aboutsummaryrefslogtreecommitdiff
path: root/test/CodeGen/X86
AgeCommit message (Collapse)Author
2012-06-29Clear kill flags in InstrEmitter::EmitSubregNode().Jakob Stoklund Olesen
When a local virtual register is made global, make sure to clear any existing kill flags. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159461 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-29In the initial exec mode we always do a load to find the address of a variable.Rafael Espindola
Before this patch in pic 32 bit code we would add the global base register and not load from that address. This is a really old bug, but before the introduction of the tls attributes we would never select initial exec for pic code. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159409 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-29X86: add more GATHER intrinsics in LLVMManman Ren
Corrected type for index of llvm.x86.avx2.gather.d.pd.256 from 256-bit to 128-bit. Corrected types for src|dst|mask of llvm.x86.avx2.gather.q.ps.256 from 256-bit to 128-bit. Support the following intrinsics: llvm.x86.avx2.gather.d.q, llvm.x86.avx2.gather.q.q llvm.x86.avx2.gather.d.q.256, llvm.x86.avx2.gather.q.q.256 llvm.x86.avx2.gather.d.d, llvm.x86.avx2.gather.q.d llvm.x86.avx2.gather.d.d.256, llvm.x86.avx2.gather.q.d.256 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159402 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-26X86: add GATHER intrinsics (AVX2) in LLVMManman Ren
Support the following intrinsics: llvm.x86.avx2.gather.d.pd, llvm.x86.avx2.gather.q.pd llvm.x86.avx2.gather.d.pd.256, llvm.x86.avx2.gather.q.pd.256 llvm.x86.avx2.gather.d.ps, llvm.x86.avx2.gather.q.ps llvm.x86.avx2.gather.d.ps.256, llvm.x86.avx2.gather.q.ps.256 Modified Disassembler to handle VSIB addressing mode. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159221 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-26Shuffle optimization for AVX/AVX2.Elena Demikhovsky
The current patch optimizes frequently used shuffle patterns and gives these instruction sequence reduction. Before: vshufps $-35, %xmm1, %xmm0, %xmm2 ## xmm2 = xmm0[1,3],xmm1[1,3] vpermilps $-40, %xmm2, %xmm2 ## xmm2 = xmm2[0,2,1,3] vextractf128 $1, %ymm1, %xmm1 vextractf128 $1, %ymm0, %xmm0 vshufps $-35, %xmm1, %xmm0, %xmm0 ## xmm0 = xmm0[1,3],xmm1[1,3] vpermilps $-40, %xmm0, %xmm0 ## xmm0 = xmm0[0,2,1,3] vinsertf128 $1, %xmm0, %ymm2, %ymm0 After: vshufps $13, %ymm0, %ymm1, %ymm1 ## ymm1 = ymm1[1,3],ymm0[0,0],ymm1[5,7],ymm0[4,4] vshufps $13, %ymm0, %ymm0, %ymm0 ## ymm0 = ymm0[1,3,0,0,5,7,4,4] vunpcklps %ymm1, %ymm0, %ymm0 ## ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5] git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159188 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-26Enable the new LoopInfo algorithm by default.Andrew Trick
The primary advantage is that loop optimizations will be applied in a stable order. This helps debugging and unit test creation. It is also a better overall implementation without pathologically bad performance on deep functions. On large functions (llvm-stress --size=200000 | opt -loops) Before: 0.1263s After: 0.0225s On deep functions (after tweaking llvm-stress, thanks Nadav): Before: 0.2281s After: 0.0227s See r158790 for more comments. The loop tree is now consistently generated in forward order, but loop passes are applied in reverse order over the program. If we have a loop optimization that prefers forward order, that can easily be achieved by adding a different type of LoopPassManager. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159183 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-25Make some ugly hacks for inline asm operands which name a specific register ↵Eli Friedman
a bit more thorough. PR13196. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159176 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-25Run ProcessImplicitDefs on SSA form where it can be much simpler.Jakob Stoklund Olesen
Implicitly defined virtual registers can simply have the <undef> bit set on all uses, and copies can be turned into implicit defs recursively. Physical registers are a bit trickier. We handle the common case where a physreg def is used by a nearby instruction in the same basic block. For more complicated cases, just leave the IMPLICIT_DEF instruction in. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159149 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-24%RCX is not a function live-out in eh.return functions.Jakob Stoklund Olesen
The function live-out registers must be live at all function returns, and %RCX is only used by eh.return. When a function also has a normal return, only %RAX holds a return value. This fixes PR13188. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159116 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-23Extend the IL for selecting TLS models (PR9788)Hans Wennborg
This allows the user/front-end to specify a model that is better than what LLVM would choose by default. For example, a variable might be declared as @x = thread_local(initialexec) global i32 42 if it will not be used in a shared library that is dlopen'ed. If the specified model isn't supported by the target, or if LLVM can make a better choice, a different model may be used. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159077 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-22FileCheckize tests.Chad Rosier
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159044 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-22EmitZerofill should take a 64-bit size or else it's chopping off large ↵Evan Cheng
zero-filled global. rdar://11729134 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159023 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-22Functions calling __builtin_eh_return must have a frame pointer.Jakob Stoklund Olesen
