> (IRC)
* radv: use correct .specVersion for extensionsEmil Velikov2016-11-091-4/+4
| | | | | | | | Analogous to previous commit. Cc: "13.0" <[email protected]> Signed-off-by: Emil Velikov <[email protected]> Reviewed-by: Dave Airlie <[email protected]> (IRC)
* amd/addrlib: limit fastcall/regparm to GCC i386Emil Velikov2016-11-091-1/+5
| | | | | | | | | | | | | | | | The use of regparm causes an error on arm/arm64 builds with clang. fastcall is allowed, but still throws a warning. As both options only have effect on 32-bit x86 builds, limit them to that case. v2: keep the __i386__ within GCC (Nicolai) Cc: 13.0 <[email protected]> Cc: Rob Herring <[email protected]> Cc: Nicolai Hähnle <[email protected]> Signed-off-by: Emil Velikov <[email protected]> Reviewed-by: Nicolai Hähnle <[email protected]> Reviewed-by: Marek Olšák <[email protected]> Reviewed-by: Rob Herring <[email protected]>
* radv: fix GetFenceStatus for signaled fencesDave Airlie2016-11-091-0/+2
| | | | | | | | | | if a fence is created pre-signaled we should return that in GetFenceStatus even if it hasn't been submitted. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Reviewed-by: Gustaw Smolarczyk <[email protected]> Cc: "13.0" <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: enable conditional discard optimisation on radv.Dave Airlie2016-11-101-0/+1
| | | | | | | | | | | | | This fixes a bunch of GPU hangs introduced in some CTS tests like dEQP-VK.memory.pipeline_barrier.host_write_uniform_buffer.65536 It works around an issue seen in the LLVM backend, but also makes the radv code work more like the radeonsi stack. Cc: "13.0" <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* ac/nir: add support for discard_if intrinsic (v2)Dave Airlie2016-11-101-0/+21
| | | | | | | | | | We are going to start lowering to this in NIR code, so prepare radv for it. v2: handle conversion to kilp properly (nha) Cc: "13.0" <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: emit correct last export when Z/stencil export is enabledDave Airlie2016-11-091-3/+5
| | | | | | | | | | | | | | | I was getting a random GPU hang in the renderpass simple tests, it turns out sometimes radv emitted the wrong thing "last". This fixes the logic to emit Z/stencil last if they occur, and not mark a color output as last. Also this relies on the Z/STENCIL being the first two fragment outputs, which they are so yay. Fixes: dEQP-VK.renderpass.simple.color_depth (random hangs) Cc: "13.0" <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* android: amd/common: add support for libmesa_amd_commonMauro Rossi2016-11-053-0/+59
| | | | | | | | | | | | | | | Fixes the following building error introduced with commit 7115e56 and related amd/common dependencies: external/mesa/src/gallium/drivers/radeonsi/si_shader.c:6861: error: undefined reference to 'ac_is_sgpr_param' external/mesa/src/gallium/drivers/radeonsi/si_shader.c:6951: error: undefined reference to 'ac_is_sgpr_param' clang++: error: linker command failed with exit code 1 (use -v to see invocation) ninja: build stopped: subcommand failed. build/core/ninja.mk:148: recipe for target 'ninja_wrapper' failed make: *** [ninja_wrapper] Error 1 Signed-off-by: Marek Olšák <[email protected]>
* amd/common: add ac_is_sgpr_param helperNicolai Hähnle2016-11-032-0/+12
| | | | | Reviewed-by: Dave Airlie <[email protected]> Reviewed-by: Marek Olšák <[email protected]>
* amd/common: build also for gallium driversNicolai Hähnle2016-11-032-1/+9
| | | | | | | | At least when LLVM is used, which is basically always (unless you're only building r600 without OpenCL). Reviewed-by: Dave Airlie <[email protected]> Reviewed-by: Marek Olšák <[email protected]>
* amd/common: move llvm helper prototype to ac_llvm_util.hNicolai Hähnle2016-11-034-7/+13
| | | | | Reviewed-by: Dave Airlie <[email protected]> Reviewed-by: Marek Olšák <[email protected]>
* radv: add support for anisotropic filtering on VI+Fredrik Höglund2016-11-031-3/+27
| | | | | | | Ported from radeonsi. Cc: "13.0" <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: fix dual source blendingDave Airlie2016-11-031-3/+9
| | | | | | | | | | | Dolphin tried to use this, but we hadn't had any tests for it properly. All that is required is the shader output format needs to be set for 0 and 1 exports. Cc: "13.0" <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: expose xlib platform extensionDave Airlie2016-11-021-0/+6
| | | | | | | | | I missed this when I added the xlib code, this allows dolphin emu to start and crash later. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Cc: "13.0" <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* amd: fix a typo in PIXEL_PIPE_STAT_RESET definitionMarek Olšák2016-11-011-1/+1
