summaryrefslogtreecommitdiffstats
path: root/src
Commit message (Collapse)AuthorAgeFilesLines
* vc4: Fix build from recent NIR cleanups.Eric Anholt2015-09-141-2/+1
|
* i965/vec4_nir: Load constants as integersAntia Puentes2015-09-141-2/+2
| | | | | | | | | | | Loads constants using integer as their register type, like it is done in FS backend. No shader-db changes in HSW. Cc: "10.6 11.0" <[email protected]> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=91716 Reviewed-by: Jason Ekstrand <[email protected]>
* i965/vec4: Fix saturation errors when coalescing registersAntia Puentes2015-09-141-0/+21
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If the register types do not match and the instruction that contains the final destination is saturated, register coalescing generated non-equivalent code. This did not happen when using IR because types usually matched, but it is visible in nir-vec4. For example, mov vgrf7:D vgrf2:D mov.sat m4:F vgrf7:F is coalesced to: mov.sat m4:D vgrf2:D The patch prevents coalescing in such scenario, unless the instruction we want to coalesce into is a MOV (without type conversion implied). In that case, the patch sets the register types to the type of the final destination. Shader-db results in HSW (only vec4 instructions shown): total instructions in shared programs: 1754415 -> 1754416 (0.00%) instructions in affected programs: 74 -> 75 (1.35%) helped: 0 HURT: 1 GAINED: 0 LOST: 0 Only one extra instruction in one of the shaders, that comes from eliminating a saturation error by preventing register coalesce. Cc: "10.6 11.0" <[email protected]> Reviewed-by: Jason Ekstrand <[email protected]>
* st/mesa: emit TXQS, support ARB_shader_texture_image_samplesIlia Mirkin2015-09-132-1/+6
| | | | | | | | | The image component of the ext is a no-op since there is no image support in gallium (yet). Signed-off-by: Ilia Mirkin <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]> Reviewed-by: Brian Paul <[email protected]>
* r600g: add support for TXQS tgsi opcodeIlia Mirkin2015-09-132-5/+13
| | | | | Signed-off-by: Ilia Mirkin <[email protected]> Reviewed-by: Glenn Kennard <[email protected]>
* nv50/ir: add support for TXQS tgsi opcodeIlia Mirkin2015-09-135-9/+41
| | | | Signed-off-by: Ilia Mirkin <[email protected]>
* gallium: add PIPE_CAP_TGSI_TXQS to let st know if TXQS is supportedIlia Mirkin2015-09-1315-0/+15
| | | | | Signed-off-by: Ilia Mirkin <[email protected]> Reviewed-by: Glenn Kennard <[email protected]>
* tgsi: add a TXQS opcode to retrieve the number of texture samplesIlia Mirkin2015-09-133-2/+14
| | | | | | Signed-off-by: Ilia Mirkin <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]>
* glsl/cs: Initialize gl_LocalInvocationIndex in main()Jordan Justen2015-09-131-0/+22
| | | | | | | | | | | | | | | We initialize gl_LocalInvocationIndex based on the extension spec formula: gl_LocalInvocationIndex = gl_LocalInvocationID.z * gl_WorkGroupSize.x * gl_WorkGroupSize.y + gl_LocalInvocationID.y * gl_WorkGroupSize.x + gl_LocalInvocationID.x; https://www.opengl.org/registry/specs/ARB/compute_shader.txt Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Tapani Pälli <[email protected]>
* glsl/cs: Exclude gl_LocalInvocationIndex from builtin variable strippingJordan Justen2015-09-131-0/+8
| | | | | | | | | | | | | | | | | | We lower gl_LocalInvocationIndex based on the extension spec formula: gl_LocalInvocationIndex = gl_LocalInvocationID.z * gl_WorkGroupSize.x * gl_WorkGroupSize.y + gl_LocalInvocationID.y * gl_WorkGroupSize.x + gl_LocalInvocationID.x; https://www.opengl.org/registry/specs/ARB/compute_shader.txt We need to set this variable in main(), even if gl_LocalInvocationIndex is not referenced by the shader. (It may be used by a linked shader.) Therefore, we can't eliminate it as a dead variable. Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Tapani Pälli <[email protected]>
* glsl/cs: Initialize gl_GlobalInvocationID in main()Jordan Justen2015-09-133-0/+72
