Commit Graph

6240 Commits

Author SHA1 Message Date
Devang Patel
5c1d941f00 Add DEBUG message.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@110224 91177308-0d34-0410-b5e6-96231b3b80d8
2010-08-04 18:06:05 +00:00
Benjamin Kramer
56d23947ca Enable COFF writer on mingw32 and cygwin.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@110200 91177308-0d34-0410-b5e6-96231b3b80d8
2010-08-04 15:32:40 +00:00
Benjamin Kramer
c575283675 Print an error message when someone tries -integrated-as on an unsupported target.
- The COFF backend doesn't support MingW/Cygwin at the moment, it'll report an
  error, but it's still much better than random assertions from the MachO backend.
- We want to make ELF the default eventually, it's what the majority of targets use.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@110197 91177308-0d34-0410-b5e6-96231b3b80d8
2010-08-04 13:16:30 +00:00
Chris Lattner
656f6800b2 fix a win64 encoding problem, patch by Cameron Esfahani!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@110164 91177308-0d34-0410-b5e6-96231b3b80d8
2010-08-03 22:49:22 +00:00
Michael J. Spencer
0cd1ee2308 MC: Remove HasAbsolutizedSet from WindowsX86AsmBackend.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109949 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-31 07:21:44 +00:00
Michael J. Spencer
e2195d8b35 Add relax all support to the COFF object streamer.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109947 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-31 06:22:29 +00:00
Bruno Cardoso Lopes
98f985607b Support all 128-bit AVX vector intrinsics. Most part of them I already
declared during the addition of the assembler support, the additional
changes are:
- Add missing intrinsics
- Move all SSE conversion instructions in X86InstInfo64.td to the SSE.td file.
- Duplicate some patterns to AVX mode.
- Step into PCMPEST/PCMPIST custom inserter and add AVX versions.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109878 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-30 19:54:33 +00:00
Bruno Cardoso Lopes
5b7dab83e9 Fix typo!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109877 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-30 19:41:24 +00:00
Jakob Stoklund Olesen
b2eeed7464 Revert r109652, and remove the offending assert in loadRegFromStackSlot instead.
We do sometimes load from a too small stack slot when dealing with x86 arguments
(varargs and smaller-than-32-bit args). It looks like we know what we are doing
in those cases, so I am going to remove the assert instead of artifically
enlarging stack slot sizes.

The assert in storeRegToStackSlot stays in. We don't want to write beyond the
bounds of a stack slot.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109764 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-29 17:42:27 +00:00
Jakob Stoklund Olesen
4c010ec851 Create a fixed stack object for varargs that is as large as any register.
The size of this object isn't used for anything - technically it is of variable
size.

This avoids a false positive from the assert in
X86InstrInfo::loadRegFromStackSlot, and fixes PR7735.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109652 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-28 20:55:38 +00:00
Nate Begeman
51409214d7 Implement a vectorized algorithm for <16 x i8> << <16 x i8>
This is about 4x faster and smaller than the existing scalarization.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109566 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-28 00:21:48 +00:00
Nate Begeman
bdcb5afb77 ~40% faster vector shl <4 x i32> on SSE 4.1 Larger improvements for smaller types coming in future patches.
For:

define <2 x i64> @shl(<4 x i32> %r, <4 x i32> %a) nounwind readnone ssp {
entry:
  %shl = shl <4 x i32> %r, %a                     ; <<4 x i32>> [#uses=1]
  %tmp2 = bitcast <4 x i32> %shl to <2 x i64>     ; <<2 x i64>> [#uses=1]
  ret <2 x i64> %tmp2
}

We get:

_shl:                                   ## @shl
	pslld	$23, %xmm1
	paddd	LCPI0_0, %xmm1
	cvttps2dq	%xmm1, %xmm1
	pmulld	%xmm1, %xmm0
	ret

Instead of:

_shl:                                   ## @shl
	pshufd	$3, %xmm0, %xmm2
	movd	%xmm2, %eax
	pshufd	$3, %xmm1, %xmm2
	movd	%xmm2, %ecx
	shll	%cl, %eax
	movd	%eax, %xmm2
	pshufd	$1, %xmm0, %xmm3
	movd	%xmm3, %eax
	pshufd	$1, %xmm1, %xmm3
	movd	%xmm3, %ecx
	shll	%cl, %eax
	movd	%eax, %xmm3
	punpckldq	%xmm2, %xmm3
	movd	%xmm0, %eax
	movd	%xmm1, %ecx
	shll	%cl, %eax
	movd	%eax, %xmm2
	movhlps	%xmm0, %xmm0
	movd	%xmm0, %eax
	movhlps	%xmm1, %xmm1
	movd	%xmm1, %ecx
	shll	%cl, %eax
	movd	%eax, %xmm0
	punpckldq	%xmm0, %xmm2
	movdqa	%xmm2, %xmm0
	punpckldq	%xmm3, %xmm0
	ret


