2006-09-04 12:14:57 +08:00
|
|
|
//===-- PPC.h - Top-level interface for PowerPC Target ----------*- C++ -*-===//
|
2005-04-22 07:30:14 +08:00
|
|
|
//
|
2004-06-22 00:55:25 +08:00
|
|
|
// The LLVM Compiler Infrastructure
|
|
|
|
//
|
2007-12-30 04:36:04 +08:00
|
|
|
// This file is distributed under the University of Illinois Open Source
|
|
|
|
// License. See LICENSE.TXT for details.
|
2005-04-22 07:30:14 +08:00
|
|
|
//
|
2004-06-22 00:55:25 +08:00
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//
|
|
|
|
// This file contains the entry points for global functions defined in the LLVM
|
|
|
|
// PowerPC back-end.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
2014-08-14 00:26:38 +08:00
|
|
|
#ifndef LLVM_LIB_TARGET_POWERPC_PPC_H
|
|
|
|
#define LLVM_LIB_TARGET_POWERPC_PPC_H
|
2004-06-22 00:55:25 +08:00
|
|
|
|
2011-07-15 04:59:42 +08:00
|
|
|
#include "MCTargetDesc/PPCMCTargetDesc.h"
|
2010-11-15 16:49:58 +08:00
|
|
|
#include <string>
|
|
|
|
|
2006-11-04 13:27:39 +08:00
|
|
|
// GCC #defines PPC on Linux but we use it as our namespace name
|
|
|
|
#undef PPC
|
2006-08-24 05:08:52 +08:00
|
|
|
|
2006-11-04 13:27:39 +08:00
|
|
|
namespace llvm {
|
|
|
|
class PPCTargetMachine;
|
[PowerPC] Select between VSX A-type and M-type FMA instructions just before RA
The VSX instruction set has two types of FMA instructions: A-type (where the
addend is taken from the output register) and M-type (where one of the product
operands is taken from the output register). This adds a small pass that runs
just after MI scheduling (and, thus, just before register allocation) that
mutates A-type instructions (that are created during isel) into M-type
instructions when:
1. This will eliminate an otherwise-necessary copy of the addend
2. One of the product operands is killed by the instruction
The "right" moment to make this decision is in between scheduling and register
allocation, because only there do we know whether or not one of the product
operands is killed by any particular instruction. Unfortunately, this also
makes the implementation somewhat complicated, because the MIs are not in SSA
form and we need to preserve the LiveIntervals analysis.
As a simple example, if we have:
%vreg5<def> = COPY %vreg9; VSLRC:%vreg5,%vreg9
%vreg5<def,tied1> = XSMADDADP %vreg5<tied0>, %vreg17, %vreg16,
%RM<imp-use>; VSLRC:%vreg5,%vreg17,%vreg16
...
%vreg9<def,tied1> = XSMADDADP %vreg9<tied0>, %vreg17, %vreg19,
%RM<imp-use>; VSLRC:%vreg9,%vreg17,%vreg19
...
