| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | Replace the arm.neon.vmovls and vmovlu intrinsics with vector sign-extend and | Bob Wilson | 2010-08-20 | 2 | -21/+6 |
| * | It's possible to sink a def if its local uses are PHI's. | Evan Cheng | 2010-08-19 | 1 | -0/+39 |
| * | When sending stats output to stdout for grepping, don't emit normal | Dan Gohman | 2010-08-18 | 1 | -1/+1 |
| * | When sending stats output to stdout for grepping, don't emit normal | Dan Gohman | 2010-08-18 | 8 | -9/+9 |
| * | Fix a bug with insertelement on SPU. | Kalle Raiskila | 2010-08-18 | 1 | -0/+15 |
| * | Remove all traces of v2[i,f]32 on SPU. | Kalle Raiskila | 2010-08-18 | 3 | -10/+10 |
| * | Change SPU C calling convention to match that described in | Kalle Raiskila | 2010-08-18 | 1 | -0/+33 |
| * | Expand ZERO_EXTEND operations for NEON vector types. | Bob Wilson | 2010-08-18 | 1 | -0/+7 |
| * | Tweak IVUsers' concept of "interesting" to exclude add recurrences | Dan Gohman | 2010-08-17 | 2 | -1/+52 |
| * | Add nounwind. | Evan Cheng | 2010-08-17 | 1 | -1/+1 |
| * | Make fast scheduler handle asm clobbers correctly. | Dale Johannesen | 2010-08-17 | 1 | -0/+17 |
| * | Change ARM PKHTB and PKHBT instructions to use a shift_imm operand to avoid | Bob Wilson | 2010-08-17 | 2 | -2/+2 |
| * | Allow more cases of undef shuffle indices and add tests for them. | Bob Wilson | 2010-08-17 | 5 | -0/+119 |
| * | PHI elimination should not break back edge. It can cause some significant cod... | Evan Cheng | 2010-08-17 | 2 | -2/+31 |
| * | Add a testcase for svn 111208. | Bob Wilson | 2010-08-16 | 1 | -0/+14 |
| * | Generalize a pattern for PKHTB: an SRL of 16-31 bits will guarantee | Bob Wilson | 2010-08-16 | 2 | -1/+19 |
| * | Convert test to FileCheck. | Bob Wilson | 2010-08-16 | 1 | -4/+19 |
| * | Convert a test to use FileCheck. | Bob Wilson | 2010-08-16 | 1 | -4/+19 |
| * | Test expects SSE, give him SSE. | Benjamin Kramer | 2010-08-15 | 1 | -1/+1 |
| * | Restore arch on these test, they fail on arm. | Benjamin Kramer | 2010-08-15 | 2 | -2/+2 |
| * | Mark as XFAIL on darwin 8. PR 7886. | Dale Johannesen | 2010-08-15 | 1 | -0/+2 |
| * | Temporarily disable tail calls on ARM to work around some linker problems. | Bob Wilson | 2010-08-13 | 4 | -0/+4 |
| * | Revert 110491. While not wrong, it was based on a | Dale Johannesen | 2010-08-13 | 1 | -27/+0 |
| * | - Teach SSEDomainFix to switch between different levels of AVX instructions. ... | Bruno Cardoso Lopes | 2010-08-12 | 1 | -0/+12 |
| * | Begin to support some vector operations for AVX 256-bit intructions. The long | Bruno Cardoso Lopes | 2010-08-12 | 1 | -0/+15 |
| * | This is x86 only test. | Devang Patel | 2010-08-12 | 1 | -1/+1 |
| * | Add testcases for all AVX 256-bit intrinsics added in the last couple days | Bruno Cardoso Lopes | 2010-08-11 | 1 | -0/+751 |
| * | Reapply r109881 using a more strict command line for llc. | Bruno Cardoso Lopes | 2010-08-11 | 2 | -0/+2006 |
| * | fix silly typo | Jim Grosbach | 2010-08-11 | 1 | -2/+2 |
| * | Add a target triple, as the runtime library invocation varies a bit by | Jim Grosbach | 2010-08-11 | 1 | -3/+3 |
| * | Fix test and re-enable it. | Evan Cheng | 2010-08-11 | 1 | -4/+4 |
| * | Temporarily disable some failing tests, until they can be | Dan Gohman | 2010-08-11 | 1 | -2/+2 |
| * | cortex m4 has floating point support, but only single precision. | Jim Grosbach | 2010-08-11 | 1 | -0/+24 |
| * | Temporarily disable some failing tests, until they can be | Dan Gohman | 2010-08-11 | 1 | -2/+2 |
| * | Consider this code snippet: | Bill Wendling | 2010-08-11 | 1 | -0/+25 |
| * | Report error if codegen tries to instantiate a ARM target when the cpu does s... | Evan Cheng | 2010-08-11 | 2 | -11/+1 |
| * | Add ARM Archv6M and let it implies FeatureDB (having dmb, etc.) | Evan Cheng | 2010-08-11 | 1 | -6/+6 |
| * | Add Cortex-M0 support. It's a ARMv6m device (no ARM mode) with some 32-bit | Evan Cheng | 2010-08-11 | 1 | -5/+12 |
| * | - Add subtarget feature -mattr=+db which determine whether an ARM cpu has the | Evan Cheng | 2010-08-11 | 2 | -0/+34 |
| * | Update test to match output of optimize compares for ARM. | Bill Wendling | 2010-08-11 | 1 | -4/+2 |
| * | The optimize comparisons pass removes the "cmp" instruction this is checking ... | Bill Wendling | 2010-08-10 | 1 | -1/+0 |
| * | Re-apply r110655 with fixes. Epilogue must restore sp from fp if the function... | Evan Cheng | 2010-08-10 | 2 | -7/+75 |
| * | Revert r110655, "Fix ARM hasFP() semantics. It should return true whenever FP | Daniel Dunbar | 2010-08-10 | 1 | -22/+7 |
| * | Fix test for more architectures. Patch by Tobias Grosser. | Jakob Stoklund Olesen | 2010-08-10 | 1 | -1/+1 |
| * | Fix failing testcase. | Tobias Grosser | 2010-08-10 | 1 | -1/+1 |
| * | Handle TAG_constant for integers. | Devang Patel | 2010-08-10 | 1 | -0/+25 |
| * | Fix ARM hasFP() semantics. It should return true whenever FP register is | Evan Cheng | 2010-08-10 | 1 | -7/+22 |
| * | Have SPU handle halfvec stores aligned by 8 bytes. | Kalle Raiskila | 2010-08-09 | 2 | -3/+15 |
| * | Use sdmem and sse_load_f64 (etc.) for the vector | Dale Johannesen | 2010-08-07 | 1 | -0/+27 |
| * | Fix eabi calling convention when a 64 bit value shadows r3. | Rafael Espindola | 2010-08-06 | 1 | -0/+14 |
