aboutsummaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* radv: bump texel offsets to align with radeonsiDave Airlie2016-12-231-4/+4
| | | | | | | | | | it appears from the amdgpu-pro results the hw can do more, but let's just align with radeonsi for now. No CTS regressions. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* nir/algebraic: Add optimizations for "a == a && a CMP b"Jason Ekstrand2016-12-221-0/+8
| | | | | | | | This sequence shows up The Talos Principal, at least under Vulkan, and prevents loop analysis from properly computing trip counts in a few loops. Reviewed-by: Ian Romanick <[email protected]>
* i965: Use nir_opt_trivial_continues and nir_opt_ifJason Ekstrand2016-12-221-0/+9
| | | | Reviewed-by: Timothy Arceri <[email protected]>
* nir: Add a pass for moving SPIR-V continue blocks to the ends of loopsJason Ekstrand2016-12-223-0/+259
| | | | | | | | | | | | | | | When shaders come in from SPIR-V, we handle continue blocks by placing the contents of the continue inside of a "if (!first_iteration)". We do this so that we can properly handle the fact that continues in SPIR-V jump to the continue block at the end of the loop rather than jumping directly to the top of the loop like they do in NIR. In particular, the increment step of a simple for loop ends up in the continue block. This pass looks for this case in loops that don't actually have any continues and moves the continue contents to the end of the loop instead. We need this because loop unrolling doesn't work if the increment is inside of a condition. Reviewed-by: Timothy Arceri <[email protected]>
* nir: Add an optimization pass to remove trivial continuesJason Ekstrand2016-12-223-0/+140
| | | | Reviewed-by: Timothy Arceri <[email protected]>
* nir: Correctly handle blocks in cf_node_cf_tree_nextJason Ekstrand2016-12-221-1/+1
| | | | Reviewed-by: Timothy Arceri <[email protected]>
* i965: make use of nir_lower_returns() for GLTimothy Arceri2016-12-232-6/+2
| | | | | | | | | | | | | | | | | | | | | Fixes two new piglit tests: spec/glsl-1.10/execution/vs-nested-return-sibling-loop.shader_test spec/glsl-1.10/execution/vs-nested-return-sibling-loop2.shader_test shader-db results for BDW: total instructions in shared programs: 12903158 -> 12903134 (-0.00%) instructions in affected programs: 27100 -> 27076 (-0.09%) helped: 32 HURT: 6 total cycles in shared programs: 294922518 -> 294922804 (0.00%) cycles in affected programs: 4372828 -> 4373114 (0.01%) helped: 31 HURT: 8 Reviewed-by: Kenneth Graunke <[email protected]>
* nir: update nir_lower_returns to only predicate instructions when neededTimothy Arceri2016-12-231-6/+41
| | | | | | | | | | | | | | Unless an if statement contains nested returns we can simply add any following instructions to the branch without the return. V2: fix handling if_nested_return value when there is a sibling if/loop that doesn't contain a return. (Spotted by Ken) V3: - add a better comment to the new variable - remove instructions after if when both branches return Reviewed-by: Jason Ekstrand <[email protected]>
* i965: disable loop unrolling in GLSL IRTimothy Arceri2016-12-231-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | There is a single regression in loop unrolling which is: loops HURT: shaders/orbital_explorer.shader_test GS SIMD8: 0 -> 1 However the loop is huge so it seems reasonable not to unroll it. It's surprising that GLSL IR does unroll it. shader-db results BDW: total instructions in shared programs: 13037455 -> 13036947 (-0.00%) instructions in affected programs: 17982 -> 17474 (-2.83%) helped: 63 HURT: 25 total cycles in shared programs: 262217870 -> 262227990 (0.00%) cycles in affected programs: 2287046 -> 2297166 (0.44%) helped: 969 HURT: 844 total loops in shared programs: 2951 -> 2952 (0.03%) loops in affected programs: 0 -> 1 helped: 0 HURT: 1 LOST: 0 GAINED: 1 Reviewed-by: Jason Ekstrand <[email protected]>
* i965: use nir loop unrolling passTimothy Arceri2016-12-232-5/+20
