Refactor CmpHelper into something simpler. It was overkill to use
templates for this - instead, use a simple CmpConstants structure to
hold the opcodes and other constants that are different when selecting
int / float / double comparisons. Also, extract some of the helpers that
were in CmpHelper into ARMInstructionSelector and make use of some of
them when selecting other things than just compares.
llvm-svn: 307766
The issue is not if the value is pcrel. It is whether we have a
relocation or not.
If we have a relocation, the static linker will select the upper
bits. If we don't have a relocation, we have to do it.
llvm-svn: 307730
OpenCL 2.0 introduces the notion of memory scopes in atomic operations to
global and local memory. These scopes restrict how synchronization is
achieved, which can result in improved performance.
This change extends existing notion of synchronization scopes in LLVM to
support arbitrary scopes expressed as target-specific strings, in addition to
the already defined scopes (single thread, system).
The LLVM IR and MIR syntax for expressing synchronization scopes has changed
to use *syncscope("<scope>")*, where <scope> can be "singlethread" (this
replaces *singlethread* keyword), or a target-specific name. As before, if
the scope is not specified, it defaults to CrossThread/System scope.
Implementation details:
- Mapping from synchronization scope name/string to synchronization scope id
is stored in LLVM context;
- CrossThread/System and SingleThread scopes are pre-defined to efficiently
check for known scopes without comparing strings;
- Synchronization scope names are stored in SYNC_SCOPE_NAMES_BLOCK in
the bitcode.
Differential Revision: https://reviews.llvm.org/D21723
llvm-svn: 307722
This patch implements the .module and .set directives for the MT ASE,
notably that .module sets the relevant flags in .MIPS.abiflags and .set
doesn't.
Reviewers: slthakur, atanasyan
Differential Revision: https://reviews.llvm.org/D35249
llvm-svn: 307716
For ELF, a movw+movt pair is handled as two separate relocations.
If an offset should be applied to the symbol address, this offset is
stored as an immediate in the instruction (as opposed to stored as an
offset in the relocation itself).
Even though the actual value stored in the movt immediate after linking
is the top half of the value, we need to store the unshifted offset
prior to linking. When the relocation is made during linking, the offset
gets added to the target symbol value, and the upper half of the value
is stored in the instruction.
This makes sure that movw+movt with offset symbols get properly
handled, in case the offset addition in the lower half should be
carried over to the upper half.
This makes the output from the additions to the test case match
the output from GNU binutils.
For COFF and MachO, the movw/movt relocations are handled as a pair,
and the overflow from the lower half gets carried over to the movt,
so they should keep the shifted offset just as before.
Differential Revision: https://reviews.llvm.org/D35242
llvm-svn: 307713
Preparatory work for adding the MIPS MT (multi-threading) ASE instructions.
Reviewers: slthakur, atanasyan
Differential Revision: https://reviews.llvm.org/D35247
llvm-svn: 307679
1. The available program storage region of the red zone to compilers is 288
bytes rather than 244 bytes.
2. The formula for negative number alignment calculation should be
y = x & ~(n-1) rather than y = (x + (n-1)) & ~(n-1).
Differential Revision: https://reviews.llvm.org/D34337
llvm-svn: 307672
This change allows the pc to be used as a destination register for the
pseudo instruction LDR pc,=expression . The pseudo instruction must not be
transformed into a MOV, but it can use the Thumb2 LDR (literal) instruction
to a constant pool entry. See (A7.7.43 from ARMv7M ARM ARM).
Differential Revision: https://reviews.llvm.org/D34751
llvm-svn: 307640
We used to forget to erase the original instruction when replacing a
G_FCMP true/false. Fix this bug and make sure the tests check for it.
llvm-svn: 307639
TreePatternNode considers them to be plain integers but MachineInstr considers
them to be a distinct kind of operand.
