aboutsummaryrefslogtreecommitdiffstats
path: root/test/CodeGen/ARM
Commit message (Collapse)AuthorAgeFilesLines
* Add test for ARM FastISel load/store register classesJF Bastien2013-06-101-0/+70
| | | | | | r183624 fixed an issue that was tested indirectly. Test it directly with this new test. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@183634 91177308-0d34-0410-b5e6-96231b3b80d8
* Refine the ARM EHABI test cases.Logan Chien2013-06-099-413/+323
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Since we have ARM unwind directive parser and assembler, we can check the correctness in two stages: 1. From LLVM assembly (.ll) to ARM assembly (.s) 2. From ARM assembly (.s) to ELF object file (.o) We already have several "*.s to *.o" test cases. This CL adds some "*.ll to *.s" test cases and removes the redundant "*.ll to *.o" test cases. New test cases to check "*.ll to *.s" code generator: - ehabi.ll: Check the correctness of the generated unwind directives. - section-name.ll: Check the section name of functions. Removed test cases: - ehabi-mc-cantunwind.ll (Covered by ehabi-cantunwind.ll, and eh-directive-cantunwind.s) - ehabi-mc-compact-pr0.ll (Covered by ehabi.ll, eh-compact-pr0.s, eh-directive-save.s, and eh-directive-setfp.s) - ehabi-mc-compact-pr1.ll (Covered by ehabi.ll, eh-compact-pr1.s, eh-directive-save.s, and eh-directive-setfp.s) - ehabi-mc.ll (Covered by ehabi.ll, and eh-directive-integrated-test.s) - ehabi-mc-section-group.ll (Covered by section-name.ll, and eh-directive-section-comdat.s) - ehabi-mc-section.ll (Covered by section-name.ll, and eh-directive-section.s) - ehabi-mc-sh_link.ll (Covered by eh-directive-text-section.s, and eh-directive-section.s) git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@183628 91177308-0d34-0410-b5e6-96231b3b80d8
* Fix ARM unwind opcode assembler in several cases.Logan Chien2013-06-092-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Changes to ARM unwind opcode assembler: * Fix multiple .save or .vsave directives. Besides, the order is preserved now. * For the directives which will generate multiple opcodes, such as ".save {r0-r11}", the order of the unwind opcode is fixed now, i.e. the registers with less encoding value are popped first. * Fix the $sp offset calculation. Now, we can use the .setfp, .pad, .save, and .vsave directives at any order. Changes to test cases: * Add test cases to check the order of multiple opcodes for the .save directive. * Fix the incorrect $sp offset in the test case. The stack pointer offset specified in the test case was incorrect. (Changed test cases: ehabi-mc-section.ll and ehabi-mc.ll) * The opcode to restore $sp are slightly reordered. The behavior are not changed, and the new output is same as the output of GNU as. (Changed test cases: eh-directive-pad.s and eh-directive-setfp.s) git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@183627 91177308-0d34-0410-b5e6-96231b3b80d8
* Reapply r183552. This time, use a standard type for the option to avoid templateQuentin Colombet2013-06-081-0/+24
| | | | | | | | | | | | | | | | instantiation issue with non-standard type. Add a backend option to warn on a given stack size limit. Option: -mllvm -warn-stack-size=<limit> Output (if limit is exceeded): warning: Stack size limit exceeded (<actual size>) in <functionName>. The longer term plan is to hook that to a clang warning. PR:4072 <rdar://problem/13987214>. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@183595 91177308-0d34-0410-b5e6-96231b3b80d8
* Revert commits related to stack warning.Quentin Colombet2013-06-071-24/+0
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@183579 91177308-0d34-0410-b5e6-96231b3b80d8
* Explicit triple in warn stack size test cases to not depend on OS.Quentin Colombet2013-06-071-2/+2
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@183574 91177308-0d34-0410-b5e6-96231b3b80d8
* Add a backend option to warn on a given stack size limit.Quentin Colombet2013-06-071-0/+24
| | | | | | | | | | | | | Option: -mllvm -warn-stack-size=<limit> Output (if limit is exceeded): warning: Stack size limit exceeded (<actual size>) in <functionName>. The longer term plan is to hook that to a clang warning. PR:4072 <rdar://problem/13987214> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@183552 91177308-0d34-0410-b5e6-96231b3b80d8