The code in X86TargetLowering::LowerEH_RETURN() assumes that a frame pointer exists, but the frame pointer was forced by the presence of llvm.eh.unwind.init which isn't guaranteed. If llvm.eh.unwind.init is actually required in functions calling eh.return (is it?), we should diagnose that instead of emitting bad machine code. This should fix the dragonegg-x86_64-linux-gcc-4.6-test bot. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158961 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-20Remove the -live-regunits command line option.Jakob Stoklund Olesen
Register allocators depend on it being permanently enabled now. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158873 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-20Only update regunit live ranges that have been precomputed.Jakob Stoklund Olesen
Regunit live ranges are computed on demand, so when mi-sched calls handleMove, some regunits may not have live ranges yet. That makes updating them easier: Just skip the non-existing ranges. They will be computed correctly from the rescheduled machine code when they are needed. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158831 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-20Don't insert 128-bit UNDEF into 256-bit vectors. Just keep the 256-bit ↵Craig Topper
vector. Original patch by Elena Demikhovsky. Tweaked by me to allow possibility of covering more cases. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158792 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-19really add a triple :-(Rafael Espindola
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158696 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-19Add a triple to the test.Rafael Espindola
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158695 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-19Move the support for using .init_array from ARM to the genericRafael Espindola
TargetLoweringObjectFileELF. Use this to support it on X86. Unlike ARM, on X86 it is not easy to find out if .init_array should be used or not, so the decision is made via TargetOptions and defaults to off. Add a command line option to llc that enables it. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158692 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-18Add a regression test for the bug exposed by r158087, which has beenChandler Carruth
temporarily reverted. This test is annoyingly overspecified, but I don't know of another way to thoroughly test the saving and restoring of the registers. While this will have to be adjusted even with the issue fixed in order to re-apply r158087, those adjustments should very clearly indicate that it is still correct (%esp getting restored prior to pops), whereas without it, this case can easily slip under the radar. Still, any suggestions for improvements are very welcome. All credit to Matt Beaumont-Gay for reducing this out of an insane Address Sanitizer crash to a reasonably small seg-faulting C program when built with -mstackrealign. I just reduced it to IR, which was much simpler. =] git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158656 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-18Temporarily revert r158087.Chandler Carruth
This patch causes problems when both dynamic stack realignment and dynamic allocas combine in the same function. With this patch, we no longer build the epilog correctly, and silently restore registers from the wrong position in the stack. Thanks to Matt for tracking this down, and getting at least an initial test case to Chad. I'm going to try to check a variation of that test case in so we can easily track the fixes required. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158654 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-13Fix intrinsics for XOP frczss/sd instructions. These instructions only take ↵Craig Topper
one source register and zero the upper bits of the destination rather than preserving them. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158396 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-09Replace XOP vpcom intrinsics with fewer intrinsics that take the immediate ↵Craig Topper
as an argument. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158278 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-08Don't run RAFast in the optimizing regalloc pipeline.Jakob Stoklund Olesen
The fast register allocator is not supposed to work in the optimizing pipeline. It doesn't make sense to compute live intervals, run full copy coalescing, and then run RAFast. Fast register allocation in the optimizing pipeline is better done by RABasic. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158242 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-08Test case for r158160Manman Ren
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158218 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-07X86: optimize generated code for integer ABSManman Ren
This patch will generate the following for integer ABS: movl %edi, %eax negl %eax cmovll %edi, %eax INSTEAD OF movl %edi, %ecx sarl $31, %ecx leal (%rdi,%rcx), %eax xorl %ecx, %eax There exists a target-independent DAG combine for integer ABS, which converts integer ABS to sar+add+xor. For X86, we match this pattern back to neg+cmov. This is implemented in PerformXorCombine. rdar://10695237 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158175 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-07Use a base register instead of an index register with the local dynamic model.Rafael Espindola
Fixes pr13048. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158158 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-07X86: replace SUB with CMP if possibleManman Ren
This patch will optimize the following movq %rdi, %rax subq %rsi, %rax cmovsq %rsi, %rdi movq %rdi, %rax to cmpq %rsi, %rdi cmovsq %rsi, %rdi movq %rdi, %rax Perform this optimization if the actual result of SUB is not used. rdar: 11540023 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158126 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-06Revert r157755.Manman Ren
The commit is intended to fix rdar://11540023. It is implemented as part of peephole optimization. We can actually implement this in the SelectionDAG lowering phase. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158122 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-06Add support for dynamic stack realignment in the presence of dynamic allocas onChad Rosier
