Notably, this adds simple micro-architecture names for the Intel CPU
variants, and defines the old 'core'-based names as aliases. GCC has
started to simplify their documented interface to use these names as
well, so it seems like we can start to converge on a consistent pattern.
I'd appreciate Intel double checking the entries that aren't yet
documented widely, especially Atom (Bonnell and Silvermont), Knights
Landing, and Skylake. But this change shouldn't break any existing
users.
Also, ran clang-format to re-format this code and it actually worked
(modulo a tiny bug) so hopefully we can start to stop thinking about
formatting this stuff.
llvm-svn: 223769
Allow unaligned 16-byte memop codegen for btver2. No functional changes for any other subtargets.
Replace the existing supposed small memcpy test with an actual test of a small memcpy.
The previous test wasn't using FileCheck either.
This patch should allow us to close PR21541 ( http://llvm.org/bugs/show_bug.cgi?id=21541 ).
Differential Revision: http://reviews.llvm.org/D6360
llvm-svn: 222925
This patch adds a feature flag to avoid unaligned 32-byte load/store AVX codegen
for Sandy Bridge and Ivy Bridge. There is no functionality change intended for
those chips. Previously, the absence of AVX2 was being used as a proxy to detect
this feature. But that hindered codegen for AVX-enabled AMD chips such as btver2
that do not have the 32-byte unaligned access slowdown.
Performance measurements are included in PR21541 ( http://llvm.org/bugs/show_bug.cgi?id=21541 ).
Differential Revision: http://reviews.llvm.org/D6355
llvm-svn: 222544
This is a first step for generating SSE rcp instructions for reciprocal
calcs when fast-math allows it. This is very similar to the rsqrt optimization
enabled in D5658 ( http://reviews.llvm.org/rL220570 ).
For now, be conservative and only enable this for AMD btver2 where performance
improves significantly both in terms of latency and throughput.
We may never enable this codegen for Intel Core* chips because the divider circuits
are just too fast. On SandyBridge, divss can be as fast as 10 cycles versus the 21
cycle critical path for the rcp + mul + sub + mul + add estimate.
Follow-on patches may allow configuration of the number of Newton-Raphson refinement
steps, add AVX512 support, and enable the optimization for more chips.
More background here: http://llvm.org/bugs/show_bug.cgi?id=21385
Differential Revision: http://reviews.llvm.org/D6175
llvm-svn: 221706
This patch adds 'FeatureSlowSHLD' to 'bdver3'.
According to the official AMD optimization guide for amdfam15: "Using
alternative code in place of SHLD achieves lower overall latency and
requires fewer execution resources. The 32-bit and 64-bit forms of
ADD, ADC, SHR, and LEA (except 16-bit form) are DirectPath
instructions, while SHLD is a VectorPath instruction."
This patch also explicitly sets feature AVX and SSE4A for all the bdver*
cpus. This part of the patch is a non-functional change and it is mainly
done for clarity reasons (Both XOP and FMA4 already imply AVX and SSE4A).
llvm-svn: 221296
This is a first step for generating SSE rsqrt instructions for
reciprocal square root calcs when fast-math is allowed.
For now, be conservative and only enable this for AMD btver2
where performance improves significantly - for example, 29%
on llvm/projects/test-suite/SingleSource/Benchmarks/BenchmarkGame/n-body.c
(if we convert the data type to single-precision float).
This patch adds a two constant version of the Newton-Raphson
refinement algorithm to DAGCombiner that can be selected by any target
via a parameter returned by getRsqrtEstimate()..
See PR20900 for more details:
http://llvm.org/bugs/show_bug.cgi?id=20900
Differential Revision: http://reviews.llvm.org/D5658
llvm-svn: 220570
This is a first pass at a scheduling model for Jaguar.
It's structured largely on the existing SandyBridge and SLM sched models.
Using this model, in addition to turning on the PostRA scheduler, results in
some perf wins on internal and 3rd party benchmarks. There's not much difference
in LLVM's test-suite benchmarking subset of tests.
