Commit Graph

90 Commits

Author SHA1 Message Date
Jakob Stoklund Olesen
b203ef3938 Annotate X86InstrCompiler.td with SchedRW lists.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@177936 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-25 23:07:35 +00:00
Jakob Stoklund Olesen
f36a4afaae Annotate X86InstrCompiler.td with SchedRW lists.
Add a new WriteZero SchedWrite type for the common dependency-breaking
instructions that clear a register.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@177442 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-19 21:16:56 +00:00
Ulrich Weigand
58ebc04078 Remove an invalid and unnecessary Pat pattern from the X86 backend:
def : Pat<(load (i64 (X86Wrapper tglobaltlsaddr :$dst))),
            (MOV64rm tglobaltlsaddr :$dst)>;

This pattern is invalid because the MOV64rm instruction expects a
source operand of type "i64mem", which is a subclass of X86MemOperand
and thus actually consists of five MI operands, but the Pat provides
only a single MI operand ("tglobaltlsaddr" matches an SDnode of
type ISD::TargetGlobalTLSAddress and provides a single output).

Thus, if the pattern were ever matched, subsequent uses of the MOV64rm
instruction pattern would access uninitialized memory.  In addition,
with the TableGen patch I'm about to check in, this would actually be
reported as a build-time error.

Fortunately, the pattern does in fact never match, for at least two
independent reasons.

First, the code generator actually never generates a pattern of the
form (load (X86Wrapper (tglobaltlsaddr))).  For most combinations of
TLS and code models, (tglobaltlsaddr) represents just an offset that
needs to be added to some base register, so it is never directly
dereferenced.  The only exception is the initial-exec model, where
(tglobaltlsaddr) refers to the (pc-relative) address of a GOT slot,
which *is* in fact directly dereferenced: but in that case, the
X86WrapperRIP node is used, not X86Wrapper, so the Pat doesn't match.

Second, even if some patterns along those lines *were* ever generated,
we should not need an extra Pat pattern to match it.  Instead, the
original MOV64rm instruction pattern ought to match directly, since
it uses an "addr" operand, which is implemented via the SelectAddr
C++ routine; this routine is supposed to accept the full range of
input DAGs that may be implemented by a single mov instruction,
including those cases involving ISD::TargetGlobalTLSAddress (and
actually does so e.g. in the initial-exec case as above).

To avoid build breaks (due to the above-mentioned error) after the
TableGen patch is checked in, I'm removing this Pat here.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@177426 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-19 19:49:52 +00:00
Benjamin Kramer
36bd16ef0b X86: Disable cmov-memory patterns on subtargets without cmov.
Fixes PR15115.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175962 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-23 10:40:58 +00:00
Michael Liao
13d08bf415 Fix an issue of pseudo atomic instruction DAG schedule
- Add list of physical registers clobbered in pseudo atomic insts
  Physical registers are clobbered when pseudo atomic instructions are
  expanded. Add them in clobber list to prevent DAG scheduler to
  mis-schedule them after these insns are declared side-effect free.
- Add test case from Michael Kuperstein <michael.m.kuperstein@intel.com>



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@173200 91177308-0d34-0410-b5e6-96231b3b80d8
2013-01-22 21:47:38 +00:00
Craig Topper
c12979aa1c Remove # from the beginning and end of def names.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@171696 91177308-0d34-0410-b5e6-96231b3b80d8
2013-01-07 05:26:58 +00:00
Craig Topper
ee5b63cb52 Add hasSideEffects=0 to some atomic instructions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@171122 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-26 23:08:12 +00:00
Michael Liao
6c0e04c823 Add __builtin_setjmp/_longjmp supprt in X86 backend
- Besides used in SjLj exception handling, __builtin_setjmp/__longjmp is also
  used as a light-weight replacement of setjmp/longjmp which are used to
  implementation continuation, user-level threading, and etc. The support added
  in this patch ONLY addresses this usage and is NOT intended to support SjLj
  exception handling as zero-cost DWARF exception handling is used by default
  in X86.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165989 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-15 22:39:43 +00:00
Benjamin Kramer
dcf2420b07 X86: fcmov doesn't handle all possible EFLAGS, fall back to a branch for the others.
Otherwise it will try to use SSE patterns and fail horribly if sse is disabled.
Fixes PR14035.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165377 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-07 15:34:27 +00:00
Craig Topper
7a922307db Remove some encoding bits I forgot to remove from SETB_C16r and SETB_C64r in r165302.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165303 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-05 06:11:52 +00:00
Craig Topper
ff9d51b994 Move expansion of SETB_C(8/16/32/64)r from MCInstLower to ExpandPostRAPseudos and mark them as pseudos in the td file.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165302 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-05 06:05:15 +00:00
Michael Liao
4e9485d732 Add 'lock' prefix output support in assembly printer
- Instead of embedding 'lock' into each mnemonic of atomic
  instructions except 'xchg', we teach X86 assembly printer to output 'lock'
  prefix similar to or consistent with code emitter.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164659 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-26 05:13:44 +00:00
Michael Liao
23bd47c2d6 Fix 16-bit atomic inst encoding and keep pseudo-inst starting with '#'
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164453 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-22 05:41:15 +00:00
Michael Liao
730b9dd2ce Fix typo in r164357
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164452 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-22 03:39:42 +00:00
Michael Liao
ba4388656c Fix a typo in r164357
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164372 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-21 16:03:03 +00:00
Michael Liao
0838249a6a Revise td of X86 atomic instructions
- Rewirte most atomic instructions in templates for both better
  maintenance and future extensions, such as HLE in TSX.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164357 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-21 03:00:17 +00:00
Michael Liao
b118a073d7 Re-work X86 code generation of atomic ops with spin-loop
- Rewrite/merge pseudo-atomic instruction emitters to address the
  following issue:
  * Reduce one unnecessary load in spin-loop

