The method is called "get *Param* Alignment", and is only used for
return values exactly once, so it should take argument indices, not
attribute indices.
Avoids confusing code like:
IsSwiftError = CS->paramHasAttr(ArgIdx, Attribute::SwiftError);
Alignment = CS->getParamAlignment(ArgIdx + 1);
Add getRetAlignment to handle the one case in Value.cpp that wants the
return value alignment.
This is a potentially breaking change for out-of-tree backends that do
their own call lowering.
llvm-svn: 301682
Adds a new method finalizeLowering to TargetLoweringBase. This is in
preparation for an upcoming commit.
This function is meant for target specific adjustments to
MachineFrameInfo or register reservations.
Move the freezeRegisters() and the hasCopyImplyingStackAdjustment()
handling into the new function to prove the concept. As an added bonus
GlobalISel no longer missed the hasCopyImplyingStackAdjustment()
handling with this.
Differential Revision: https://reviews.llvm.org/D32621
llvm-svn: 301679
This patch replaces flush with a last ditch attempt at synchronizing
the section list with the linker script "AST".
The synchronization is a bit of a hack and should in time be avoided
by creating the AST earlier so that modifications can be made directly
to it instead of modifying the section list and synchronizing it back.
This is the main step for fixing
https://bugs.llvm.org/show_bug.cgi?id=32816. With this in place I
think the only missing thing would be to have processCommands assign
section indexes as dummy offsets so that the sort in
OutputSection::finalize works.
With this LinkerScript::assignAddresses becomes much simpler, which
should help with the thunk work.
llvm-svn: 301678
Summary:
When using ThinLTO, the linker performs its own parallelism. This
change limits the number of parallel link jobs that Ninja will issue
to keep the total number of threads reasonable when linking with
ThinLTO.
Reviewers: hans, ruiu
Subscribers: mgorny, mehdi_amini, Prazek
Differential Revision: https://reviews.llvm.org/D31990
llvm-svn: 301676
As has been reported in the previous commit, codegen verification can result in
quadratic compile time increases for large functions with many scops. This is
certainly not something we would like to have in the Polly default
configuration. Hence, we disable codegen verification by default -- also to see
if this resolves some of the compilation timeouts we currently see on the AOSP
buildbots. We still leave this feature in Polly as it has shown _very_ useful
for debugging. In fact, we may want to have a discussion if we can bring this
feature back in a way that does not impact compilation time so much.
Thanks to Eli Friedman <efriedma@codeaurora.org> for reporting this issue and
for providing the test case in the previous commit (where I forgot to
acknowledge him).
llvm-svn: 301670
Before this change, we always tried to verify the function and printed
verification errors, but just did not abort in case -polly-codegen-verify=false
was set and verification failed. As verification can become very cosly -- for
large functions with many scops we may verify the very same function very often
-- this can affect compile time very negatively. Hence, we respect the
-polly-codegen-verify flag with this check, ensuring that no verification is run
if -polly-codegen-verify=false.
This reduces code generation time from 26 seconds to 4 seconds on the test
case below with -polly-codegen-verify=false:
struct X { int x; };
void a();
#define SIG (int x, X **y, X **z)
typedef void (*fn)SIG;
#define FN { for (int i = 0; i < x; ++i) { (*y)[i].x += (*z)[i].x; } a(); }
#define FN5 FN FN FN FN FN
#define FN25 FN5 FN5 FN5 FN5
#define FN125 FN25 FN25 FN25 FN25 FN25
#define FN250 FN125 FN125
#define FN1250 FN250 FN250 FN250 FN250 FN250
void x SIG { FN1250 }
llvm-svn: 301669
creation that are const-qualified.
When a block captures an ObjC object pointer, clang retains the pointer
to prevent prematurely destroying the object the pointer points to
before the block is called or copied.
When the captured object pointer is const-qualified, we can avoid
emitting the retain/release pair since the pointer variable cannot be
modified in the scope in which the block literal is introduced.
For example:
void test(const id x) {
callee(^{ (void)x; });
}
This patch implements that optimization.
rdar://problem/28894510
Differential Revision: https://reviews.llvm.org/D32601
llvm-svn: 301667
This eliminates many extra 'Idx' induction variables in loops over
arguments in CodeGen/ and Target/. It also reduces the number of places
where we assume that ReturnIndex is 0 and that we should add one to
argument numbers to get the corresponding attribute list index.