* ARM FastISel integer sext/zext improvementsJF Bastien2013-06-079-29/+188
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | My recent ARM FastISel patch exposed this bug: http://llvm.org/bugs/show_bug.cgi?id=16178 The root cause is that it can't select integer sext/zext pre-ARMv6 and asserts out. The current integer sext/zext code doesn't handle other cases gracefully either, so this patch makes it handle all sext and zext from i1/i8/i16 to i8/i16/i32, with and without ARMv6, both in Thumb and ARM mode. This should fix the bug as well as make FastISel faster because it bails to SelectionDAG less often. See fastisel-ext.patch for this. fastisel-ext-tests.patch changes current tests to always use reg-imm AND for 8-bit zext instead of UXTB. This simplifies code since it is supported on ARMv4t and later, and at least on A15 both should perform exactly the same (both have exec 1 uop 1, type I). 2013-05-31-char-shift-crash.ll is a bitcode version of the above bug 16178 repro. fast-isel-ext.ll tests all sext/zext combinations that ARM FastISel should now handle. Note that my ARM FastISel enabling patch was reverted due to a separate failure when dealing with MCJIT, I'll fix this second failure and then turn FastISel on again for non-iOS ARM targets. I've tested "make check-all" on my x86 box, and "lnt test-suite" on A15 hardware. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@183551 91177308-0d34-0410-b5e6-96231b3b80d8
* Teach AsmPrinter how to print odd constants.Quentin Colombet2013-06-071-0/+18
| | | | | | | | | | | | Fix an assertion when the compiler encounters big constants whose bit width is not a multiple of 64-bits. Although clang would never generate something like this, the backend should be able to handle any legal IR. <rdar://problem/13363576> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@183544 91177308-0d34-0410-b5e6-96231b3b80d8
* Cortex-R5 can issue Thumb2 integer division instructions.Evan Cheng2013-06-041-11/+12
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@183275 91177308-0d34-0410-b5e6-96231b3b80d8
* ARM: Fix crash in ARM backend inside of ARMConstantIslandPassDavid Majnemer2013-06-041-0/+14
| | | | | | | | | | | The ARM backend did not expect LDRBi12 to hold a constant pool operand. Allow for LLVM to deal with the instruction similar to how it deals with LDRi12. This fixes PR16215. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@183238 91177308-0d34-0410-b5e6-96231b3b80d8
* Revert r182937 and r182877.Rafael Espindola2013-05-3024-82/+12
| | | | | | | | | r182877 broke MCJIT tests on ARM and r182937 was working around another failure by r182877. This should make the ARM bots green. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@182960 91177308-0d34-0410-b5e6-96231b3b80d8
* Change how we iterate over relocations on ELF.Rafael Espindola2013-05-303-7/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | For COFF and MachO, sections semantically have relocations that apply to them. That is not the case on ELF. In relocatable objects (.o), a section with relocations in ELF has offsets to another section where the relocations should be applied. In dynamic objects and executables, relocations don't have an offset, they have a virtual address. The section sh_info may or may not point to another section, but that is not actually used for resolving the relocations. This patch exposes that in the ObjectFile API. It has the following advantages: * Most (all?) clients can handle this more efficiently. They will normally walk all relocations, so doing an effort to iterate in a particular order doesn't save time. * llvm-readobj now prints relocations in the same way the native readelf does. * probably most important, relocations that don't point to any section are now visible. This is the case of relocations in the rela.dyn section. See the updated relocation-executable.test for example. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@182908 91177308-0d34-0410-b5e6-96231b3b80d8
* Order CALLSEQ_START and CALLSEQ_END nodes.Andrew Trick2013-05-291-10/+9
| | | | | | | | | | | | Fixes PR16146: gdb.base__call-ar-st.exp fails after pre-RA-sched=source fixes. Patch by Xiaoyi Guo! This also fixes an unsupported dbg.value test case. Codegen was previously incorrect but the test was passing by luck. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@182885 91177308-0d34-0410-b5e6-96231b3b80d8
