summaryrefslogtreecommitdiffstats
path: root/src/gallium
Commit message (Collapse)AuthorAgeFilesLines
* freedreno/a3xx/compiler: 1D texturesRob Clark2014-05-181-4/+25
| | | | | | | | Gallium already gives us height==1 for these, so the texture state is already setup correctly to emulate 1D textures as a Nx1 2D texture. We just need to supply the .y coord. Signed-off-by: Rob Clark <[email protected]>
* freedreno: fix capsRob Clark2014-05-181-2/+2
| | | | | | In particular, we want mesa to emulate primitive restart for us. Signed-off-by: Rob Clark <[email protected]>
* freedreno: fix index buffer offsetRob Clark2014-05-181-1/+1
| | | | Signed-off-by: Rob Clark <[email protected]>
* freedreno/a3xx: add sRBG texture supportRob Clark2014-05-162-0/+15
| | | | | | | That was easy. Turns out it is just a matter of setting one bit. Enable sampling from sRGB texture, and therefore enable GL 2.1 :-) Signed-off-by: Rob Clark <[email protected]>
* freedreno: update generated headersRob Clark2014-05-164-20/+21
| | | | Signed-off-by: Rob Clark <[email protected]>
* gallivm: (trivial) fix compilation with llvm 3.1, 3.2Roland Scheidegger2014-05-171-0/+4
| | | | | | I actually checked the getModuleIdentifier() function exists with 3.1 but missed that the file moved... This fixes https://bugs.freedesktop.org/show_bug.cgi?id=78803
* gallivm: print out how long it takes to optimize shader IR.Roland Scheidegger2014-05-163-1/+31
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Enabled with GALLIVM_DEBUG=perf (which up to now was only used to print warnings for unoptimized code). While some unexpectedly long shader compile times for some shaders were fixed with 8a9f5ecdb116d0449d63f7b94efbfa8b205d826f this should help recognize such problems in the future. For now though only available in debug builds (which are not always suitable for such analysis). And since this uses system time, it might not be all that accurate (even llvmpipe's own rasterization threads might be running at the same time, or just other tasks). (llvmpipe also has LP_DEBUG=counters but this only gives an average per shader and the the total time for all shaders.) This prints information like this: optimizing module fs17_variant0 took 1 msec optimizing module setup_variant_0 took 0 msec optimizing module draw_llvm_vs_variant0 took 9 msec optimizing module draw_llvm_vs_variant0 took 12 msec optimizing module fs17_variant1 took 2 msec v2: rebase for recent gallivm compilation changes, and print time for whole modules instead of functions (otherwise it would be very spammy since it would include all trivial inline sse2 functions), using the shiny new module names, prying them off LLVM using new helper (not available through C bindings). Per function timings, while possibly giving more information (if there'd be a problem only in for instance the partial not the whole function), don't seem all that useful for now. Reviewed-by: Brian Paul <[email protected]> Reviewed-by: Jose Fonseca <[email protected]>
* gallivm: give more verbose names to modulesRoland Scheidegger2014-05-1610-26/+38
| | | | | | | | | When we had just one module "gallivm" was an appropriate name. But now we have modules containing all functions for a particular variant, so give it a corresponding name (this is really just for helping debugging). Reviewed-by: Brian Paul <[email protected]> Reviewed-by: Jose Fonseca <[email protected]>
* gallivm: remove optimization workaround when not having sse 4.1Roland Scheidegger2014-05-161-8/+1
| | | | | | | | | | | This workaround doesn't list any llvm version, but it was introduced 2010-06-10 (e277d5c1f6b2c5a6d202561e67d2b6821a69ecc4). It is unlikely this bug is still present in llvm versions we support (3.1+). There's no specific test listed, but I ran lp_test_arit (which uses the mentioned functions) on llvm 3.1 and 3.3 with sse41 disabled and this pass enabled without issues. Reviewed-by: Jose Fonseca <[email protected]>
* gallivm: remove workaround for reversing optimization pass order.Roland Scheidegger2014-05-161-13/+2
| | | | | | | | | | | | | | | | | 32bit code generation and llvm >= 2.7 used a different optimization pass order - this code was initially introduced (2010-07-23) by 815e79e72c1f4aa849c0ee6103621685b678bc9d, apparently due to buggy code being generated with then brand new llvm versions (which was llvm 2.7 plus pre 2.8 devel). It seems very highly likely that whatever this bug was it has been fixed in newer llvm versions, though there's no easy way to test this - the mentioned piglit test has been removed years ago, and even if you'd build it I'm sceptical the glsl compiler would still produce the required code to trigger it. I have no idea what a good order of passes is, but just remove the workaround and use the same order everywhere. Reviewed-by: Jose Fonseca <[email protected]>