NFC
llvm-svn: 301666
This became no longer necessary after D19462 landed, and will be incompatible
with an upcoming change to the summary data structures that changes how we
represent references.
llvm-svn: 301660
We found that some part of code for the -Map option takes O(m*n)
where m is the number of input sections in some file and n is
the number of symbols in the same file. If you do LTO, we usually
have only a few object files as inputs for the -Map option
feature, so this performance characteristic was worse than I
expected.
This patch rewrites the -Map option feature to speed it up.
I eliminated the O(m*n) bottleneck and also used multi-threading.
As a result, clang link time with the -Map option improved from
18.7 seconds to 11.2 seconds. Without -Map, it takes 7.7 seconds,
so the -Map option is now about 3x faster than before for this
test case (from 11.0 seconds to 3.5 seconds.) The generated output
file size was 223 MiB, and the file contains 1.2M lines.
Differential Revision: https://reviews.llvm.org/D32631
llvm-svn: 301659
CONSTANT imports expect both the `_imp_` prefixed and non-prefixed
symbols should be added to the symbol table. This allows for linking
symbols like _NSConcreteGlobalBlock in WinObjC. The previous change
would generate the import library properly by handling the option but
would not consume the generated entry properly.
llvm-svn: 301657
. swap 4-bit register encoding, 16-bit offset and 32-bit imm to support big endian archs
. add a test
Reported-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
llvm-svn: 301653
- I removed doxygen comments for the intrinsics that "alias" the other existing documented intrinsics and that only sligtly differ in spelling (single underscores vs. double underscores).
#define _tzcnt_u16(a) (__tzcnt_u16((a)))
It will be very hard to keep the documentation for these "aliases" in sync with the documentation for the intrinsics they alias to. Out of sync documentation will be more confusing than no documentation.
I got an OK from Eric Christopher to commit doxygen comments without prior code
review upstream.
llvm-svn: 301652
Summary:
When there is a push_back with a call to make_pair, turn it into emplace_back and remove the unnecessary make_pair call.
Eg.
```
std::vector<std::pair<int, int>> v;
v.push_back(std::make_pair(1, 2)); // --> v.emplace_back(1, 2);
```
make_pair doesn't get removed when explicit template parameters are provided, because of potential problems with type conversions.
Reviewers: Prazek, aaron.ballman, hokein, alexfh
Reviewed By: Prazek, alexfh
Subscribers: JDevlieghere, JonasToth, cfe-commits
Tags: #clang-tools-extra
Differential Revision: https://reviews.llvm.org/D32395
llvm-svn: 301651
Summary:
The motivation example is like below which has 13 cases but only 2 distinct targets
```
lor.lhs.false2: ; preds = %if.then
switch i32 %Status, label %if.then27 [
i32 -7012, label %if.end35
i32 -10008, label %if.end35
i32 -10016, label %if.end35
i32 15000, label %if.end35
i32 14013, label %if.end35
i32 10114, label %if.end35
i32 10107, label %if.end35
i32 10105, label %if.end35
i32 10013, label %if.end35
i32 10011, label %if.end35
i32 7008, label %if.end35
i32 7007, label %if.end35
i32 5002, label %if.end35
]
```
which is compiled into a balanced binary tree like this on AArch64 (similar on X86)
```
.LBB853_9: // %lor.lhs.false2
mov w8, #10012
cmp w19, w8
b.gt .LBB853_14
// BB#10: // %lor.lhs.false2
mov w8, #5001
cmp w19, w8
b.gt .LBB853_18
// BB#11: // %lor.lhs.false2
mov w8, #-10016
cmp w19, w8
b.eq .LBB853_23
// BB#12: // %lor.lhs.false2
mov w8, #-10008
cmp w19, w8
b.eq .LBB853_23
// BB#13: // %lor.lhs.false2
mov w8, #-7012
cmp w19, w8
b.eq .LBB853_23
b .LBB853_3
.LBB853_14: // %lor.lhs.false2
mov w8, #14012
cmp w19, w8
b.gt .LBB853_21
// BB#15: // %lor.lhs.false2
mov w8, #-10105
add w8, w19, w8
cmp w8, #9 // =9
b.hi .LBB853_17
// BB#16: // %lor.lhs.false2
orr w9, wzr, #0x1
lsl w8, w9, w8
mov w9, #517
and w8, w8, w9
cbnz w8, .LBB853_23
.LBB853_17: // %lor.lhs.false2
mov w8, #10013
cmp w19, w8
b.eq .LBB853_23
b .LBB853_3
.LBB853_18: // %lor.lhs.false2
mov w8, #-7007
add w8, w19, w8
cmp w8, #2 // =2
b.lo .LBB853_23
// BB#19: // %lor.lhs.false2
mov w8, #5002
cmp w19, w8
b.eq .LBB853_23
// BB#20: // %lor.lhs.false2
mov w8, #10011
cmp w19, w8
b.eq .LBB853_23
b .LBB853_3
.LBB853_21: // %lor.lhs.false2
mov w8, #14013
cmp w19, w8
b.eq .LBB853_23
// BB#22: // %lor.lhs.false2
mov w8, #15000
cmp w19, w8
b.ne .LBB853_3
```
However, the inline cost model estimates the cost to be linear with the number
of distinct targets and the cost of the above switch is just 2 InstrCosts.