* Enable FastISel on ARM for Linux and NaClJF Bastien2013-05-2924-12/+82
| | | | | | | | | | | | | | | | | | | | | | | | | | | | FastISel was only enabled for iOS ARM and Thumb2, this patch enables it for ARM (not Thumb2) on Linux and NaCl. Thumb2 support needs a bit more work, mainly around register class restrictions. The patch punts to SelectionDAG when doing TLS relocation on non-Darwin targets. I will fix this and other FastISel-to-SelectionDAG failures in a separate patch. The patch also forces FastISel to retain frame pointers: iOS always keeps them for backtracking (so emitted code won't change because of this), but Linux was getting much worse code that was incorrect when using big frames (such as test-suite's lencod). I'll also fix this in a later patch, it will probably require a peephole so that FastISel doesn't rematerialize frame pointers back-to-back. The test changes are straightforward, similar to: http://lists.cs.uiuc.edu/pipermail/llvm-commits/Week-of-Mon-20130513/174279.html They also add a vararg test that got dropped in that change. I ran all of test-suite on A15 hardware with --optimize-option=-O0 and all the tests pass. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@182877 91177308-0d34-0410-b5e6-96231b3b80d8
* Track IR ordering of SelectionDAG nodes 4/4.Andrew Trick2013-05-251-0/+21
| | | | | | Unit test cases for -pre-RA-sched=source. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@182706 91177308-0d34-0410-b5e6-96231b3b80d8
* Track IR ordering of SelectionDAG nodes 3/4.Andrew Trick2013-05-252-5/+5
| | | | | | | Remove the old IR ordering mechanism and switch to new one. Fix unit test failures. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@182704 91177308-0d34-0410-b5e6-96231b3b80d8
* ARM: implement @llvm.readcyclecounter intrinsicTim Northover2013-05-231-0/+24
| | | | | | | | | | | | | This implements the @llvm.readcyclecounter intrinsic as the specific MRC instruction specified in the ARM manuals for CPUs with the Power Management extensions. Older CPUs had slightly different methods which may also have to be implemented eventually, but this should cover all v7 cases. rdar://problem/13939186 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@182603 91177308-0d34-0410-b5e6-96231b3b80d8
* Fix PR16110: Handle DBG_VALUE in ConnectedVNInfoEqClasses::Distribute().Jakob Stoklund Olesen2013-05-231-0/+113
| | | | | | | | | | | | Now that the LiveDebugVariables pass is running *after* register coalescing, the ConnectedVNInfoEqClasses class needs to deal with DBG_VALUE instructions. This only comes up when rematerialization during coalescing causes the remaining live range of a virtual register to separate into two connected components. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@182592 91177308-0d34-0410-b5e6-96231b3b80d8
* PR15868 fix.Stepan Dyatkovskiy2013-05-203-8/+64
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Introduction: In case when stack alignment is 8 and GPRs parameter part size is not N*8: we add padding to GPRs part, so part's last byte must be recovered at address K*8-1. We need to do it, since remained (stack) part of parameter starts from address K*8, and we need to "attach" "GPRs head" without gaps to it: Stack: |---- 8 bytes block ----| |---- 8 bytes block ----| |---- 8 bytes... [ [padding] [GPRs head] ] [ ------ Tail passed via stack ------ ... FIX: Note, once we added padding we need to correct *all* Arg offsets that are going after padded one. That's why we need this fix: Arg offsets were never corrected before this patch. See new test-cases included in patch. We also don't need to insert padding for byval parameters that are stored in GPRs only. We need pad only last byval parameter and only in case it outsides GPRs and stack alignment = 8. Though, stack area, allocated for recovered byval params, must satisfy "Size mod 8 = 0" restriction. This patch reduces stack usage for some cases: We can reduce ArgRegsSaveArea since inner N*4 bytes sized byval params my be "packed" with alignment 4 in some cases. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@182237 91177308-0d34-0410-b5e6-96231b3b80d8
