aboutsummaryrefslogtreecommitdiff
path: root/lib
AgeCommit message (Collapse)Author
2013-03-04Bypass Slow DividesPreston Gurd
* Only apply divide bypass optimization when not optimizing for size. * Fixed bug caused by constant for 0 value of type Int32, used dividend type to generate the constant instead. * For atom x86-64 apply the divide bypass to use 16-bit divides instead of 64-bit divides when operand values are small enough. * Added lit tests for 64-bit divide bypass. Patch by Tyler Nowicki! git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176442 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-04R600: Clean up datalayout strings so they better match hardware capabilitiesTom Stellard
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176439 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-04Mips ISD typoJia Liu
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176426 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-02ARM: Creating a vector from a lane of another.Jim Grosbach
The VDUP instruction source register doesn't allow a non-constant lane index, so make sure we don't construct a ARM::VDUPLANE node asking it to do so. rdar://13328063 http://llvm.org/bugs/show_bug.cgi?id=13963 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176413 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-02Clean up code format a bit.Jim Grosbach
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176412 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-02Tidy up. Trailing whitespace.Jim Grosbach
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176411 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-02ARM NEON: Fix v2f32 float intrinsicsArnold Schwaighofer
Mark them as expand, they are not legal as our backend does not match them. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176410 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-02recommit r172363 & r171325 (reverted in r172756)Nuno Lopes
This adds minimalistic support for PHI nodes to llvm.objectsize() evaluation fingers crossed so that it does break clang boostrap again.. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176408 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-02add getUnderlyingObjectSize()Nuno Lopes
this is similar to getObjectSize(), but doesnt subtract the offset tweak the BasicAA code accordingly (per PR14988) git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176407 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-02X86 cost model: Adjust cost for custom lowered vector multipliesArnold Schwaighofer
This matters for example in following matrix multiply: int **mmult(int rows, int cols, int **m1, int **m2, int **m3) { int i, j, k, val; for (i=0; i<rows; i++) { for (j=0; j<cols; j++) { val = 0; for (k=0; k<cols; k++) { val += m1[i][k] * m2[k][j]; } m3[i][j] = val; } } return(m3); } Taken from the test-suite benchmark Shootout. We estimate the cost of the multiply to be 2 while we generate 9 instructions for it and end up being quite a bit slower than the scalar version (48% on my machine). Also, properly differentiate between avx1 and avx2. On avx-1 we still split the vector into 2 128bits and handle the subvector muls like above with 9 instructions. Only on avx-2 will we have a cost of 9 for v4i64. I changed the test case in test/Transforms/LoopVectorize/X86/avx1.ll to use an add instead of a mul because with a mul we now no longer vectorize. I did verify that the mul would be indeed more expensive when vectorized with 3 kernels: for (i ...) r += a[i] * 3; for (i ...) m1[i] = m1[i] * 3; // This matches the test case in avx1.ll and a matrix multiply. In each case the vectorized version was considerably slower. radar://13304919 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176403 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-02Added FIXME for future Hexagon cleanup.Andrew Trick
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176400 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-02PR14448 - prevent the loop vectorizer from vectorizing the same loop twice.Nadav Rotem
The LoopVectorizer often runs multiple times on the same function due to inlining. When this happens the loop vectorizer often vectorizes the same loops multiple times, increasing code size and adding unneeded branches. With this patch, the vectorizer during vectorization puts metadata on scalar loops and marks them as 'already vectorized' so that it knows to ignore them when it sees them a second time. PR14448. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176399 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-02Modify {Call,Invoke}Inst::addAttribute to take an AttrKind.Peter Collingbourne
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176397 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01Only fold small constants into memory reference displacements.Derek Schuff
This should more generally prevent negative values in index registers, but still allow most uses of this address mode for structure references. R=sehr@chromium.org BUG= https://code.google.com/p/nativeclient/issues/detail?id=3302 Review URL: https://codereview.chromium.org/12389054
2013-03-01Remove duplicate line and move another closer to its actual useEli Bendersky
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176391 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01In llvm::MemoryBuffer::getFile() remove an unnecessary stat call check.Argyrios Kyrtzidis
The sys::fs::is_directory() check is unnecessary because, if the filename is a directory, the function will fail anyway with the same error code returned. Remove the check to avoid an unnecessary stat call. Someone needs to review on windows and see if the check is necessary there or not. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176386 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01[mips] Fix inefficient code generation.Akira Hatanaka
This patch eliminates the need to emit a constant move instruction when this pattern is matched: (select (setgt a, Constant), T, F) The pattern above effectively turns into this: (conditional-move (setlt a, Constant + 1), F, T) git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176384 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01Removed extraneous #include "LLVMContextImpl.h" from lib/IR/Module.cppJean-Luc Duprat
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176382 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01Fix indentation.Akira Hatanaka
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176380 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01Set properties for f128 type.Akira Hatanaka
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176378 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01Generate an error message instead of asserting or segfaulting when we can'tChad Rosier
handle indirect register inputs. rdar://13322011 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176367 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01LoopVectorize: Don't hang forever if a PHI only has skipped PHI uses.Benjamin Kramer
Fixes PR15384. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176366 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01Cache the result of Function::getIntrinsicID() in a DenseMap attached to the ↵Michael Ilseman
LLVMContext. This reduces the time actually spent doing string to ID conversion and shows a 10% improvement in compile time for a particularly bad case that involves ARM Neon intrinsics (these have many overloads). Patch by Jean-Luc Duprat! git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176365 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01Fix PR10475Michael Liao