| | | | | | | | | | | | | | We initialize gl_GlobalInvocationID based on the extension spec formula: gl_GlobalInvocationID = gl_WorkGroupID * gl_WorkGroupSize + gl_LocalInvocationID https://www.opengl.org/registry/specs/ARB/compute_shader.txt Signed-off-by: Jordan Justen <[email protected]> Cc: Ilia Mirkin <[email protected]> Reviewed-by: Tapani Pälli <[email protected]>
* glsl: Move link_get_main_function_signature to a common locationJordan Justen2015-09-135-33/+34
| | | | | | | | | | | Also rename to _mesa_get_main_function_signature. We will call it near the end of compilation to insert some code into main for initializing some compute shader global variables. Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Tapani Pälli <[email protected]> Reviewed-by: Eduardo Lima Mitev <[email protected]>
* glsl/cs: Don't strip gl_GlobalInvocationID and dependenciesJordan Justen2015-09-131-0/+14
| | | | | | | | | | | | | | | | We lower gl_GlobalInvocationID based on the extension spec formula: gl_GlobalInvocationID = gl_WorkGroupID * gl_WorkGroupSize + gl_LocalInvocationID https://www.opengl.org/registry/specs/ARB/compute_shader.txt We need to set this variable in main(), even if gl_GlobalInvocationID is not referenced by the shader. (It may be used by a linked shader.) Therefore, we can't eliminate these as dead variables. Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Tapani Pälli <[email protected]>
* i965/nir: Support gl_WorkGroupID variableJordan Justen2015-09-131-1/+9
| | | | | Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kristian Høgsberg <[email protected]>
* i965/cs: Initialize gl_WorkGroupID variable from payloadJordan Justen2015-09-132-0/+20
| | | | | Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kristian Høgsberg <[email protected]>
* nir: Add gl_WorkGroupID system variableJordan Justen2015-09-133-0/+6
| | | | | Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kristian Høgsberg <[email protected]>
* glsl/cs: Add gl_WorkGroupID variableJordan Justen2015-09-132-0/+2
| | | | | Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kristian Høgsberg <[email protected]>
* i965/nir: Support gl_LocalInvocationID variableJordan Justen2015-09-131-0/+17
| | | | | Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kristian Høgsberg <[email protected]>
* i965/cs: Initialize gl_LocalInvocationID from payloadJordan Justen2015-09-132-2/+24
| | | | | Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kristian Høgsberg <[email protected]>
* i965/cs: Initialize gl_LocalInvocationID in push constant dataJordan Justen2015-09-131-4/+52
| | | | | Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kristian Høgsberg <[email protected]>
* i965/cs: Reserve local invocation id in payload regsJordan Justen2015-09-134-0/+45
| | | | | | Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kristian Høgsberg <[email protected]> Reviewed-by: Iago Toral Quiroga <[email protected]>
* nir: Add gl_LocalInvocationID variableJordan Justen2015-09-133-0/+6
| | | | | | Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Iago Toral Quiroga <[email protected]> Reviewed-by: Kristian Høgsberg <[email protected]>
* glsl/cs: Add gl_LocalInvocationID variableJordan Justen2015-09-132-0/+13
| | | | | | Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Iago Toral Quiroga <[email protected]> Reviewed-by: Kristian Høgsberg <[email protected]>
* softpipe: Change faces type to uintKrzesimir Nowak2015-09-132-6/+6
| | | | | | | | This is to avoid needless float<->int conversions, since all face-related computations are made on integers. Spotted by Emil Velikov. Reviewed-by: Brian Paul <[email protected]>
* freedreno/ir3: fix compile warn after 1807a08eRob Clark2015-09-131-0/+1
| | | | | | | | | | | | | | New enum to add to switch so compiler doesn't complain. commit 1807a08e4f35b014f2a80d1e88dd74a9f096d7a5 Author: Ilia Mirkin <[email protected]> AuthorDate: Thu Aug 27 23:05:03 2015 -0400 Commit: Ilia Mirkin <[email protected]> CommitDate: Thu Sep 10 17:38:33 2015 -0400 nir: add nir_texop_texture_samples and convert from glsl Signed-off-by: Rob Clark <[email protected]>
* freedreno/ir3: fix compile break after a4aa25beRob Clark2015-09-131-2/+1
