summaryrefslogtreecommitdiffstats
path: root/src/gallium/auxiliary/gallivm
Commit message (Expand)AuthorAgeFilesLines
* gallivm: support more immediates in lp_build_tgsi_info()Brian Paul2013-01-041-1/+1
* gallivm: fix conversion for pure integer formatsRoland Scheidegger2012-12-181-0/+1
* gallivm: fix texel fetch for array textures (2)Roland Scheidegger2012-12-171-2/+3
* gallivm: fix texel fetch for array texturesRoland Scheidegger2012-12-131-17/+38
* gallivm: Lower TGSI_OPCODE_MUL to fmul by defaultTom Stellard2012-12-101-2/+3
* llvmpipe: fix txq for 1d/2d arrays. (v3)Dave Airlie2012-12-111-2/+15
* llvmpipe: increase texture target width to reflect increaseDave Airlie2012-12-111-1/+1
* gallivm: Rudimentary native integer support.José Fonseca2012-12-072-5/+20
* gallivm: Allow indirection from TEMP registers too.José Fonseca2012-12-071-3/+18
* gallivm,llvmpipe,draw: Support multiple constant buffers.José Fonseca2012-12-072-3/+19
* gallivm: Fix lerping of (un)signed normalized numbers.José Fonseca2012-12-061-49/+43
* gallivm: Fix lp_build_print_value of smaller integer types.José Fonseca2012-12-061-1/+12
* gallivm: Have a default emit function for min/max opcodeVincent Lejeune2012-12-051-0/+29
* gallivm: have a default emit function for fdiv/rcpVincent Lejeune2012-12-051-0/+25
* gallivm: Re-add the kludge for lp_build_lerp of fixed point types.José Fonseca2012-12-041-1/+5
* gallivm: Generalize lp_build_mul and lp_build_lerp for signed normalized types.José Fonseca2012-12-041-92/+82
* gallivm: fix srgb format fetchRoland Scheidegger2012-12-031-1/+2
* gallivm: drop border wrap clamping codeRoland Scheidegger2012-12-011-33/+16
* gallivm: Fix lp_build_float_to_half.José Fonseca2012-11-291-30/+75
* gallivm: fix a trivial txq issue for 2d shadow and cube shadow samplersRoland Scheidegger2012-11-291-2/+2
* gallivm: support array texturesRoland Scheidegger2012-11-296-65/+103
* util/u_format: Kill util_format_is_array().José Fonseca2012-11-292-2/+4
* gallivm: Fix format manipulation for big-endianAdhemerval Zanella2012-11-295-12/+145
* gallivm: Add byte-swap construct callsAdhemerval Zanella2012-11-292-0/+89
* gallivm: Fix vector constant for shuffleAdhemerval Zanella2012-11-291-1/+6
* gallivm: clear Altivec NJ bitAdhemerval Zanella2012-11-291-0/+19
* gallivm: Altivec floating-point roundingAdhemerval Zanella2012-11-291-23/+70
* gallivm: Altivec vector add/sub intrisicsAdhemerval Zanella2012-11-292-15/+27
* gallivm: Altivec vector max/min intrisicsAdhemerval Zanella2012-11-291-2/+54
* gallivm: Altivec pack/unpack intrisicsAdhemerval Zanella2012-11-291-14/+30
* llvmpipe: Unswizzled rendering.James Benton2012-11-2812-29/+360
* gallivm: Updated lp_build_const_mask_aos to input number of channels.James Benton2012-11-285-18/+26
* gallivm: Added support for float to half-float conversion in lp_build_conv.James Benton2012-11-282-7/+94
* gallivm: Changed lp_build_pad_vector to correctly handle scalar argument.James Benton2012-11-283-17/+22
* gallivm: Add a function to generate lp_type for a format.James Benton2012-11-282-7/+31
* gallivm: Add support for unorm16 in lp_build_mul.James Benton2012-11-281-0/+45
* gallivm: fix multiple lods with different min/mag filter and wide vectorsRoland Scheidegger2012-11-281-0/+3
* gallivm: Fix bug in lp_build_one which would incorrectly return a vector for ...James Benton2012-11-271-1/+1
* gallivm: use the new mip per quad handling in texture fetch pathRoland Scheidegger2012-11-273-193/+212
* gallivm,llvmpipe: handle TXF (texelFetch) instruction, including offsetsRoland Scheidegger2012-11-279-64/+602
* gallivm,draw,llvmpipe: use base ptr + mip offsets instead of mip pointersRoland Scheidegger2012-11-123-9/+19
* gallium/gallivm: code generation options for LLVM 3.1+Alexander V. Nikolaev2012-10-283-17/+44
* gallivm/llvmpipe: fix 64-bit %ll format compiler warnings for mingw32Brian Paul2012-10-261-4/+3
* gallivm: Hide AVX support when requested by LP_NATIVE_VECTOR_WIDTH or unsuppo...José Fonseca2012-10-171-0/+10
* gallivm: Use mcjit for ppc_64 architectureWill Schmidt2012-10-171-1/+4
* Revert "gallivm: Don't use llvm.x86.avx.max/min.ps.256 inadvertently."José Fonseca2012-10-171-4/+4
* gallivm: Don't use llvm.x86.avx.max/min.ps.256 inadvertently.José Fonseca2012-10-121-4/+4
* gallivm: fix rsqrt failuresRoland Scheidegger2012-10-121-8/+41
* llvmpipe: remove unused variables to fix compile warningsMarek Olšák2012-10-092-6/+3
* gallivm,llvmpipe: Use 4-wide vectors on AMD Bulldozer.José Fonseca2012-09-041-1/+9