summaryrefslogtreecommitdiffstats
path: root/src/intel/compiler
Commit message (Expand)AuthorAgeFilesLines
* intel/fs: Disable SIMD32 dispatch on Gen4-6 with control flowFrancisco Jerez2018-06-281-0/+8
* intel/fs: Split instructions low to high in lower_simd_widthJason Ekstrand2018-06-281-2/+35
* intel/fs: Rework KSP data to be SIMD width-basedJason Ekstrand2018-06-283-47/+43
* intel/compiler: Add and use helpers for working with KSP indicesJason Ekstrand2018-06-281-0/+85
* intel/fs: Remove program key argument from generator.Francisco Jerez2018-06-287-10/+7
* intel/fs: Set up FB write message headers in the visitorJason Ekstrand2018-06-282-83/+86
* intel/fs: Fix implied_mrf_writes() for headerless FB writes.Francisco Jerez2018-06-281-1/+2
* intel/fs: Fix fs_inst::flags_written() for Gen4-5 FB writes.Francisco Jerez2018-06-281-1/+2
* intel/eu: Return new instruction to caller from brw_fb_WRITE().Francisco Jerez2018-06-282-21/+23
* intel/fs: Pull FB write implied headers from src[0]Jason Ekstrand2018-06-281-9/+6
* intel/fs: Properly track implied header regs read by FB writesJason Ekstrand2018-06-281-1/+16
* intel/fs: FS_OPCODE_REP_FB_WRITE has side effectsJason Ekstrand2018-06-281-0/+1
* i965/gen6/gs: Handle case where a GS doesn't allocate VUEAndrii Simiklit2018-06-261-21/+21
* nir: Rework lower_locals_to_regs to use deref instructionsJason Ekstrand2018-06-221-2/+0
* intel,ir3: Re-enable nir_opt_copy_prop_varsJason Ekstrand2018-06-221-1/+1
* intel/nir: Only lower load/store derefsJason Ekstrand2018-06-221-1/+1
* intel/fs: Use image_deref intrinsics instead of image_varJason Ekstrand2018-06-223-75/+86
* i965: Move nir_lower_deref_instrs to right before locals_to_regsJason Ekstrand2018-06-221-0/+2
* intel,ir3: Disable nir_opt_copy_prop_varsJason Ekstrand2018-06-221-1/+1
* intel/fs: shuffle_64bit_data_for_32bit_write is not used anymoreJose Maria Casanova Crespo2018-06-162-36/+0
* intel/fs: Use new shuffle_32bit_write for all 64-bit storage writesJose Maria Casanova Crespo2018-06-161-7/+6
* intel/fs: shuffle_32bit_load_result_to_64bit_data is not used anymoreJose Maria Casanova Crespo2018-06-162-58/+0
* intel/fs: Use shuffle_from_32bit_read for 64-bit FS load_inputJose Maria Casanova Crespo2018-06-161-4/+4
* intel/fs: shuffle_from_32bit_read at load_per_vertex_input at TCS/TESJose Maria Casanova Crespo2018-06-161-14/+8
* intel/fs: Use shuffle_from_32bit_read at VS load_inputJose Maria Casanova Crespo2018-06-161-10/+5
* intel/fs: Use shuffle_from_32bit_read for 64-bit gs_input_loadJose Maria Casanova Crespo2018-06-161-5/+5
* intel/fs: shuffle_from_32bit_read for 64-bit do_untyped_vector_readJose Maria Casanova Crespo2018-06-161-10/+2
* intel/fs: Remove old 16-bit shuffle/unshuffle functionsJose Maria Casanova Crespo2018-06-162-73/+0
* intel/fs: Use shuffle_for_32bit_write for 16-bits store_ssboJose Maria Casanova Crespo2018-06-161-5/+2
* intel/fs: Use shuffle_from_32bit_read to read 16-bit SSBOJose Maria Casanova Crespo2018-06-161-4/+2
* intel/fs: Use shuffle_from_32bit_read at VARYING_PULL_CONSTANT_LOADJose Maria Casanova Crespo2018-06-161-15/+2
* intel/fs: New shuffle_for_32bit_write and shuffle_from_32bit_readJose Maria Casanova Crespo2018-06-162-0/+54
* intel/fs: general 8/16/32/64-bit shuffle_src_to_dst functionJose Maria Casanova Crespo2018-06-161-0/+101
* i965/fs: Propagate conditional modifiers from not instructionsIan Romanick2018-06-151-1/+61
* i965/fs: Rearrange code to remove most of the gotosIan Romanick2018-06-151-11/+3
* i965/fs: Refactor propagation of conditional modifiers from compares to addsIan Romanick2018-06-151-57/+80
* i965/vec4: Optimize OR with 0 into a MOVIan Romanick2018-06-151-0/+8
* i965/vec4: Don't register coalesce into source of VS_OPCODE_UNPACK_FLAGS_SIMD4X2Ian Romanick2018-06-151-0/+9
* i965/fs: Optimize OR with 0 into a MOVIan Romanick2018-06-151-1/+2
* intel/compiler: Properly consider UBO loads that cross 32B boundaries.Kenneth Graunke2018-06-141-2/+14
* Revert "intel/compiler: Properly consider UBO loads that cross 32B boundaries."Jason Ekstrand2018-06-131-7/+1
* intel/compiler: Properly consider UBO loads that cross 32B boundaries.Kenneth Graunke2018-06-131-1/+7
* intel/eu: Use a struct copy instead of a memcpyJason Ekstrand2018-06-051-1/+1
* intel/eu: Switch to a logical state stackJason Ekstrand2018-06-043-126/+72
* intel/eu: Set flag [sub]register number differently for 3srcJason Ekstrand2018-06-041-3/+10
* intel/eu: Copy fields manually in brw_next_insnJason Ekstrand2018-06-041-1/+94
* intel/eu: Add some brw_get_default_ helpersJason Ekstrand2018-06-044-55/+79
* i965: Add ARB_fragment_shader_interlock support.Plamena Manolova2018-06-017-6/+34
* intel/fs: Add explicit last_rt flag to fb writes orthogonal to eot.Francisco Jerez2018-05-294-5/+5
* intel/fs: Replace the CINTERP opcode with a simple MOVFrancisco Jerez2018-05-295-12/+3
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-19 06:22:14 +0000