Differential Revision: http://reviews.llvm.org/D5229
llvm-svn: 217457
This allows assembling the two new instructions, encls and enclu for the
SKX processor model.
Note the diffs are a bigger than what might think, but to fit the new
MRM_CF and MRM_D7 in things in the right places things had to be
renumbered and shuffled down causing a bit more diffs.
rdar://16228228
llvm-svn: 214460
According to Intel Software Optimization Manual
on Silvermont INC or DEC instructions require
an additional uop to merge the flags.
As a result, a branch instruction depending
on an INC or a DEC instruction incurs a 1 cycle penalty.
Differential Revision: http://reviews.llvm.org/D3990
llvm-svn: 210466
According to Intel Software Optimization Manual on Silvermont in some cases LEA
is better to be replaced with ADD instructions:
"The rule of thumb for ADDs and LEAs is that it is justified to use LEA
with a valid index and/or displacement for non-destructive destination purposes
(especially useful for stack offset cases), or to use a SCALE.
Otherwise, ADD(s) are preferable."
Differential Revision: http://reviews.llvm.org/D3826
llvm-svn: 209198
default architecture for reasonable modern x86 processors, actually be
modern. This processor model should essentially be "tuned" for modern
x86 chips as much as possible without undue penalties on any specific
architecture. Previously we weren't even using the nice scheduling
models. There are a few other tweaks needed here, but this change at
least I have benchmarked across a decent swatch of chips (intel's
clovertown, westmere, and sandybridge; amd's istanbul) and seen no
significant regressions.
If anyone has suggested ways to test this, just let me know. Somewhat
alarmingly, no existing tests failed.
llvm-svn: 208230
This is not really expected to work right yet. Mostly because we will
still emit the OpSize (0x66) prefix in all the wrong places, along with
a number of other corner cases. Those will all be fixed in the subsequent
commits.
Patch from David Woodhouse.
llvm-svn: 198584
AMD's processors family K7, K8, K10, K12, K15 and K16 are known to have SHLD/SHRD instructions with very poor latency. Optimization guides for these processors recommend using an alternative sequence of instructions. For these AMD's processors, I disabled folding (or (x << c) | (y >> (64 - c))) when we are not optimizing for size.
It might be beneficial to disable this folding for some of the Intel's processors. However, since I couldn't find specific recommendations regarding using SHLD/SHRD instructions on Intel's processors, I haven't disabled this peephole for Intel.
llvm-svn: 195383
bulldozer and piledriver. Support for the instruction itself seems to have
already been added in r178040.
Differential Revision: http://llvm-reviews.chandlerc.com/D1933
llvm-svn: 192828
Implements Instruction scheduler latencies for Silvermont,
using latencies from the Intel Silvermont Optimization Guide.
Auto detects SLM.
Turns on post RA scheduler when generating code for SLM.
llvm-svn: 190717
Add basic assembly/disassembly support for the first Intel SHA
instruction 'sha1rnds4'. Also includes feature flag, and test cases.
Support for the remaining instructions will follow in a separate patch.
llvm-svn: 190611
latency for certain models of the Intel Atom family, by converting
instructions into their equivalent LEA instructions, when it is both
useful and possible to do so.
llvm-svn: 180573
variant/dialect. Addresses a FIXME in the emitMnemonicAliases function.
Use and test case to come shortly.
rdar://13688439 and part of PR13340.
llvm-svn: 179804
indirect through a memory address is to load the memory address into
a register and then call indirect through the register.
This patch implements this improvement by modifying SelectionDAG to
force a function address which is a memory reference to be loaded
into a virtual register.
Patch by Sriram Murali.
llvm-svn: 178171
All Intel CPUs since Yonah look a lot alike, at least at the granularity
of the scheduling models. We can add more accurate models for
processors that aren't Sandy Bridge if required. Haswell will probably
need its own.
The Atom processor and anything based on NetBurst is completely
different. So are the non-Intel chips.
llvm-svn: 178080
The current Intel Atom microarchitecture has a feature whereby
when a function returns early then it is slightly faster to execute
a sequence of NOP instructions to wait until the return address is ready,
as opposed to simply stalling on the ret instruction until
the return address is ready.
