summaryrefslogtreecommitdiffstats
path: root/src/gallium/drivers/vc4
Commit message (Collapse)AuthorAgeFilesLines
* vc4: Add QPU scheduling to handle MUL rotate sources.Eric Anholt2016-08-251-0/+13
| | | | We need MUL rotates to do ddx/ddy support.
* vc4: Add disassembly for constant MUL rotatesEric Anholt2016-08-251-9/+11
|
* vc4: Add real validation for MUL rotation.Eric Anholt2016-08-252-10/+43
| | | | Caught problems in the upcoming DDX/DDY implementation.
* vc4: Add a QIR value for the QPU element register.Eric Anholt2016-08-254-0/+8
| | | | | This will be used in the ddx/ddy support for "Am I the top half?" or "Am I the left half?" checks.
* vc4: Fix GPU hangs with >16 varying values.Eric Anholt2016-08-242-19/+68
| | | | Fixes glsl-routing in piglit and hangs in glbenchmark 2.0.2.
* gallium: add a cap to expose whether driver supports mixed color/zs bitsIlia Mirkin2016-08-231-0/+1
| | | | | | | | | | Some hardware can't render to color/depth buffers of mixed bitness. When that happens a fallback has to happen, but this allows the driver to express that this isn't an optimal scenario. The purpose of this is to remove such fbconfigs from the GLX/EGL config list. Signed-off-by: Ilia Mirkin <[email protected]> Reviewed-by: Marek Olšák <[email protected]>
* vc4: Tell state_tracker that we would prefer NIR.Eric Anholt2016-08-223-8/+31
| | | | | | | | | | Before this series, the code generation path was: GLSL IR -> TGSI -> NIR -> NIR clone -> QIR -> QPU Now it's (generally) GLSL IR -> NIR -> NIR clone -> QIR -> QPU
* vc4: Use proper type sizes for uniforms.Eric Anholt2016-08-221-4/+5
|
* vc4: Add VARYING_SLOT_PNTC support.Eric Anholt2016-08-221-4/+5
| | | | We end up with this when doing GLSL-to-NIR.
* vc4: Fix vc4_nir_lower_io for non-vec4 I/O.Eric Anholt2016-08-221-22/+12
| | | | | To support GLSL-to-NIR, we need to be able to support actual float/vec2/vec3 varyings.
* nir: Define system values for vc4's blending-lowering arguments.Eric Anholt2016-08-224-46/+54
| | | | | | | | | | | | | In the GLSL-to-NIR conversion of VC4, I had a bit of trouble with what I was calling the "state uniforms" that I was putting into the NIR fighting with its other lowering passes. Instead of using magic uniform base numbers in the backend, follow the lead of load_user_clip_plane and just define system values for them. v2: Fix unintended change to channel_num, drop unspecified const_index value on blend_const_color_r_float. Reviewed-by: Kenneth Graunke <[email protected]>
* vc4: Switch store_output to using nir_lower_io_to_scalar / component.Eric Anholt2016-08-192-44/+16
|
* vc4: Use the intrinsic's first_component for vattr VPM index.Eric Anholt2016-08-192-7/+3
| | | | Avoids another multiplication by 4 of the base in the NIR.
* vc4: Convert to using nir_lower_io_scalar for FS inputs.Eric Anholt2016-08-192-44/+62
| | | | | The scalarizing of FS inputs can be done in a non-driver-dependent manner, so extract it out of the driver.
* vc4: Switch to using the intrinsic accessors.Eric Anholt2016-08-193-23/+29
| | | | | The const_index[] values have always felt magic, and this documents them a bit better.
* ttn: Use nir_load_front_face instead of the TGSI-style input.Eric Anholt2016-08-191-14/+1
| | | | | | | This reduces the diff between GLSL-to-NIR and TGSI-to-NIR, and gives NIR more optimization to work on. Reviewed-by: Kenneth Graunke <[email protected]>
* ttn: Make FRAG_RESULT_DEPTH be a float variable to match gtn and ptn.Eric Anholt2016-08-191-1/+1
| | | | | | | This lets TTN-using drivers handle FRAG_RESULT_DEPTH the same between all their source paths. Reviewed-by: Rob Clark <[email protected]>
* vc4: Dump the TGSI before trying to convert it to NIR.Eric Anholt2016-08-191-4/+3
| | | | In the case of debugging a crash in TTN, this is nice to have.
* gallium: add a pipe_context parameter to fence_finishMarek Olšák2016-08-101-0/+1
| | | | | | | | required by glClientWaitSync (GL 4.5 Core spec) that can optionally flush the context Reviewed-by: Rob Clark <[email protected]> Reviewed-by: Nicolai Hähnle <[email protected]>
* gallium: add render_condition_enable param to clear_render_target/depth_stencilMarek Olšák2016-08-101-2/+4
| | | | | Reviewed-by: Roland Scheidegger <[email protected]> Reviewed-by: Nicolai Hähnle <[email protected]>
* vc4: Move scalarizing and some lowering to link time.Eric Anholt2016-08-041-5/+12
| | | | | | | This works out to be a wash in terms of memory usage: We use more memory to store the separate ALU instructions, but we optimize out a lot of code as well. The main result, though, is that we do more of our work at link time rather than draw time.