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | shader-db results for BDW: total instructions in shared programs: 12589614 -> 12590119 (0.00%) instructions in affected programs: 50525 -> 51030 (1.00%) helped: 7 HURT: 145 total cycles in shared programs: 241524604 -> 241490502 (-0.01%) cycles in affected programs: 1941404 -> 1907302 (-1.76%) helped: 302 HURT: 449 total loops in shared programs: 4245 -> 2947 (-30.58%) loops in affected programs: 1535 -> 237 (-84.56%) helped: 1142 HURT: 0 total spills in shared programs: 14453 -> 14453 (0.00%) spills in affected programs: 0 -> 0 helped: 0 HURT: 0 total fills in shared programs: 18984 -> 18984 (0.00%) fills in affected programs: 0 -> 0 helped: 0 HURT: 0 LOST: 26 GAINED: 15 Reviewed-by: Jason Ekstrand <[email protected]>
* nir: pass compiler rather than devinfo to functions that call nir_optimizeTimothy Arceri2016-12-237-21/+18
| | | | | | | Later we will pass compiler to nir_optimise to be used by the loop unroll pass. Reviewed-by: Jason Ekstrand <[email protected]>
* nir: add a loop unrolling passTimothy Arceri2016-12-233-0/+578
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | V2: - tidy ups suggested by Connor. - tidy up cloning logic and handle copy propagation based of suggestion by Connor. - use nir_ssa_def_rewrite_uses to fix up lcssa phis suggested by Connor. - add support for complex loop unrolling (two terminators) - handle case were the ssa defs use outside the loop is already a phi - support unrolling loops with multiple terminators when trip count is know for each terminator V3: - set correct num_components when creating phi in complex unroll - rewrite update remap table based on Jasons suggestions. - remove unrequired extract_loop_body() helper as suggested by Jason. - simplify the lcssa phi fix up code for simple loops as per Jasons suggestions. - use mem context to keep track of hash table memory as suggested by Jason. - move is_{complex,simple}_loop helpers to the unroll code - require nir_metadata_block_index - partially rewrote complex unroll to be simpler and easier to follow. V4: - use rzalloc() when creating nir_phi_src but not setting pred right away fixes regression cause by ralloc() no longer zeroing memory. V5: - simplify calling of complex_unroll() - use new loop terminator fields to get the break/continue from blocks and simplify loop unrolling code - handle slightly less trivial loop terminators. if branches can now have instructions but can only contain a single block. - use nir print type IR snippets in unroll function descriptions - add better explanation and variable for why we need to clone additional times when the second terminator it the limiting terminator. - partially convert out of ssa before unrolling loops (suggested by Jason) v6: - remove unused nir_builder - use Jasons new from ssa helper - tidy/fixup cursor use - unroll terminators that contain control flow correctly - unroll complex loops with control flow before the terminators correctly Reviewed-by: Jason Ekstrand <[email protected]>
* nir: add helper for cloning nir_cf_listTimothy Arceri2016-12-232-9/+56
| | | | | | | | | V2: - updated to create a generic list clone helper nir_cf_list_clone() - continue to assert on clone when fallback flag not set as suggested by Jason. Reviewed-by: Jason Ekstrand <[email protected]>
* nir: update fixup_phi_srcs() to handle registersTimothy Arceri2016-12-231-4/+9
| | | | | | | We need to do this because we partially get out of SSA when unrolling and cloning loops. Reviewed-by: Jason Ekstrand <[email protected]>
* nir: create helper for fixing phi srcs when cloningTimothy Arceri2016-12-231-15/+21
| | | | | | | This will be useful for fixing phi srcs when cloning a loop body during loop unrolling. Reviewed-by: Jason Ekstrand <[email protected]>
* nir: Add a LCSAA-passThomas Helland2016-12-233-0/+206