When compiling for X86 Atom only, this patch will run a pass,
called "X86PadShortFunction" which will add NOP instructions where less
than four cycles elapse between function entry and return.
It includes tests.
This patch has been updated to address Nadav's review comments
- Optimize only at >= O1 and don't do optimization if -Os is set
- Stores MachineBasicBlock* instead of BBNum
- Uses DenseMap instead of std::map
- Fixes placement of braces
Patch by Andy Zhang.
llvm-svn: 171879
URL: http://llvm.org/viewvc/llvm-project?rev=171524&view=rev
Log:
The current Intel Atom microarchitecture has a feature whereby when a function
returns early then it is slightly faster to execute a sequence of NOP
instructions to wait until the return address is ready,
as opposed to simply stalling on the ret instruction
until the return address is ready.
When compiling for X86 Atom only, this patch will run a pass, called
"X86PadShortFunction" which will add NOP instructions where less than four
cycles elapse between function entry and return.
It includes tests.
Patch by Andy Zhang.
llvm-svn: 171603
returns early then it is slightly faster to execute a sequence of NOP
instructions to wait until the return address is ready,
as opposed to simply stalling on the ret instruction
until the return address is ready.
When compiling for X86 Atom only, this patch will run a pass, called
"X86PadShortFunction" which will add NOP instructions where less than four
cycles elapse between function entry and return.
It includes tests.
Patch by Andy Zhang.
llvm-svn: 171524
Not all chips targeted by x86_64 have this feature, but a dramatically
increasing number do. Specifying a chip-specific tuning parameter will
continue to turn the feature on or off as appropriate for that
particular chip, but the generic flag should try to achieve the best
performance on the most widely available hardware. Today, the number of
chips with fast UA access dwarfs those without in the x86-64 space.
Note that this also brings LLVM's code generation for this '-march' flag
more in line with that of modern GCCs. Reviewed by Dan Gohman.
llvm-svn: 170269
Summary:
Not all chips targeted by x86_64 have this feature, but a dramatically
increasing number do. Specifying a chip-specific tuning parameter will
continue to turn the feature on or off as appropriate for that
particular chip, but the generic flag should try to achieve the best
performance on the most widely available hardware. Today, the number of
chips with fast UA access dwarfs those without in the x86-64 space.
Note that this also brings LLVM's code generation for this '-march' flag
more in line with that of modern GCCs.
CC: llvm-commits
Differential Revision: http://llvm-reviews.chandlerc.com/D195
llvm-svn: 169740
Intel chips.
The model number rules were determined by inspecting Intel's
documentation for their newer chip model numbers. My understanding is
that all of the newer Intel chips have fast unaligned memory access, but
if anyone is concerned about a particular chip, just shout.
No tests updated; it's not clear we have dedicated tests for the chips'
various features, but if anyone would like tests (or can point me at
some existing ones), I'm happy to oblige.
llvm-svn: 169730
- Add RTM code generation support throught 3 X86 intrinsics:
xbegin()/xend() to start/end a transaction region, and xabort() to abort a
tranaction region
llvm-svn: 167573
- CodeGenPrepare pass for identifying div/rem ops
- Backend specifies the type mapping using addBypassSlowDivType
- Enabled only for Intel Atom with O2 32-bit -> 8-bit
- Replace IDIV with instructions which test its value and use DIVB if the value
is positive and less than 256.
- In the case when the quotient and remainder of a divide are used a DIV
and a REM instruction will be present in the IR. In the non-Atom case
they are both lowered to IDIVs and CSE removes the redundant IDIV instruction,
using the quotient and remainder from the first IDIV. However,
due to this optimization CSE is not able to eliminate redundant
IDIV instructions because they are located in different basic blocks.
This is overcome by calculating both the quotient (DIV) and remainder (REM)
in each basic block that is inserted by the optimization and reusing the result
values when a subsequent DIV or REM instruction uses the same operands.
- Test cases check for the presents of the optimization when calculating
either the quotient, remainder, or both.
Patch by Tyler Nowicki!
llvm-svn: 163150
subtarget CPU descriptions and support new features of
MachineScheduler.
