- 44d798d Add support for a new extension to the .file directive: by Nick Lewycky · 13 years ago
- 68226a4 PTX: Print .ptr kernel attributes if PTX version >= 2.2 by Justin Holewinski · 13 years ago
- 9a6eba6 PTX: Implement signed division by Justin Holewinski · 13 years ago
- de8f33c Build system infrastructure for multiple tblgens. by Peter Collingbourne · 13 years ago
- 591c1c6 PTX: Fixup a case where getRegClassFor() should be used instead of custom code. by Justin Holewinski · 13 years ago
- 62c607b Ensure OpCode is not used uninitialized. by Duncan Sands · 13 years ago
- 72478e6 Comment out a variable that is only used in commented out code. by Duncan Sands · 13 years ago
- 37f8065 Remove a bunch of unused variables in the PTX backend (warned about by gcc-4.6). by Duncan Sands · 13 years ago
- f51b7e5 PTX: Various stylistic and code readability changes recommended by Jim Grosbach. by Justin Holewinski · 13 years ago
- 8c1dac5 PTX: Add programmable rounding mode specifier for int <-> fp conversion instrs. by Justin Holewinski · 13 years ago
- c90e149 PTX: Attempt to cleanup/unify the handling of FP rounding modes. This requires by Justin Holewinski · 13 years ago
- 2097d70 PTX: Fix broken shared library build by Justin Holewinski · 13 years ago
- d57c1bc PTX: Add new patterns for bitconvert and any_extend by Justin Holewinski · 13 years ago
- cfab2be PTX: Fix alignment logic by Justin Holewinski · 13 years ago
- ed0e4c8 PTX: MC-ize the PTX backend (patch 2 of N) by Justin Holewinski · 13 years ago
- d8e4ed2 PTX: MC-ize the PTX back-end (patch 1 of N) by Justin Holewinski · 13 years ago
- ca92159 PTX: Simplify code. No functionality change. by Benjamin Kramer · 13 years ago
- 8adae0c PTX: Pass param name strings per const reference. by Benjamin Kramer · 13 years ago
- 332850d PTX: Fix case where printed alignment could be 0 by Justin Holewinski · 13 years ago
- f47dfba PTX: Use external symbols to keep track of params and locals. This also fixes by Justin Holewinski · 13 years ago
- 13e0c80 PTX: Add support for sitofp in backend by Justin Holewinski · 13 years ago
- 22d54da PTX: Fix memcpy intrinsic to handle 64-bit pointers by Justin Holewinski · 13 years ago
- bc97f44 PTX: Implement PTXSelectionDAGInfo by Justin Holewinski · 13 years ago
- 63bce90 PTX: Implement ISD::ANY_EXTEND by Justin Holewinski · 13 years ago
- 63602ed PTX: Fix detection of stack load/store vs. global load/store, as well as fix the by Justin Holewinski · 13 years ago
- 22f3c59 PTX: SM > 2.0 implies +double by Justin Holewinski · 13 years ago
- 5878850 PTX: Fix some lingering issues with stack allocation by Justin Holewinski · 13 years ago
- d5c3920 PTX: Split up the TableGen instruction definitions into logical units by Justin Holewinski · 13 years ago
- c1d8fbd PTX: Unify handling of loads/stores by Justin Holewinski · 13 years ago
- 6b8990d PTX: Handle FrameIndex nodes by Justin Holewinski · 13 years ago
- 74e2d6e Clean up code after renaming LowerSubregs -> ExpandPostRAPseudos. by Jakob Stoklund Olesen · 13 years ago
- a574556 PTX: Fix parameter order bug by Justin Holewinski · 13 years ago
- dc0baf9 PTX: Cleanup unused code in PTXMachineFunctionInfo by Justin Holewinski · 13 years ago
- d7070fe PTX: Fix another 80-column violation by Justin Holewinski · 13 years ago
- 75d8095 PTX: Handle function call return values by Justin Holewinski · 13 years ago
- e953a64 PTX: Start fixing function calls by Justin Holewinski · 13 years ago