We can eliminate the copy by changing from the A-type to the
M-type instruction. This means:
%vreg5<def,tied1> = XSMADDADP %vreg5<tied0>, %vreg17, %vreg16,
%RM<imp-use>; VSLRC:%vreg5,%vreg17,%vreg16
is replaced by:
%vreg16<def,tied1> = XSMADDMDP %vreg16<tied0>, %vreg18, %vreg9,
%RM<imp-use>; VSLRC:%vreg16,%vreg18,%vreg9
and we remove: %vreg5<def> = COPY %vreg9; VSLRC:%vreg5,%vreg9
llvm-svn: 204768
2014-03-26 07:29:21 +08:00
|
|
|
class PassRegistry;
|
2006-11-04 13:27:39 +08:00
|
|
|
class FunctionPass;
|
2013-01-26 07:05:59 +08:00
|
|
|
class ImmutablePass;
|
2010-11-15 05:12:33 +08:00
|
|
|
class MachineInstr;
|
|
|
|
class AsmPrinter;
|
Implement a basic MCCodeEmitter for PPC. This doesn't handle
fixups yet, and doesn't handle actually encoding operand values,
but this is enough for llc -show-mc-encoding to show the base
instruction encoding information, e.g.:
mflr r0 ; encoding: [0x7c,0x08,0x02,0xa6]
stw r0, 8(r1) ; encoding: [0x90,0x00,0x00,0x00]
stwu r1, -64(r1) ; encoding: [0x94,0x00,0x00,0x00]
Ltmp0:
lhz r4, 4(r3) ; encoding: [0xa0,0x00,0x00,0x00]
cmplwi cr0, r4, 8 ; encoding: [0x28,0x00,0x00,0x00]
beq cr0, LBB0_2 ; encoding: [0x40,0x00,0x00,0x00]
llvm-svn: 119116
2010-11-15 12:16:32 +08:00
|
|
|
class MCInst;
|
2012-03-18 02:46:09 +08:00
|
|
|
|
Implement PPC counter loops as a late IR-level pass
The old PPCCTRLoops pass, like the Hexagon pass version from which it was
derived, could only handle some simple loops in canonical form. We cannot
directly adapt the new Hexagon hardware loops pass, however, because the
Hexagon pass contains a fundamental assumption that non-constant-trip-count
loops will contain a guard, and this is not always true (the result being that
incorrect negative counts can be generated). With this commit, we replace the
pass with a late IR-level pass which makes use of SE to calculate the
backedge-taken counts and safely generate the loop-count expressions (including
any necessary max() parts). This IR level pass inserts custom intrinsics that
are lowered into the desired decrement-and-branch instructions.
The most fragile part of this new implementation is that interfering uses of
the counter register must be detected on the IR level (and, on PPC, this also
includes any indirect branches in addition to function calls). Also, to make
all of this work, we need a variant of the mtctr instruction that is marked
as having side effects. Without this, machine-code level CSE, DCE, etc.
illegally transform the resulting code. Hopefully, this can be improved
in the future.
This new pass is smaller than the original (and much smaller than the new
Hexagon hardware loops pass), and can handle many additional cases correctly.
In addition, the preheader-creation code has been copied from LoopSimplify, and
after we decide on where it belongs, this code will be refactored so that it
can be explicitly shared (making this implementation even smaller).
The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for
the new Hexagon pass. There are a few classes of loops that this pass does not
transform (noted by FIXMEs in the files), but these deficiencies can be
addressed within the SE infrastructure (thus helping many other passes as well).
llvm-svn: 181927
2013-05-16 05:37:41 +08:00
|
|
|
FunctionPass *createPPCCTRLoops(PPCTargetMachine &TM);
|
Add a PPCCTRLoops verification pass
When asserts are enabled, this adds a verification pass for PPC counter-loop
formation. Unfortunately, without sacrificing code quality, there is no better
way of forming counter-based loops except at the (late) IR level. This means
that we need to recognize, at the IR level, anything which might turn into a
function call (or indirect branch). Because this is currently a finite set of
things, and because SelectionDAG lowering is basic-block local, this can be
done. Nevertheless, it is fragile, and failure results in a miscompile. This
verification pass checks that all (reachable) counter-based branches are
dominated by a loop mtctr instruction, and that no instructions in between
clobber the counter register. If these conditions are not satisfied, then an
ICE will be triggered.
In short, this is to help us sleep better at night.
llvm-svn: 182295
2013-05-21 00:08:17 +08:00
|
|
|
#ifndef NDEBUG
|
|
|
|
FunctionPass *createPPCCTRLoopsVerify();
|
|
|
|
#endif
|
[PowerPC] Loop Data Prefetching for the BG/Q
The IBM BG/Q supercomputer's A2 cores have a hardware prefetching unit, the
L1P, but it does not prefetch directly into the A2's L1 cache. Instead, it
prefetches into its own L1P buffer, and the latency to access that buffer is
significantly higher than that to the L1 cache (although smaller than the
latency to the L2 cache). As a result, especially when multiple hardware
threads are not actively busy, explicitly prefetching data into the L1 cache is
advantageous.