The tweak to AArch64InstrInfo.td to produce a simple test case is a NFC for
everything except GlobalISelEmitter (confirmed by diffing the tablegenerated
files). GlobalISelEmitter is currently unable to infer the type of operands in
the Dst pattern from the operands in the Src pattern.
llvm-svn: 307634
In the POWER9 instruction scheduler, SchedWriteRes for the simple integer instructions are misconfigured to use that of (costly) DFU instructions.
This results in surprisingly long instruction latency estimation and causes misbehavior in some optimizers such as if-conversion.
Differential Revision: https://reviews.llvm.org/D34869
llvm-svn: 307624
This patch reduces compilation time by avoiding redundant analysis while selecting instructions to create an immediate.
If the instruction count required to create the input number without rotate is 2, we do not need further analysis to find a shorter instruction sequence with rotate; rotate + load constant cannot be done by 1 instruction (i.e. getInt64CountDirectnever return 0).
This patch should not change functionality.
Differential Revision: https://reviews.llvm.org/D34986
llvm-svn: 307623
An instruction that has an immediate operand can't reach
this point. This is only called for a freshly shrunk instruction,
which prevously couldn't have had a literal constant operand.
This was also not conservative enough since it woudl also have
had to filter other constant-like inputs like frame indexes.
llvm-svn: 307574
For this example:
float test (int *arr) {
return arr[2];
}
We currently generate the following code:
li r4, 8
lxsiwax f0, r3, r4
xscvsxdsp f1, f0
With this patch, we will now generate:
addi r3, r3, 8
lxsiwax f0, 0, r3
xscvsxdsp f1, f0
Originally reported in: https://bugs.llvm.org/show_bug.cgi?id=27204
Differential Revision: https://reviews.llvm.org/D35027
llvm-svn: 307553
The SandyBridge architects have provided us with a more accurate information about each instruction latency, number of uOPs and used ports and I used it to replace the existing estimated SNB instructions scheduling and to add missing scheduling information.
Please note that the patch extensively affects the X86 MC instr scheduling for SNB.
Also note that this patch will be followed by additional patches for the remaining target architectures HSW, IVB, BDW, SKL and SKX.
The updated and extended information about each instruction includes the following details:
•static latency of the instruction
•number of uOps from which the instruction consists of
•all ports used by the instruction's' uOPs
For example, the following code dictates that instructions, ADC64mr, ADC8mr, SBB64mr, SBB8mr have a static latency of 9 cycles. Each of these instructions is decoded into 6 micro operations which use ports 4, ports 2 or 3 and port 0 and ports 0 or 1 or 5:
def SBWriteResGroup94 : SchedWriteRes<[SBPort4,SBPort23,SBPort0,SBPort015]> {
let Latency = 9;
let NumMicroOps = 6;
let ResourceCycles = [1,2,2,1];
}
def: InstRW<[SBWriteResGroup94], (instregex "ADC64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "ADC8mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB8mr")>;
Note that apart for the header, most of the X86SchedSandyBridge.td file was generated by a script.
Reviewers: zvi, chandlerc, RKSimon, m_zuckerman, craig.topper, igorb
Differential Revision: https://reviews.llvm.org/D35019#inline-304691
llvm-svn: 307529
Summary:
Mark G_ZEXT/G_SEXT i1 to i8/i16, i8 to i16 as legal.
Support G_ZEXT i1 to i8/i16 instruction selection ( C++ code).
This patch requred to support G_LOAD/G_STORE i1.
Reviewers: zvi, guyblank
Reviewed By: guyblank
Subscribers: rovka, llvm-commits, kristof.beyls
Differential Revision: https://reviews.llvm.org/D35177
llvm-svn: 307526
GHC 8.4 will know how to use YMM and ZMM registers for calls.
Submitted on behalf of @bgamari (Ben Gamari)
Differential Revision: https://reviews.llvm.org/D34854
llvm-svn: 307504
Add breaks - doesn't affect results as both GPR/FPU both check for 32/64 bit sizes. So will still default to GenericOps in the same way.
llvm-svn: 307484
x86 scalar select-of-constants (Cond ? C1 : C2) combining/lowering is a mess
with missing optimizations. We handle some patterns, but miss logical variants.
