into the operand array of the start of the memory reference descriptor.
Additional code in EncodeInstruction provides an additional adjustment.
This patch places that additional code in a separate function,
called getOperandBias, so that any caller of getMemoryOperandNo
can also call getOperandBias.
llvm-svn: 179211
wasn't always the start of the operand. If there was a symbol reference, then
Start pointed to that token. It's very likely there are other places that need
to be updated.
llvm-svn: 179210
Test cases that regressed due to r179115, plus a few more, were added in
r179182. Original commit message below:
[ms-inline asm] Use parsePrimaryExpr in lieu of parseExpression if we need to
parse an identifier. Otherwise, parseExpression may parse multiple tokens,
which makes it impossible to properly compute an immediate displacement.
An example of such a case is the source operand (i.e., [Symbol + ImmDisp]) in
the below example:
__asm mov eax, [Symbol + ImmDisp]
Part of rdar://13611297
llvm-svn: 179187
parse an identifier. Otherwise, parseExpression may parse multiple tokens,
which makes it impossible to properly compute an immediate displacement.
An example of such a case is the source operand (i.e., [Symbol + ImmDisp]) in
the below example:
__asm mov eax, [Symbol + ImmDisp]
The existing test cases exercise this patch.
rdar://13611297
llvm-svn: 179115
rather than deriving the StringRef from the Start and End SMLocs.
Using the Start and End SMLocs works fine for operands such as [Symbol], but
not for operands such as [Symbol + ImmDisp]. All existing test cases that
reference a variable exercise this patch.
rdar://13602265
llvm-svn: 179109
The costs are overfitted so that I can still use the legalization factor.
For example the following kernel has about half the throughput vectorized than
unvectorized when compiled with SSE2. Before this patch we would vectorize it.
unsigned short A[1024];
double B[1024];
void f() {
int i;
for (i = 0; i < 1024; ++i) {
B[i] = (double) A[i];
}
}
radar://13599001
llvm-svn: 179033
During LTO, the target options on functions within the same Module may
change. This would necessitate resetting some of the back-end. Do this for X86,
because it's a Friday afternoon.
llvm-svn: 178917
memory operands.
Essentially, this layers an infix calculator on top of the parsing state
machine. The scale on the index register is still expected to be an immediate
__asm mov eax, [eax + ebx*4]
and will not work with more complex expressions. For example,
__asm mov eax, [eax + ebx*(2*2)]
The plus and minus binary operators assume the numeric value of a register is
zero so as to not change the displacement. Register operands should never
be an operand for a multiply or divide operation; the scale*indexreg
expression is always replaced with a zero on the operand stack to prevent
such a case.
rdar://13521380
llvm-svn: 178881
SSE2 has efficient support for shifts by a scalar. My previous change of making
shifts expensive did not take this into account marking all shifts as expensive.
This would prevent vectorization from happening where it is actually beneficial.
With this change we differentiate between shifts of constants and other shifts.
radar://13576547
llvm-svn: 178808
On certain architectures we can support efficient vectorized version of
instructions if the operand value is uniform (splat) or a constant scalar.
An example of this is a vector shift on x86.
We can efficiently support
for (i = 0 ; i < ; i += 4)
w[0:3] = v[0:3] << <2, 2, 2, 2>
but not
for (i = 0; i < ; i += 4)
w[0:3] = v[0:3] << x[0:3]
This patch adds a parameter to getArithmeticInstrCost to further qualify operand
values as uniform or uniform constant.
Targets can then choose to return a different cost for instructions with such
operand values.
A follow-up commit will test this feature on x86.
radar://13576547
llvm-svn: 178807
The default logic does not correctly identify costs of casts because they are
marked as custom on x86.
For some cases, where the shift amount is a scalar we would be able to generate
better code. Unfortunately, when this is the case the value (the splat) will get
hoisted out of the loop, thereby making it invisible to ISel.
radar://13130673
radar://13537826
llvm-svn: 178703
qualifiers.
This patch only adds support for parsing these identifiers in the
X86AsmParser. The front-end interface isn't capable of looking up
these identifiers at this point in time. The end result is the
compiler now errors during object file emission, rather than at
parse time. Test case coming shortly.
Part of rdar://13499009 and PR13340
llvm-svn: 178566
Buffered means a later divide may be executed out-of-order while a
prior divide is sitting (buffered) in a reservation station.
You can tell it's not pipelined, because operations that use it
reserve it for more than one cycle:
def : WriteRes<WriteIDiv, [HWPort0, HWDivider]> {
let Latency = 25;
let ResourceCycles = [1, 10];
}
We don't currently distinguish between an unpipeline operation and one
that is split into multiple micro-ops requiring the same unit. Except
that the later may have NumMicroOps > 1 if they also consume
issue/dispatch resources.
llvm-svn: 178519
'@SECREL' is what is used by the Microsoft assembler, but GNU as expects '@SECREL32'.
With the patch, the MC-generated code works fine in combination with a recent GNU as (2.23.51.20120920 here).
