aboutsummaryrefslogtreecommitdiff
path: root/lib/Target
AgeCommit message (Collapse)Author
2012-04-06Eliminate iOS-specific tail call instructions.Jakob Stoklund Olesen
After register masks were introdruced to represent the call clobbers, it is no longer necessary to have duplicate instruction for iOS. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154209 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-06There is no portable std::abs overload for int64_t, use the llvm::abs64Chandler Carruth
which exists for this purpose. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154199 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-06Allow negative immediates in ARM and Thumb2 compares.Jakob Stoklund Olesen
ARM and Thumb2 mode can use cmn instructions to compare against negative immediates. Thumb1 mode can't. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154183 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-06Fix narrowing conversion.Benjamin Kramer
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154171 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-06Allow 256-bit shuffles to be split if a 128-bit lane contains elements from ↵Craig Topper
a single source. This is a rewrite of the 256-bit shuffle splitting code based on similar code from legalize types. Fixes PR12413. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154166 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-06Deduplicate ARM call-related instructions.Jakob Stoklund Olesen
We had special instructions for iOS because r9 is call-clobbered, but that is represented dynamically by the register mask operands now, so there is no need for the pseudo-instructions. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154144 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-05ARM: Don't form a t2LDRi8 or t2STRi8 with an offset of zero.Jim Grosbach
The load/store optimizer splits LDRD/STRD into two instructions when the register pairing doesn't work out. For negative offsets in Thumb2, it uses t2STRi8 to do that. That's fine, except for the case when the offset is in the range [-4,-1]. In that case, we'll also form a second t2STRi8 with the original offset plus 4, resulting in a t2STRi8 with a non-negative offset, which ends up as if it were an STRT, which is completely bogus. Similarly for loads. No testcase, unfortunately, as any I've been able to construct is both large and extremely fragile. rdar://11193937 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154141 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-05ARM assembly aliases for add negative immediates using sub.Jim Grosbach
'add r2, #-1024' should just use 'sub r2, #1024' rather than erroring out. Thumb1 aliases for adding a negative immediate to the stack pointer, also. rdar://11192734 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154123 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-05Added support for unpredictable ADC/SBC instructions on ARM, and also fixed ↵Silviu Baranga
some corner cases involving the PC register as an operand for these instructions. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154101 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-05Added support for handling unpredictable arithmetic instructions on ARM.Silviu Baranga
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154100 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-05ARM assembly aliases for two-operand V[R]SHR instructions.Jim Grosbach
rdar://11189467 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154087 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-05ARM assembly parsing for 'msr' plain 'cpsr' operand.Jim Grosbach
Plain 'cpsr' is an alias for 'cpsr_fc'. rdar://11153753 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154080 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-04Reapply 154038 without the failing test.Akira Hatanaka
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154062 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-04Revert r154038. It was causing make check failures.Owen Anderson
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154054 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-04Fix LowerGlobalAddress to produce instructions with the correct relocationAkira Hatanaka
types for N32 ABI. Add new test case and update existing ones. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154038 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-04Fix LowerJumpTable to produce instructions with the correct relocationAkira Hatanaka
types for N32 ABI. Test case will be updated after the patch that fixes TargetLowering::getPICJumpTableRelocBase is checked in. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154036 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-04Fix LowerConstantPool to produce instructions with the correct relocationAkira Hatanaka
types for N32 ABI and update test case. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154034 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-04Implement ARMBaseInstrInfo::commuteInstruction() for MOVCCr.Jakob Stoklund Olesen
A MOVCCr instruction can be commuted by inverting the condition. This can help reduce register pressure and remove unnecessary copies in some cases. <rdar://problem/11182914> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154033 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-04Fix LowerBlockAddress to produce instructions with the correct relocationAkira Hatanaka
types for N32 ABI and update test case. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154031 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-04Always compute all the bits in ComputeMaskedBits.Rafael Espindola
This allows us to keep passing reduced masks to SimplifyDemandedBits, but know about all the bits if SimplifyDemandedBits fails. This allows instcombine to simplify cases like the one in the included testcase. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154011 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-03ARMDisassembler: drop bogus dependency on ARMCodeGenDylan Noblesmith
And indirectly, a dependency on most of the core LLVM optimization libraries. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153957 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-03Make PPCCompilationCallbackC function to be static, so there will be no need ↵Anton Korobeynikov
to issue call via PLT when LLVM is built as shared library. This mimics the X86 backend towards the approach. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153938 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-03Add support for AVX enhanced comparison predicates. Patch from Kay Tiong Khoo.Craig Topper
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153935 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-03Revert r153924. Delete test/MC/Disassembler/Mips and ↵Akira Hatanaka
lib/Target/Mips/Disassembler. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153926 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-03Revert r153924. There were buildbot failures.Akira Hatanaka
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153925 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-03MIPS disassembler support.Akira Hatanaka
Patch by Vladimir Medic. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153924 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-02Initial 64 bit direct object support.Akira Hatanaka
This patch allows llvm to recognize that a 64 bit object file is being produced and that the subsequently generated ELF header has the correct information. The test case checks for both big and little endian flavors. Patch by Jack Carter. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153889 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-02The binutils for the IBM BG/P are too old to support CFI.Hal Finkel