To clean that up, we should convert all select-of-constants to logic/math and
enhance the combining for the expected patterns from that. Selecting 0 or -1
needs extra attention to produce the optimal code as shown here.
Attempt to verify that all of these IR forms are logically equivalent:
http://rise4fun.com/Alive/plxs
Earlier steps in this series:
rL306040
rL306072
rL307404 (D34652)
As acknowledged in the earlier review, there's a possibility that some Intel
uarch would prefer to produce an xor to clear the fake register operand with
sbb %eax, %eax. This will likely need to be addressed in a separate pass.
llvm-svn: 307471
r306334 fixed a bug in AArch64 dealing with wide interleaved accesses having
pointer types. The bug also exists in ARM, so this patch copies over the fix.
llvm-svn: 307409
x86 scalar select-of-constants (Cond ? C1 : C2) combining/lowering is a mess
with missing optimizations. We handle some patterns, but miss logical variants.
To clean that up, we should convert all select-of-constants to logic/math and
enhance the combining for the expected patterns from that. DAGCombiner already
has the foundation to allow the transforms, so we just need to fill in the holes
for x86 math op lowering. Selecting 0 or -1 needs extra attention to produce the
optimal code as shown here.
Attempt to verify that all of these IR forms are logically equivalent:
http://rise4fun.com/Alive/plxs
Earlier steps in this series:
rL306040
rL306072
Differential Revision: https://reviews.llvm.org/D34652
llvm-svn: 307404
Summary:
This change gives a 0.89% speed on execution time, a 0.94% improvement
in benchmark scores and a 0.62% increase in binary size on a Cortex-A57.
These numbers are the geomean results on a wide range of benchmarks from
the test-suite, SPEC2000, SPEC2006 and a range of proprietary suites.
The software optimization guide for the Cortex-A57 recommends 16 byte
branch alignment.
Reviewers: t.p.northover, mcrosier, javed.absar, kristof.beyls, sbaranga
Reviewed By: kristof.beyls
Subscribers: aemerson, rengolin, llvm-commits
Differential Revision: https://reviews.llvm.org/D34954
llvm-svn: 307389
Summary:
This change gives a 0.34% speed on execution time, a 0.61% improvement
in benchmark scores and a 0.57% increase in binary size on a Cortex-A72.
These numbers are the geomean results on a wide range of benchmarks from
the test-suite, SPEC2000, SPEC2006 and a range of proprietary suites.
The software optimization guide for the Cortex-A72 recommends 16 byte
branch alignment.
Reviewers: t.p.northover, kristof.beyls, rengolin, sbaranga, mcrosier, javed.absar
Reviewed By: kristof.beyls
Subscribers: llvm-commits, aemerson
Differential Revision: https://reviews.llvm.org/D34961
llvm-svn: 307380
We lower to a sequence consisting of:
- MOVi 0 into a register
- VCMPS to do the actual comparison and set the VFP flags
- FMSTAT to move the flags out of the VFP unit
- MOVCCi to either use the "zero register" that we have previously set
with the MOVi, or move 1 into the result register, based on the values
of the flags
As was the case with soft-float, for some predicates (one, ueq) we
actually need two comparisons instead of just one. When that happens, we
generate two VCMPS-FMSTAT-MOVCCi sequences and chain them by means of
using the result of the first MOVCCi as the "zero register" for the
second one. This is a bit overkill, since one comparison followed by
two non-flag-setting conditional moves should be enough. In any case,
the backend manages to CSE one of the comparisons away so it doesn't
matter much.
Note that unlike SelectionDAG and FastISel, we always use VCMPS, and not
VCMPES. This makes the code a lot simpler, and it also seems correct
since the LLVM Lang Ref defines simple true/false returns if the
operands are QNaN's. For SNaN's, even VCMPS throws an Invalid Operand
exception, so they won't be slipping through unnoticed.