I've been using this pass out-of-tree for data prefetching on the BG/Q for well
over a year, and it has worked quite well. It is enabled by default only for
the BG/Q, but can be enabled for other cores as well via a command-line option.
Eventually, we might want to add some TTI interfaces and move this into
Transforms/Scalar (there is nothing particularly target dependent about it,
although only machines like the BG/Q will benefit from its simplistic
strategy).
llvm-svn: 229966
2015-02-20 13:08:21 +08:00
|
|
|
FunctionPass *createPPCLoopDataPrefetchPass();
|
[PowerPC] Prepare loops for pre-increment loads/stores
PowerPC supports pre-increment load/store instructions (except for Altivec/VSX
vector load/stores). Using these on embedded cores can be very important, but
most loops are not naturally set up to use them. We can often change that,
however, by placing loops into a non-canonical form. Generically, this means
transforming loops like this:
for (int i = 0; i < n; ++i)
array[i] = c;
to look like this:
T *p = array[-1];
for (int i = 0; i < n; ++i)
*++p = c;
the key point is that addresses accessed are pulled into dedicated PHIs and
"pre-decremented" in the loop preheader. This allows the use of pre-increment
load/store instructions without loop peeling.
A target-specific late IR-level pass (running post-LSR), PPCLoopPreIncPrep, is
introduced to perform this transformation. I've used this code out-of-tree for
generating code for the PPC A2 for over a year. Somewhat to my surprise,
running the test suite + externals on a P7 with this transformation enabled
showed no performance regressions, and one speedup:
External/SPEC/CINT2006/483.xalancbmk/483.xalancbmk
-2.32514% +/- 1.03736%
So I'm going to enable it on everything for now. I was surprised by this
because, on the POWER cores, these pre-increment load/store instructions are
cracked (and, thus, harder to schedule effectively). But seeing no regressions,
and feeling that it is generally easier to split instructions apart late than
it is to combine them late, this might be the better approach regardless.
In the future, we might want to integrate this functionality into LSR (but
currently LSR does not create new PHI nodes, so (for that and other reasons)
significant work would need to be done).
llvm-svn: 228328
2015-02-06 02:43:00 +08:00
|
|
|
FunctionPass *createPPCLoopPreIncPrepPass(PPCTargetMachine &TM);
|
[PowerPC] Add extra r2 read deps on @toc@l relocations
If some commits are happy, and some commits are sad, this is a sad commit. It
is sad because it restricts instruction scheduling to work around a binutils
linker bug, and moreover, one that may never be fixed. On 2012-05-21, GCC was
updated not to produce code triggering this bug, and now we'll do the same...
When resolving an address using the ELF ABI TOC pointer, two relocations are
generally required: one for the high part and one for the low part. Only
the high part generally explicitly depends on r2 (the TOC pointer). And, so,
we might produce code like this:
.Ltmp526:
addis 3, 2, .LC12@toc@ha
.Ltmp1628:
std 2, 40(1)
ld 5, 0(27)
ld 2, 8(27)
ld 11, 16(27)
ld 3, .LC12@toc@l(3)
rldicl 4, 4, 0, 32
mtctr 5
bctrl
ld 2, 40(1)
And there is nothing wrong with this code, as such, but there is a linker bug
in binutils (https://sourceware.org/bugzilla/show_bug.cgi?id=18414) that will
misoptimize this code sequence to this:
nop
std r2,40(r1)
ld r5,0(r27)
ld r2,8(r27)
ld r11,16(r27)
ld r3,-32472(r2)
clrldi r4,r4,32
mtctr r5
bctrl
ld r2,40(r1)
because the linker does not know (and does not check) that the value in r2
changed in between the instruction using the .LC12@toc@ha (TOC-relative)
relocation and the instruction using the .LC12@toc@l(3) relocation.