- d3dec06 PTX: Remove PTX calling convention files by Justin Holewinski · 13 years ago
- 1cde87d [PATCH 2/2] PTXInstrInfo.td PTXIntrinsicInstrInfo.td 80 columns by Justin Holewinski · 13 years ago
- 27f08fc PTX: Generalize handling of .param types by Justin Holewinski · 13 years ago
- 04b5ebc PTX: Cleanup unused code in the PTXMFInfoExtract pass by Justin Holewinski · 13 years ago
- 7c9dd62 PTX: Remove physical register defs by Justin Holewinski · 13 years ago
- 5422a0f PTX: Use .param space for device function return values on SM 2.0+, and attempt by Justin Holewinski · 13 years ago
- 05591be PTX: Fix style issues by Justin Holewinski · 13 years ago
- 297984d PTX: Fixup codegen to handle emission of virtual registers. by Justin Holewinski · 13 years ago
- 40466cc PTX: Customize codegen passes in backend by Justin Holewinski · 13 years ago
- 247ee00 PTX: Add new PTX-specific register allocator that keeps virtual registers by Justin Holewinski · 13 years ago
- 98c5dda Don't attach annotations to MCInst's. Instead, have the disassembler return, and the printer accept, an annotation string which can be passed through if the client cares about annotations. by Owen Anderson · 13 years ago
- 28b77e9 Add codegen support for vector select (in the IR this means a select by Duncan Sands · 13 years ago
- 36a1601 Don't drop alignment info on local common symbols. by Benjamin Kramer · 13 years ago
- 3e74d6f Move TargetRegistry and TargetSelect from Target to Support where they belong. by Evan Cheng · 13 years ago
- 7801136 Some refactoring so TargetRegistry.h no longer has to include any files from MC. by Evan Cheng · 13 years ago
- 1f6a329 Silence a bunch (but not all) "variable written but not read" warnings by Duncan Sands · 13 years ago
- 4bdd4ed PTX: Add initial support for device function calls by Justin Holewinski · 13 years ago
- 81fd0ba Actually finish switching to the new system for Target sublibrary by Chandler Carruth · 13 years ago
- ac03e73 Rewrite the CMake build to use explicit dependencies between libraries, by Chandler Carruth · 13 years ago
- b35552d Clean up a pile of hacks in our CMake build relating to TableGen. by Chandler Carruth · 13 years ago
- 78c10ee Rename TargetAsmBackend to MCAsmBackend; rename createAsmBackend to createMCAsmBackend. by Evan Cheng · 13 years ago
- 7f8dff6 createXXXMCCodeGenInfo should be static. by Evan Cheng · 13 years ago
- e78085a Combine all MC initialization routines into one. e.g. InitializeX86MCAsmInfo, by Evan Cheng · 13 years ago
- 34ad6db - Move CodeModel from a TargetMachine global option to MCCodeGenInfo. by Evan Cheng · 13 years ago
- 4396613 Introduce MCCodeGenInfo, which keeps information that can affect codegen by Evan Cheng · 13 years ago
- 0e6a052 Sink getDwarfRegNum, getLLVMRegNum, getSEHRegNum from TargetRegisterInfo down by Evan Cheng · 13 years ago
- db125cf land David Blaikie's patch to de-constify Type, with a few tweaks. by Chris Lattner · 13 years ago
- 1be0e27 Move some parts of TargetAsmInfo down to MCAsmInfo. This is not the greatest by Evan Cheng · 13 years ago
- 1abf2cb Rename createAsmInfo to createMCAsmInfo and move registration code to MCTargetDesc to prepare for next round of changes. by Evan Cheng · 13 years ago
- c60f9b7 Next round of MC refactoring. This patch factor MC table instantiations, MC by Evan Cheng · 13 years ago