* egl-static: include libradeonwinsys.la only onceEmil Velikov2014-05-151-8/+5
| | | | | | | | | | | With this and the previous patch, we no longer have multiple definitions in the final egl_gallium.so. v2: Drop duplicate libloader link. Signed-off-by: Emil Velikov <[email protected]> Reviewed-by: Chia-I Wu <[email protected]> (v1) Reviewed-by: Tom Stellard <[email protected]> (v1)
* gallium/radeon: link in libradeon.la at target levelEmil Velikov2014-05-1512-20/+22
| | | | | | | | | | | | It makes more sense to link the core and common parts of the driver as the target is build. Additionally this will help us drop duplicating symbols for targets that static link mulitple pipe-drivers. Only egl-static needs that currently with more to come. To simplify things a bit add HAVE_GALLIUM_RADEON_COMMON variable. Signed-off-by: Emil Velikov <[email protected]> Reviewed-by: Tom Stellard <[email protected]>
* gallium/radeon: build only a single common library libradeonEmil Velikov2014-05-153-12/+5
| | | | | | | Just fold libllvmradeon in libradeon. Signed-off-by: Emil Velikov <[email protected]> Reviewed-by: Tom Stellard <[email protected]>
* freedreno/a3xx: fix write to bogus registerRob Clark2014-05-141-2/+2
| | | | | | | | | | | The loops for updating the multiple packed fields in SP_VS_OUT[] and SP_VS_VPC_DST[] will zero out one register beyond the last that on required. Which is normally not a problem (and is kinda convenient when looking at cmdstream dumps) unless we have maximum (16) varyings. Fix loop termination condition so that this does not happen. Signed-off-by: Rob Clark <[email protected]>
* freedreno/a3xx: account for special inputs/outputsRob Clark2014-05-141-2/+2
| | | | | | | | | We need to size input/output tables big enough for special inputs/ outputs (gl_Position, gl_FrontFacing, etc) which, while they don't count towards the hw limit of 16 attributes or 16 varyings, we do still need to track them all the same. Signed-off-by: Rob Clark <[email protected]>
* freedreno/a3xx: fix MAX_INPUTS shader capRob Clark2014-05-143-1/+9
| | | | | | | | | | Hardware only supports 16. Which fd3_shader_variant properly reflected, but the pipe cap did not, leading to array overflow (and shaders that could not possibly work). Also a bunch of asserts to make problems like this easier to see. Signed-off-by: Rob Clark <[email protected]>
* freedreno/a3xx: add debug flag to expose glsl130Rob Clark2014-05-142-3/+8
| | | | | | | | | | We are starting to add integer support to the compiler, which does not get exercised with glsl feature level 120 and without advertising integer support. But doing so breaks too many things right now. So for now use a debug flag to conditionally expose the functionality while it is in development. Signed-off-by: Rob Clark <[email protected]>
* freedreno/a3xx/compiler: add KILL_IFRyan Houdek2014-05-141-1/+35
| | | | | | | | | The KILL_IF opcode could potentially be merged in to the regular KILL opcode function. It was a pain to do so, so I've left is separated for cleanliness. Signed-off-by: Ryan Houdek <[email protected]> Signed-off-by: Rob Clark <[email protected]>
* freedreno/a3xx/compiler: start adding integer supportRyan Houdek2014-05-141-0/+169
| | | | | | | | | | | | | Adds a large sum of TGSI opcodes to the a3xx compiler. For integer opcodes we have 28 opcodes added. Adds 4 floating point compare opcodes If GLSL 1.30 is enabled, this allows the GLSL 1.30 piglits to have a completion amount of 432/641. Signed-off-by: Ryan Houdek <[email protected]> Signed-off-by: Rob Clark <[email protected]>
* draw: better llvm names for shaders for debugging.Roland Scheidegger2014-05-151-6/+12
| | | | | | | | All shaders had the same name. We could probably use some identifier per shader too, but for now only use the variant number. Reviewed-by: Jose Fonseca <[email protected]>
* llvmpipe: improve setup shader names (for debugging)Roland Scheidegger2014-05-151-38/+40
| | | | | | | | | | | | | The setup shaders were composed of both a fs shader number and a variant number. But since they aren't tied to a particular fragment shader, the former was a fixed zero while the latter was also always zero because it was never assigned. So, similar to what the fs code does, use a ever increasing number to give it a more catchy name (unlike fragment shaders though where this number is for each explicitly created shader, we just use it for the implicitly created variants). And while here, fix whitespace a bit. Reviewed-by: Jose Fonseca <[email protected]>