Because it finds these instructions using the relocations (and not by
scanning the instructions), it has been asserted that there is no good way
to detect the change of r2 in between. As a result, this bug may never be
fixed (i.e. it may become part of the definition of the ABI). GCC was
updated to add extra dependencies on r2 to instructions using the @toc@l
relocations to avoid this problem, and we'll do the same here.
This is done as a separate pass because:
1. These extra r2 dependencies are not really properties of the
instructions, but rather due to a linker bug, and maybe one day we'll be
able to get rid of them when targeting linkers without this bug (and,
thus, keeping the logic centralized here will make that
straightforward).
2. There are ISel-level peephole optimizations that propagate the @toc@l
relocations to some user instructions, and so the exta dependencies do
not apply only to a fixed set of instructions (without undesirable
definition replication).
The test case was reduced with the help of bugpoint, with minimal cleaning. I'm
looking forward to our upcoming MI serialization support, and with that, much
better tests can be created.
llvm-svn: 237556
2015-05-18 14:25:59 +08:00
|
|
|
FunctionPass *createPPCTOCRegDepsPass();
|
2013-04-09 00:24:03 +08:00
|
|
|
FunctionPass *createPPCEarlyReturnPass();
|
[PowerPC] Initial support for the VSX instruction set
VSX is an ISA extension supported on the POWER7 and later cores that enhances
floating-point vector and scalar capabilities. Among other things, this adds
<2 x double> support and generally helps to reduce register pressure.
The interesting part of this ISA feature is the register configuration: there
are 64 new 128-bit vector registers, the 32 of which are super-registers of the
existing 32 scalar floating-point registers, and the second 32 of which overlap
with the 32 Altivec vector registers. This makes things like vector insertion
and extraction tricky: this can be free but only if we force a restriction to
the right register subclass when needed. A new "minipass" PPCVSXCopy takes care
of this (although it could do a more-optimal job of it; see the comment about
unnecessary copies below).
Please note that, currently, VSX is not enabled by default when targeting
anything because it is not yet ready for that. The assembler and disassembler
are fully implemented and tested. However:
- CodeGen support causes miscompiles; test-suite runtime failures:
MultiSource/Benchmarks/FreeBench/distray/distray
MultiSource/Benchmarks/McCat/08-main/main
MultiSource/Benchmarks/Olden/voronoi/voronoi
MultiSource/Benchmarks/mafft/pairlocalalign
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
SingleSource/Benchmarks/CoyoteBench/almabench
SingleSource/Benchmarks/Misc/matmul_f64_4x4
- The lowering currently falls back to using Altivec instructions far more
than it should. Worse, there are some things that are scalarized through the
stack that shouldn't be.
- A lot of unnecessary copies make it past the optimizers, and this needs to
be fixed.
- Many more regression tests are needed.
Normally, I'd fix these things prior to committing, but there are some
students and other contributors who would like to work this, and so it makes
sense to move this development process upstream where it can be subject to the
regular code-review procedures.
llvm-svn: 203768
2014-03-13 15:58:58 +08:00
|
|
|
FunctionPass *createPPCVSXCopyPass();
|
[PowerPC] Select between VSX A-type and M-type FMA instructions just before RA
The VSX instruction set has two types of FMA instructions: A-type (where the
addend is taken from the output register) and M-type (where one of the product
operands is taken from the output register). This adds a small pass that runs
just after MI scheduling (and, thus, just before register allocation) that
mutates A-type instructions (that are created during isel) into M-type
instructions when:
1. This will eliminate an otherwise-necessary copy of the addend
2. One of the product operands is killed by the instruction
The "right" moment to make this decision is in between scheduling and register
allocation, because only there do we know whether or not one of the product
operands is killed by any particular instruction. Unfortunately, this also
makes the implementation somewhat complicated, because the MIs are not in SSA
form and we need to preserve the LiveIntervals analysis.
