| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | Remove the PTX back-end and all of its artifacts (triple, etc.) | Justin Holewinski | 2012-05-24 | 1 | -516/+0 |
| * | Convert more uses of XXXRegisterClass to &XXXRegClass. No functional change s... | Craig Topper | 2012-04-20 | 1 | -26/+20 |
| * | PTX: Fix predicate logic bug | Justin Holewinski | 2012-03-24 | 1 | -21/+31 |
| * | Reorder includes in Target backends to following coding standards. Remove som... | Craig Topper | 2012-03-17 | 1 | -1/+1 |
| * | Re-commit r151623 with fix. Only issue special no-return calls if it's a dire... | Evan Cheng | 2012-02-28 | 1 | -1/+1 |
| * | Revert r151623 "Some ARM implementaions, e.g. A-series, does return stack pre... | Daniel Dunbar | 2012-02-28 | 1 | -1/+1 |
| * | Some ARM implementaions, e.g. A-series, does return stack prediction. That is, | Evan Cheng | 2012-02-28 | 1 | -1/+1 |
| * | Make all pointers to TargetRegisterClass const since they are all pointers to... | Craig Topper | 2012-02-22 | 1 | -18/+11 |
| * | More dead code removal (using -Wunreachable-code) | David Blaikie | 2012-01-20 | 1 | -1/+0 |
| * | PTX: Continue to fix up the register mess. | Justin Holewinski | 2011-12-06 | 1 | -2/+33 |
| * | PTX: Let LLVM use loads/stores for all mem* intrinsics, instead of relying on... | Justin Holewinski | 2011-11-14 | 1 | -0/+5 |
| * | allow non-device function calls in PTX when natively handling device-side printf | Dan Bailey | 2011-11-11 | 1 | -20/+82 |
| * | PTX: Print .ptr kernel attributes if PTX version >= 2.2 | Justin Holewinski | 2011-10-09 | 1 | -0/+6 |
| * | PTX: Fixup a case where getRegClassFor() should be used instead of custom code. | Justin Holewinski | 2011-10-05 | 1 | -17/+1 |
| * | Remove a bunch of unused variables in the PTX backend (warned about by gcc-4.6). | Duncan Sands | 2011-10-05 | 1 | -25/+7 |
| * | PTX: MC-ize the PTX back-end (patch 1 of N) | Justin Holewinski | 2011-09-28 | 1 | -5/+7 |
| * | PTX: Simplify code. No functionality change. | Benjamin Kramer | 2011-09-28 | 1 | -13/+5 |
| * | PTX: Pass param name strings per const reference. | Benjamin Kramer | 2011-09-28 | 1 | -4/+4 |
| * | PTX: Use external symbols to keep track of params and locals. This also fixes | Justin Holewinski | 2011-09-27 | 1 | -12/+21 |
| * | PTX: Cleanup unused code in PTXMachineFunctionInfo | Justin Holewinski | 2011-09-23 | 1 | -54/+7 |
| * | PTX: Handle function call return values | Justin Holewinski | 2011-09-23 | 1 | -9/+31 |
| * | PTX: Start fixing function calls | Justin Holewinski | 2011-09-23 | 1 | -1/+3 |
| * | PTX: Generalize handling of .param types | Justin Holewinski | 2011-09-23 | 1 | -5/+11 |
| * | PTX: Remove physical register defs | Justin Holewinski | 2011-09-22 | 1 | -6/+0 |
| * | PTX: Use .param space for device function return values on SM 2.0+, and attempt | Justin Holewinski | 2011-09-22 | 1 | -28/+101 |
| * | PTX: Fix style issues | Justin Holewinski | 2011-09-22 | 1 | -21/+21 |
| * | Add codegen support for vector select (in the IR this means a select | Duncan Sands | 2011-09-06 | 1 | -1/+2 |
| * | Silence a bunch (but not all) "variable written but not read" warnings | Duncan Sands | 2011-08-12 | 1 | -2/+2 |
| * | PTX: Add initial support for device function calls | Justin Holewinski | 2011-08-09 | 1 | -0/+49 |
| * | Remove unused array. | Duncan Sands | 2011-07-02 | 1 | -21/+0 |
| * | PTX: Reverting implementation of i8. | Dan Bailey | 2011-06-25 | 1 | -34/+40 |
| * | PTX: Add support for i8 type and introduce associated .b8 registers | Dan Bailey | 2011-06-24 | 1 | -1/+16 |
| * | PTX: Re-work target sm/compute selection and add some basic GPU | Justin Holewinski | 2011-06-24 | 1 | -1/+1 |
| * | PTX: Always use registers for return values, but use .param space for device | Justin Holewinski | 2011-06-23 | 1 | -32/+18 |
| * | PTX: Whitespace fixes and remove commented out code | Justin Holewinski | 2011-06-23 | 1 | -1/+0 |
| * | PTX: Prevent DCE from eliminating st.param calls, and unify the handling of | Justin Holewinski | 2011-06-23 | 1 | -4/+4 |
| * | PTX: Use .param space for parameters in device functions for SM >= 2.0 | Justin Holewinski | 2011-06-23 | 1 | -17/+44 |
| * | PTX: Finish new calling convention implementation | Justin Holewinski | 2011-06-16 | 1 | -70/+101 |
| * | PTX: Rename register classes for readability and combine int and fp registers | Justin Holewinski | 2011-06-16 | 1 | -16/+16 |
| * | PTX: Fix whitespace errors | Justin Holewinski | 2011-06-16 | 1 | -9/+9 |
| * | Make the logic for determining function alignment more explicit. No function... | Eli Friedman | 2011-05-06 | 1 | -1/+3 |
| * | PTX: support for select_cc and fixes for setcc | Justin Holewinski | 2011-04-28 | 1 | -0/+36 |
| * | PTX: support for zext loads and trunc stores | Justin Holewinski | 2011-04-28 | 1 | -1/+13 |
| * | ptx: clean up branch code a bit | Che-Liang Chiou | 2011-03-28 | 1 | -2/+0 |
| * | PTX: Improve support for 64-bit addressing | Justin Holewinski | 2011-03-23 | 1 | -1/+4 |
| * | PTX: Fix various codegen issues | Justin Holewinski | 2011-03-18 | 1 | -1/+10 |
| * | ptx: add unconditional and conditional branch | Che-Liang Chiou | 2011-03-18 | 1 | -2/+9 |
| * | Avoid a compiler warning about reg possibly being used uninitialized | Duncan Sands | 2011-03-15 | 1 | -4/+2 |
| * | Extend initial support for primitive types in PTX backend | Che-Liang Chiou | 2011-03-02 | 1 | -7/+24 |
| * | Add preliminary support for .f32 in the PTX backend. | Che-Liang Chiou | 2011-02-28 | 1 | -5/+17 |