| | | | Reviewed-by: Nicolai Hähnle <[email protected]>
* radv: drop some unused cmask info members.Dave Airlie2016-11-012-8/+0
| | | | | | | | These were assigned but never used. Inspired by similiar patch in radeonsi. Signed-off-by: Dave Airlie <[email protected]>
* radv: split the device local memory heap into twoFredrik Höglund2016-10-283-6/+20
| | | | | | | | | | Advertise two device local memory heaps; one that is host visible and one that is not. This makes it possible for clients to tell how much host visible vs. non-host visible memory is available. Signed-off-by: Dave Airlie <[email protected]>
* radv: add a write-combining host-local memory typeFredrik Höglund2016-10-281-4/+13
| | | | | | | | | | | | | | | | | | | | | | Add the new memory type between the two device-local types. This makes the list of supported memory types look like this: 1) DEVICE_LOCAL | | | 2) | HOST_VISIBLE | HOST_COHERENT | 3) DEVICE_LOCAL | HOST_VISIBLE | HOST_COHERENT | 4) | HOST_VISIBLE | HOST_COHERENT | HOST_CACHED With this order a client that searches for a HOST_VISIBLE and HOST_COHERENT memory type using the algorithm described in section 10.2 of the Vulkan specification (revision 32) will find the host- local memory type first. A client that requires the memory type to be HOST_VISIBLE and HOST_COHERENT, but not DEVICE_LOCAL is most likely searching for a memory type suitable for staging buffers / images. Reviewed-by: Edward O'Callaghan <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv/ac/llvm: trim texture return valuesDave Airlie2016-10-271-1/+2
| | | | | | | | | | | | | The intrinsic engine asserts in llvm due to this, as we put a vec4 into a vec1, and the next instruction isn't expecting it. So trim the vector at the end before inserting it. Reported-by: Christoph Haag <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]> Cc: "13.0" <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* gallium/radeon: fix a ZPASS comment, EVENT_WRITE_EOP fixupsMarek Olšák2016-10-261-1/+1
| | | | Reviewed-by: Nicolai Hähnle <[email protected]>
* nir/i965/anv/radv/gallium: make shader info a pointerTimothy Arceri2016-10-2611-54/+54
| | | | | | | | | | When restoring something from shader cache we won't have and don't want to create a nir_shader this change detaches the two. There are other advantages such as being able to reuse the shader info populated by GLSL IR. Reviewed-by: Jason Ekstrand <[email protected]>
* radv: mark the fence as submitted and signalled in vkAcquireNextImageKHRFredrik Höglund2016-10-263-9/+18
| | | | | | | | This stops the debug layers from complaining when fences are used to throttle image acquisition. Cc: "13.0" <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: Replace "abi_versions" with correct "api_version".Matt Turner2016-10-252-2/+2
| | | | | | | | git history shows "abi_versions" was used from the outset. Cc: <[email protected]> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=98415 Reviewed-by: Dave Airlie <[email protected]>
* radv: allow cmask transitions without fast clearDave Airlie2016-10-241-3/+0
| | | | | | | | | | | | | | This fixes dEQP-VK.pipeline.multisample.sampled_image* These all render to multisampled image, and then sample from it, so we must transition it correctly, since we have a cmask and fmask this will cause the correct transition. Cc: "13.0" <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: use emit_icmp for samples_identicalDave Airlie2016-10-201-1/+1
| | | | | | | | | On a debug llvm build we'd assert on the next compare when the return from samples_identical was i1 instead of i32. Cc: "13.0" <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: decompress fmask before reading using texture unitDave Airlie2016-10-193-6/+5
| | | | | | | | Before we can read the fmask using the compute shader, we need to decompress the fmask in place. This fixes a bunch of remaining failure and hopefully multisampling in Talos.
* radv: fix samples_identical return value.Dave Airlie2016-10-191-0/+3
| | | | | | | This was returning an inversion, so not doing as it should have. We need to compare the fmask value with 0, and return the result from that.
* radv: fix wsi porting regression in swapchain destroy.Dave Airlie2016-10-191-3/+10
| | | | | The code in anv is right, there's a pending patch to fix this up different, but I'll sync the code for now.
* radv: fix fmask ptr issueDave Airlie2016-10-191-4/+18
| | | | We were using the wrong descriptor in the fmask picking code.
* radv: simplify fast clear shadersDave Airlie2016-10-191-46/+2
| | | | There is no need for anything but a noop shader here.