As a simple example, if we have:
%vreg5<def> = COPY %vreg9; VSLRC:%vreg5,%vreg9
%vreg5<def,tied1> = XSMADDADP %vreg5<tied0>, %vreg17, %vreg16,
%RM<imp-use>; VSLRC:%vreg5,%vreg17,%vreg16
...
%vreg9<def,tied1> = XSMADDADP %vreg9<tied0>, %vreg17, %vreg19,
%RM<imp-use>; VSLRC:%vreg9,%vreg17,%vreg19
...
We can eliminate the copy by changing from the A-type to the
M-type instruction. This means:
%vreg5<def,tied1> = XSMADDADP %vreg5<tied0>, %vreg17, %vreg16,
%RM<imp-use>; VSLRC:%vreg5,%vreg17,%vreg16
is replaced by:
%vreg16<def,tied1> = XSMADDMDP %vreg16<tied0>, %vreg18, %vreg9,
%RM<imp-use>; VSLRC:%vreg16,%vreg18,%vreg9
and we remove: %vreg5<def> = COPY %vreg9; VSLRC:%vreg5,%vreg9
llvm-svn: 204768
2014-03-26 07:29:21 +08:00
|
|
|
FunctionPass *createPPCVSXFMAMutatePass();
|
[PPC64LE] Remove unnecessary swaps from lane-insensitive vector computations
This patch adds a new SSA MI pass that runs on little-endian PPC64
code with VSX enabled. Loads and stores of 4x32 and 2x64 vectors
without alignment constraints are accomplished for little-endian using
lxvd2x/xxswapd and xxswapd/stxvd2x. The existence of the additional
xxswapd instructions hurts performance in comparison with big-endian
code, but they are necessary in the general case to support correct
semantics.
However, the general case does not apply to most vector code. Many
vector instructions are lane-insensitive; they do not "care" which
lanes the parallel computations are performed within, provided that
the resulting data is stored into the correct locations. Thus this
pass looks for computations that perform only lane-insensitive
operations, and remove the unnecessary swaps from loads and stores in
such computations.
Future improvements will allow computations using certain
lane-sensitive operations to also be optimized in this manner, by
modifying the lane-sensitive operations to account for the permuted
order of the lanes. However, this patch only adds the infrastructure
to permit this; no lane-sensitive operations are optimized at this
time.
This code is heavily exercised by the various vectorizing applications
in the projects/test-suite tree. For the time being, I have only added
one simple test case to demonstrate what the pass is doing. Although
it is quite simple, it provides coverage for much of the code,
including the special case handling of copies and subreg-to-reg
operations feeding the swaps. I plan to add additional tests in the
future as I fill in more of the "special handling" code.
Two existing tests were affected, because they expected the swaps to
be present, but they are now removed.
llvm-svn: 235910
2015-04-28 03:57:34 +08:00
|
|
|
FunctionPass *createPPCVSXSwapRemovalPass();
|
2010-11-15 11:13:19 +08:00
|
|
|
FunctionPass *createPPCBranchSelectionPass();
|
|
|
|
FunctionPass *createPPCISelDag(PPCTargetMachine &TM);
|
2015-02-11 03:09:05 +08:00
|
|
|
FunctionPass *createPPCTLSDynamicCallPass();
|
2010-11-15 11:13:19 +08:00
|
|
|
void LowerPPCMachineInstrToMCInst(const MachineInstr *MI, MCInst &OutMI,
|
[PowerPC] Always use "assembler dialect" 1
A setting in MCAsmInfo defines the "assembler dialect" to use. This is used
by common code to choose between alternatives in a multi-alternative GNU
inline asm statement like the following:
__asm__ ("{sfe|subfe} %0,%1,%2" : "=r" (out) : "r" (in1), "r" (in2));
The meaning of these dialects is platform specific, and GCC defines those
for PowerPC to use dialect 0 for old-style (POWER) mnemonics and 1 for
new-style (PowerPC) mnemonics, like in the example above.