The function containing this switch is then inlined about 900 times.
This change use the general way of switch lowering for the inline heuristic. It
etimate the number of case clusters with the suitability check for a jump table
or bit test. Considering the binary search tree built for the clusters, this
change modifies the model to be linear with the size of the balanced binary
tree. The model is off by default for now :
-inline-generic-switch-cost=false
This change was originally proposed by Haicheng in D29870.
Reviewers: hans, bmakam, chandlerc, eraman, haicheng, mcrosier
Reviewed By: hans
Subscribers: joerg, aemerson, llvm-commits, rengolin
Differential Revision: https://reviews.llvm.org/D31085
llvm-svn: 301649
This allows users to query the target triple and target pointer width, which
would make me able to fix https://github.com/servo/rust-bindgen/issues/593 and
other related bugs in an elegant way (without having to manually parse the
target triple in the command line arguments).
Differential Revision: https://reviews.llvm.org/D32389
llvm-svn: 301648
diagnostic in #pragma diagnostic
This matches the warning group that's specified for the unknown warning options
that are passed-in as command line arguments.
rdar://29526025
llvm-svn: 301647
Summary:
Skip memops if the total value profiled count is 0, we can't correctly
scale up the counts and there is no point anyway.
Reviewers: davidxl
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D32624
llvm-svn: 301645
Reapplied r299221 after fix for nondeterminism in ThinLTO builder (rL301599), with extra check for implicit truncation of inserted element.
llvm-svn: 301644
Summary: ConstStrings are immutable, so there is no need to grab even a reader lock in order to read the length field.
Reviewers: #lldb, labath
Reviewed By: labath
Subscribers: zturner, labath, lldb-commits
Differential Revision: https://reviews.llvm.org/D32306
Patch by Scott Smith <scott.smith@purestorage.com>
llvm-svn: 301642
generation.
This needs changes to GPURuntime to expose synchronization between host
and device.
1. Needs better function naming, I want a better name than
"getOrCreateManagedDeviceArray"
2. DeviceAllocations is used by both the managed memory and the
non-managed memory path. This exploits the fact that the two code paths
are never run together. I'm not sure if this is the best design decision
Reviewed by: PhilippSchaad
Tags: #polly
Differential Revision: https://reviews.llvm.org/D32215
llvm-svn: 301640
Summary:
It turns out that even though ppoll is available on all the android
devices we support, it does not seem to be working properly on all of
them -- MainLoop just does a busy loop with ppoll returning EINTR and
not making any progress.
This brings back the pselect implementation and makes it available on
android. I could not do any cmake checks for this as the ppoll symbol is
actually avaiable -- it just does not work.
Reviewers: beanz, eugene
Subscribers: srhines, lldb-commits
Differential Revision: https://reviews.llvm.org/D32600
llvm-svn: 301636
Declare the ARMInstructionSelector in an anonymous namespace, to make it
more in line with the other targets which were migrated to this in
r299637 in order to avoid TableGen'erated headers being included in
non-GlobalISel builds.
llvm-svn: 301632
There was a garbage character in output introduced by myself in
r290040 "[DWARF] - Introduce DWARFDebugPubTable class for dumping pub* sections."
llvm-svn: 301631
Reid Kleckner