aboutsummaryrefslogtreecommitdiffstats
path: root/test/CodeGen/R600
Commit message (Expand)AuthorAgeFilesLines
* R600: Fix calculation of stack offset in AMDGPUFrameLoweringTom Stellard2013-06-071-0/+33
* R600: Fix the fetch limits for R600 generation GPUsTom Stellard2013-06-072-0/+129
* R600: Add a pass that merge Vector RegisterVincent Lejeune2013-06-051-0/+30
* R600: Schedule copy from phys register at beginning of blockVincent Lejeune2013-06-0510-10/+10
* R600: Make sure to schedule AR register uses and defs in the same clauseTom Stellard2013-06-051-0/+32
* Revert "R600: Add a pass that merge Vector Register"Rafael Espindola2013-06-051-30/+0
* R600: Add a pass that merge Vector RegisterVincent Lejeune2013-06-041-0/+30
* R600: Const/Neg/Abs can be folded to dot4Vincent Lejeune2013-06-041-0/+27
* R600: Swizzle texture/export instructionsVincent Lejeune2013-06-041-5/+5
* R600: Add a test for r183108Vincent Lejeune2013-06-041-0/+2
* R600/SI: Add support for work item and work group intrinsicsTom Stellard2013-06-031-0/+211
* R600/SI: Add a calling convention for compute shadersTom Stellard2013-06-037-10/+10
* R600/SI: Custom lower i64 sign_extendTom Stellard2013-06-031-0/+12
* R600/SI: Add support for global loadsTom Stellard2013-06-031-3/+49
* R600: use capital letter for PV channelVincent Lejeune2013-06-0314-17/+17
* R600: Fix R600ControlFlowFinalizer not considering VTX_READ 128 bit dst regTom Stellard2013-05-231-0/+22
* R600: Fix rotr.ll on non-asserts buildsTom Stellard2013-05-201-6/+2
* R600/SI: Add pattern for rotrTom Stellard2013-05-201-9/+19
* R600: Swap the legality of rotl and rotrTom Stellard2013-05-201-0/+29
* R600/SI: Add patterns for 64-bit shift operationsTom Stellard2013-05-201-0/+3
* R600: Lower int_load_input to copyFromReg instead of Register nodeVincent Lejeune2013-05-171-0/+121
* R600: Use bottom up scheduling algorithmVincent Lejeune2013-05-1715-17/+19
* R600: Use depth first scheduling algorithmVincent Lejeune2013-05-172-2/+2
* R600: Relax some vector constraints on Dot4.Vincent Lejeune2013-05-171-1/+1
* R600: Improve texture handlingVincent Lejeune2013-05-171-16/+16
* R600: Rename 128 bit registers.Vincent Lejeune2013-05-171-16/+16
* R600: Fix encoding for R600 family GPUsTom Stellard2013-05-171-0/+24
* R600/SI: Add lit test coverage for the remaining patterns added recentlyMichel Danzer2013-05-146-11/+111
* R600: Remove AMDILPeeopholeOptimizer and replace optimizations with tablegen ...Tom Stellard2013-05-101-0/+26
* R600: Expand SUB for v2i32/v4i32Tom Stellard2013-05-101-0/+15
* R600: Expand MUL for v4i32/v2i32Tom Stellard2013-05-101-0/+16
* R600: Expand SRA for v4i32/v2i32Tom Stellard2013-05-101-0/+13
* R600: Expand vselect for v4i32 and v2i32Tom Stellard2013-05-101-0/+17
* R600/SI: Add lit tests for llvm.SI.imageload and llvm.SI.resinfo intrinsicsMichel Danzer2013-05-082-0/+197
* R600: Emit config values in register / value pairsTom Stellard2013-05-061-2/+3
* R600: Stop emitting the instruction type byte before each instructionTom Stellard2013-05-062-4/+4
* R600: Emit ISA for CALL_FS_* instructionsTom Stellard2013-05-061-0/+15
* R600: Expand vector or, shl, srl, and xor nodesTom Stellard2013-05-034-0/+52
* R600: Add pattern for SHA-256 Ma functionTom Stellard2013-05-031-0/+18
* R600: Signed literals are 64bits wideVincent Lejeune2013-05-021-0/+165
* R600: If previous bundle is dot4, PV valid chan is always XVincent Lejeune2013-05-021-0/+244
* R600: Add a test to check that use_kill is emittedVincent Lejeune2013-05-021-0/+1
* R600: Prettier asmPrint of AluVincent Lejeune2013-05-0234-101/+127
* TBAA: remove !tbaa from testing cases if not used.Manman Ren2013-04-301-4/+1
* R600: fix loop-address.ll testVincent Lejeune2013-04-301-2/+2
* R600: use native for aluVincent Lejeune2013-04-303-5/+6
* R600: Add FetchInst bit to instruction defs to denote vertex/tex instructionsVincent Lejeune2013-04-301-2/+2
* R600: Use correct CF_END instruction on Northern Island GPUsTom Stellard2013-04-291-2/+5
* R600: Fix encoding of CF_END_{EG, R600} instructionsTom Stellard2013-04-291-0/+6
* R600: Initialize AMDGPUMachineFunction::ShaderType to ShaderType::COMPUTETom Stellard2013-04-261-1/+3