| | | | | | | | | | | | | | Following commit dropped the unused memctx arg: commit a4aa25be1e0a27b1a6a6b0bcf576beb9dfe1ea7a Author: Jason Ekstrand <[email protected]> AuthorDate: Wed Sep 9 13:24:35 2015 -0700 Commit: Jason Ekstrand <[email protected]> CommitDate: Fri Sep 11 09:21:20 2015 -0700 nir: Remove the mem_ctx parameter from ssa_def_rewrite_uses Signed-off-by: Rob Clark <[email protected]>
* nir: add nir_channel() to get at single components of vec'sRob Clark2015-09-133-28/+22
| | | | | | | Rather than make yet another copy of channel(), let's move it into nir. Signed-off-by: Rob Clark <[email protected]> Reviewed-by: Jason Ekstrand <[email protected]>
* tgsi/scan: add support to figure out max nesting depthRob Clark2015-09-132-0/+21
| | | | | | | | | Sometimes a useful thing for compilers (or, for example, tgsi_to_nir) to know. And pretty trivial for scan to figure this out for us. Signed-off-by: Rob Clark <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]> Reviewed-by: Brian Paul <[email protected]>
* r600: Fix llvm build since const buffer changesKai Wasserbäch2015-09-131-1/+1
| | | | | | | | | | | In commit f9caabe8f1bff86d19b53d9ecba5c72b238d9e23: One place in r600_llvm.c was forgotten when replacing R600_UCP_CONST_BUFFER with R600_BUFFER_INFO_CONST_BUFFER. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=91985 Signed-off-by: Kai Wasserbäch <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* i965/vec4: Don't reswizzle hardware registersJason Ekstrand2015-09-121-0/+8
| | | | | | Cc: "11.0 10.6" <[email protected]> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=91719 Reviewed-by: Kenneth Graunke <[email protected]>
* i965/emit: Add assertions for accumulator restrictionsJason Ekstrand2015-09-121-0/+17
| | | | Reviewed-by: Kenneth Graunke <[email protected]>
* r600: Enable fp64 on chips with native supportGlenn Kennard2015-09-121-0/+3
| | | | | | | | Cypress/Cayman/Aruba, earlier r6xx/r7xx chips only support a subset of the needed fp64 ops, and don't do GL4 anyway. Signed-off-by: Glenn Kennard <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* r600g: Support I2D/U2D/D2I/D2UGlenn Kennard2015-09-121-8/+98
| | | | | | | | | Only for Cypress/Cayman/Aruba, older chips have only partial fp64 support. Uses float intermediate values so only accurate for int24 range, which matches what the blob does. Signed-off-by: Glenn Kennard <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* r600g: lower number of driver const buffersDave Airlie2015-09-123-70/+131
| | | | | | | | | | | | | | I'm going to want a driver constant buffer for tess to coordinate LDS storage, so before I go tackling that I decided to merge the clip/samplepos and texture info buffers into one. So I can steal the spare one. This creates a single constant buffer between the two, with clip/samplepos taking up a reserved 128 bytes at the start. Reviewed-by: Edward O'Callaghan <[email protected]> Reviewed-by: Glenn Kennard <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* r600: define some values for the fetch constant offsets.Dave Airlie2015-09-124-27/+47
| | | | | | | | This just puts these in one place and #defines them. Reviewed-by: Glenn Kennard <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* softpipe: Constify variablesKrzesimir Nowak2015-09-111-242/+199
| | | | | | | | | This commit makes a lot of variables constant - this is basically done by moving the computation to variable definition. Some of them are moved into lower scopes (like in img_filter_2d_ewa). Reviewed-by: Brian Paul <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* softpipe: Constify sp_tgsi_samplerKrzesimir Nowak2015-09-111-12/+23
| | | | | | | | | | | Add a small inline function doing the casting - this is to make sure we don't do a cast from some completely unrelated type. This commit does not make tgsi_sampler parameters const in vfuncs themselves for now - probably llvmpipe would need looking at before making such a change. Reviewed-by: Brian Paul <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* softpipe: Constify sampler and view parameters in mip filtersKrzesimir Nowak2015-09-112-18/+18