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | V2: Do a "depth first search" to convert to LCSSA V3: Small comment fixup V4: Rebase, adapt to removal of function overloads V5: Rebase, adapt to relocation of nir to compiler/nir Still need to adapt to potential if-uses Work around nir_validate issue V6 (Timothy): - tidy lcssa and stop leaking memory - dont rewrite the src for the lcssa phi node - validate lcssa phi srcs to avoid postvalidate assert - don't add new phi if one already exists - more lcssa phi validation fixes - Rather than marking ssa defs inside a loop just mark blocks inside a loop. This is simpler and fixes lcssa for intrinsics which do not have a destination. - don't create LCSSA phis for loops we won't unroll - require loop metadata for lcssa pass - handle case were the ssa defs use outside the loop is already a phi V7: (Timothy) - pass indirect mask to metadata call v8: (Timothy) - make convert to lcssa a helper function rather than a nir pass - replace inside loop bitset with on the fly block index logic. - remove lcssa phi validation special cases - inline code from useless helpers, suggested by Jason. - always do lcssa on loops, suggested by Jason. - stop making lcssa phis special. Add as many source as the block has predecessors, suggested by Jason. V9: (Timothy) - fix regression with the is_lcssa_phi field not being initialised to false now that ralloc() doesn't zero out memory. V10: (Timothy) - remove extra braces in SSA example, pointed out by Topi V11: (Timothy) - add missing support for LCSSA phis in if conditions. V12: (Timothy) - small tidy up suggested by Jason. - always create lcssa phi even if it just points to an lcssa phi from an inner loop Reviewed-by: Jason Ekstrand <[email protected]>
* nir: Add a loop analysis passThomas Helland2016-12-236-3/+986
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This pass detects induction variables and calculates the trip count of loops to be used for loop unrolling. V2: Rebase, adapt to removal of function overloads V3: (Timothy Arceri) - don't try to find trip count if loop terminator conditional is a phi - fix trip count for do-while loops - replace conditional type != alu assert with return - disable unrolling of loops with continues - multiple fixes to memory allocation, stop leaking and don't destroy structs we want to use for unrolling. - fix iteration count bugs when induction var not on RHS of condition - add FIXME for && conditions - calculate trip count for unsigned induction/limit vars V4: (Timothy Arceri) - count instructions in a loop - set the limiting_terminator even if we can't find the trip count for all terminators. This is needed for complex unrolling where we handle 2 terminators and the trip count is unknown for one of them. - restruct structs so we don't keep information not required after analysis and remove dead fields. - force unrolling in some cases as per the rules in the GLSL IR pass V5: (Timothy Arceri) - fix metadata mask value 0x10 vs 0x16 V6: (Timothy Arceri) - merge loop_variable and nir_loop_variable structs and lists suggested by Jason - remove induction var hash table and store pointer to induction information in the loop_variable suggested by Jason. - use lowercase list_addtail() suggested by Jason. - tidy up init_loop_block() as per Jasons suggestions. - replace switch with nir_op_infos[alu->op].num_inputs == 2 in is_var_basic_induction_var() as suggested by Jason. - use nir_block_last_instr() in and rename foreach_cf_node_ex_loop() as suggested by Jason. - fix else check for is_trivial_loop_terminator() as per Connors suggetions. - simplify offset for induction valiables incremented before the exit conditions is checked. - replace nir_op_isub check with assert() as it should have been lowered away. V7: (Timothy Arceri) - use rzalloc() on nir_loop struct creation. Worked previously because ralloc() was broken and always zeroed the struct. - fix cf_node_find_loop_jumps() to find jumps when loops contain nested if statements. Code is tidier as a result. V8: (Timothy Arceri) - move is_trivial_loop_terminator() to nir.h so we can use it to assert is the loop unroll pass - fix analysis to not bail when looking for terminator when the break is in the else rather then the if - added new loop terminator fields: break_block, continue_from_block and continue_from_then so we don't have to gather these when doing unrolling. - get correct array length when forcing unrolling of variables indexed arrays that are the same size as the iteration count - add support for induction variables of type float - update trival loop terminator check to allow an if containing instructions as long as both branches contain only a single block. V9: (Timothy) - bunch of tidy ups and simplifications suggested by Jason. - rewrote trivial terminator detection, now the only restriction is there must be no nested jumps, anything else goes. - rewrote the iteration test to use nir_eval_const_opcode(). - count instruction properly even when forcing an unroll. - bunch of other tidy ups and simplifications. V10: (Timothy) - some trivial tidy ups suggested by Jason. - conditional fix for break inside continue branch by Jason. Reviewed-by: Jason Ekstrand <[email protected]>
