Fixed decode of existing 3dNow prefetchw instruction
Intel is scheduled to add a compatible prefetchw (same encoding) to future CPUs

llvm-svn: 174920

When building the pairable-instruction dependency map, don't search
past the last pairable instruction. For large blocks that have been
divided into multiple instruction groups, searching past the last
instruction in each group is very wasteful. This gives a 32% speedup
on the csa.ll test case from PR15222 (when using 50 instructions
in each group).

No functionality change intended.

llvm-svn: 174915

This map is queried only for instructions in pairs of pairable
instructions; so make sure that only pairs of pairable
instructions are added to the map. This gives a 3.5% speedup
on the csa.ll test case from PR15222.

No functionality change intended.

llvm-svn: 174914

llvm-svn: 174913

MipsCodeEmitter.cpp.

JALR and NOP are expanded by function emitPseudoExpansionLowering, which is not
called when the old JIT is used.

This fixes the following tests which have been failing on
llvm-mips-linux builder:

LLVM :: ExecutionEngine__2003-01-04-LoopTest.ll
LLVM :: ExecutionEngine__2003-05-06-LivenessClobber.ll
LLVM :: ExecutionEngine__2003-06-04-bzip2-bug.ll
LLVM :: ExecutionEngine__2005-12-02-TailCallBug.ll
LLVM :: ExecutionEngine__2003-10-18-PHINode-ConstantExpr-CondCode-Failure.ll
LLVM :: ExecutionEngine__hello2.ll
LLVM :: ExecutionEngine__stubs.ll
LLVM :: ExecutionEngine__test-branch.ll
LLVM :: ExecutionEngine__test-call.ll
LLVM :: ExecutionEngine__test-common-symbols.ll
LLVM :: ExecutionEngine__test-loadstore.ll
LLVM :: ExecutionEngine__test-loop.ll

llvm-svn: 174912

llvm-svn: 174911

llvm-svn: 174910

llvm-svn: 174909

llvm-svn: 174907

llvm-svn: 174905

- variety of compare instructions,
- loops with no preheader,
- arbitrary lower and upper bounds.

llvm-svn: 174904

llvm-svn: 174903

llvm-svn: 174901

*added file for test cases for i386 intel syntax

llvm-svn: 174900

[NVPTX] Remove NoCapture from address space conversion intrinsics. NoCapture is not valid in this case, and was causing incorrect optimizations.

llvm-svn: 174896

This eliminates one more linear search over a range of
std::multimap entries. This gives a 22% speedup on the
csa.ll test case from PR15222.

No functionality change intended.

llvm-svn: 174893

llvm-svn: 174891

The modifiers don't seem to have any effect with V_MOV_B32, supposedly it's
meant to just move bits untouched.

Fixes 46 piglit tests with radeonsi, though unfortunately 11 of those had
just regressed because they started using the clamp modifier.

NOTE: This is a candidate for the Mesa stable branch.

Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 174890

This flag makes asan use a small (<2G) offset for 64-bit asan shadow mapping.
On x86_64 this saves us a register, thus achieving ~2/3 of the
zero-base-offset's benefits in both performance and code size.

Thanks Jakub Jelinek for the idea.

llvm-svn: 174886

This does two things:

It removes a call to abs() which may have "long long" parameter on Windows,
which is not necessarily available in C++03.

It also corrects the signedness of Amount, which was relying on
implementation-defined conversions previously.

Code was already tested (albeit in an implemnetation defined way) so no extra
tests.

llvm-svn: 174885

llvm-svn: 174884

llvm-svn: 174881

Previous code had a confusing comment which was mostly an implementation
detail. This condition corresponds to "lsb up to register width" and "width not
ridiculous".

llvm-svn: 174877

This allows llvm-dwarfdump to handle the relocations needed, at least
for LLVM-produced code.

llvm-svn: 174874

This broke on Windows, presumably due to interleaving of output streams.

llvm-svn: 174873

This gives a DiagnosticType to all AsmOperands in sight. This replaces all
"invalid operand" diagnostics with something more specific. The messages given
should still be sufficiently vague that they're not usually actively misleading
when LLVM guesses your instruction incorrectly.

llvm-svn: 174871

This is currently a bit hairier than it needs to be, since depending on where the
split block resides the end ListEntry of the split block may be the end ListEntry
of the original block or a new entry. Some changes to the SlotIndexes updating
should make it possible to eliminate the two cases here.

This also isn't as optimized as it could be. In the future Liveinterval should
probably get a flag that indicates whether the LiveInterval is within a single
basic block. We could ignore all such intervals when splitting an edge.

llvm-svn: 174870

really trying to avoid piping SlotIndexes through to RemoveBranch() and friends.

llvm-svn: 174869

particular, holes were being left between two blocks after splitting an edge.

llvm-svn: 174868

This emits the attribute groups that are used by the functions. (It currently
doesn't print out return type or parameter attributes within attribute groups.)

Note: The functions still retrieve their attributes from the "old" bitcode
format (using the deprecated 'Raw()' method). This means that string attributes
within an attribute group will not show up during a disassembly. This will be
addressed in a future commit.

llvm-svn: 174867

llvm-svn: 174865

llvm-svn: 174864

This reverts my commit 171047. Now that I've removed my misguided attempt to
support backend warnings, these diagnostics are only about inline assembly.
It would take quite a bit more work to generalize them properly, so I'm
just reverting this.

llvm-svn: 174860

This removes the last of the linear searches over ranges of std::multimap
iterators, giving a 7% speedup on the doduc.bc input from PR15222.

No functionality change intended.

llvm-svn: 174859

This is another cleanup aimed at eliminating linear searches
in ranges of std::multimap.

No functionality change intended.

llvm-svn: 174858

Profiling suggests that getInstructionTypes is performance-sensitive,
this cleans up some double-casting in that function in favor of
using dyn_cast.

No functionality change intended.

llvm-svn: 174857

By itself, this does not have much of an effect, but only because in the default
configuration the full cycle checks are used only for small problem sizes.
This is part of a general cleanup of uses of iteration over std::multimap
ranges only for the purpose of checking membership.

No functionality change intended.

llvm-svn: 174856

function is successfully handled by fast-isel. That's because function
arguments are *always* handled by SDISel. Introduce FastLowerArguments to
allow each target to provide hook to handle formal argument lowering.

As a proof-of-concept, add ARMFastIsel::FastLowerArguments to handle
functions with 4 or fewer scalar integer (i8, i16, or i32) arguments. It
completely eliminates the need for SDISel for trivial functions.

rdar://13163905

llvm-svn: 174855

llvm-svn: 174854

I have some uncommitted changes to the cast code that catch this sort of thing
at compile-time but I still need to do some other cleanup before I can enable
it.

llvm-svn: 174853