* Support unaligned load/store on more ARM targetsJF Bastien2013-05-172-130/+147
| | | | | | | | | | | | | | | | | | | | | This patch matches GCC behavior: the code used to only allow unaligned load/store on ARM for v6+ Darwin, it will now allow unaligned load/store for v6+ Darwin as well as for v7+ on Linux and NaCl. The distinction is made because v6 doesn't guarantee support (but LLVM assumes that Apple controls hardware+kernel and therefore have conformant v6 CPUs), whereas v7 does provide this guarantee (and Linux/NaCl behave sanely). The patch keeps the -arm-strict-align command line option, and adds -arm-no-strict-align. They behave similarly to GCC's -mstrict-align and -mnostrict-align. I originally encountered this discrepancy in FastIsel tests which expect unaligned load/store generation. Overall this should slightly improve performance in most cases because of reduced I$ pressure. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@182175 91177308-0d34-0410-b5e6-96231b3b80d8
* ARM ISel: Don't create illegal types during LowerMULArnold Schwaighofer2013-05-141-0/+24
| | | | | | | | | | | | | | | | | The transformation happening here is that we want to turn a "mul(ext(X), ext(X))" into a "vmull(X, X)", stripping off the extension. We have to make sure that X still has a valid vector type - possibly recreate an extension to a smaller type. In case of a extload of a memory type smaller than 64 bit we used create a ext(load()). The problem with doing this - instead of recreating an extload - is that an illegal type is exposed. This patch fixes this by creating extloads instead of ext(load()) sequences. Fixes PR15970. radar://13871383 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@181842 91177308-0d34-0410-b5e6-96231b3b80d8
* Fix ARM FastISel tests, as a first step to enabling ARM FastISelDerek Schuff2013-05-1416-161/+134
| | | | | | | | | | | | | | | | | | | | | ARM FastISel is currently only enabled for iOS non-Thumb1, and I'm working on enabling it for other targets. As a first step I've fixed some of the tests. Changes to ARM FastISel tests: - Different triples don't generate the same relocations (especially movw/movt versus constant pool loads). Use a regex to allow either. - Mangling is different. Use a regex to allow either. - The reserved registers are sometimes different, so registers get allocated in a different order. Capture the names only where this occurs. - Add -verify-machineinstrs to some tests where it works. It doesn't work everywhere it should yet. - Add -fast-isel-abort to many tests that didn't have it before. - Split out the VarArg test from fast-isel-call.ll into its own test. This simplifies test setup because of --check-prefix. Patch by JF Bastien git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@181801 91177308-0d34-0410-b5e6-96231b3b80d8
* Correctly preserve the input chain for potential tailcall nodes whoseLang Hames2013-05-131-0/+17
| | | | | | | | | | | | | return values are bitcasts. The chain had previously been being clobbered with the entry node to the dag, which sometimes caused other code in the function to be erroneously deleted when tailcall optimization kicked in. <rdar://problem/13827621> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@181696 91177308-0d34-0410-b5e6-96231b3b80d8
* Fix PR15950 A bug in DAG Combiner about undef maskHao Liu2013-05-131-0/+10
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@181682 91177308-0d34-0410-b5e6-96231b3b80d8
* Test case for r181160 and r181161. rdar://13782395Evan Cheng2013-05-051-0/+71
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@181162 91177308-0d34-0410-b5e6-96231b3b80d8
* For ARM backend, fixed "byval" attribute support.Stepan Dyatkovskiy2013-05-053-0/+166
| | | | | | | | | | | | | | | | | | | | | | | | | Now even the small structures could be passed within byval (small enough to be stored in GPRs). In regression tests next function prototypes are checked: PR15293: %artz = type { i32 } define void @foo(%artz* byval %s) define void @foo2(%artz* byval %s, i32 %p, %artz* byval %s2) foo: "s" stored in R0 foo2: "s" stored in R0, "s2" stored in R2. Next AAPCS rules are checked: 5.5 Parameters Passing, C.4 and C.5, "ParamSize" is parameter size in 32bit words: -- NSAA != 0, NCRN < R4 and NCRN+ParamSize > R4. Parameter should be sent to the stack; NCRN := R4. -- NSAA != 0, and NCRN < R4, NCRN+ParamSize < R4. Parameter stored in GPRs; NCRN += ParamSize. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@181148 91177308-0d34-0410-b5e6-96231b3b80d8