    previously the spin-loop looks like

        thisMBB:
        newMBB:
          ld  t1 = [bitinstr.addr]
          op  t2 = t1, [bitinstr.val]
          not t3 = t2  (if Invert)
          mov EAX = t1
          lcs dest = [bitinstr.addr], t3  [EAX is implicit]
          bz  newMBB
          fallthrough -->nextMBB

    the 'ld' at the beginning of newMBB should be lift out of the loop
    as lcs (or CMPXCHG on x86) will load the current memory value into
    EAX. This loop is refined as:

        thisMBB:
          EAX = LOAD [MI.addr]
        mainMBB:
          t1 = OP [MI.val], EAX
          LCMPXCHG [MI.addr], t1, [EAX is implicitly used & defined]
          JNE mainMBB
        sinkMBB:

  * Remove immopc as, so far, all pseudo-atomic instructions has
    all-register form only, there is no immedidate operand.

  * Remove unnecessary attributes/modifiers in pseudo-atomic instruction
    td

  * Fix issues in PR13458

- Add comprehensive tests on atomic ops on various data types.
  NOTE: Some of them are turned off due to missing functionality.

- Revise tests due to the new spin-loop generated.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164281 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-20 03:06:15 +00:00
Jakob Stoklund Olesen
7bba7d0efc Fix the TCRETURNmi64 bug differently.
Add a PatFrag to match X86tcret using 6 fixed registers or less. This
avoids folding loads into TCRETURNmi64 using 7 or more volatile
registers.

<rdar://problem/12282281>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163819 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-13 18:31:27 +00:00
Jakob Stoklund Olesen
0767dc546e Revert r163761 "Don't fold indexed loads into TCRETURNmi64."
The patch caused "Wrong topological sorting" assertions.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163810 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-13 16:52:17 +00:00
Jakob Stoklund Olesen
aa0cfea9a4 Don't fold indexed loads into TCRETURNmi64.
We don't have enough GR64_TC registers when calling a varargs function
with 6 arguments. Since %al holds the number of vector registers used,
only %r11 is available as a scratch register.

This means that addressing modes using both base and index registers
can't be folded into TCRETURNmi64.

<rdar://problem/12282281>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163761 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-13 00:25:00 +00:00
Hans Wennborg
f0234fcbc9 Implement the local-dynamic TLS model for x86 (PR3985)
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
2012-06-01 16:27:21 +00:00
Jakob Stoklund Olesen
cf661a040c Use ptr_rc_tailcall instead of GR32_TC.
The getPointerRegClass() hook will return GR32_TC, or whatever is
appropriate for the current function.

Patch by Yiannis Tsiouris!

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156459 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-09 01:50:09 +00:00
Manman Ren
ed57984483 X86: optimization for -(x != 0)
This patch will optimize -(x != 0) on X86
FROM 
cmpl	$0x01,%edi
sbbl	%eax,%eax
notl	%eax
TO
negl %edi
sbbl %eax %eax

In order to generate negl, I added patterns in Target/X86/X86InstrCompiler.td:
def : Pat<(X86sub_flag 0, GR32:$src), (NEG32r GR32:$src)>;

rdar: 10961709


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156312 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-07 18:06:23 +00:00
Rafael Espindola
26c8dcc692 Always compute all the bits in ComputeMaskedBits.
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
2012-04-04 12:51:34 +00:00
Lang Hames
616c841946 Make x86 REP_MOV* and REP_STO instructions use the correct operand sizes in 64-bit mode.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153680 91177308-0d34-0410-b5e6-96231b3b80d8
2012-03-29 19:54:28 +00:00
Preston Gurd
3e99b715d1 This patch adds X86 instruction itineraries for non-pseudo opcodes in
X86InstrCompiler.td.
 