- ISD::SHL/SRL/SRA must have either both scalar or both vector operands but TLI.getShiftAmountTy() so far only return scalar type. As a result, backend logic assuming that breaks. - Rename the original TLI.getShiftAmountTy() to TLI.getScalarShiftAmountTy() and re-define TLI.getShiftAmountTy() to return target-specificed scalar type or the same vector type as the 1st operand. - Fix most TICG logic assuming TLI.getShiftAmountTy() a simple scalar type. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176364 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01Add support for using non-pic code for arm and thumb1 when emitting the sjljChad Rosier
dispatch code. As far as I can tell the thumb2 code is behaving as expected. I was able to compile and run the associated test case for both arm and thumb1. rdar://13066352 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176363 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01Hexagon: Add constant extender support framework.Jyotsna Verma
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176358 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01R600/SI: handle all registers in copyPhysReg v2Christian Konig
v2: based on Michels patch, but now allows copying of all registers sizes. Signed-off-by: Michel Dänzer <michel.daenzer@amd.com> Signed-off-by: Christian König <christian.koenig@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176346 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01R600/SI: remove S_MOV immediate patternsChristian Konig
They won't match anyway. Signed-off-by: Christian König <christian.koenig@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176345 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01R600/SI: remove GPR*AlignEncodeChristian Konig
It's much easier to specify the encoding with tablegen directly. Signed-off-by: Christian König <christian.koenig@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176344 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01R600/SI: fix warning about overloaded virtualChristian Konig
Signed-off-by: Christian König <christian.koenig@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176343 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01R600/SI: fix inserting waits for unordered definesChristian Konig
Signed-off-by: Christian König <christian.koenig@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176342 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01GCC thinks that this variable might be used uninitialized (it isn't).Duncan Sands
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176341 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01[mips] Remove unused option. Fix 80-column violations.Akira Hatanaka
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176330 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01[mips] Add the capability to search delay slot filling instructions inAkira Hatanaka
successor basic blocks. Currently this is off by default. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176329 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01[mips] Do not add SecondLastInst to list BranchInstrs if there is only oneAkira Hatanaka
terminator. No functionality change. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176326 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01[mips] Define an overloaded version of function MipsInstrInfo::AnalyzeBranchAdd.Akira Hatanaka
This function will be used later when the capability to search delay slot filling instructions in successor blocks is added. No intended functionality changes. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176325 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01[mips] Add options to disable searching backward and in successor blocks.Akira Hatanaka
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176321 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01[mips] Add capability to search in the forward direction for instructions thatAkira Hatanaka
can fill the delay slot. Currently, this is off by default. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176320 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01[mips] Define helper function searchRangeAkira Hatanaka
No functionality change. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176318 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01[mips] Rename function findDelayInstr to searchBackward.Akira Hatanaka
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176317 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01Scheduler diagnostics. Print the register name.Andrew Trick
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176316 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01Instructions schedulers should report correct height/depth.Andrew Trick
We avoided computing DAG height/depth during Node printing because it shouldn't depend on an otherwise valid DAG. But this has become far too annoying for the common case of a valid DAG where we want to see valid values. If doing the computation on-the-fly turns out to be a problem in practice, then I'll add a mode to the diagnostics to only force it when we're likely to have a valid DAG, otherwise explicitly print INVALID instead of bogus numbers. For now, just go for it all the time. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176314 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-01[mips] Define class MemDefsUses.Akira Hatanaka
This class tracks dependence between memory instructions using underlying objects of memory operands. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176313 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-28A small refactoring + adding comments.Eli Bendersky
SelectionDAGIsel::LowerArguments needs a function, not a basic block. So it makes sense to pass it the function instead of extracting a basic-block from the function and then tossing it. This is also more self-documenting (functions have arguments, BBs don't). In addition, added comments to a couple of Select* methods. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176305 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-28Don't add the 'Value' string if there isn't one.Bill Wendling
This was causing the folding set to fail to fold attributes, because it was being calculated in one spot without an empty values string but here with an empty values string. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176301 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-28Fix a bug in instcombine for fmul in fast math mode.Quentin Colombet
The instcombine recognized pattern looks like: a = b * c d = a +/- Cst or a = b * c d = Cst +/- a When creating the new operands for fadd or fsub instruction following the related fmul, the first operand was created with the second original operand (M0 was created with C1) and the second with the first (M1 with Opnd0). The fix consists in creating the new operands with the appropriate original operand, i.e., M0 with Opnd0 and M1 with C1. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176300 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-28Move an assert earlier in a file and check that the result ofEric Christopher
our bitwise compare is equal to the field we're looking for. Noticed on inspection. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176296 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-28Don't add an attribute that already exists and don't remove an attribute ↵Bill Wendling
that doesn't exist. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176289 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-28Tidy up; no functional change.Chad Rosier
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176288 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-28Cost model support for lowered math builtins.Benjamin Kramer
We make the cost for calling libm functions extremely high as emitting the calls is expensive and causes spills (on x86) so performance suffers. We still vectorize important calls like ceilf and friends on SSE4.1. and fabs. Differential Revision: http://llvm-reviews.chandlerc.com/D466 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176287 91177308-0d34-0410-b5e6-96231b3b80d8
generated by cgit v1.2.3-18-g5258 (git 2.32.0) at 2025-07-15 16:10:29 +0000