| | | | | | | Those functions actually could always take them as constants. Reviewed-by: Brian Paul <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* softpipe: Constify sampler and view parameters in img filtersKrzesimir Nowak2015-09-112-36/+36
| | | | | | | Those functions actually could always take them as constants. Reviewed-by: Brian Paul <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* tgsi, softpipe: Constify tgsi_sampler in query_lod vfuncKrzesimir Nowak2015-09-112-2/+2
| | | | | | | | | | A followup from previous commit - since all functions called by query_lod take pointers to const sp_sampler_view and const sp_sampler, which are taken from tgsi_sampler subclass, we can the tgsi_sampler as const itself now. Reviewed-by: Brian Paul <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* softpipe: Constify some sampler and view parametersKrzesimir Nowak2015-09-112-27/+28
| | | | | | | | | This is to prepare for making tgsi_sampler parameter in query_lod a const too. These functions do not modify anything in either sampler or view anymore. Reviewed-by: Brian Paul <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* softpipe: Move the faces array from view to filter_argsKrzesimir Nowak2015-09-112-17/+23
| | | | | | | | With that, sp_sampler_view instances are not abused anymore as a local storage, so we can later make them constant. Reviewed-by: Brian Paul <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* nir/from_ssa: Use instr_rewrite_destJason Ekstrand2015-09-111-3/+1
| | | | Reviewed-by: Eduardo Lima Mitev <[email protected]>
* nir: Add a function for rewriting instruction destinationsJason Ekstrand2015-09-112-0/+26
| | | | Reviewed-by: Eduardo Lima Mitev <[email protected]>
* nir: Only unlink sources that are actually validJason Ekstrand2015-09-111-7/+8
| | | | Reviewed-by: Thomas Helland <[email protected]>
* nir: Remove the mem_ctx parameter from ssa_def_rewrite_usesJason Ekstrand2015-09-1120-47/+25
| | | | Reviewed-by: Thomas Helland <[email protected]>
* nir: Fix a bunch of ralloc parenting errorsJason Ekstrand2015-09-1110-31/+32
| | | | | | | | | | | | | | As of a10d4937, we would really like things associated with an instruction to be allocated out of that instruction and not out of the shader. In particular, you should be passing the instruction that will ultimately be holding the source into nir_src_copy rather than an arbitrary memory context. We also change the prototypes of nir_dest_copy and nir_alu_src/dest_copy to explicitly take an instruction so we catch this earlier in the future. Cc: "11.0" <[email protected]> Reviewed-by: Thomas Helland <[email protected]>
* nir/lower_outputs_to_temporaries: Reparent the output nameJason Ekstrand2015-09-111-0/+3
| | | | | | | | | | We copy the output, make the old output the temporary, and give the temporary a new name. The copy keeps the pointer to the old name. This works just fine up until the point where we lower things to SSA and delete the old variable and, with it, the name. Instead, we should re-parent to the copy. Reviewed-by: Eduardo Lima Mitev <[email protected]>
* i965/vec4: check writemask when bailing out at register coalesceAlejandro Piñeiro2015-09-111-4/+6
| | | | | | | | | | | | | | | | | | | | | | | opt_register_coalesce stopped to check previous instructions to coalesce with if somebody else was writing on the same destination. This can be optimized to check if somebody else was writing to the same channels of the same destination using the writemask. Shader DB results (taking into account only vec4): total instructions in shared programs: 1781593 -> 1734957 (-2.62%) instructions in affected programs: 1238390 -> 1191754 (-3.77%) helped: 12782 HURT: 0 GAINED: 0 LOST: 0 v2: removed some parenthesis, fixed indentation, as suggested by Matt Turner v3: added brackets, for consistency, as suggested by Eduardo Lima Reviewed-by: Matt Turner <[email protected]>
* tgsi,softpipe: capitalize the tgsi_sampler_control enum valuesBrian Paul2015-09-113-48/+49
| | | | | | | We use capitalized enum values everywhere else. This improves understanding a bit too. Reviewed-by: Roland Scheidegger <[email protected]>
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-25 21:40:17 +0000