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109549 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-27 22:37:06 +00:00
Michael J. Spencer
dfd30187c6 Make MC use Windows COFF on Windows and add tests.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109494 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-27 06:46:15 +00:00
Jakob Stoklund Olesen
81c7b19f04 The isLoadFromStackSlot and isStoreToStackSlot have no way of reporting
subregister operands like this:

%reg1040:sub_32bit<def> = MOV32rm <fi#-2>, 1, %reg0, 0, %reg0, %reg1040<imp-def>; mem:LD4[FixedStack-2](align=8)

Make them return false when subreg operands are present. VirtRegRewriter is
making bad assumptions otherwise.

This fixes PR7713.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109489 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-27 04:17:01 +00:00
Jakob Stoklund Olesen
516cd4575e Add assertions that expose the PR7713 miscompilation: Accessing a stack slot
with a too-big register class.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109488 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-27 04:16:58 +00:00
Evan Cheng
dee81010eb On x86, f32 / f64 nodes share the same registers as 128-bit vector values.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109450 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-26 21:50:05 +00:00
Bruno Cardoso Lopes
3c45734274 Temporary hack to let codegen assert or generate poor code in case
we are using AVX and no AVX version of the desired intruction is present,
this is better for incremental dev (without fallbacks it's easier to spot
what's missing). Not sure this is the best hack thought (we can also disable
all HasSSE* predicates by dinamically marking them 'false' if AVX is present)



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109434 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-26 21:01:18 +00:00
Evan Cheng
70017e44cd Add an ILP scheduler. This is a register pressure aware scheduler that's
appropriate for targets without detailed instruction iterineries.
The scheduler schedules for increased instruction level parallelism in
low register pressure situation; it schedules to reduce register pressure
when the register pressure becomes high.

On x86_64, this is a win for all tests in CFP2000. It also sped up 256.bzip2
by 16%.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109300 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-24 00:39:05 +00:00
Bruno Cardoso Lopes
3c8e1bee63 Support x86 "eiz" and "riz" pseudo index registers in the assembler.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109295 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-24 00:06:39 +00:00
Bruno Cardoso Lopes
f64a7d49a0 Remove trailing whitespace
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109276 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-23 22:15:26 +00:00
Bruno Cardoso Lopes
f528d2b438 Add AVX version of CLMUL instructions
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109248 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-23 18:41:12 +00:00
Bruno Cardoso Lopes
26a9142bd6 Declare CLMUL as a subtarget feature
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109207 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-23 01:22:45 +00:00
Bruno Cardoso Lopes
cdae7e8244 Add x86 CLMUL (Carry-less multiplication) cpu feature
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109206 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-23 01:17:51 +00:00
Bruno Cardoso Lopes
6b7e9168a4 Add complete assembler support for FMA3 instructions, with descriptions and encodings taken from the AVX manual
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109204 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-23 00:54:35 +00:00
Dale Johannesen
c76d23f2e2 The only supported calling convention for X86-64 uses
SSE, so we can't return floating point values if this
is disabled.  Detect this error for clang.

With SSE1 only, f64 is a problem; it can be done, but
neither llvm-gcc nor clang has ever generated correct
code for it.  Since nobody noticed this I think it's
OK to treat it as an error for now.

This also handles SSE-sized vectors of floating point.
8207686, 8204109.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109201 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-23 00:30:35 +00:00
Bruno Cardoso Lopes
06e6e101a0 Fix some AVX instructions which didnt had HasAVX prefix. And also a problem with PINSRW, which was totally wrong because of a typo I introduced previously
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109198 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-23 00:14:54 +00:00
Bruno Cardoso Lopes
fb583a9842 Add remaining AVX instructions (most of them dealing with GR64 destinations. This complete the assembler support for the general AVX ISA. But we still miss instructions from FMA3 and CLMUL specific feature flags, which are now the next step
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109168 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-22 21:18:49 +00:00
Chris Lattner
134d8eec87 remove the JIT "NeedsExactSize" feature and supporting logic.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109167 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-22 21:17:55 +00:00
Chris Lattner
0123c1da35 X86MCInstLower now depends on AsmPrinter being around.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109154 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-22 21:10:04 +00:00
Chris Lattner
456fdaf0ce instead of migrating it to the MC instruction encoder, just
rip out the implementation of X86InstrInfo::GetInstSizeInBytes.
The code being ripped out just implemented a copy and hacked up
version of the (old) instruction encoder, and is buggy and 
terrible in other ways.  Since "GetInstSizeInBytes" is really 
only there to support the JIT's "NeedsExactSize" hook (which
noone is using), just rip out the code.  I will rip out the
NeedsExactSize hook next.