* i965: use nir_lower_indirect_derefs() for GLSLTimothy Arceri2016-12-233-27/+12
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This moves the nir_lower_indirect_derefs() call into brw_preprocess_nir() so thats is called by both OpenGL and Vulkan and removes that call to the old GLSL IR pass lower_variable_index_to_cond_assign() We want to do this pass in nir to be able to move loop unrolling to nir. There is a increase of 1-3 instructions in a small number of shaders, and 2 Kerbal Space program shaders that increase by 32 instructions. The changes seem to be caused be the difference in the GLSL IR vs NIR variable index lowering passes. The GLSL IR pass creates a simple if ladder for arrays of size 4 or less, while the NIR pass implements a binary search for all arrays regardless of size. Shader-db results BDW: total instructions in shared programs: 13021176 -> 13021819 (0.00%) instructions in affected programs: 57693 -> 58336 (1.11%) helped: 20 HURT: 190 total cycles in shared programs: 299805580 -> 299750826 (-0.02%) cycles in affected programs: 2290024 -> 2235270 (-2.39%) helped: 337 HURT: 442 total fills in shared programs: 19984 -> 19984 (0.00%) fills in affected programs: 0 -> 0 helped: 0 HURT: 0 LOST: 4 GAINED: 0 V2: remove the do_copy_propagation() call from the i965 GLSL IR linking code. This call was added in f7741c52111 but since we are moving the variable index lowering to NIR we no longer need it and can just rely on the nir copy propagation pass. Reviewed-by: Kenneth Graunke <[email protected]> Reviewed-by: Jason Ekstrand <[email protected]>
* i965: allow sampler indirects on all gensTimothy Arceri2016-12-231-4/+0
| | | | | | | | | | | | | Without this we will regress the max-samplers piglit test on Gen6 and lower when loop unrolling is done in NIR. There is a check in the GLSL IR linker that errors when it finds indirects and EmitNoIndirectSampler is set. As far as I can tell there is no reason for not enabling this for all gens regardless of whether they fully support ARB_gpu_shader5 or not. Reviewed-by: Jason Ekstrand <[email protected]>
* nir: Add a couple quick-and-dirty out-of-SSA helpersJason Ekstrand2016-12-232-12/+180
| | | | | | | | | | | These are designed for use within an optimization pass when SSA becomes more pain than it's worth. They're very naive and don't generate anything close to optimal register-based NIR. Also, they may result in shaders which do not validate because of, for instance, registers in phi sources. However, the register-based into-SSA pass should be pretty efficient at cleaning up the mess. Reviewed-by: Timothy Arceri <[email protected]>
* vulkan/wsi/x11: don't crash on null wsi x11 connectionArda Coskunses2016-12-221-0/+3
| | | | | | | | | Without this check driver crash when application window closed unexpectedly. Acked-by: Edward O'Callaghan <[email protected]> Reviewed-by: Jason Ekstrand <[email protected]> Cc: "13.0" <[email protected]>
* vulkan/wsi/x11: don't crash on null visualArda Coskunses2016-12-221-0/+3
| | | | | | | | | | When application window closed unexpectedly due to lost window visualtypes getting invlaid parameters which is causing a crash. Necessary check is added to prevent the crash. Reviewed-by: Jason Ekstrand <[email protected]> Cc: "13.0" <[email protected]>
* radeonsi: Bugfix needed for hashcatChristian Inci2016-12-221-5/+7
| | | | | | | | | Hashcat needs MAX_GLOBAL_BUFFERS to be 21 or even 22 for some modes. It'll crash otherwise. I'm adding an assert to see if programs need it to be even higher. Signed-off-by: Christian Inci <[email protected]> [Handle first properly; should be NFC, since clover always uses first == 0.] Signed-off-by: Nicolai Hähnle <[email protected]>
