Summary:
Previously it was implemented as inline asm in the CUDA headers.
This change allows us to use the [addr+imm] addressing mode when
executing ld.global.nc instructions. This translates into a 1.3x
speedup on some benchmarks that call this instruction from within an
unrolled loop.
Reviewers: tra, rsmith
Subscribers: jhen, cfe-commits, jholewinski
Differential Revision: http://reviews.llvm.org/D19990
llvm-svn: 270150
- Fixed cdp intrinsic to only accept compile time
constant values previously you could pass in a
variable to the builtin which would result in
illegal llvm assembly output
Differential Revision: http://reviews.llvm.org/D20394
llvm-svn: 270058
Summary:
MONITORX/MWAITX instructions provide similar capability to the MONITOR/MWAIT
pair while adding a timer function, such that another termination of the MWAITX
instruction occurs when the timer expires. The presence of the MONITORX and
MWAITX instructions is indicated by CPUID 8000_0001, ECX, bit 29.
The MONITORX and MWAITX instructions are intercepted by the same bits that
intercept MONITOR and MWAIT. MONITORX instruction establishes a range to be
monitored. MWAITX instruction causes the processor to stop instruction
execution and enter an implementation-dependent optimized state until
occurrence of a class of events.
Opcode of MONITORX instruction is "0F 01 FA". Opcode of MWAITX instruction is
"0F 01 FB". These opcode information is used in adding tests for the
disassembler.
These instructions are enabled for AMD's bdver4 architecture.
Patch by Ganesh Gopalasubramanian!
Reviewers: echristo, craig.topper
Subscribers: RKSimon, joker.eph, llvm-commits, cfe-commits
Differential Revision: http://reviews.llvm.org/D19796
llvm-svn: 269907
Visual Studio's C++ standard library headers include intrin.h, so the intrinsic
headers get included a lot more often in Microsoft mode than elsewhere. The
AVX512 intrinsics are a lot of code (0.7 MB, causing 30% compile time overhead
for small programs including e.g. <string> and 6% compile time overhead for
larger projects like e.g. v8). Since multiversioning can't be relied on in
Microsoft mode (cl.exe doesn't support it), having faster compiles seems like
the much better tradeoff until we have a better intrinsic story going forward
(which we'll need for e.g. PR19898).
Actually using intrinsics on Windows already requires the right /arch:
settings, so this patch should have no big behavior change.
See also thread "The intrinsics headers (especially avx512) are too big. What
to do about it?" on cfe-dev.
http://reviews.llvm.org/D20291
llvm-svn: 269675
Summary:
Clang does not detect `aapcs-vfp` for the EABIHF environment. The reason is that only GNUEABIHF is considered while choosing calling convention, EABIHF is ignored.
This causes clang to use `aapcs` for EABIHF and add the `arm_aapcscc` specifier to functions in generated IR.
The modified `arm-cc.c` test checks that no calling convention specifier is added to functions for EABIHF, which means the default one is used (`CallingConv::ARM_AAPCS_VFP`).
Reviewers: rengolin, compnerd, t.p.northover
Subscribers: aemerson, rengolin, asl, cfe-commits
Differential Revision: http://reviews.llvm.org/D20219
llvm-svn: 269419
Summary:
This option allows the user to control how much of the file name is
emitted by UBSan. Tuning this option allows one to save space in the
resulting binary, which is helpful for restricted execution
environments.
With a positive N, UBSan skips the first N path components.
With a negative N, UBSan only keeps the last N path components.
Reviewers: rsmith
Subscribers: cfe-commits
Differential Revision: http://reviews.llvm.org/D19666
llvm-svn: 269309
Currently, if clang::isBetterOverloadCandidate encounters an enable_if
attribute on either candidate that it's inspecting, it will ignore all
lower priority attributes (e.g. pass_object_size). This is problematic
in cases like:
```
void foo(char *c) __attribute__((enable_if(1, "")));
void foo(char *c __attribute__((pass_object_size(0))))
__attribute__((enable_if(1, "")));
```
...Because we would ignore the pass_object_size attribute in the second
`foo`, and consider any call to `foo` to be ambiguous.
This patch makes overload resolution consult further tiebreakers (e.g.
pass_object_size) if two candidates have equally good enable_if
attributes.
llvm-svn: 269005
This option, like the corresponding gcc option, is SystemZ-specific and
enables storing frame backchain links, as specified in the ABI.
Differential Revision: http://reviews.llvm.org/D19891
llvm-svn: 268575
The -malign-double flag causes i64 and f64 types to have alignment 8
instead of 4. On x86-64, the behavior of -malign-double is enabled by default.
Rebases and cleans phosek's work here: http://reviews.llvm.org/D12860
Patch by Sean Klein
Reviewers: rnk
Subscribers: rnk, jfb, dschuff, phosek
Differential Revision: http://reviews.llvm.org/D19734
llvm-svn: 268473
We were seeing an internal failure when running this test. I can't
see a good reason for the difference, but the simple fix is to use
%{{.*}} instead of %1.
llvm-svn: 268416