* vc4: Avoid VS shader recompiles by keeping a set of FS inputs seen so far.Eric Anholt2016-08-043-25/+81
| | | | | | | | | | | | We don't want to bake the whole array into the FS key, because of the hashing overhead. But we can keep a set of the arrays seen, and use a pointer to the copy in as the array's proxy. Between this and the previous patch, gl-1.0-blend-func now passes on hardware, where previously it was filling the 256MB CMA area with shaders and OOMing. Drops 712 shaders from shader-db.
* vc4: Don't recompile the CS when the FS changes.Eric Anholt2016-08-041-0/+2
| | | | | | | The compiled_fs_id is a proxy for the vc4->prog.fs->input_slots[], but only the VS dereferences it. Drops 754 shaders from shader-db.
* vc4: Move FS inputs setup out to a helper function.Eric Anholt2016-08-041-34/+41
| | | | It's a pretty big block, and I was about to make it bigger.
* vc4: Avoid generating a custom shader per level in glGenerateMipmaps().Eric Anholt2016-08-033-7/+25
| | | | | | | | | | We were baking in the LOD of the source level to each shader. Instead, pass it in as a uniform -- this requires storing it to a temp register, but that's better than compiling a ton of separate shaders: total instructions in shared programs: 115032 -> 115036 (0.00%) instructions in affected programs: 96 -> 100 (4.17%) LOST: 572
* vc4: Tell valgrind about BO allocations from mmap time to destroy.Eric Anholt2016-08-032-0/+11
| | | | | | This helps in debugging memory pressure. It would be nice if we could tell valgrind about it all the way from allocation time to destroy, but we need a pointer to hand to VALGRIND_MALLOCLIKE_BLOCK.
* vc4: Fix a leak of the src[] array of VPM reads in optimization.Eric Anholt2016-08-031-4/+5
| | | | Cc: "12.0" <[email protected]>
* vc4: Fix leak of the bo_handles table.Eric Anholt2016-08-031-0/+1
|
* vc4: Fix handling of UBO range offsets.Eric Anholt2016-08-031-2/+3
| | | | | | The ranges are in units of bytes, not dwords. This wasn't caught by piglit tests because ttn tends to make one big uniform file, so we only had one UBO range with a src and dst offset of 0.
* vc4: Dump NIR at shader state creation time as well.Eric Anholt2016-08-031-0/+8
| | | | I keep wanting to see this version of the NIR.
* vc4: Zero-initialize the hardware sampler view structure.Eric Anholt2016-07-311-1/+1
| | | | | Fixes failure to initialize the force_first_level flag, causing failures in piglit levelclamp.
* vc4: automake: remove vc4_drm.h from the sources listsEmil Velikov2016-07-281-1/+0
| | | | | | | | | The file was removed with earlier commit breaking 'make dist'. Drop it from Makefile.sources since it's no longer around. Fixes: 16985eb308e ("vc4: Switch to using the libdrm-provided vc4_drm.h.") Signed-off-by: Emil Velikov <[email protected]>
* vc4: add hash table look-up for exported dmabufsRob Herring2016-07-264-3/+56
| | | | | | | | | | | | | It is necessary to reuse existing BOs when dmabufs are imported. There are 2 cases that need to be handled. dmabufs can be created/exported and imported by the same process and can be imported multiple times. Copying other drivers, add a hash table to track exported BOs so the BOs get reused. v2: Whitespace fixup (by anholt) Signed-off-by: Rob Herring <[email protected]> Reviewed-by: Eric Anholt <[email protected]>
* vc4: Disable early Z with computed depth.Eric Anholt2016-07-263-2/+11
| | | | | We don't tell the hardware whether we're computing depth, so we need to manage early Z state manually. Fixes piglit early-z.
* gallium: split transfer_inline_write into buffer and texture callbacksMarek Olšák2016-07-231-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | to reduce the call indirections with u_resource_vtbl. The worst call tree you could get was: - u_transfer_inline_write_vtbl - u_default_transfer_inline_write - u_transfer_map_vtbl - driver_transfer_map - u_transfer_unmap_vtbl - driver_transfer_unmap That's 6 indirect calls. Some drivers only had 5. The goal is to have 1 indirect call for drivers that care. The resource type can be determined statically at most call sites. The new interface is: pipe_context::buffer_subdata(ctx, resource, usage, offset, size, data) pipe_context::texture_subdata(ctx, resource, level, usage, box, data, stride, layer_stride) v2: fix whitespace, correct ilo's behavior Reviewed-by: Nicolai Hähnle <[email protected]> Acked-by: Roland Scheidegger <[email protected]>
* vc4: Return V3D version details in the GL renderer info.Eric Anholt2016-07-202-1/+12
| | | | This is as close as we get to a name for the 3D blocks.