To be compatible with inline asm used with GCC, LLVM ought to do the same.
Specifically, this means we should always use assembler dialect 1 since
old-style mnemonics really aren't supported on any current platform.
However, the current LLVM back-end uses:
AssemblerDialect = 1; // New-Style mnemonics.
in PPCMCAsmInfoDarwin, and
AssemblerDialect = 0; // Old-Style mnemonics.
in PPCLinuxMCAsmInfo.
The Linux setting really isn't correct, we should be using new-style
mnemonics everywhere. This is changed by this commit.
Unfortunately, the setting of this variable is overloaded in the back-end
to decide whether or not we are on a Darwin target. This is done in
PPCInstPrinter (the "SyntaxVariant" is initialized from the MCAsmInfo
AssemblerDialect setting), and also in PPCMCExpr. Setting AssemblerDialect
to 1 for both Darwin and Linux no longer allows us to make this distinction.
Instead, this patch uses the MCSubtargetInfo passed to createPPCMCInstPrinter
to distinguish Darwin targets, and ignores the SyntaxVariant parameter.
As to PPCMCExpr, this patch adds an explicit isDarwin argument that needs
to be passed in by the caller when creating a target MCExpr. (To do so
this patch implicitly also reverts commit 184441.)
llvm-svn: 185858
2013-07-09 04:20:51 +08:00
|
|
|
AsmPrinter &AP, bool isDarwin);
|
2013-01-26 07:05:59 +08:00
|
|
|
|
[PowerPC] Select between VSX A-type and M-type FMA instructions just before RA
The VSX instruction set has two types of FMA instructions: A-type (where the
addend is taken from the output register) and M-type (where one of the product
operands is taken from the output register). This adds a small pass that runs
just after MI scheduling (and, thus, just before register allocation) that
mutates A-type instructions (that are created during isel) into M-type
instructions when:
1. This will eliminate an otherwise-necessary copy of the addend
2. One of the product operands is killed by the instruction
The "right" moment to make this decision is in between scheduling and register
allocation, because only there do we know whether or not one of the product
operands is killed by any particular instruction. Unfortunately, this also
makes the implementation somewhat complicated, because the MIs are not in SSA
form and we need to preserve the LiveIntervals analysis.
As a simple example, if we have:
%vreg5<def> = COPY %vreg9; VSLRC:%vreg5,%vreg9
%vreg5<def,tied1> = XSMADDADP %vreg5<tied0>, %vreg17, %vreg16,
%RM<imp-use>; VSLRC:%vreg5,%vreg17,%vreg16
...
%vreg9<def,tied1> = XSMADDADP %vreg9<tied0>, %vreg17, %vreg19,
%RM<imp-use>; VSLRC:%vreg9,%vreg17,%vreg19
...
We can eliminate the copy by changing from the A-type to the
M-type instruction. This means:
%vreg5<def,tied1> = XSMADDADP %vreg5<tied0>, %vreg17, %vreg16,
%RM<imp-use>; VSLRC:%vreg5,%vreg17,%vreg16
is replaced by:
%vreg16<def,tied1> = XSMADDMDP %vreg16<tied0>, %vreg18, %vreg9,
%RM<imp-use>; VSLRC:%vreg16,%vreg18,%vreg9
and we remove: %vreg5<def> = COPY %vreg9; VSLRC:%vreg5,%vreg9
llvm-svn: 204768
2014-03-26 07:29:21 +08:00
|
|
|
void initializePPCVSXFMAMutatePass(PassRegistry&);
|
|
|
|
extern char &PPCVSXFMAMutateID;
|
|
|
|
|
2010-11-15 07:42:06 +08:00
|
|
|
namespace PPCII {
|
|
|
|
|
|
|
|
/// Target Operand Flag enum.