* Optimize away nop CONCAT_VECTOR nodes.Nadav Rotem2013-05-011-0/+13
| | | | | | | | | | | Optimize CONCAT_VECTOR nodes that merge EXTRACT_SUBVECTOR values that extract from the same vector. rdar://13402653 PR15866 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180871 91177308-0d34-0410-b5e6-96231b3b80d8
* Only pass 'returned' to target-specific lowering code when the value of ↵Stephen Lin2013-04-302-64/+178
| | | | | | entire register is guaranteed to be preserved. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180825 91177308-0d34-0410-b5e6-96231b3b80d8
* Temporarily revert "Change the informal convention of DBG_VALUE so that we ↵Adrian Prantl2013-04-301-2/+2
| | | | | | | | | | can express a" because it breaks some buildbots. This reverts commit 180816. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180819 91177308-0d34-0410-b5e6-96231b3b80d8
* Change the informal convention of DBG_VALUE so that we can express aAdrian Prantl2013-04-301-2/+2
| | | | | | | | | | | | register-indirect address with an offset of 0. It used to be that a DBG_VALUE is a register-indirect value if the offset (operand 1) is nonzero. The new convention is that a DBG_VALUE is register-indirect if the first operand is a register and the second operand is an immediate. For plain registers use the combination reg, reg. rdar://problem/13658587 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180816 91177308-0d34-0410-b5e6-96231b3b80d8
* TBAA: remove !tbaa from testing cases if not used.Manman Ren2013-04-304-36/+19
| | | | | | | | This will make it easier to turn on struct-path aware TBAA since the metadata format will change. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180796 91177308-0d34-0410-b5e6-96231b3b80d8
* TBAA: remove !tbaa from testing cases if not used.Manman Ren2013-04-2911-69/+32
| | | | | | | | This will make it easier to turn on struct-path aware TBAA since the metadata format will change. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180745 91177308-0d34-0410-b5e6-96231b3b80d8
* ARM/NEON: Pattern match vector integer abs to vabs.Benjamin Kramer2013-04-261-0/+91
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180604 91177308-0d34-0410-b5e6-96231b3b80d8
* Fix constant folding for one lane vector types. Constant folding one lane ↵Silviu Baranga2013-04-251-0/+18
| | | | | | vector types not returns a vector instead of a scalar. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180254 91177308-0d34-0410-b5e6-96231b3b80d8
* MI Sched: eliminate local vreg copies.Andrew Trick2013-04-241-0/+30
| | | | | | | | | | | | | | | | For now, we just reschedule instructions that use the copied vregs and let regalloc elliminate it. I would really like to eliminate the copies on-the-fly during scheduling, but we need a complete implementation of repairIntervalsInRange() first. The general strategy is for the register coalescer to eliminate as many global copies as possible and shrink live ranges to be extended-basic-block local. The coalescer should not have to worry about resolving local copies (e.g. it shouldn't attemp to reorder instructions). The scheduler is a much better place to deal with local interference. The coalescer side of this equation needs work. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180193 91177308-0d34-0410-b5e6-96231b3b80d8
* Add more tests for r179925 to verify correct handling of signext/zeroext; ↵Stephen Lin2013-04-231-0/+64
| | | | | | strengthen condition check to require actual MVT::i32 virtual register types, just in case (no actual functionality change) git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180138 91177308-0d34-0410-b5e6-96231b3b80d8
* Extra paranoid test for r179925 (verify that tail calls are not generated to ↵Stephen Lin2013-04-221-0/+14
| | | | | | 'this'-returning constructors of objects with different 'this' pointers than the caller) git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180032 91177308-0d34-0410-b5e6-96231b3b80d8