- 672b93a Unfortunately several files in MC are badly violating layering rule by using by Evan Cheng · 13 years ago
- 59ee62d - Eliminate MCCodeEmitter's dependency on TargetMachine. It now uses MCInstrInfo by Evan Cheng · 13 years ago
- ffc0e73 Change createAsmParser to take a MCSubtargetInfo instead of triple, by Evan Cheng · 13 years ago
- ebdeeab Eliminate asm parser's dependency on TargetMachine: by Evan Cheng · 13 years ago
- 0ddff1b Compute feature bits at time of MCSubtargetInfo initialization. by Evan Cheng · 13 years ago
- d6b98e8 Remove unused array. by Duncan Sands · 13 years ago
- 385e930 Rename XXXGenSubtarget.inc to XXXGenSubtargetInfo.inc for consistency. by Evan Cheng · 13 years ago
- 5b1b4489 Rename TargetSubtarget to TargetSubtargetInfo for consistency. by Evan Cheng · 13 years ago
- 9421470 - Added MCSubtargetInfo to capture subtarget features and scheduling by Evan Cheng · 13 years ago
- 4db3cff Hide the call to InitMCInstrInfo into tblgen generated ctor. by Evan Cheng · 13 years ago
- 276365d Fix the ridiculous SubtargetFeatures API where it implicitly expects CPU name to by Evan Cheng · 13 years ago
- 6844f7b Hide more details in tablegen generated MCRegisterInfo ctor function. by Evan Cheng · 13 years ago
- 22fee2d Merge XXXGenRegisterNames.inc into XXXGenRegisterInfo.inc by Evan Cheng · 13 years ago
- e837dea - Rename TargetInstrDesc, TargetOperandInfo to MCInstrDesc and MCOperandInfo and by Evan Cheng · 13 years ago
- 73f50d9 Merge XXXGenRegisterDesc.inc XXXGenRegisterNames.inc XXXGenRegisterInfo.h.inc by Evan Cheng · 13 years ago
- 8414946 PTX: Reverting implementation of i8. by Dan Bailey · 13 years ago
- b05a8a8 PTX: Add support for i8 type and introduce associated .b8 registers by Dan Bailey · 13 years ago
- 4799729 PTX: Add preliminary support for outputting debug information in the form of by Justin Holewinski · 13 years ago
- 35f4fb3 PTX: Re-work target sm/compute selection and add some basic GPU by Justin Holewinski · 13 years ago
- a347f85 Starting to refactor Target to separate out code that's needed to fully describe by Evan Cheng · 13 years ago
- d8149c1 PTX: Always use registers for return values, but use .param space for device by Justin Holewinski · 13 years ago
- 486ca24 PTX: Whitespace fixes and remove commented out code by Justin Holewinski · 13 years ago
- a5ccb4e PTX: Prevent DCE from eliminating st.param calls, and unify the handling of by Justin Holewinski · 13 years ago
- 67a9184 PTX: Use .param space for parameters in device functions for SM >= 2.0 by Justin Holewinski · 13 years ago
- 08d0316 PTX: Fix FrameIndex mapping bug by Justin Holewinski · 13 years ago
- 3e8cff4 Test Commit. by Dan Bailey · 13 years ago
- 6332fde PTX: Add signed integer comparisons by Justin Holewinski · 13 years ago
- a9c85f9 PTX: Add .address_size directive if PTX version >= 2.3 by Justin Holewinski · 13 years ago
- c882df2 PTX: Fix conversion between predicates and value types by Justin Holewinski · 13 years ago
- cad129b PTX: Fix if-then-else formatting and add missing asserts by Justin Holewinski · 13 years ago
- df1c8d8 PTX: Add basic register spilling code by Justin Holewinski · 13 years ago
- 7d715df Fix a FIXME by making GlobalVariable::getInitializer() return a by Jay Foad · 13 years ago
- e266ce6 Use the verbose asm flag instead of a new flag for decoding the LSDA. by Bill Wendling · 13 years ago
- 916a94b Add an option that allows one to "decode" the LSDA. by Bill Wendling · 13 years ago