MachineModel has three categories of data:
1) Basic properties for coarse grained instruction cost model.
2) Scheduler Read/Write resources for simple per-opcode and operand cost model (TBD).
3) Instruction itineraties for detailed per-cycle reservation tables.
These will all live side-by-side. Any subtarget can use any
combination of them. Instruction itineraries will not change in the
near term. In the long run, I expect them to only be relevant for
in-order VLIW machines that have complex contraints and require a
precise scheduling/bundling model. Once itineraries are only actively
used by VLIW-ish targets, they could be replaced by something more
appropriate for those targets.
This tablegen backend rewrite sets things up for introducing
MachineModel type #2: per opcode/operand cost model.
llvm-svn: 159891
Adds an instruction itinerary to all x86 instructions, giving each a default latency of 1, using the InstrItinClass IIC_DEFAULT.
Sets specific latencies for Atom for the instructions in files X86InstrCMovSetCC.td, X86InstrArithmetic.td, X86InstrControl.td, and X86InstrShiftRotate.td. The Atom latencies for the remainder of the x86 instructions will be set in subsequent patches.
Adds a test to verify that the scheduler is working.
Also changes the scheduling preference to "Hybrid" for i386 Atom, while leaving x86_64 as ILP.
Patch by Preston Gurd!
llvm-svn: 149558
http://lab.llvm.org:8011/builders/llvm-x86_64-linux/builds/101
--- Reverse-merging r141854 into '.':
U test/MC/Disassembler/X86/x86-32.txt
U test/MC/Disassembler/X86/simple-tests.txt
D test/CodeGen/X86/bmi.ll
U lib/Target/X86/X86InstrInfo.td
U lib/Target/X86/X86ISelLowering.cpp
U lib/Target/X86/X86.td
U lib/Target/X86/X86Subtarget.h
llvm-svn: 141857
instructions are more aligned than the CPU requires, and adds some additional
directives, to follow in future patches. Patch by David Meyer!
llvm-svn: 139125
use MC instructions in the printInstruction() method via the tablegen flag
for it rather than a #define prior to including the autogenerated bits.
llvm-svn: 115238
- The idea is that when a match fails, we just try to match each of +'b', +'w',
+'l'. If exactly one matches, we assume this is a mnemonic prefix and accept
it. If all match, we assume it is width generic, and take the 'l' form.
- This would be a horrible hack, if it weren't so simple. Therefore it is an
elegant solution! Chris gets the credit for this particular elegant
solution. :)
- Next step to making this more robust is to have the X86 matcher generate the
mnemonic prefix information. Ideally we would also compute up-front exactly
which mnemonic to attempt to match, but this may require more custom code in
the matcher than is really worth it.
llvm-svn: 103012
When a target instruction wants to set target-specific flags, it should simply
set bits in the TSFlags bit vector defined in the Instruction TableGen class.
This works well because TableGen resolves member references late:
class I : Instruction {
AddrMode AM = AddrModeNone;
let TSFlags{3-0} = AM.Value;
}
let AM = AddrMode4 in
def ADD : I;
TSFlags gets the expected bits from AddrMode4 in this example.
llvm-svn: 100384
a new subtarget option for AES and check for the support. Add "westmere"
line of processors and add AES-NI support to the core i7.
Add a couple of TODOs for information I couldn't verify.
llvm-svn: 100231
On Nehalem and newer CPUs there is a 2 cycle latency penalty on using a register
in a different domain than where it was defined. Some instructions have
equvivalents for different domains, like por/orps/orpd.
The SSEDomainFix pass tries to minimize the number of domain crossings by
changing between equvivalent opcodes where possible.
This is a work in progress, in particular the pass doesn't do anything yet. SSE
instructions are tagged with their execution domain in TableGen using the last
two bits of TSFlags. Note that not all instructions are tagged correctly. Life
just isn't that simple.
The SSE execution domain issue is very similar to the ARM NEON/VFP pipeline
issue handled by NEONMoveFixPass. This pass may become target independent to
handle both.
llvm-svn: 99524
temporary workaround for matching inc/dec on x86_64 to the correct instruction.