* Fix for 5.5 Parameter Passing --> Stage C:Stepan Dyatkovskiy2013-04-223-0/+184
| | | | | | | | | | | | | | | | | -- C.4 and C.5 statements, when NSAA is not equal to SP. -- C.1.cp statement for VA functions. Note: There are no VFP CPRCs in a variadic procedure. Before this patch "NSAA != 0" means "don't use GPRs anymore ". But there are some exceptions in AAPCS. 1. For non VA function: allocate all VFP regs for CPRC. When all VFPs are allocated CPRCs would be sent to stack, while non CPRCs may be still allocated in GRPs. 2. Check that for VA functions all params uses GPRs and then stack. No exceptions, no CPRCs here. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180011 91177308-0d34-0410-b5e6-96231b3b80d8
* Cleanup: test source files do not need to be executableArnaud A. de Grandmaison2013-04-221-0/+0
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180003 91177308-0d34-0410-b5e6-96231b3b80d8
* Revert "Revert "PR14606: debug info imported_module support""David Blaikie2013-04-229-9/+9
| | | | | | | | | | This reverts commit r179840 with a fix to test/DebugInfo/two-cus-from-same-file.ll I'm not sure why that test only failed on ARM & MIPS and not X86 Linux, even though the debug info was clearly invalid on all of them, but this ought to fix it. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179996 91177308-0d34-0410-b5e6-96231b3b80d8
* Legalize vector truncates by parts rather than just splitting.Jim Grosbach2013-04-211-32/+14
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Rather than just splitting the input type and hoping for the best, apply a bit more cleverness. Just splitting the types until the source is legal often leads to an illegal result time, which is then widened and a scalarization step is introduced which leads to truly horrible code generation. With the loop vectorizer, these sorts of operations are much more common, and so it's worth extra effort to do them well. Add a legalization hook for the operands of a TRUNCATE node, which will be encountered after the result type has been legalized, but if the operand type is still illegal. If simple splitting of both types ends up with the result type of each half still being legal, just do that (v16i16 -> v16i8 on ARM, for example). If, however, that would result in an illegal result type (v8i32 -> v8i8 on ARM, for example), we can get more clever with power-two vectors. Specifically, split the input type, but also widen the result element size, then concatenate the halves and truncate again. For example on ARM, To perform a "%res = v8i8 trunc v8i32 %in" we transform to: %inlo = v4i32 extract_subvector %in, 0 %inhi = v4i32 extract_subvector %in, 4 %lo16 = v4i16 trunc v4i32 %inlo %hi16 = v4i16 trunc v4i32 %inhi %in16 = v8i16 concat_vectors v4i16 %lo16, v4i16 %hi16 %res = v8i8 trunc v8i16 %in16 This allows instruction selection to generate three VMOVN instructions instead of a sequences of moves, stores and loads. Update the ARMTargetTransformInfo to take this improved legalization into account. Consider the simplified IR: define <16 x i8> @test1(<16 x i32>* %ap) { %a = load <16 x i32>* %ap %tmp = trunc <16 x i32> %a to <16 x i8> ret <16 x i8> %tmp } define <8 x i8> @test2(<8 x i32>* %ap) { %a = load <8 x i32>* %ap %tmp = trunc <8 x i32> %a to <8 x i8> ret <8 x i8> %tmp } Previously, we would generate the truly hideous: .syntax unified .section __TEXT,__text,regular,pure_instructions .globl _test1 .align 2 _test1: @ @test1 @ BB#0: push {r7} mov r7, sp sub sp, sp, #20 bic sp, sp, #7 add r1, r0, #48 add r2, r0, #32 vld1.64 {d24, d25}, [r0:128] vld1.64 {d16, d17}, [r1:128] vld1.64 {d18, d19}, [r2:128] add r1, r0, #16 vmovn.i32 d22, q8 vld1.64 {d16, d17}, [r1:128] vmovn.i32 d20, q9 vmovn.i32 d18, q12 vmov.u16 r0, d22[3] strb r0, [sp, #15] vmov.u16 r0, d22[2] strb r0, [sp, #14] vmov.u16 r0, d22[1] strb r0, [sp, #13] vmov.u16 r0, d22[0] vmovn.i32 d16, q8 strb r0, [sp, #12] vmov.u16 r0, d20[3] strb r0, [sp, #11] vmov.u16 r0, d20[2] strb r0, [sp, #10] vmov.u16 r0, d20[1] strb r0, [sp, #9] vmov.u16 r0, d20[0] strb r0, [sp, #8] vmov.u16 r0, d18[3] strb r0, [sp, #3] vmov.u16 r0, d18[2] strb r0, [sp, #2] vmov.u16 r0, d18[1] strb r0, [sp, #1] vmov.u16 r0, d18[0] strb r0, [sp] vmov.u16 r0, d16[3] strb r0, [sp, #7] vmov.u16 r0, d16[2] strb r0, [sp, #6] vmov.u16 