It also adds –mcpu-generic to the legalize-shift-64.ll test so the test
will pass if run on an Intel Atom CPU, which would otherwise
produce an instruction schedule which differs from that which the test expects.




git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153033 91177308-0d34-0410-b5e6-96231b3b80d8
2012-03-19 14:10:12 +00:00
Michael J. Spencer
1a2d061ec0 Add WIN_FTOL_* psudo-instructions to model the unique calling convention
used by the Win32 _ftol2 runtime function. Patch by Joe Groff!

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@151382 91177308-0d34-0410-b5e6-96231b3b80d8
2012-02-24 19:01:22 +00:00
Jakob Stoklund Olesen
527a08b253 Use the same CALL instructions for Windows as for everything else.
The different calling conventions and call-preserved registers are
represented with regmask operands that are added dynamically.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@150708 91177308-0d34-0410-b5e6-96231b3b80d8
2012-02-16 17:56:02 +00:00
Eli Friedman
1857b51ef5 Make sure the non-SSE lowering for fences correctly clobbers EFLAGS. PR11768.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@148240 91177308-0d34-0410-b5e6-96231b3b80d8
2012-01-16 16:42:21 +00:00
Eli Friedman
a20b71518a Get rid of unused codegen-only instruction.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@148239 91177308-0d34-0410-b5e6-96231b3b80d8
2012-01-16 16:29:35 +00:00
Benjamin Kramer
fb418bab97 X86: Generalize the x << (y & const) optimization to also catch masks with more set bits set than 31 or 63.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@148024 91177308-0d34-0410-b5e6-96231b3b80d8
2012-01-12 12:41:34 +00:00
Chandler Carruth
acc068e873 Switch the lowering of CTLZ_ZERO_UNDEF from a .td pattern back to the
X86ISelLowering C++ code. Because this is lowered via an xor wrapped
around a bsr, we want the dagcombine which runs after isel lowering to
have a chance to clean things up. In particular, it is very common to
see code which looks like:

  (sizeof(x)*8 - 1) ^ __builtin_clz(x)

Which is trying to compute the most significant bit of 'x'. That's
actually the value computed directly by the 'bsr' instruction, but if we
match it too late, we'll get completely redundant xor instructions.

The more naive code for the above (subtracting rather than using an xor)
still isn't handled correctly due to the dagcombine getting confused.

Also, while here fix an issue spotted by inspection: we should have been
expanding the zero-undef variants to the normal variants when there is
an 'lzcnt' instruction. Do so, and test for this. We don't want to
generate unnecessary 'bsr' instructions.

These two changes fix some regressions in encoding and decoding
benchmarks. However, there is still a *lot* to be improve on in this
type of code.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147244 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-24 10:55:54 +00:00
Chandler Carruth
f2d7693fbb Begin teaching the X86 target how to efficiently codegen patterns that
use the zero-undefined variants of CTTZ and CTLZ. These are just simple
patterns for now, there is more to be done to make real world code using
these constructs be optimized and codegen'ed properly on X86.

The existing tests are spiffed up to check that we no longer generate
unnecessary cmov instructions, and that we generate the very important
'xor' to transform bsr which counts the index of the most significant
one bit to the number of leading (most significant) zero bits. Also they
now check that when the variant with defined zero result is used, the
cmov is still produced.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146974 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-20 11:19:37 +00:00
Rafael Espindola
66bf7430f5 Fixes an issue reported by -verify-machineinstrs.
Patch by Sanjoy Das.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@143064 91177308-0d34-0410-b5e6-96231b3b80d8
2011-10-26 21:16:41 +00:00
Rafael Espindola
e840e88239 This commit introduces two fake instructions MORESTACK_RET and
MORESTACK_RET_RESTORE_R10; which are lowered to a RET and a RET
followed by a MOV respectively.  Having a fake instruction prevents
the verifier from seeing a MachineBasicBlock end with a
non-terminator (MOV).  It also prevents the rather eccentric case of a
MachineBasicBlock ending with RET but having successors nevertheless.