X86. rdar://11496434 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158087 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-04Remove the "-promote-elements" flag. This flag is now enabled by default.Nadav Rotem
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157925 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-03Rename FMA3 feature flag to just FMA to match gcc so it can be added to clang.Craig Topper
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157903 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-03Rename fma4 intrinsics to just fma since they are now used for both FMA4 and ↵Craig Topper
FMA3. Autoupgrade support coming in a separate commit. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157898 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-03Revert r157831Manman Ren
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157896 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-03Use sse_load_f32/64 for scalar FMA3 intrinsic patterns instead of 128-bit ↵Craig Topper
loads to match instruction behavior. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157895 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-01X86: peephole optimization to remove cmp instructionManman Ren
This patch will optimize the following: sub r1, r3 cmp r3, r1 or cmp r1, r3 bge L1 TO sub r1, r3 bge L1 or ble L1 If the branch instruction can use flag from "sub", then we can eliminate the "cmp" instruction. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157831 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-01testcase for PR13006, thanks to Duncan for filing it.Chris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157824 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-01Implement the local-dynamic TLS model for x86 (PR3985)Hans Wennborg
This implements codegen support for accesses to thread-local variables using the local-dynamic model, and adds a clean-up pass so that the base address for the TLS block can be re-used between local-dynamic access on an execution path. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157818 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-01Remove fadd(fmul) patterns for FMA3. This needs to be implemented by paying ↵Craig Topper
attention to FP_CONTRACT and matching @llvm.fma which is not available yet. This will allow us to enablle intrinsic use at least though. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157804 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-01enhance the logic for looking through tailcalls to look through transparent ↵Chris Lattner
casts in multiple-return value scenarios, like what happens on X86-64 when returning small structs. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157800 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-01enhance getNoopInput to know about vector<->vector bitcasts of legalChris Lattner
types, as well as int<->ptr casts. This allows us to tailcall functions with some trivial casts between the call and return (i.e. because the return types disagree). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157798 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-01add some simple 64-bit tail call tests.Chris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157797 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-01merge some tests.Chris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157795 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-01rename testChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157794 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-31X86: replace SUB with CMP if possibleManman Ren
This patch will optimize the following movq %rdi, %rax subq %rsi, %rax cmovsq %rsi, %rdi movq %rdi, %rax to cmpq %rsi, %rdi cmovsq %rsi, %rdi movq %rdi, %rax Perform this optimization if the actual result of SUB is not used. rdar: 11540023 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157755 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-31Added FMA3 Intel instructions.Elena Demikhovsky
I disabled FMA3 autodetection, since the result may differ from expected for some benchmarks. I added tests for GodeGen and intrinsics. I did not change llvm.fma.f32/64 - it may be done later. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157737 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-31Add intrinsic for pclmulqdq instruction.Craig Topper
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157731 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-30Prioritize smaller register classes for urgent evictions.Jakob Stoklund Olesen
It helps compile exotic inline asm. In the test case, normal GR32 virtual registers use up eax-edx so the final GR32_ABCD live range has no registers left. Since all the live ranges were tiny, we had no way of prioritizing the smaller register class. This patch allows tiny unspillable live ranges to be evicted by tiny unspillable live ranges from a smaller register class. <rdar://problem/11542429> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157715 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-30it's pointed out that R11 can be used for magic things, and doing things ↵Chris Lattner
just for 64-bit registers is silly. Just optimize 3 more. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157699 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-30Extend the (abi-irrelevant) return convention to be able to return more than ↵Chris Lattner
two values in integer registers. This is already supported by the fastcc convention, but it doesn't hurt to support it in the standard conventions as well. In cases where we can cheat at the calling convention, this allows us to avoid returning things through memory in more cases. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157698 91177308-0d34-0410-b5e6-96231b3b80d8
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-12-29 12:52:27 +0000