* llvmpipe: kill off llvmpipe_variant_countRoland Scheidegger2014-05-154-20/+4
| | | | | | | Unused except it was increased for both fs and setup shader variants created. Probably some leftover from ages ago. Reviewed-by: Jose Fonseca <[email protected]>
* nvc0: enable support for maxwell boardsBen Skeggs2014-05-156-19/+49
| | | | | Signed-off-by: Ben Skeggs <[email protected]> Reviewed-by: Ilia Mirkin <[email protected]>
* nvc0: add maxwell (sm50) compiler backendBen Skeggs2014-05-1516-5/+3588
| | | | | | | | | | The big missing part here is proper sched data calculations, but hopefully the chosen placeholder will be sufficient for now. Passes piglit as well as GK107 does. Signed-off-by: Ben Skeggs <[email protected]> Reviewed-by: Ilia Mirkin <[email protected]>
* nvc0: maxwell isa has no per-instruction join modifierBen Skeggs2014-05-154-19/+23
| | | | | Signed-off-by: Ben Skeggs <[email protected]> Reviewed-by: Ilia Mirkin <[email protected]>
* nvc0: replace immd 0 with $rLASTGPR for emit/restart opcodesBen Skeggs2014-05-151-0/+1
| | | | | Signed-off-by: Ben Skeggs <[email protected]> Reviewed-by: Ilia Mirkin <[email protected]>
* nvc0: move nvc0 lowering pass class definitions into headerBen Skeggs2014-05-153-106/+136
| | | | | Signed-off-by: Ben Skeggs <[email protected]> Reviewed-by: Ilia Mirkin <[email protected]>
* nvc0: bump sched data member to 32-bitsBen Skeggs2014-05-151-1/+1
| | | | | | | SM50 backend requires 21 bits per instruction, not 8. Signed-off-by: Ben Skeggs <[email protected]> Reviewed-by: Ilia Mirkin <[email protected]>
* nvc0: use vertex arrays for eng3d blitBen Skeggs2014-05-151-31/+64
| | | | | | | Maxwell doesn't have immediate-mode. Signed-off-by: Ben Skeggs <[email protected]> Reviewed-by: Ilia Mirkin <[email protected]>
* nvc0: restrict "constant vbo" logic to fermi/kepler classesBen Skeggs2014-05-151-1/+1
| | | | | Signed-off-by: Ben Skeggs <[email protected]> Reviewed-by: Ilia Mirkin <[email protected]>
* nvc0: replace some vb->stride checks with constant_vbo insteadBen Skeggs2014-05-151-3/+3
| | | | | | | | Maxwell no longer has the methods to set constant attributes, and we'll want to be treating stride 0 vtxbufs the same as for stride > 0. Signed-off-by: Ben Skeggs <[email protected]> Reviewed-by: Ilia Mirkin <[email protected]>
* nvc0: add maxwell classBen Skeggs2014-05-152-0/+4
| | | | | Signed-off-by: Ben Skeggs <[email protected]> Reviewed-by: Ilia Mirkin <[email protected]>
* nvc0: allow for easier modification of compiler library routinesBen Skeggs2014-05-1513-1057/+1057
| | | | | Signed-off-by: Ben Skeggs <[email protected]> Reviewed-by: Ilia Mirkin <[email protected]>
* nvc0: properly distribute macros in source formBen Skeggs2014-05-155-244/+365
| | | | | Signed-off-by: Ben Skeggs <[email protected]> Reviewed-by: Ilia Mirkin <[email protected]>
* automake: Honor GL_LIB for gallium libgl-xlibBrad King2014-05-141-7/+7
| | | | | | | Use "@GL_LIB@" in src/gallium/targets/libgl-xlib/Makefile.am to produce the library name specified by the configure --with-gl-lib-name option. Reviewed-by: Emil Velikov <[email protected]>
* gallivm: only fetch pointers to constant buffers onceRoland Scheidegger2014-05-142-37/+65
| | | | | | | | | | | | | | | | | In 1d35f77228ad540a551a8e09e062b764a6e31f5e support for multiple constant buffers was introduced. This meant we had another indirection, and we did resolve the indirection for each constant buffer access. This looks very reasonable since llvm can figure out if it's the same pointer, however it turns out that this can cause llvm compilation time to go through the roof and beyond (I've seen cases in excess of factor 100, e.g. from 50 ms to more than 10 seconds (!)), with all the additional time spent in IR optimization passes (and in the end all of it in DominatorTree::dominate()). I've been unable to narrow it down a bit more (only some shaders seem affected, seemingly without much correlation to overall shader complexity or constant usage) but it is easily avoidable by doing the buffer lookups themeselves just once (at constant buffer declaration time). Reviewed-by: Jose Fonseca <[email protected]>
* gallivm: fix output stream flushing in error case for disassembly.Roland Scheidegger2014-05-141-0/+5
| | | | | When there's an error, also need to flush the stream, otherwise an assertion is hit (meaning you don't actually see the error neither).