* radeonsi: fix gl_ClipDistance and gl_ClipVertex for pointsNicolai Hähnle2016-12-221-2/+10
| | | | | | | | | | The clipper hardware doesn't consider points as primitives that can be clipped. Simply setting the corresponding cull bits works, and should not have an adverse effect on other primitive types according to the hardware team. Reviewed-by: Marek Olšák <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]>
* radeonsi: only set VS_OUT_MISC_SIDE_BUS_ENA when the misc vector is usedNicolai Hähnle2016-12-221-5/+6
| | | | | | | | Should have no effect (other than perhaps on power consumption), but Vulkan does this. Reviewed-by: Marek Olšák <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]>
* llvmpipe: Link tests with CLOCK_LIB.Vinson Lee2016-12-211-1/+2
| | | | | | | | | | Fix linking error with 'make check'. CXXLD lp_test_format ../../../../src/gallium/auxiliary/.libs/libgallium.a(os_time.o): In function `os_time_get_nano': src/gallium/auxiliary/os/os_time.c:59: undefined reference to `clock_gettime' Signed-off-by: Vinson Lee <[email protected]>
* radv: fix dual source blendingFredrik Höglund2016-12-221-2/+2
| | | | | | | | | | | | | | | | | | | | Add the index to the location when assigning driver locations for output variables. Otherwise two fragment shader outputs declared as: layout (location = 0, index = 0) out vec4 output1; layout (location = 0, index = 1) out vec4 output2; will end up aliasing one another. Note that this patch will make the second output variable in the above example alias a possible third output variable with location = 1 and index = 0. But this shouldn't be a problem in practice since only one color attachment is supported when dual-source blending is used. Cc: "13.0" <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* radv: enable shaderStorageImageExtendedFormatsDave Airlie2016-12-221-1/+1
| | | | | | | This passes all the CTS tests that get enabled for this. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: enable shaderGatherImageExtendedDave Airlie2016-12-221-1/+1
| | | | | | | | | Thanks to Ilia's patch this works fine on radv. No regressions in CTS, all enabled tests pass. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv/image: only touch queue family info for concurrent images.Dave Airlie2016-12-211-2/+4
| | | | | | | | | | The spec says to ignore these fields for exclusive images. Fixes crashes in: dEQP-VK.clipping.* Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: flush smem for uniform buffer bit.Dave Airlie2016-12-211-1/+3
| | | | | | | | (cc'ing stable as I'd like to backport the ubo speedup as well) Reviewed-by: Bas Nieuwenhuizen <[email protected]> Cc: "13.0" <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radeonsi: add Polaris12 PCI IDJunwei Zhang2016-12-211-0/+7
| | | | | | Reviewed-by: Marek Olšák <[email protected]> Signed-off-by: Junwei Zhang <[email protected]> Reviewed-by: Nicolai Hähnle <[email protected]>
* radeonsi: add Polaris12 support (v3)Junwei Zhang2016-12-219-2/+19
| | | | | | | | | | | v2: use gfxip names for llvm 4.0+ v3: use tonga for llvm <= 3.8, drop gfxip name, we can just change that we change the other asics. Reviewed-by: Marek Olšák <[email protected]> Signed-off-by: Junwei Zhang <[email protected]> Reviewed-by: Nicolai Hähnle <[email protected]> Acked-by: Christian König <[email protected]>
* glsl: Eliminate the open-coded version of process_block_array_leafIan Romanick2016-12-211-31/+9
| | | | | Signed-off-by: Ian Romanick <[email protected]> Reviewed-by: Timothy Arceri <[email protected]>
* ttn: handle GLSL_SAMPLER_DIM_SUBPASS_MS caseJuan A. Suarez Romero2016-12-211-0/+1
| | | | | | Fixes a warning. Reviewed-by: Samuel Iglesias Gonsálvez <[email protected]>
* i965: allow unsourced enabled VAOJuan A. Suarez Romero2016-12-211-7/+16
| | | | | | | | | | | | The GL 4.5 spec says: "If any enabled array’s buffer binding is zero when DrawArrays or one of the other drawing commands defined in section 10.4 is called, the result is undefined." This commits avoids crashing the code, which is not a very good "undefined result". This fixes spec/!opengl 3.1/vao-broken-attrib piglit test.
