| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | Simplify this code. Thanks Chris! | Dan Gohman | 2008-06-20 | 1 | -3/+2 |
| | | | | | llvm-svn: 52514 | ||||
| * | ISD::UNDEF should be expanded recursively / iteratively. | Evan Cheng | 2008-06-19 | 2 | -1/+6 |
| | | | | | llvm-svn: 52508 | ||||
| * | Add a hidden -disable-pre flag for testing purposes. This should be removed | Owen Anderson | 2008-06-19 | 1 | -2/+8 |
| | | | | | | | once benchmarking is completed. llvm-svn: 52506 | ||||
| * | PRE requires that critical edges be split. | Owen Anderson | 2008-06-19 | 1 | -0/+24 |
| | | | | | llvm-svn: 52505 | ||||
| * | Remove dead code causing a warning. | Bill Wendling | 2008-06-19 | 1 | -2/+0 |
| | | | | | llvm-svn: 52502 | ||||
| * | Use the common API for adding instructions to basic blocks instead of | Dan Gohman | 2008-06-19 | 1 | -11/+6 |
| | | | | | | | using BasicBlock::getInstList. llvm-svn: 52500 | ||||
| * | Be sure to remove values from the value numbering table after we delete them. | Owen Anderson | 2008-06-19 | 1 | -0/+1 |
| | | | | | | | This fixes a failure on povray. llvm-svn: 52499 | ||||
| * | Use Instruction::moveBefore instead of manipulating the instruction list | Dan Gohman | 2008-06-19 | 1 | -4/+2 |
| | | | | | | | directly. llvm-svn: 52498 | ||||
| * | Avoid using BasicBlock::getInstList directly in a few places. | Dan Gohman | 2008-06-19 | 1 | -9/+10 |
| | | | | | llvm-svn: 52497 | ||||
| * | Revert support for insertvalue and extractvalue instructions for the moment. | Owen Anderson | 2008-06-19 | 1 | -63/+1 |
| | | | | | | | | GVN expects that all inputs which to an instruction fall somewhere in the value hierarchy, which isn't true for these. llvm-svn: 52496 | ||||
| * | Use the transferSuccessors helper function. | Dan Gohman | 2008-06-19 | 1 | -5/+1 |
| | | | | | llvm-svn: 52495 | ||||
| * | Delete dead code. | Dan Gohman | 2008-06-19 | 1 | -4/+0 |
| | | | | | llvm-svn: 52494 | ||||
| * | Add an idx_iterator to the insertvalue and extractvalue instructions. | Owen Anderson | 2008-06-19 | 1 | -4/+6 |
| | | | | | llvm-svn: 52493 | ||||
| * | The inline keyword goes before the return type. This fixes a compiler warning. | Dan Gohman | 2008-06-19 | 1 | -1/+1 |
| | | | | | llvm-svn: 52492 | ||||
| * | Modify some ipconstprop tests to also test with invokes. | Matthijs Kooijman | 2008-06-19 | 2 | -2/+13 |
| | | | | | llvm-svn: 52491 | ||||
| * | Use a CallSite to find the nth argument of a call/invoke instruction instead of | Matthijs Kooijman | 2008-06-19 | 1 | -11/+11 |
| | | | | | | | | using getOperand() directly. This makes things work with invoke instructions as well. llvm-svn: 52489 | ||||
| * | Fix some warnings reported by gcc-4.3. Hopefully | Duncan Sands | 2008-06-19 | 2 | -8/+10 |
| | | | | | | | this still compiles on windows - I can't test! llvm-svn: 52488 | ||||
| * | Missed a check. | Evan Cheng | 2008-06-19 | 1 | -1/+1 |
| | | | | | llvm-svn: 52487 | ||||
| * | Fix a bug with <8 x i16> shuffle lowering on X86 where parts of the | Eli Friedman | 2008-06-19 | 2 | -2/+10 |
| | | | | | | | | | | | shuffle could be skipped. The check is invalid because the loop index i doesn't correspond to the element actually inserted. The correct check is already done a few lines earlier, for whether the element is already in the right spot, so this shouldn't have any effect on the codegen for code that was already correct. llvm-svn: 52486 | ||||
| * | Revert my last patch, which was causing regression test failures. | Owen Anderson | 2008-06-19 | 1 | -78/+69 |
| | | | | | llvm-svn: 52485 | ||||
| * | New test case. | Evan Cheng | 2008-06-19 | 1 | -0/+17 |
| | | | | | llvm-svn: 52483 | ||||
| * | This also got better (55 - 51 instructions). But doing one more ↵ | Evan Cheng | 2008-06-19 | 1 | -1/+1 |
| | | | | | | | re-materialization. llvm-svn: 52482 | ||||
| * | This got better. | Evan Cheng | 2008-06-19 | 1 | -1/+1 |
| | | | | | llvm-svn: 52481 | ||||
| * | Coalesce copy from one register class to a sub register class. e.g. ↵ | Evan Cheng | 2008-06-19 | 2 | -25/+98 |
| | | | | | | | X86::MOV16to16_. llvm-svn: 52480 | ||||
| * | Cosmetic changes. | Evan Cheng | 2008-06-19 | 1 | -3/+5 |
| | | | | | llvm-svn: 52479 | ||||
| * | Unneeded include's. | Evan Cheng | 2008-06-19 | 2 | -2/+0 |
| | | | | | llvm-svn: 52478 | ||||
| * | Minor spiller tweak to unfavor reload into load/store instructions. | Evan Cheng | 2008-06-19 | 3 | -6/+21 |
| | | | | | llvm-svn: 52477 | ||||