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153886 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-02Implement the SVR4 byval alignment for aggregates. Fixing a FIXME.Roman Divacky
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153876 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-02Move getOpcodeName from the various target InstPrinters into the superclass ↵Benjamin Kramer
MCInstPrinter. All implementations used the same code. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153866 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-02Remove getInstructionName from MCInstPrinter implementations in favor of ↵Craig Topper
using the instruction name table from MCInstrInfo. Reduces static data in the InstPrinter implementations. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153863 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-02Make MCInstrInfo available to the MCInstPrinter. This will be used to remove ↵Craig Topper
getInstructionName and the static data it contains since the same tables are already in MCInstrInfo. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153860 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-01Fix some 80-col. violations I introduced with the A2 PPC64 core.Hal Finkel
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153852 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-01Enable prefetch generation on PPC64.Hal Finkel
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153851 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-01Add LdStSTD* itin. for the PPC64 A2 core.Hal Finkel
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153850 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-01This commit contains a few changes that had to go in together.Nadav Rotem
1. Simplify xor/and/or (bitcast(A), bitcast(B)) -> bitcast(op (A,B)) (and also scalar_to_vector). 2. Xor/and/or are indifferent to the swizzle operation (shuffle of one src). Simplify xor/and/or (shuff(A), shuff(B)) -> shuff(op (A, B)) 3. Optimize swizzles of shuffles: shuff(shuff(x, y), undef) -> shuff(x, y). 4. Fix an X86ISelLowering optimization which was very bitcast-sensitive. Code which was previously compiled to this: movd (%rsi), %xmm0 movdqa .LCPI0_0(%rip), %xmm2 pshufb %xmm2, %xmm0 movd (%rdi), %xmm1 pshufb %xmm2, %xmm1 pxor %xmm0, %xmm1 pshufb .LCPI0_1(%rip), %xmm1 movd %xmm1, (%rdi) ret Now compiles to this: movl (%rsi), %eax xorl %eax, (%rdi) ret git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153848 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-01Set the default PPC node scheduling preference to ILP (for the embedded cores).Hal Finkel
The 440 and A2 cores have detailed itineraries, and this allows them to be fully used to maximize throughput. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153845 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-01Add ppc440 itin. entries for LdStSTD*Hal Finkel
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153844 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-01Use full anti-dep. breaking with post-ra sched. on the embedded ppc cores.Hal Finkel
Post-RA scheduling gives a significant performance improvement on the embedded cores, so turn it on. Using full anti-dep. breaking is important for FP-intensive blocks, so turn it on (just on the embedded cores for now; this should also be good on the 970s because post-ra scheduling is all that we have for now, but that should have more testing first). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153843 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-01Add instruction itinerary for the PPC64 A2 core.Hal Finkel
This adds a full itinerary for IBM's PPC64 A2 embedded core. These cores form the basis for the CPUs in the new IBM BG/Q supercomputer. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153842 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-01Split the LdStGeneral PPC itin. class into LdStLoad and LdStStore.Hal Finkel
Loads and stores can have different pipeline behavior, especially on embedded chips. This change allows those differences to be expressed. Except for the 440 scheduler, there are no functionality changes. On the 440, the latency adjustment is only by one cycle, and so this probably does not affect much. Nevertheless, it will make a larger difference in the future and this removes a FIXME from the 440 itin. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153821 91177308-0d34-0410-b5e6-96231b3b80d8
2012-03-31Fix dynamic linking on PPC64.Hal Finkel
Dynamic linking on PPC64 has had problems since we had to move the top-down hazard-detection logic post-ra. For dynamic linking to work there needs to be a nop placed after every call. It turns out that it is really hard to guarantee that nothing will be placed in between the call (bl) and the nop during post-ra scheduling. Previous attempts at fixing this by placing logic inside the hazard detector only partially worked. This is now fixed in a different way: call+nop codegen-only instructions. As far as CodeGen is concerned the pair is now a single instruction and cannot be split. This solution works much better than previous attempts. The scoreboard hazard detector is also renamed to be more generic, there is currently no cpu-specific logic in it. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153816 91177308-0d34-0410-b5e6-96231b3b80d8
2012-03-31Select static relocation model if it is jitting.Akira Hatanaka
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153795 91177308-0d34-0410-b5e6-96231b3b80d8
2012-03-31Add a 2 byte safety margin in offset computations.Jakob Stoklund Olesen
ARMConstantIslandPass still has bugs where jump table compression can cause constant pool entries to go out of range. Add a safety margin of 2 bytes when placing constant islands, but use the real max displacement for verification. <rdar://problem/11156595> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153789 91177308-0d34-0410-b5e6-96231b3b80d8
2012-03-31Add more debugging output to ARMConstantIslandPass.Jakob Stoklund Olesen
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153788 91177308-0d34-0410-b5e6-96231b3b80d8
2012-03-30Rip out emission of the regIsInRegClass function for the asm printer.Benjamin Kramer
It's slow, bloated and completely redundant with MCRegisterClass::contains. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153782 91177308-0d34-0410-b5e6-96231b3b80d8
2012-03-30ARM fix encoding fixup resolution for ldrd and friends.Jim Grosbach
The 8-bit payload is not contiguous in the opcode. Move the upper nibble over 4 bits into the correct place. rdar://11158641 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153780 91177308-0d34-0410-b5e6-96231b3b80d8
2012-03-30ARM assembler should prefer non-aliases encoding of cmp.Jim Grosbach
When an immediate is both a value [t2_]so_imm and a [t2_]so_imm_neg, we want to use the non-negated form to make sure we prefer the normal encoding, not the aliased encoding via the negation of, e.g., 'cmp.w'. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153770 91177308-0d34-0410-b5e6-96231b3b80d8
2012-03-30ARM encoding for VSWP got the second operand incorrect.Jim Grosbach
Make the non-tied register operand names line up with what the base class encoding handler expects. rdar://11157236 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153766 91177308-0d34-0410-b5e6-96231b3b80d8
2012-03-30ARM can only use narrow encoding for low regs.Jim Grosbach
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153765 91177308-0d34-0410-b5e6-96231b3b80d8
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2026-11-15 06:56:31 +0000