* svga: Fix a strict-aliasing violation in shader dumperEdward O'Callaghan2016-12-211-1/+9
| | | | | | | | | | | | | | | As per the C spec, it is illegal to alias pointers to different types. This results in undefined behaviour after optimization passes, resulting in very subtle bugs that happen only on a full moon.. Use a memcpy() as a well defined coercion between the isomorphic bit-field interpretations of memory. V.2: Use C99 compat STATIC_ASSERT() over C11 static_assert(). Signed-off-by: Edward O'Callaghan <[email protected]> Reviewed-by: Charmaine Lee <[email protected]>
* draw: use SoA fetch, not AoS oneRoland Scheidegger2016-12-211-48/+23
| | | | | | | | | | | | | | | | | | | Now that there's some SoA fetch which never falls back, we should always get results which are better or at least not worse (something like rgba32f will stay the same). For cases which get way better, think something like R16_UNORM with 8-wide vectors: this was 8 sign-extend fetches, 8 cvt, 8 muls, followed by a couple of shuffles to stitch things together (if it is smart enough, 6 unpacks) and then a (8-wide) transpose (not sure if llvm could even optimize the shuffles + transpose, since the 16bit values were actually sign-extended to 128bit before being cast to a float vec, so that would be another 8 unpacks). Now that is just 8 fetches (directly inserted into vector, albeit there's one 128bit insert needed), 1 cvt, 1 mul. v2: ditch the old AoS code instead of just disabling it. Reviewed-by: Jose Fonseca <[email protected]>
* gallivm: generalize the compressed format soa fetch a bitRoland Scheidegger2016-12-211-37/+49
| | | | | | | | | This can now handle rgtc (unorm) too - this path no longer handles plain formats, but that's unnecessary they now all have their proper SoA unpack (this will still be dog-slow though due to the actual fetch being per-pixel util fallbacks). Reviewed-by: Jose Fonseca <[email protected]>
* gallivm: provide soa fetch path handling formats with more than 32bitRoland Scheidegger2016-12-211-154/+375
| | | | | | | | | | | | | | | | | | | | | | | | | | | | This previously always fell back to AoS conversion. Even for 4-float formats (which is the optimal case by far for that fallback case) this was suboptimal, since it meant the conversion couldn't be done with 256bit vectors. While this may still only be partly possible for some formats, (unless there's AVX2 support) at least the transpose can be done with half the unpacks (and before using the transpose for AoS fallbacks, it was worse still). With less than 4 channels, things got way worse with the AoS fallback quickly even with 128bit vectors. The strategy is pretty much the same as the existing one for formats which fit into 32 bits, except there's now multiple vectors to be fetched (2 or 4 to be exact), which need to be shuffled first (if it's 4 vectors, this amounts to a transpose, for 2 it's a bit different), then the unpack is done the same (with the exception that the shift of the channels is now modulo 32, and we need to select the right vector). In fact the most complex part about it is to get the shuffles right for separating into lo/hi parts for AVX/AVX2... This also makes use of the new ability of gather to use provided type information, which we abuse to outsmart llvm so we get decent shuffles, and to fetch 3x32bit vectors without having to ZExt the scalar. And just because we can, we handle double formats too, albeit they are a bit different (draw sometimes needs to handle that). v2: fix typo float/int bug (generating inefficient code). Reviewed-by: Jose Fonseca <[email protected]>
* gallivm: optimize gather a bit, by using supplied destination typeRoland Scheidegger2016-12-218-79/+333
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | By using a dst_type in the the gather interface, gather has some more knowledge about how values should be fetched. E.g. if this is a 3x32bit fetch and dst_type is 4x32bit vector gather will no longer do a ZExt with a 96bit scalar value to 128bit, but just fetch the 96bit as 3x32bit vector (this is still going to be 2 loads of course, but the loads can be done directly to simd vector that way). Also, we can now do some try to use the right int/float type. This should make no difference really since there's typically no domain transition penalties for such simd loads, however it actually makes a difference