Patch by Sanjoy Das.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@143062 91177308-0d34-0410-b5e6-96231b3b80d8
2011-10-26 21:12:27 +00:00
Eli Friedman
f73c881f4a Fix the assembler strings for a couple of atomic instructions. Doesn't really matter much in practice, but it's a bit cleaner.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@139563 91177308-0d34-0410-b5e6-96231b3b80d8
2011-09-13 00:27:04 +00:00
Eli Friedman
d5ccb0558f Fix atomic load and store on x86 to pass -verify-machineinstrs (and possibly fix some subtle bugs involving passes which check mayStore()).
This isn't exactly ideal, but it is good enough for the moment.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@139245 91177308-0d34-0410-b5e6-96231b3b80d8
2011-09-07 18:48:32 +00:00
Jakob Stoklund Olesen
5047d76575 Pseudo CMOV instructions don't clobber EFLAGS.
The explanation about a 0 argument being materialized as xor is no
longer valid.  Rematerialization will check if EFLAGS is live before
clobbering it.

The code produced by X86TargetLowering::EmitLoweredSelect does not
clobber EFLAGS.

This causes one less testb instruction to be generated in the cmov.ll
test case.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@139057 91177308-0d34-0410-b5e6-96231b3b80d8
2011-09-02 23:52:55 +00:00
Rafael Espindola
d07b7ec772 Adds a SelectionDAG node X86SegAlloca which will be custom lowered
from DYNAMIC_STACKALLOC.

Two new pseudo instructions (SEG_ALLOCA_32 and SEG_ALLOCA_64) which
will match X86SegAlloca (based on word size) are also added.  They
will be custom emitted to inject the actual stack handling code.

Patch by Sanjoy Das.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@138814 91177308-0d34-0410-b5e6-96231b3b80d8
2011-08-30 19:43:21 +00:00
Eli Friedman
43f51aeca8 Add support for generating CMPXCHG16B on x86-64 for the cmpxchg IR instruction.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@138660 91177308-0d34-0410-b5e6-96231b3b80d8
2011-08-26 21:21:21 +00:00
Eli Friedman
327236cd6c Basic x86 code generation for atomic load and store instructions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@138478 91177308-0d34-0410-b5e6-96231b3b80d8
2011-08-24 20:50:09 +00:00
Bruno Cardoso Lopes
d40aa24ebf Add 256-bit support for v8i32, v4i64 and v4f64 ISD::SELECT. Fix PR10556
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@137179 91177308-0d34-0410-b5e6-96231b3b80d8
2011-08-09 23:27:13 +00:00
Eli Friedman
fc430a662f Fix a couple ridiculous copy-paste errors. rdar://9914773 .
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@137160 91177308-0d34-0410-b5e6-96231b3b80d8
2011-08-09 22:17:39 +00:00
Eli Friedman
84e7f7e267 X86ISD::MEMBARRIER does not require SSE2; it doesn't actually generate any code, and all x86 processors will honor the required semantics.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@136249 91177308-0d34-0410-b5e6-96231b3b80d8
2011-07-27 19:43:50 +00:00
Dan Gohman
a0697a7ef5 Add a comment describing why transforming (shl x, 1) to (add x, x) is to be
considered safe enough in this context.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@133159 91177308-0d34-0410-b5e6-96231b3b80d8
2011-06-16 15:55:48 +00:00
Benjamin Kramer
b22da2a72c X86: smulo -> add is now done target-independently in DAGCombiner, remove the patterns.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@131801 91177308-0d34-0410-b5e6-96231b3b80d8
2011-05-21 18:32:01 +00:00
Stuart Hastings
0e29ed081b Re-commit 131641 with fixes; de-pseudoize MOVSX16rr8 and friends.
rdar://problem/8614450


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@131746 91177308-0d34-0410-b5e6-96231b3b80d8
2011-05-20 19:04:40 +00:00
Stuart Hastings
d22f036c2a Reverting 131641 to investigate 'bot complaint.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@131654 91177308-0d34-0410-b5e6-96231b3b80d8
2011-05-19 17:54:42 +00:00
Stuart Hastings
b6dcf3c514 Revise MOVSX16rr8/MOVZX16rr8 (and rm variants) to no longer be
pseudos.  rdar://problem/8614450


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@131641 91177308-0d34-0410-b5e6-96231b3b80d8
2011-05-19 16:59:50 +00:00
Eric Christopher
c324f72ab7 Support XOR and AND optimization with no return value.
Finishes off rdar://8470697


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@131458 91177308-0d34-0410-b5e6-96231b3b80d8
2011-05-17 08:10:18 +00:00