aboutsummaryrefslogtreecommitdiffstats
path: root/src/gallium/drivers/vc4/vc4_qpu_emit.c
Commit message (Expand)AuthorAgeFilesLines
* vc4: Fix the test for skipping raw MOVs.Eric Anholt2015-10-241-1/+1
* vc4: Add QIR/QPU support for the 8-bit vector instructions.Eric Anholt2015-10-231-0/+5
* vc4: Fold the 16-bit integer pack into the instructions generating it.Eric Anholt2015-08-211-9/+5
* vc4: Pack the unorm-packing bits into a src MUL instruction when possible.Eric Anholt2015-08-201-0/+5
* vc4: Add a QIR helper for whether the op is a MUL type.Eric Anholt2015-08-201-4/+3
* vc4: Switch QPU_PACK_SCALED to be two non-SSA instructions.Eric Anholt2015-08-201-16/+7
* vc4: Make the pack-to-unorm instructions be non-SSA.Eric Anholt2015-08-201-22/+6
* vc4: Make r4-writes implicitly move to a temp, and allocate temps to r4.Eric Anholt2015-08-041-29/+29
* vc4: Fix compiler warnings on release builds.Eric Anholt2015-07-141-0/+1
* vc4: Swap around which src we spill to ra31/rb31.Eric Anholt2015-06-161-4/+4
* vc4: Convert from simple_list.h to list.hEric Anholt2015-05-291-7/+4
* vc4: Make SF be a flag on the QIR instructions.Eric Anholt2015-02-121-5/+5
* vc4: Avoid the save/restore of r3 for raddr conflicts, just use ra31.Eric Anholt2015-01-111-36/+9
* vc4: Redo VPM reads as a read file.Eric Anholt2015-01-101-5/+5
* vc4: Restructure color packing as a series of channel replacements.Eric Anholt2015-01-101-25/+25
* vc4: Redefine VPM writes as a (destination) QIR register file.Eric Anholt2014-12-171-4/+6
* vc4: Add support for turning constant uniforms into small immediates.Eric Anholt2014-12-171-9/+26
* vc4: Add support for 16-bit signed/unsigned norm/scaled vertex attrs.Eric Anholt2014-12-151-6/+19
* vc4: Add support for 8-bit unnormalized vertex attrs.Eric Anholt2014-12-151-0/+21
* vc4: Fix use of r3 as a temp in 8-bit unpacking.Eric Anholt2014-12-151-10/+7
* vc4: Rename UNPACK_8* to UNPACK_8*_F.Eric Anholt2014-12-151-5/+5
* vc4: Fix a memory leak in setting up QPU instructions for scheduling.Eric Anholt2014-12-111-1/+2
* vc4: Reserve rb31 instead of r3 for raddr conflict spills.Eric Anholt2014-12-091-8/+42
* vc4: Drop dependency on r3 for color packing.Eric Anholt2014-12-081-4/+27
* vc4: Introduce scheduling of QPU instructions.Eric Anholt2014-12-011-126/+6
* vc4: Drop the explicit scoreboard wait.Eric Anholt2014-12-011-12/+11
* vc4: Also deal with VPM reads at thread end.Eric Anholt2014-12-011-2/+6
* vc4: Add support for ARL and indirect register access on TGSI_FILE_CONSTANT.Eric Anholt2014-10-281-0/+5
* vc4: Add debug output to match shaderdb info to program dumps.Eric Anholt2014-10-241-1/+3
* vc4: Write the VPM read setup multiple times to queue all the inputs.Eric Anholt2014-10-131-3/+18
* vc4: Add support for the FACE semantic.Eric Anholt2014-10-011-0/+5
* vc4: When possible, resolve raddr conflicts by swapping files on specials.Eric Anholt2014-09-231-5/+29
* vc4: Fix overzealous raddr conflict resolution.Eric Anholt2014-09-231-5/+7
* vc4: Add support for 8-bit unorm/snorm vertex inputs.Eric Anholt2014-09-231-0/+25
* vc4: Add disasm for A-file unpack operations.Eric Anholt2014-09-231-1/+1
* vc4: Switch to using Mesa's register allocator.Eric Anholt2014-09-231-2/+2
* vc4: Use the same method as for FRAG_Z to handle fragcoord W.Eric Anholt2014-09-191-9/+3
* vc4: Add support for stencil operations.Eric Anholt2014-09-181-0/+4
* vc4: Make sure thread end doesn't have a uniform read.Eric Anholt2014-09-171-0/+8
* vc4: Move register allocation to a separate file.Eric Anholt2014-09-161-100/+6
* vc4: Restructure depth input/output in fragment shaders.Eric Anholt2014-09-161-7/+12
* vc4: Expose r4 to register allocation.Eric Anholt2014-09-091-10/+35
* vc4: Drop pointless raddr conflict handling on SF.Eric Anholt2014-09-091-1/+0
* vc4: Merge qcompile and tgsi_to_qirEric Anholt2014-09-041-8/+8
* vc4: Switch to using native integers.Eric Anholt2014-09-041-0/+12
* vc4: Expose compares at a lower level in QIR.Eric Anholt2014-09-041-31/+32
* vc4: Stop being so clever in CMP handling.Eric Anholt2014-09-041-23/+6
* vc4: Stop doing qpu_inst(add, NOP) or qpu_inst(NOP, mul).Eric Anholt2014-08-241-84/+47
* vc4: Merge qpu_a_NOP() and qpu_m_NOP to a single qpu_NOP() helper.Eric Anholt2014-08-241-43/+40
* vc4: Fix LT/GE set-0-or-1 compares.Eric Anholt2014-08-241-1/+1
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-03 00:17:12 +0000