summaryrefslogtreecommitdiff
AgeCommit message (Expand)AuthorFilesLines
2016-09-15direct-to-native-GL for GLX clients on Cygwin ("Windows-DRI")Jon Turney20-4/+2066
2016-09-15docs: add news item and link release notes for 12.0.3Emil Velikov2-0/+7
2016-09-15docs: add sha256 checksums for 12.0.3Emil Velikov1-1/+2
2016-09-15docs: add release notes for 12.0.3Emil Velikov1-0/+70
2016-09-15mesa: Expose RESET_NOTIFICATION_STRATEGY with KHR_robustness.Kenneth Graunke2-3/+10
2016-09-14anv/cmd_buffer: Set the L3 atomic disable mask bit in CHICKEN3 on HSWJason Ekstrand2-0/+2
2016-09-14intel/blorp: Stop setting 3DSTATE_DRAWING_RECTANGLEJason Ekstrand3-20/+5
2016-09-14intel/blorp: Emit 3DSTATE_MULTISAMPLE directlyJason Ekstrand3-53/+45
2016-09-14intel: Move Vulkan sample positions to common codeJason Ekstrand4-21/+21
2016-09-15Revert "tgsi/scan: don't set interp flags for inputs only used by INTERP inst...Marek Olšák1-57/+48
2016-09-14i965/vec4: Assert that pull constant load offsets are 16B-aligned.Francisco Jerez1-0/+1
2016-09-14i965/vec4: Assert that ATTR regions are register-aligned.Francisco Jerez1-0/+1
2016-09-14i965/vec4: Don't spill non-GRF-aligned register regions.Francisco Jerez2-2/+5
2016-09-14i965/vec4: Fix copy propagation for non-register-aligned regions.Francisco Jerez1-3/+6
2016-09-14i965/vec4: Compare full register offsets in cmod propagation.Francisco Jerez1-1/+1
2016-09-14i965/vec4: Assign correct destination offset to rewritten instruction in regi...Francisco Jerez1-2/+1
2016-09-14i965/vec4: Don't coalesce registers with overlapping writes not matching the ...Francisco Jerez1-4/+6
2016-09-14i965/vec4: Compare full register offsets in opt_register_coalesce nop move ch...Francisco Jerez1-1/+1
2016-09-14i965/vec4: Check that the write offsets match when setting dependency controls.Francisco Jerez1-0/+2
2016-09-14i965/vec4: Change opt_vector_float to keep track of the last offset seen in b...Francisco Jerez1-3/+3
2016-09-14i965/vec4: Simplify src/dst_reg to brw_reg conversion by using byte_offset().Francisco Jerez1-7/+8
2016-09-14i965/ir: Update several stale comments.Francisco Jerez5-26/+22
2016-09-14i965/ir: Don't print ARF subnr values twice.Francisco Jerez2-8/+0
2016-09-14i965/vec4: Print src/dst_reg::offset field consistently for all register files.Francisco Jerez1-6/+15
2016-09-14i965/fs: Print fs_reg::offset field consistently for all register files.Francisco Jerez1-16/+22
2016-09-14i965/fs: Misc simplification.Francisco Jerez4-6/+6
2016-09-14i965/fs: Get rid of fs_inst::set_smear().Francisco Jerez3-32/+15
2016-09-14i965/fs: Use region_contained_in() in compute-to-mrf coalescing pass.Francisco Jerez1-3/+2
2016-09-14i965/fs: Move region_contained_in to the IR header and fix for non-VGRF files.Francisco Jerez2-14/+13
2016-09-14i965/fs: Change region_contained_in() to use byte units.Francisco Jerez1-15/+10
2016-09-14i965/fs: Simplify copy propagation LOAD_PAYLOAD ACP setup.Francisco Jerez1-3/+2
2016-09-14i965/fs: Simplify a bunch of fs_inst::size_written calculations by using comp...Francisco Jerez4-15/+19
2016-09-14i965/fs: Simplify result_live calculation in dead_code_eliminate().Francisco Jerez1-9/+3
2016-09-14i965/fs: Simplify and fix buggy stride/offset calculations using subscript().Francisco Jerez2-59/+17
2016-09-14i965/fs: Simplify get_fpu_lowered_simd_width() by using inequalities instead ...Francisco Jerez1-2/+2
2016-09-14i965/fs: Simplify byte_offset().Francisco Jerez1-8/+4
2016-09-14i965/fs: Fix signedness of the return value of fs_inst::size_read().Francisco Jerez2-2/+2
2016-09-14i965/fs: Switch mask_relative_to() used in compute-to-mrf to byte units.Francisco Jerez1-10/+10
2016-09-14i965/fs: Fix bogus sub-MRF offset calculation in compute-to-mrf.Francisco Jerez1-6/+6
2016-09-14i965/fs: Take into account copy register offset during compute-to-mrf.Francisco Jerez1-1/+1
2016-09-14i965/vec4: Drop backend_reg::in_range() in favor of regions_overlap().Francisco Jerez5-20/+12
2016-09-14i965/vec4: Port regions_overlap() to the vec4 IR.Francisco Jerez1-4/+58
2016-09-14i965/fs: Stop using fs_reg::in_range() in favor of regions_overlap().Francisco Jerez1-1/+3
2016-09-14i965/fs: Drop fs_inst::overwrites_reg() in favor of regions_overlap().Francisco Jerez7-14/+15
2016-09-14i965/fs: Fix LOAD_PAYLOAD handling in register coalesce is_nop_mov().Francisco Jerez1-1/+3
2016-09-14i965/fs: Fix can_propagate_from() source/destination overlap check.Francisco Jerez1-2/+2
2016-09-14i965/fs: Compare full register offsets in cmod propagation pass.Francisco Jerez1-2/+1
2016-09-14i965/fs: Don't consider LOAD_PAYLOAD with stride > 1 source to behave like a ...Francisco Jerez1-1/+1
2016-09-14i965/fs: Don't consider LOAD_PAYLOAD with sub-GRF offset to behave like a raw...Francisco Jerez1-1/+1
2016-09-14i965/vec4: Take into account misalignment in regs_written() and regs_read().Francisco Jerez1-4/+6
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-22 12:29:05 +0000