* radv: start using defines for the user sgpr offsetsDave Airlie2016-10-193-14/+34
| | | | | | | | This adds some comments and adds defines for the user sgprs, so that we can move them around easier later and not have to change/revalidate every one of these. Signed-off-by: Dave Airlie <[email protected]>
* radv: port to common wsi codebaseDave Airlie2016-10-197-1860/+216
| | | | | | | | | | This drops all the radv WSI code in favour of using the new shared code that was ported from anv This regresses Talos for now, Jason has pointed out the bug is in Talos and we should wait for them to fix it. Reviewed-by: Jason Ekstrand <[email protected]>
* radv/anv/wsi: drop unneeded parameterDave Airlie2016-10-194-4/+1
| | | | Reviewed-by: Jason Ekstrand <[email protected]>
* radv: drop pointless struct decl.Dave Airlie2016-10-191-2/+0
| | | | | Acked-by: Jason Ekstrand <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: move to using shared vk_alloc inlines.Dave Airlie2016-10-1912-131/+88
| | | | | | | | This moves to the shared vk_alloc inlines for vulkan memory allocations. Acked-by: Jason Ekstrand <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: drop local MIN/MAX macros.Dave Airlie2016-10-194-7/+4
| | | | | | | Use the ones in macros.h instead. Acked-by: Jason Ekstrand <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: make use of shared vector helper.Dave Airlie2016-10-193-135/+8
| | | | | | | | This removes the vector code from radv in favour of sharing code with anv. Acked-by: Jason Ekstrand <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv/winsys: Fail early on overgrown cs.Gustaw Smolarczyk2016-10-161-4/+14
| | | | | | | | When !use_ib_bos, we can't easily chain ibs one to another. If the required cs size grows over 1Mi - 8 dwords just fail the cs so that we won't assert-fail in radv_amdgpu_winsys_cs_submit later on. Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* radv: move AMDGPU_LIBS later in the link chainEmil Velikov2016-10-141-1/+2
| | | | | | | | | | At the moment (albeit unlikely) one could get link-time issues, since libdrm_amdgpu.so is before it's users in the link chain. Signed-off-by: Emil Velikov <[email protected]> Reviewed-by: Dave Airlie <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]> Acked-by: Bas Nieuwenhuizen <[email protected]>
* radv: correct variable name VISIBILITY_{, C}FLAGSEmil Velikov2016-10-141-1/+2
| | | | | | | | | | | The letter C was missing, thus in turn all the internal symbols were exported. As a result we hide ~150 symbols and cut ~36K from libvulkan_radeon.so. Signed-off-by: Emil Velikov <[email protected]> Reviewed-by: Dave Airlie <[email protected]> Acked-by: Bas Nieuwenhuizen <[email protected]>
* amd/addrlib: hide private symbols via VISIBILITY_CXXFLAGSEmil Velikov2016-10-141-0/+3
| | | | | | | | | Private/internal symbols should not be exported. Using the CXXFLAGS cuts ~300 exported symbols and ~23K from libvulkan_radeon.so. Signed-off-by: Emil Velikov <[email protected]> Acked-by: Bas Nieuwenhuizen <[email protected]> Reviewed-by: Marek Olšák <[email protected]>
* radv: fix the wayland wsi busy bitDave Airlie2016-10-141-1/+1
| | | | Signed-off-by: Dave Airlie <[email protected]>
* radv: Use new image load/store intrinsic signatures v2Tom Stellard2016-10-141-25/+108
| | | | | | | | | | These were changed in LLVM r284024. v2: - Only use float types for vdata of llvm.amdgcn.image.store. LLVM doesn't support integer types for this intrinsic. Signed-off-by: Dave Airlie <[email protected]>
* radv: Fix incorrect commentTom Stellard2016-10-141-2/+2
| | | | Signed-off-by: Dave Airlie <[email protected]>
* radv: fix identity swizzle handlingDave Airlie2016-10-141-8/+10
| | | | | | | | | | The identity swizzle should operate exactly like an .r = R, .g = G, .b = B, .a = A swizzle. This fixes a bunch of the 16-bit BGRA blit tests dEQP-VK.api.copy_and_blit.blit_image.all_formats.b4g4r4a4* Signed-off-by: Dave Airlie <[email protected]>
* radv/wsi: fix app that acquire multiple images up frontDave Airlie2016-10-142-0/+2
| | | | | | | | | | | | | | dota2 does multiple acquires followed by multiple queues, this bug manifested itself as a hang in the xshmfence code randomly when dota2 was doing it's menus. It also occured when running dota2 under phoronix-test-suite. The fix is once the image is acquired to mark it busy then so nobody else can acquire. We have to trust vulkan apps that they will eventually submit it. Acked-by: Edward O'Callaghan <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-17 04:43:54 +0000