* radeonsi: Fix anisotropic filtering state setupMichel Dänzer2014-05-143-13/+12
| | | | | | | | | | | | Bring it back in line with r600g. I broke this in the original radeonsi bringup. :( Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=78537 Cc: "10.1 10.2" <[email protected]> Reviewed-by: Marek Olšák <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
* tgsi: support parsing texture offsets from text tgsi shadersIlia Mirkin2014-05-141-5/+48
| | | | | Signed-off-by: Ilia Mirkin <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* gallium/docs: clarify when query results are resetRob Clark2014-05-141-0/+2
| | | | | | | | It wasn't completely clear from the docs, so I had to figure out by looking at piglit results. Hopefully this saves the next driver writer implementing queries some time. Signed-off-by: Rob Clark <[email protected]>
* gallivm: Remove lp_func_delete_body.José Fonseca2014-05-143-15/+0
| | | | | | | Not necessary, now that we will free the whole module (hence all function bodies) immediately after compiling. Reviewed-by: Roland Scheidegger <[email protected]>
* gallivm: Remove gallivm_free_function.José Fonseca2014-05-142-23/+0
| | | | | | Unused. Deprecated by gallivm_free_ir(). Reviewed-by: Roland Scheidegger <[email protected]>
* llvmpipe: Delete unneeded LLVM stuff earlier.José Fonseca2014-05-147-34/+16
| | | | | | Same as Frank's change to draw module but for llvmpipe module. Reviewed-by: Roland Scheidegger <[email protected]>
* draw: Delete unneeded LLVM stuff earlier.Frank Henigman2014-05-141-15/+4
| | | | | | | | | | Free up unneeded LLVM stuff immediately after generating vertex shader code. Saves about 500K per shader. v2: Don't bother calling gallivm_free_function (Jose) Signed-off-by: José Fonseca <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* gallivm: Separate freeing LLVM intermediate data from freeing final code.Frank Henigman2014-05-142-7/+22
| | | | | | | | | | | | Split free_gallivm_state() into two steps. First step is gallivm_free_ir() which cleans up the LLVM scaffolding used to generate code while preserving the code itself. Second step is gallivm_free_code() to free the memory occupied by the code. v2: s/gallivm_teardown/gallivm_free_ir/ (Jose) Signed-off-by: José Fonseca <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* gallivm: One code memory pool with deferred free.Frank Henigman2014-05-144-1/+283
| | | | | | | | | | | | | | | | Provide a JITMemoryManager derivative which puts all generated code into one memory pool instead of creating a new one each time code is generated. This saves significant memory per shader as the pool size is 512K and a small shader occupies just several K. This memory manager also defers freeing generated code until you tell it to do so, making it possible to destroy the LLVM engine while keeping the code, thus enabling future memory savings. v2: Fix compilation errors with LLVM 3.4 (Jose) Signed-off-by: José Fonseca <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* gallivm: Run passes per module, not per function.José Fonseca2014-05-141-28/+19
| | | | | | This is how it is meant to be done nowadays. Reviewed-by: Roland Scheidegger <[email protected]>
* gallivm: Use LLVM global context.José Fonseca2014-05-141-23/+17
| | | | | | | | | | | I saw that LLVM internally uses its global context for some things, even when we use our own. Given ours is also global, might as well use LLVM's. However, sepearate contexts can still be enabled with a simple source code modification, for when the need/benefit arises. Reviewed-by: Roland Scheidegger <[email protected]>
* gallivm: Stop using module providers.José Fonseca2014-05-142-27/+7
| | | | | | | Nowadays LLVMModuleProviderRef is just an alias for LLVMModuleRef, so its use just causes unnecessary confusion. Reviewed-by: Roland Scheidegger <[email protected]>
* gallivm,draw,llvmpipe: Remove support for versions of LLVM prior to 3.1.José Fonseca2014-05-1415-548/+20
| | | | | | | Older versions haven't been tested probably don't work anyway. But more importantly, code supporting it is hindering further work. Reviewed-by: Roland Scheidegger <[email protected]>
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-22 11:42:36 +0000