since llvm will use different shuffle lowering afterwards so the caller can use this to trick llvm into using sane shuffle afterwards (and yes llvm is really stupid there - nothing against using the shuffle instruction from the correct domain, but not at the cost of doing 3 times more shuffles, the case which actually matters is refusal to use shufps for integer values). Also do some attempt to avoid things which look great on paper but llvm doesn't really handle (e.g. fetching 3-element 8 bit and 16 bit vectors which is simply disastrous - I suspect type legalizer is to blame trying to extend these vectors to 128bit types somehow, so fetching these with scalars like before which is suboptimal due to the ZExt). Remove the ability for truncation (no point, this is gather, not conversion) as it is complex enough already. While here also implement not just the float, but also the 64bit avx2 gathers (disabled though since based on the theoretical numbers the benefit just isn't there at all until Skylake at least). Reviewed-by: Jose Fonseca <[email protected]>
* gallivm: optimize SoA AoS fallback fetch path a littleRoland Scheidegger2016-12-211-22/+46
| | | | | | | | | | We should do transpose, not extract/insert, at least with "sufficient" amount of channels (for 4 channels, extract/insert shuffles generated otherwise look truly terrifying). Albeit we shouldn't fallback to that so often in any case. v2: ditch the extract/insert path, not worth keeping (we're going to avoid hitting the fallback that often with future patches). Reviewed-by: Jose Fonseca <[email protected]>
* gallivm: (trivial) handle non-aligned fetch for lp_build_fetch_rgba_soaRoland Scheidegger2016-12-213-8/+12
| | | | | | | | | | soa fetch so far always assumed that data was aligned. However, we want to use this for vertex fetch, and data might not be aligned there, so handle it in this path too (basically just pass through alignment through to other functions). (It looks like it wouldn't work for for cached s3tc but this is no different than with AoS fetch.) Reviewed-by: Jose Fonseca <[email protected]>
* st/nine: Upload on secondary context for Draw*UpAxel Davy2016-12-201-8/+15
| | | | | | | | | | Avoid synchronization by using the secondary context for uploading the vertex data for Draw*Up. v2: Rely on u_upload_mgr to use persistent coherent buffers. Do not flush. Signed-off-by: Axel Davy <[email protected]>
* st/nine: Dirty MANAGED buffers at Lock timeAxel Davy2016-12-201-2/+3
| | | | | | | Tests suggest MANAGED buffers are made dirty at Lock time, not at Unlock time. Signed-off-by: Axel Davy <[email protected]>
* st/nine: Implement new buffer upload pathAxel Davy2016-12-2010-24/+461
| | | | | | | | | | | | | | | | | | | | This new buffer upload path enables to lock faster than the normal path when using DISCARD/NOOVERWRITE. v2: Diverse cleanups and fixes. v3: Fix allocation size for 'lone' buffers and add more debug info. v4: Rewrite of the path to handle when DISCARD/NOOVERWRITE is not used anymore. The resource content is copied to the new resource used. v5: flush for safety after unmap (not sure it is really required here, but safer to flush). v6: Do not use the path if persistent coherent mapping is unavailable. Fix buffer creation flags. v7: Do not flush since it is not needed. Signed-off-by: Axel Davy <[email protected]>
* st/nine: Allow non-zero resource offset for vertex buffersAxel Davy2016-12-203-8/+12
| | | | | | Next patches will introduce an offset. Signed-off-by: Axel Davy <[email protected]>
* st/nine: Do not wait for DEFAULT lock for volumes when we canAxel Davy2016-12-201-1/+8
| | | | | | | If the volumes (and the texture container) are not referenced, then they are no pending operations on them. We can lock directly. Signed-off-by: Axel Davy <[email protected]>
* st/nine: Do not wait for DEFAULT lock for surfaces when we canAxel Davy2016-12-201-1/+11
| | | | | | | If the surfaces (and the texture container) are not referenced, then they are no pending operations on them. We can lock directly. Signed-off-by: Axel Davy <[email protected]>
* st/nine: Add arguments to context's blit and copy_regionAxel Davy2016-12-203-6/+22
| | | | | | | The new arguments enable to reference the objects while the function hasn't run. Signed-off-by: Axel Davy <[email protected]>
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-27 01:22:16 +0000