Implementation-wise, this introduces a template so we can share the same
code that we use for handling integer comparisons, since the only
differences are in the details (exact opcodes to be used etc). Hopefully
this will be easy to extend to s64 G_FCMP.
llvm-svn: 307365
Contrary to the stepForward()/stepBackward() method accumulate() doesn't
have a direction as defs, uses and clobbers all have the same effect.
Also improve the documentation comment.
llvm-svn: 307351
Adds loop expansions for known-size and unknown-sized memcpy calls, allowing the
target to provide the operand types through TTI callbacks. The default values
for the TTI callbacks use int8 operand types and matches the existing behaviour
if they aren't overridden by the target.
Differential revision: https://reviews.llvm.org/D32536
llvm-svn: 307346
The patch adds support of i128 params lowering. The changes are quite trivial to
support i128 as a "special case" of integer type. With this patch, we lower i128
params the same way as aggregates of size 16 bytes: .param .b8 _ [16].
Currently, NVPTX can't deal with the 128 bit integers:
* in some cases because of failed assertions like
ValVTs.size() == OutVals.size() && "Bad return value decomposition"
* in other cases emitting PTX with .i128 or .u128 types (which are not valid [1])
[1] http://docs.nvidia.com/cuda/parallel-thread-execution/index.html#fundamental-types
Differential Revision: https://reviews.llvm.org/D34555
Patch by: Denys Zariaiev (denys.zariaiev@gmail.com)
llvm-svn: 307326
This fixes calls to external functions starting with a capital L,
fixing errors like this:
fatal error: error in backend: assembler label 'LocalFree' can not be undefined
Differential Revision: https://reviews.llvm.org/D35079
llvm-svn: 307317
Regardless of relaxation options such as -cl-fast-relaxed-math
we are producing rather long code for fdiv via amdgcn_fdiv_fast
intrinsic. This intrinsic is used to replace fdiv with 2.5ulp
metadata and does not handle denormals, thus believed to be fast.
An fdiv instruction can also have fast math flag either by itself
or together with fpmath metadata. Clang used with a relaxation flag
always produces both metadata and fast flag:
%div = fdiv fast float %v, %0, !fpmath !12!12 = !{float 2.500000e+00}
Current implementation ignores fast flag and favors metadata. An
instruction with just fast flag would be lowered to a fastest rcp +
mul, but that never happen on practice because of described mutual
clang and BE behavior.
This change allows an "fdiv fast" to be always lowered as rcp + mul.
Differential Revision: https://reviews.llvm.org/D34844
llvm-svn: 307308
Allows the MachineIRBuilder APIs to directly create registers (based on
LLT or TargetRegisterClass) as well as accept MachineInstrBuilders
and implicitly converts to register(with getOperand(0).getReg()).
Eg usage:
LLT s32 = LLT::scalar(32);
auto C32 = Builder.buildConstant(s32, 32);
auto Tmp = Builder.buildInstr(TargetOpcode::G_SUB, s32, C32,
OtherReg);
auto Tmp2 = Builder.buildInstr(Opcode, DstReg,
Builder.buildConstant(s32, 31)); ....
Only a few methods added for now.
Reviewed by Tim
llvm-svn: 307302
Going through the Constant methods requires redetermining that the Constant is a ConstantInt and then calling isZero/isOne/isMinusOne.
llvm-svn: 307292
This covers both hard and soft float.
Hard float is easy, since it's just Legal.
Soft float is more involved, because there are several different ways to
handle it based on the predicate: one and ueq need not only one, but two
libcalls to get a result. Furthermore, we have large differences between
the values returned by the AEABI and GNU functions.
AEABI functions return a nice 1 or 0 representing true and respectively
false. GNU functions generally return a value that needs to be compared
against 0 (e.g. for ogt, the value returned by the libcall is > 0 for
true). We could introduce redundant comparisons for AEABI as well, but
they don't seem easy to remove afterwards, so we do different processing
based on whether or not the result really needs to be compared against
something (and just truncate if it doesn't).
llvm-svn: 307243
Simon Dardis