This resolves rdar://7617809 - switch X86InstrInfo::GetInstSizeInBytes to use X86MCCodeEmitter



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109149 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-22 21:05:13 +00:00
Chandler Carruth
8a89a6ae9c Attempt to fix linking issues with CMake. Please review other CMake users,
especially on other platforms. Is there a better way to fix this.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109084 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-22 06:27:45 +00:00
Eric Christopher
9a9d275dc7 Custom lower the memory barrier instructions and add support
for lowering without sse2.  Add a couple of new testcases.

Fixes a few libgomp tests and latent bugs.  Remove a few todos.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109078 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-22 02:48:34 +00:00
Eric Christopher
90eb4024ba 80-columns.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109070 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-22 00:26:08 +00:00
Nate Begeman
0c07b64fec Make fast isel win64-aware w.r.t. call-clobbered regs
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109069 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-22 00:09:39 +00:00
Bruno Cardoso Lopes
2b69143083 Add more 256-bit forms for a bunch of regular AVX instructions
Add 64-bit (GR64) versions of some instructions (which are not
described in their SSE forms, but are described in AVX)


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109063 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-21 23:53:50 +00:00
Rafael Espindola
fcbd1a749f Fixes win64. It was broken by a previous patch where I missed the !isWin64
and then forced every register to be a vr128 on win64.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109060 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-21 23:19:57 +00:00
Chris Lattner
908bafe6fa add some rough support for making mcinst lowering work without an
asmprinter or mangler around.  This is option #B for killing off 
X86InstrInfo::GetInstSizeInBytes.  Option #A (killing 
"needsexactsize") was sent for consideration to llvmdev.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109056 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-21 23:03:35 +00:00
Bruno Cardoso Lopes
e29f37f6a1 Add missing AVX convert instructions. Those instructions are not described in their SSE forms (although they exist), but add the AVX forms anyway, so the assembler can benefit from it
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109039 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-21 21:37:59 +00:00
Nate Begeman
c8ea673bc0 Fix a couple issues with Win64 ABI
1) all registers were spilled as xmm, regardless of actual size
2) win64 abi doesn't do the varargs-size-in-%al thing

Still to look into:

xmm6-15 are marked as clobbered by call instructions on win64 even though they aren't.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109035 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-21 20:49:52 +00:00
Bruno Cardoso Lopes
928fc3b4a0 Avoid AVX instructions to be selected instead of its SSE form
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109032 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-21 20:38:42 +00:00
Eric Christopher
dab4dac2a0 Pulling out previous patch, must've run the tests in
the wrong directory.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109005 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-21 09:23:56 +00:00
Eric Christopher
87f41370a8 Lower MEMBARRIER on x86 and support processors without SSE2.
Fixes a pile of libgomp failures in the llvm-gcc testsuite due
to the libcall not existing.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109004 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-21 09:05:23 +00:00
Bruno Cardoso Lopes
cf6ca03128 Add AVX only vzeroall and vzeroupper instructions
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109002 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-21 08:56:24 +00:00
Bruno Cardoso Lopes
7d7d15a159 Add new AVX vpermilps, vpermilpd and vperm2f128 instructions
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@108984 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-21 03:07:42 +00:00
Bruno Cardoso Lopes
4b13f3cf3d Add new AVX vmaskmov instructions, and also fix the VEX encoding bits to support it
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@108983 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-21 02:46:58 +00:00
Bruno Cardoso Lopes
1154f426d7 Add new AVX vextractf128 instructions
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@108964 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-20 23:19:02 +00:00
Chris Lattner
6e8154354f make asmprinter optional, even though passing in null will cause things to explode right now.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@108955 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-20 22:45:33 +00:00
Chris Lattner
cb63ecba31 continue pushing dependencies around.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@108952 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-20 22:35:40 +00:00
Chris Lattner
c0115b5ca1 reduce X86MCInstLower dependencies on asmprinter.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@108950 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-20 22:30:53 +00:00
Chris Lattner
0c13cf36ad pass around MF, not MMI.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@108949 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-20 22:26:07 +00:00