r0, d16[1] strb r0, [sp, #5] vmov.u16 r0, d16[0] strb r0, [sp, #4] vldmia sp, {d16, d17} vmov r0, r1, d16 vmov r2, r3, d17 mov sp, r7 pop {r7} bx lr .globl _test2 .align 2 _test2: @ @test2 @ BB#0: push {r7} mov r7, sp sub sp, sp, #12 bic sp, sp, #7 vld1.64 {d16, d17}, [r0:128] add r0, r0, #16 vld1.64 {d20, d21}, [r0:128] vmovn.i32 d18, q8 vmov.u16 r0, d18[3] vmovn.i32 d16, q10 strb r0, [sp, #3] vmov.u16 r0, d18[2] strb r0, [sp, #2] vmov.u16 r0, d18[1] strb r0, [sp, #1] vmov.u16 r0, d18[0] strb r0, [sp] vmov.u16 r0, d16[3] strb r0, [sp, #7] vmov.u16 r0, d16[2] strb r0, [sp, #6] vmov.u16 r0, d16[1] strb r0, [sp, #5] vmov.u16 r0, d16[0] strb r0, [sp, #4] ldm sp, {r0, r1} mov sp, r7 pop {r7} bx lr Now, however, we generate the much more straightforward: .syntax unified .section __TEXT,__text,regular,pure_instructions .globl _test1 .align 2 _test1: @ @test1 @ BB#0: add r1, r0, #48 add r2, r0, #32 vld1.64 {d20, d21}, [r0:128] vld1.64 {d16, d17}, [r1:128] add r1, r0, #16 vld1.64 {d18, d19}, [r2:128] vld1.64 {d22, d23}, [r1:128] vmovn.i32 d17, q8 vmovn.i32 d16, q9 vmovn.i32 d18, q10 vmovn.i32 d19, q11 vmovn.i16 d17, q8 vmovn.i16 d16, q9 vmov r0, r1, d16 vmov r2, r3, d17 bx lr .globl _test2 .align 2 _test2: @ @test2 @ BB#0: vld1.64 {d16, d17}, [r0:128] add r0, r0, #16 vld1.64 {d18, d19}, [r0:128] vmovn.i32 d16, q8 vmovn.i32 d17, q9 vmovn.i16 d16, q8 vmov r0, r1, d16 bx lr git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179989 91177308-0d34-0410-b5e6-96231b3b80d8
* ARM: Split out cost model vcvt testcases.Jim Grosbach2013-04-212-172/+171
| | | | | | They had a separate RUN line already, so may as well be in a separate file. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179988 91177308-0d34-0410-b5e6-96231b3b80d8
* ARM: fix part of test which actually needed an asserts buildTim Northover2013-04-212-6/+30
| | | | | | This should fix a buildbot failure that occurred after r179977. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179978 91177308-0d34-0410-b5e6-96231b3b80d8
* ARM: Use ldrd/strd to spill 64-bit pairs when available.Tim Northover2013-04-211-13/+27
| | | | | | | This allows common sp-offsets to be part of the instruction and is probably faster on modern CPUs too. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179977 91177308-0d34-0410-b5e6-96231b3b80d8
* ARM: don't add FrameIndex offset for LDMIA (has no immediate)Tim Northover2013-04-201-0/+36
| | | | | | | | | | | | Previously, when spilling 64-bit paired registers, an LDMIA with both a FrameIndex and an offset was produced. This kind of instruction shouldn't exist, and the extra operand was being confused with the predicate, causing aborts later on. This removes the invalid 0-offset from the instruction being produced. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179956 91177308-0d34-0410-b5e6-96231b3b80d8
* Add CodeGen support for functions that always return arguments via a new ↵Stephen Lin2013-04-201-0/+91
| | | | | | parameter attribute 'returned', which is taken advantage of in target-independent tail call opportunity detection and in ARM call lowering (when placed on an integral first parameter). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179925 91177308-0d34-0410-b5e6-96231b3b80d8
* Revert "PR14606: debug info imported_module support"Eric Christopher2013-04-199-9/+9
| | | | | | This reverts commit r179836 as it seems to have caused test failures. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179840 91177308-0d34-0410-b5e6-96231b3b80d8
* PR14606: debug info imported_module supportDavid Blaikie2013-04-199-9/+9
| | | | | | | | | | Adding another CU-wide list, in this case of imported_modules (since they should be relatively rare, it seemed better to add a list where each element had a "context" value, rather than add a (usually empty) list to every scope). This takes care of DW_TAG_imported_module, but to fully address PR14606 we'll need to expand this to cover DW_TAG_imported_declaration too. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179836 91177308-0d34-0410-b5e6-96231b3b80d8
* Fix for PR14824, An ARM Load/Store Optimization bugHao Liu2013-04-181-0/+82
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179751 91177308-0d34-0410-b5e6-96231b3b80d8
generated by cgit v1.1 at 2025-02-09 12:11:34 +0000