|
|
|
|
enum TOF {
|
|
|
|
//===------------------------------------------------------------------===//
|
|
|
|
// PPC Specific MachineOperand flags.
|
|
|
|
MO_NO_FLAG,
|
|
|
|
|
2014-07-19 07:29:49 +08:00
|
|
|
/// MO_PLT_OR_STUB - On a symbol operand "FOO", this indicates that the
|
|
|
|
/// reference is actually to the "FOO$stub" or "FOO@plt" symbol. This is
|
|
|
|
/// used for calls and jumps to external functions on Tiger and earlier, and
|
|
|
|
/// for PIC calls on Linux and ELF systems.
|
|
|
|
MO_PLT_OR_STUB = 1,
|
2010-11-15 07:42:06 +08:00
|
|
|
|
2010-11-15 11:13:19 +08:00
|
|
|
/// MO_PIC_FLAG - If this bit is set, the symbol reference is relative to
|
|
|
|
/// the function's picbase, e.g. lo16(symbol-picbase).
|
2013-02-21 08:05:29 +08:00
|
|
|
MO_PIC_FLAG = 2,
|
2010-11-15 10:46:57 +08:00
|
|
|
|
2010-11-15 11:13:19 +08:00
|
|
|
/// MO_NLP_FLAG - If this bit is set, the symbol reference is actually to
|
|
|
|
/// the non_lazy_ptr for the global, e.g. lo16(symbol$non_lazy_ptr-picbase).
|
2013-02-21 08:05:29 +08:00
|
|
|
MO_NLP_FLAG = 4,
|
2010-11-15 10:46:57 +08:00
|
|
|
|
2010-11-15 11:13:19 +08:00
|
|
|
/// MO_NLP_HIDDEN_FLAG - If this bit is set, the symbol reference is to a
|
|
|
|
/// symbol with hidden visibility. This causes a different kind of
|
|
|
|
/// non-lazy-pointer to be generated.
|
2013-02-21 08:05:29 +08:00
|
|
|
MO_NLP_HIDDEN_FLAG = 8,
|
2012-06-05 01:36:38 +08:00
|
|
|
|
|
|
|
/// The next are not flags but distinct values.
|
2013-02-21 08:05:29 +08:00
|
|
|
MO_ACCESS_MASK = 0xf0,
|
2012-06-05 01:36:38 +08:00
|
|
|
|
2013-06-21 22:42:20 +08:00
|
|
|
/// MO_LO, MO_HA - lo16(symbol) and ha16(symbol)
|
|
|
|
MO_LO = 1 << 4,
|
|
|
|
MO_HA = 2 << 4,
|
2012-06-05 01:36:38 +08:00
|
|
|
|
2013-06-21 22:42:20 +08:00
|
|
|
MO_TPREL_LO = 4 << 4,
|
|
|
|
MO_TPREL_HA = 3 << 4,
|
2013-02-21 08:05:29 +08:00
|
|
|
|
|
|
|
/// These values identify relocations on immediates folded
|
|
|
|
/// into memory operations.
|
2013-06-21 22:42:20 +08:00
|
|
|
MO_DTPREL_LO = 5 << 4,
|
|
|
|
MO_TLSLD_LO = 6 << 4,
|
2013-07-05 20:22:36 +08:00
|
|
|
MO_TOC_LO = 7 << 4,
|
|
|
|
|
|
|
|
// Symbol for VK_PPC_TLS fixup attached to an ADD instruction
|
2015-02-11 03:09:05 +08:00
|
|
|
MO_TLS = 8 << 4
|
2010-11-15 07:42:06 +08:00
|
|
|
};
|
|
|
|
} // end namespace PPCII
|
|
|
|
|
2015-06-19 23:57:42 +08:00
|
|
|
} // namespace llvm
|
2004-06-22 00:55:25 +08:00
|
|
|
|
|
|
|
#endif
|