* vc4: Check the V3D version reported by the kernel.Eric Anholt2016-07-202-0/+62
| | | | | | We don't want to bring up an old userspace driver on a kernel for newer hardware. We'll also want to look at the other ident fields in the future.
* vc4: Detect and report kernel support for branching.Eric Anholt2016-07-201-2/+12
|
* vc4: Switch to using the libdrm-provided vc4_drm.h.Eric Anholt2016-07-202-280/+2
| | | | | The required version is set to .69 for the getparam ioctl that will be used in the next commit.
* gallium: add a cap for VIEWPORT_SUBPIXEL_BITS (v2)Józef Kucia2016-07-201-0/+1
| | | | | | | | | | | | This allows Gallium drivers to advertise the subpixel precision for floating point viewports bounds. v2: - Set ViewportSubpixelBits in st_init_limits. Signed-off-by: Józef Kucia <[email protected]> Signed-off-by: Marek Olšák <[email protected]> Reviewed-by: Ilia Mirkin <[email protected]>
* vc4: Speed up glGenerateMipmaps by avoiding shadow baselevel.Eric Anholt2016-07-155-3/+23
| | | | | | | | | | | | | To support general GL_TEXTURE_BASE_LEVEL we have to copy to a temporary miptree. However, if a single level is being selected, we can use the existing miptree and force all the sampling to be from that particular level. This avoids a ton of software fallbacks in glGenerateMipmaps(), which uses base levels in the blit implementation in gallium. Improves "glmark2 -b terrain" from 2 fps to 3 (perhaps some more precision would be useful?), and cuts its CPU usage during the benchmarking from ~30% to ~10% (total CPU time from 8.8s to 7.6s).
* vc4: Drop VC4_DIRTY_TEXSTATE in favor of the per-stage flags.Eric Anholt2016-07-154-8/+4
| | | | | | The compiler uses the per-stage flags already, so it didn't need this. vc4_uniforms was using it, so just replace it with both of the stage flags for now.
* vc4: Remove dead dirty_samplers field.Eric Anholt2016-07-152-5/+0
| | | | We use a big VC4_DIRTY_FRAGTEX/VC4_DIRTY_VERTEX on the stage, instead.
* vc4: Turn on control flow support in the simulator environment.Eric Anholt2016-07-151-0/+4
| | | | | We can't merge the non-simulator support until we merge the kernel side and get a new libdrm release.
* vc4: Emit resets of the uniform stream at the starts of blocks.Eric Anholt2016-07-139-0/+167
| | | | | | | | If a block might be entered from multiple locations, then the uniform stream will (probably) be at different points, and we need to make sure that it's pointing where we expect it to be. The kernel also enforces that any block reading a uniform resets uniforms, to prevent reading outside of the uniform stream by using looping.
* vc4: Add support for scheduling of branch instructions.Eric Anholt2016-07-132-17/+114
| | | | For now we don't fill the delay slots, and instead just drop in NOPs.
* vc4: Move the QPU instructions to schedule into each block.Eric Anholt2016-07-134-141/+180
| | | | We'll want to schedule them individually, to handle delay slots.
* vc4: Disable vc4_opt_vpm in the presence of control flow.Eric Anholt2016-07-131-0/+5
| | | | | | It's a really valuable pass currently, but it will be a mess to rewrite for control flow. For now, just disable it if we have multiple blocks present.
* vc4: Convert vc4_opt_dead_code to work in the presence of control flow.Eric Anholt2016-07-131-18/+29
| | | | | | | | | | | | With control flow, we can't be sure that we'll see the uses of a variable before its def as we walk backwards. Given that NIR is eliminating our long chains of dead code, a simple solution for now seems fine. This slightly changes the order of some optimizations, and so an opt_vpm happens before opt_dce, causing 3 dead MOVs to be turned into dead FMAXes in Minecraft: instructions in affected programs: 52 -> 54 (3.85%)
* vc4: Update copy propagation for control flow.Eric Anholt2016-07-131-62/+137
| | | | | | | | | | | | | | Previously, we could assume that a MOV from a temp was always an available copy, because all temps were SSA in NIR, and their non-SSA state in QIR was just due to the fact that they were from a bcsel or pack_unorm_4x8, so we could use the current value of the temp after that series of QIR instructions to define it. However, this is no longer the case with control flow. Instead, we track a new array of MOVs defined within the block that haven't had their source or dest killed yet, and use that primarily. We fall back to looking through the QIR defs array to handle across-block MOVs, but now require that copies from the SSA defs have an SSA src as well.
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-22 17:26:53 +0000