Patch by David Nadlinger!
Differential Revision: http://llvm-reviews.chandlerc.com/D429
llvm-svn: 178427
- RDRAND always clears the destination value when a random value is not
available (i.e. CF == 0). This value is truncated or zero-extended as
the false boolean value to be returned. Boolean simplification needs
to skip this 'zext' or 'trunc' node.
llvm-svn: 178312
To enable a load of a call address to be folded with that call, this
load is moved from outside of callseq into callseq. Such a moving
adds a non-glued node (that load) into a glued sequence. This non-glue
load is only removed when DAG selection folds them into a memory form
call instruction. When such instruction selection is disabled, it breaks
DAG schedule.
To prevent that, such moving is disabled when target favors register
indirect call.
Previous workaround disabling CALL32m/CALL64m insn selection is removed.
llvm-svn: 178308
form of call in preference to memory indirect on Atom.
In this case, the patch applies the optimization to the code for reloading
spilled registers.
The patch also includes changes to sibcall.ll and movgs.ll, which were
failing on the Atom buildbot after the first patch was applied.
This patch by Sriram Murali.
llvm-svn: 178193
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
Now all x86 instructions that have itinerary classes also have SchedRW
lists. This is required before the new scheduling models can be used.
There are still unannotated instructions remaining, but they don't have
itinerary classes either.
llvm-svn: 178051
- It's still considered aligned when the specified alignment is larger
than the natural alignment;
- The new alignment for the high 128-bit vector should be min(16,
alignment) as the pointer is advanced by 16, a power-of-2 offset.
llvm-svn: 177947
All the instructions tagged with IIC_DEFAULT had nothing in common, and
we already have a NoItineraries class to represent untagged
instructions.
llvm-svn: 177937
- After moving logic recognizing vector shift with scalar amount from
DAG combining into DAG lowering, we declare to customize all vector
shifts even vector shift on AVX is legal. As a result, the cost model
needs special tuning to identify these legal cases.
llvm-svn: 177586
an X86Operand, but also performs a Sema lookup and adds the sizing directive
when appropriate. Use this when parsing a bracketed statement. This is
necessary to get the instruction matching correct as well. Test case coming
on clang side.
rdar://13455408
llvm-svn: 177439
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.
llvm-svn: 177426
We hitch a ride with the existing OpndItins class that was used to add
instruction itinerary classes in the many multiclasses in this file.
Use the link provided by the X86FoldableSchedWrite.Folded to find the
right SchedWrite for folded loads.
llvm-svn: 177326
This new-style scheduling information is going to replace the
instruction iteneraries.
This also serves as a test case for Andy's fix in r177317.
llvm-svn: 177323
MinGW is almost completely compatible to MSVC, with the exception of the _tls_array global not being available.
Patch by David Nadlinger!
llvm-svn: 177257
Since almost all X86 instructions can fold loads, use a multiclass to
define register/memory pairs of SchedWrites.
An X86FoldableSchedWrite represents the register version of an
instruction. It holds a reference to the SchedWrite to use when the
instruction folds a load.
This will be used inside multiclasses that define rr and rm instruction
versions together.
llvm-svn: 177210
The new InstrSchedModel is easier to use than the instruction
itineraries. It will be used to model instruction latency and throughput
in modern Intel microarchitectures like Sandy Bridge.
InstrSchedModel should be able to coexist with instruction itinerary
classes, but for cleanliness we should switch the Atom processor model
to the new InstrSchedModel as well.
llvm-svn: 177122
LegalizeDAG.cpp uses the value of the comparison operands when checking
the legality of BR_CC, so DAGCombiner should do the same.
v2:
- Expand more BR_CC value types for NVPTX
v3:
- Expand correct BR_CC value types for Hexagon, Mips, and XCore.
llvm-svn: 176694
That can usually be lowered efficiently and is common in sandybridge code.
It would be nice to do this in DAGCombiner but we can't insert arbitrary
BUILD_VECTORs this late.
Fixes PR15462.
llvm-svn: 176634
- Phi nodes should be replaced/updated after lowering CMOV into branch
because 'mainMBB' updating operand in Phi node is changed.
- Add EFLAGS in livein before lowering the 2nd CMOV. It's necessary as
we will reuse the EFLAGS generated before the 1st lowered CMOV, which
won't clobber EFLAGS. However, we need explicitly specify that.
- '-attr=-cmov' test case are added.
llvm-svn: 176598
- Clear 'mayStore' flag when loading from the atomic variable before the
spin loop
- Clear kill flag from one use to multiple use in registers forming the
address to that atomic variable
- don't use a physical register as live-in register in BB (neither entry
nor landing pad.) by copying it into virtual register
(patch by Cameron Zwarich)
llvm-svn: 176538
one-byte NOPs. If the processor actually executes those NOPs, as it sometimes
does with aligned bundling, this can have a performance impact. From my
micro-benchmarks run on my one machine, a 15-byte NOP followed by twelve
one-byte NOPs is about 20% worse than a 15 followed by a 12. This patch
changes NOP emission to emit as many 15-byte (the maximum) as possible followed
by at most one shorter NOP.
llvm-svn: 176464
* Only apply divide bypass optimization when not optimizing for size.