- This hack will eventually be replaced with a robust mechanism for handling
matching instructions based on the available target features.
llvm-svn: 98858
ignore alignment requirements for SIMD memory operands. This
is useful on architectures like the AMD 10h that do not trap on
unaligned references if a status bit is twiddled at startup time.
llvm-svn: 93151
be non-optimal. To be precise, we should avoid folding loads if the instructions
only update part of the destination register, and the non-updated part is not
needed. e.g. cvtss2sd, sqrtss. Unfolding the load from these instructions breaks
the partial register dependency and it can improve performance. e.g.
movss (%rdi), %xmm0
cvtss2sd %xmm0, %xmm0
instead of
cvtss2sd (%rdi), %xmm0
An alternative method to break dependency is to clear the register first. e.g.
xorps %xmm0, %xmm0
cvtss2sd (%rdi), %xmm0
llvm-svn: 91672
- added processors k8-sse3, opteron-sse3, athlon64-sse3, amdfam10, and
barcelona with appropriate sse3/4a levels
- added FeatureSSE4A for amdfam10 processors
in X86Subtarget:
- added hasSSE4A
- updated AutoDetectSubtargetFeatures to detect SSE4A
- updated GetCurrentX86CPU to detect family 15 with sse3 as k8-sse3 and
family 10h as amdfam10
New processor names match those used by gcc.
Patch by Paul Redmond!
llvm-svn: 72434
SSE2, however it's possible to disable SSE2, and the subtarget support
code thinks that if 64-bit implies SSE2 and SSE2 is disabled then
64-bit should also be disabled. Instead, just mark all the 64-bit
subtargets as explicitly supporting SSE2.
Also, move the code that makes -march=x86-64 enable 64-bit support by
default to only apply when there is no explicit subtarget. If you
need to specify a subtarget and you want 64-bit code, you'll need to
select a subtarget that supports 64-bit code.
llvm-svn: 63575
feature is set, then the features in the implied list should be set also.
The opposite is also enforced: if a feature in the implied list isn't set,
then the feature that owns that implies list shouldn't be set either.
llvm-svn: 36756
- Added a new format for instructions where the source register is implied
and it is same as the destination register. Used for pseudo instructions
that clear the destination register.
llvm-svn: 25872
XMM registers. There are many known deficiencies and fixmes, which will be
addressed ASAP. The major benefit of this work is that it will allow the
LLVM register allocator to allocate FP registers across basic blocks.
The x86 backend will still default to x87 style FP. To enable this work,
you must pass -enable-sse-scalar-fp and either -sse2 or -sse3 to llc.
An example before and after would be for:
double foo(double *P) { double Sum = 0; int i; for (i = 0; i < 1000; ++i)
Sum += P[i]; return Sum; }
The inner loop looks like the following:
x87:
.LBB_foo_1: # no_exit
fldl (%esp)
faddl (%eax,%ecx,8)
fstpl (%esp)
incl %ecx
cmpl $1000, %ecx
#FP_REG_KILL
jne .LBB_foo_1 # no_exit
SSE2:
addsd (%eax,%ecx,8), %xmm0
incl %ecx
cmpl $1000, %ecx
#FP_REG_KILL
jne .LBB_foo_1 # no_exit
llvm-svn: 22340
Intel and AT&T style assembly language. The ultimate goal of this is to
eliminate the GasBugWorkaroundEmitter class, but for now AT&T style emission
is not fully operational.
llvm-svn: 16639
I/O port instructions on x86. The specific code sequence is tailored to
the parameters and return value of the intrinsic call.
Added the ability for implicit defintions to be printed in the Instruction
Printer.
Added the ability for RawFrm instruction to print implict uses and
defintions with correct comma output. This required adjustment to some
methods so that a leading comma would or would not be printed.
llvm-svn: 12782
the size of the immediate and the memory operand on instructions that
use them. This resolves problems with instructions that take both a
memory and an immediate operand but their sizes differ (i.e. ADDmi32b).
llvm-svn: 11967
Chandler Carruth