summaryrefslogtreecommitdiffstats
path: root/src/gallium/drivers/radeon/radeon_llvm.h
Commit message (Expand)AuthorAgeFilesLines
* gallium/radeon: normalize the code styleMarek Olšák2016-07-131-66/+32
* radeon/llvm: Use alloca instructions for larger arraysTom Stellard2016-07-061-1/+6
* radeonsi: keep using v_rcp_f32 for division in future LLVM (v2)Marek Olšák2016-07-051-0/+3
* radeonsi: convert to 64-bitness checks instead of doubles.Dave Airlie2016-06-111-3/+4
* radeonsi: add shared memoryBas Nieuwenhuizen2016-04-191-0/+3
* gallium/radeon: remove remnants of R600 TGSI->LLVMMarek Olšák2016-03-201-17/+0
* gallium/radeon: add basic code for setting shader return valuesMarek Olšák2016-02-211-1/+3
* radeon/llvm: Set the target triple on the moduleTom Stellard2016-02-171-1/+2
* gallium/radeon: remove unused variables and old commentsMarek Olšák2015-07-311-19/+0
* gallium/radeon: remove build_intrinsic and build_tgsi_intrinsicMarek Olšák2015-07-311-8/+0
* radeonsi: fix GLSL textureGrad(samplerCube*) functionsMarek Olšák2015-07-251-2/+3
* gallium/radeon: expose emit_fetchMarek Olšák2015-07-231-0/+5
* gallium/radeon: expose LLVM functions implementing emit_storeMarek Olšák2015-07-231-0/+9
* radeonsi: ARB_gpu_shader_fp64 + ARB_vertex_attrib_64bit support.Dave Airlie2015-07-121-1/+6
* radeon/llvm: don't use a static array size for radeon_llvm_context::arrays (v2)Marek Olšák2015-05-291-3/+1
* radeon/llvm: Dynamically allocate branch/loop stack arraysMichel Dänzer2014-10-291-4/+6
* r600/llvm: Allow arbitrary amount of temps in tgsi to llvmVincent Lejeune2013-12-071-0/+6
* r600/llvm: Store inputs in function argumentsVincent Lejeune2013-11-111-0/+1
* r600/llvm: Adds support for MSAAVincent Lejeune2013-10-021-0/+1
* r600g/llvm: fix txq for texture bufferVincent Lejeune2013-10-021-0/+1
* r600g/llvm: Fix cubearray textureSizeVincent Lejeune2013-05-201-0/+1
* radeon/llvm: rework input fetch and output storeChristian König2013-03-191-13/+19
* radeon/llvm: make SGPRs proper function arguments v2Christian König2013-03-071-0/+3
* r600g/llvm: Set Inputs/Outputs count to 32 (api reported value)Vincent Lejeune2013-02-181-2/+2
* r600g/llvm: Fix alpha_to_one piglit testsVincent Lejeune2013-02-181-0/+1
* radeonsi: Adapt to sample intrinsics changes.Michel Dänzer2013-02-041-1/+1
* r600g: improve inputs/interpolation handling with llvm backendVadim Girlin2013-01-281-2/+1
* r600g/llvm: tgsi to llvm emits store.swizzle intrinsic for vs/fs outputVincent Lejeune2013-01-181-0/+1
* r600g/llvm: tgsi to llvm emits stream output intrinsics.Vincent Lejeune2013-01-181-0/+1
* radeon/llvm: improve cube map handlingVadim Girlin2012-12-181-1/+2
* radeon/llvm: Export prepare_cube_coords helper to driver.Michel Dänzer2012-12-061-0/+3
* r600g: make tgsi-to-llvm generates store.pixel* intrinsic for fsVincent Lejeune2012-11-021-0/+3
* r600g: add some members to radeon_llvm_contextVincent Lejeune2012-09-281-0/+6
* radeon/llvm: use IntrNoMem property for intrinsics where possibleVadim Girlin2012-05-151-0/+16
* radeon/llvm: add support for VertexID, InstanceIDVadim Girlin2012-05-081-0/+7
* radeon/llvm: use bitcasts for integersVadim Girlin2012-05-081-0/+31
* radeon: Move radeon_llvm_emit.cpp declarations into their own headerTom Stellard2012-04-231-17/+3
* radeonsi: initial WIP SI codeTom Stellard2012-04-131-0/+136