* Fixed bug caused by constant for 0 value of type Int32,
used dividend type to generate the constant instead.
* For atom x86-64 apply the divide bypass to use 16-bit divides instead of
64-bit divides when operand values are small enough.
* Added lit tests for 64-bit divide bypass.
Patch by Tyler Nowicki!
llvm-svn: 176442
This matters for example in following matrix multiply:
int **mmult(int rows, int cols, int **m1, int **m2, int **m3) {
int i, j, k, val;
for (i=0; i<rows; i++) {
for (j=0; j<cols; j++) {
val = 0;
for (k=0; k<cols; k++) {
val += m1[i][k] * m2[k][j];
}
m3[i][j] = val;
}
}
return(m3);
}
Taken from the test-suite benchmark Shootout.
We estimate the cost of the multiply to be 2 while we generate 9 instructions
for it and end up being quite a bit slower than the scalar version (48% on my
machine).
Also, properly differentiate between avx1 and avx2. On avx-1 we still split the
vector into 2 128bits and handle the subvector muls like above with 9
instructions.
Only on avx-2 will we have a cost of 9 for v4i64.
I changed the test case in test/Transforms/LoopVectorize/X86/avx1.ll to use an
add instead of a mul because with a mul we now no longer vectorize. I did
verify that the mul would be indeed more expensive when vectorized with 3
kernels:
for (i ...)
r += a[i] * 3;
for (i ...)
m1[i] = m1[i] * 3; // This matches the test case in avx1.ll
and a matrix multiply.
In each case the vectorized version was considerably slower.
radar://13304919
llvm-svn: 176403
- ISD::SHL/SRL/SRA must have either both scalar or both vector operands
but TLI.getShiftAmountTy() so far only return scalar type. As a
result, backend logic assuming that breaks.
- Rename the original TLI.getShiftAmountTy() to
TLI.getScalarShiftAmountTy() and re-define TLI.getShiftAmountTy() to
return target-specificed scalar type or the same vector type as the
1st operand.
- Fix most TICG logic assuming TLI.getShiftAmountTy() a simple scalar
type.
llvm-svn: 176364
fewer scalar integer (i32 or i64) arguments. It completely eliminates the need
for SDISel for trivial functions.
Also, add the new llc -fast-isel-abort-args option, which is similar to
-fast-isel-abort option, but for formal argument lowering.
llvm-svn: 176052
to TargetFrameLowering, where it belongs. Incidentally, this allows us
to delete some duplicated (and slightly different!) code in TRI.
There are potentially other layering problems that can be cleaned up
as a result, or in a similar manner.
The refactoring was OK'd by Anton Korobeynikov on llvmdev.
Note: this touches the target interfaces, so out-of-tree targets may
be affected.
llvm-svn: 175788
exists solely to enable it to call itself for i8 with some registers.
The proposed patch simplifies the function somewhat to make the High
bit only meaningful for the i8 mode, which makes sense. No functional
difference (getX86SubSuperRegister is not getting called from anywhere
outside with i64 and High=true).
llvm-svn: 175762
sext <4 x i1> to <4 x i64>
sext <4 x i8> to <4 x i64>
sext <4 x i16> to <4 x i64>
I'm running Combine on SIGN_EXTEND_IN_REG and revert SEXT patterns:
(sext_in_reg (v4i64 anyext (v4i32 x )), ExtraVT) -> (v4i64 sext (v4i32 sext_in_reg (v4i32 x , ExtraVT)))
The sext_in_reg (v4i32 x) may be lowered to shl+sar operations.
The "sar" does not exist on 64-bit operation, so lowering sext_in_reg (v4i64 x) has no vector solution.
I also added a cost of this operations to the AVX costs table.
llvm-svn: 175619
MS-style inline assembly.
This is a follow-on to r175334. Forcing a FP to be emitted doesn't ensure it
will be used. Therefore, force the base pointer as well. We now treat MS
inline assembly in the same way we treat functions with dynamic stack
realignment and VLAs. This guarantees the BP will be used to reference
parameters and locals.
rdar://13218191
llvm-svn: 175576
If the frame pointer is omitted, and any stack changes occur in the inline
assembly, e.g.: "pusha", then any C local variable or C argument references
will be incorrect.
I pass no judgement on anyone who would do such a thing. ;)
rdar://13218191
llvm-svn: 175334
If two functions require different features (e.g., `-mno-sse' vs. `-msse') then
we want to honor that, especially during LTO. We can do that by resetting the
subtarget's features depending upon the 'target-feature' attribute.
llvm-svn: 175314
blocks. We still don't have consensus if we should try to change clang or
the standard, but llvm should work with compilers that implement the current
standard and mangle those functions.
llvm-svn: 175267
Preston Gurd