aboutsummaryrefslogtreecommitdiffstats
Commit message (Expand)AuthorAgeFilesLines
* soft-fp64/fadd: Common code optimization for differing sign caseIan Romanick2020-03-181-21/+11
* soft-fp64/fadd: Move common code out of both branches of an if-statementIan Romanick2020-03-181-22/+11
* soft-fp64/fadd: Use absolute value of expDiffIan Romanick2020-03-181-3/+4
* soft-fp64/fadd: Rename aFrac and bFrac variablesIan Romanick2020-03-181-6/+21
* soft-fp64/fadd: Combine an if-statement into the preceeding else-clauseIan Romanick2020-03-181-4/+2
* soft-fp64/fadd: Reformat after previous commitIan Romanick2020-03-181-19/+21
* soft-fp64/fadd: Delete a redundant condition checkIan Romanick2020-03-181-1/+1
* soft-fp64/fadd: Just let the subtraction happen when the result will be zeroIan Romanick2020-03-181-4/+5
* soft-fp64/fadd: Pick zero or non-zero result based on subtraction resultIan Romanick2020-03-181-6/+1
* soft-fp64/fadd: Massively split the live range of zFrac0 and zFrac1Ian Romanick2020-03-181-3/+12
* soft-fp64/fadd: Instead of tracking "b < a", track sign of the differenceIan Romanick2020-03-181-5/+5
* soft-fp64: Optimize __fmin64 and __fmax64 by using different evaluation order...Ian Romanick2020-03-181-8/+16
* soft-fp64/ffloor: Simplify the >= 0 comparisonIan Romanick2020-03-181-1/+13
* soft-fp64: Relax the way NaN is propagatedIan Romanick2020-03-181-2/+19
* soft-fp64/fsat: Micro-optimize x >= 1 testIan Romanick2020-03-181-1/+19
* soft-fp64/fsat: Micro-optimize x < 0 testIan Romanick2020-03-181-1/+3
* soft-fp64/fsat: Correctly handle NaNIan Romanick2020-03-181-2/+3
* soft-fp64/flt: Perform checks in a different orderIan Romanick2020-03-182-16/+67
* soft-fp64/fneg: Don't treat NaN speciallyIan Romanick2020-03-181-4/+1
* soft-fp64: Store sign value as 0 or 0x80000000Ian Romanick2020-03-181-16/+16
* soft-fp64: Pick a single idiom for treating sign value as a BooleanIan Romanick2020-03-181-10/+10
* soft-fp64: Simplify __countLeadingZeros32 functionIan Romanick2020-03-181-3/+1
* soft-fp64: Don't open-code umulExtendedIan Romanick2020-03-181-32/+8
* soft-fp64/b2f: Reimplement using bitwise logic opsIan Romanick2020-03-181-1/+1
* nir/algebraic: Simplify a contradiction that can occur in __flt64_nonnanIan Romanick2020-03-181-0/+1
* nir/algebraic: Constant reassociation for bitwise operations tooIan Romanick2020-03-181-0/+3
* nir/algebraic: Generalize some and-of-shift-right patterns [v2]Ian Romanick2020-03-181-2/+19
* nir/algebraic: optimize ior(ine(a, 0), ine(b, 0)) to ine(ior(a, b), 0)Ian Romanick2020-03-181-1/+5
* nir/algebraic: Simplify logic to detect sign of an integerIan Romanick2020-03-181-0/+15
* st/mesa: disallow deferred flush if there are multiple contextsPierre-Eric Pelloux-Prayer2020-03-181-1/+2
* anv: Use isl_drm_modifier_get_default_aux_state()Chad Versace2020-03-181-18/+21
* intel/isl: Don't align linear images to 64K on Gen12+Jason Ekstrand2020-03-181-3/+12
* radv: fix random depth range unrestricted failures due to a cache issueSamuel Pitoiset2020-03-181-2/+6
* turnip: Do gathering xfb info after nir_remove_dead_variablesHyunjun Ko2020-03-181-3/+5
* turnip: Fix wrong assignment of xfb output's offset.Hyunjun Ko2020-03-181-1/+1
* intel/decoder: don't consider header fields past dword0Lionel Landwerlin2020-03-181-2/+4
* lima: decode depth/stencil write bits in RSWVasily Khoruzhick2020-03-181-2/+10
* lima: implement zsbuf reloadIcenowy Zheng2020-03-187-38/+84
* lima: disable Z16 formatVasily Khoruzhick2020-03-182-3/+0
* gallium/util: Switch util_float_to_half to _mesa_float_to_half()'s impl.Eric Anholt2020-03-171-52/+2
* amd/llvm: Fix divergent descriptor regressions with radeonsi.Bas Nieuwenhuizen2020-03-171-11/+13
* gallium: fix build with latest meson and gcc10Dave Airlie2020-03-171-1/+1
* ac: don't set old denormals flags with LLVM >= 11Marek Olšák2020-03-171-1/+2
* ac: set new LLVM denormal flagsMarek Olšák2020-03-171-0/+9
* ac: unify denorm setting enforcementMarek Olšák2020-03-173-32/+14
* gallium/u_vbuf: simplify the first if statement in u_vbuf_upload_buffersMarek Olšák2020-03-171-6/+8
* gallium/u_threaded: don't sync the thread for all unsychronized mappingsMarek Olšák2020-03-171-0/+3
* freedreno/a5xx: Fix min-vs-mag filtering decisions on non-mipmap tex.Eric Anholt2020-03-172-155/+10
* ci: Enable testing GLES2-3 on a530 (Dragonboard 820c).Eric Anholt2020-03-177-8/+2636
* ci: Enable ccaching of CMake builds as well.Eric Anholt2020-03-171-0/+5
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-02 01:48:23 +0000