| * | Insert empty slots into the instruction numbering in live intervals, so that ↵ | Owen Anderson | 2008-06-19 | 1 | -69/+78 |
| | | | | | | | | | we can more easily add new instructions. llvm-svn: 52475 | ||||
| * | Remove this test until the corresponding patch is reapplied because it's ↵ | Owen Anderson | 2008-06-18 | 1 | -39/+0 |
| | | | | | | | causing make check to crash for some people. llvm-svn: 52473 | ||||
| * | Add support for extractvalue and insertvalue instructions in GVN. | Owen Anderson | 2008-06-18 | 1 | -1/+63 |
| | | | | | llvm-svn: 52472 | ||||
| * | Add local PRE to GVN. This only operates in cases where it would not ↵ | Owen Anderson | 2008-06-18 | 2 | -30/+186 |
| | | | | | | | | | increase code size, namely when the instantiated expression would only need to be created in one predecessor. llvm-svn: 52471 | ||||
| * | Refactor the way to get a string containing the features of the target. | Bill Wendling | 2008-06-18 | 3 | -32/+26 |
| | | | | | llvm-svn: 52470 | ||||
| * | Fix the source line debug information for the Windows platform. | Argyrios Kyrtzidis | 2008-06-18 | 1 | -5/+88 |
| | | | | | | | | According to DWARF-2 specification, the line information is provided through an offset in the .debug_line section. Replace the label reference that is used with a section offset. llvm-svn: 52468 | ||||
| * | Fix a missing comma spotted by Bram Geron. | Dan Gohman | 2008-06-18 | 1 | -1/+1 |
| | | | | | llvm-svn: 52467 | ||||
| * | Fix the regressions on sext-misc.ll my patch yesterday caused. | Chris Lattner | 2008-06-18 | 1 | -0/+1 |
| | | | | | llvm-svn: 52466 | ||||
| * | Revert r52459, which was causing an infinite loop or massive slowdown on ↵ | Owen Anderson | 2008-06-18 | 1 | -469/+369 |
| | | | | | | | | | MultiSource/Applications/SPASS, and possibly others as well. Please reapply once this is fixed. llvm-svn: 52465 | ||||
| * | Move SCEVExpander::visitAddExpr out-of-line. | Dan Gohman | 2008-06-18 | 2 | -9/+11 |
| | | | | | llvm-svn: 52464 | ||||
| * | Move LSR's private isZero function to a public SCEV member | Dan Gohman | 2008-06-18 | 4 | -27/+24 |
| | | | | | | | function, and make use of it in several places. llvm-svn: 52463 | ||||
| * | fix validator warning | Gabor Greif | 2008-06-18 | 1 | -1/+1 |
| | | | | | llvm-svn: 52461 | ||||
| * | prettify, no semantic changes | Gabor Greif | 2008-06-18 | 1 | -92/+138 |
| | | | | | llvm-svn: 52460 | ||||
| * | Rewrite the DeadArgumentElimination pass, to use a more explicit tracking of | Matthijs Kooijman | 2008-06-18 | 2 | -369/+508 |
| | | | | | | | | | | | | | | dependencies between return values and/or arguments. Also make the handling of arguments and return values the same. The pass now looks properly inside returned structs, but only at the first level (ie, not inside nested structs). Also add a testcase for testing various variations of (multiple) dead rerturn values. llvm-svn: 52459 | ||||
| * | Reapply r52397 (make IPConstProp promote returned arguments), but fixed this | Matthijs Kooijman | 2008-06-18 | 2 | -3/+64 |
| | | | | | | | | | time. Sorry for the trouble! This time, also add a testcase, which I should have done in the first place... llvm-svn: 52455 | ||||
| * | XOR32rr, etc. are not AsCheapAsMove, but MOV32ri, etc. are. | Evan Cheng | 2008-06-18 | 1 | -4/+3 |
| | | | | | llvm-svn: 52454 | ||||
| * | Reapply r52396, it was unrelated to the breakage (that was caused by r52397, my | Matthijs Kooijman | 2008-06-18 | 2 | -62/+106 |
| | | | | | | | commit after this). llvm-svn: 52453 | ||||
| * | Complete support for two-address pass rematerialization. Now *almost* always ↵ | Evan Cheng | 2008-06-18 | 1 | -49/+128 |
| | | | | | | | a win. llvm-svn: 52452 | ||||
| * | Add MachineRegisterInfo::use_empty. | Evan Cheng | 2008-06-18 | 1 | -0/+4 |
| | | | | | llvm-svn: 52451 | ||||
| * | Cosmetic. | Evan Cheng | 2008-06-18 | 1 | -1/+1 |
| | | | | | llvm-svn: 52450 | ||||
| * | If compiling for PPC on an i386 box, the LTO wouldn't get the altivec (and | Bill Wendling | 2008-06-18 | 2 | -24/+51 |
| | | | | | | | | other) feature information. The workaround is inelegant and could be cleaned up if this information were available some other way (say, in the IR). llvm-svn: 52447 | ||||
| * | implement some simple bswap optimizations, rdar://5992453 | Chris Lattner | 2008-06-18 | 2 | -126/+195 |
| | | | | | llvm-svn: 52442 | ||||
| * | temporarily revert this testcase since its patch was reverted. | Chris Lattner | 2008-06-18 | 1 | -30/+9 |
| | | | | | llvm-svn: 52441 | ||||

