Was there really no other way to splat a byte in SSE2?
punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
pshuflw {{.*#+}} xmm0 = xmm0[0,0,0,0,4,5,6,7]
pshufd {{.*#+}} xmm0 = xmm0[0,0,1,1]
llvm-svn: 265172
Summary:
Implement BUFFER_ATOMIC_CMPSWAP{,_X2} instructions on all GCN targets, and FLAT_ATOMIC_CMPSWAP{,_X2} on CI+.
32-bit instruction variants tested manually on Kabini and Bonaire. Tests and parts of code provided by Jan Veselý.
Patch by: Vedran Miletić
Reviewers: arsenm, tstellarAMD, nhaehnle
Subscribers: jvesely, scchan, kanarayan, arsenm
Differential Revision: http://reviews.llvm.org/D17280
llvm-svn: 265170
Note however that this is identical to the existing SSE2 run.
What we really want is yet another run for an SSE2 machine that
also has fast unaligned 16-byte accesses.
llvm-svn: 265167
The cc1 invocation in the reproducer script should contain a valid path in
-fmodule-cache-path; for that reuse "<name>.cache/module" dir we already
use to dump the vfs and modules.
llvm-svn: 265162
Follow-up to http://reviews.llvm.org/D18566 and http://reviews.llvm.org/D18676 -
where we noticed that an intermediate splat was being generated for memsets of
non-zero chars.
That was because we told getMemsetStores() to use a 32-bit vector element type,
and it happily obliged by producing that constant using an integer multiply.
The 16-byte test that was added in D18566 is now equivalent for AVX1 and AVX2
(no splats, just a vector load), but we have PR27141 to track that splat difference.
Note that the SSE1 path is not changed in this patch. That can be a follow-up.
This patch should resolve PR27100.
llvm-svn: 265161
Extracts code for initializing dummies sections
to avoid possible duplication in following patches.
Differential review: http://reviews.llvm.org/D18691
llvm-svn: 265159
A catchswitch cannot be preceded by another instruction in the same
basic block (other than a PHI node).
Instead, insert the extract element right after the materialization of
the vectorized value. This isn't optimal but is a reasonable compromise
given the constraints of WinEH.
This fixes PR27163.
llvm-svn: 265157
Some functions in Writer reports error using HasError, and some reports
their return values. This patch makes them to consistently use HasError.
llvm-svn: 265156
fixAbsoluteSymbols fixes linker-created symbol addresses. Since we don't
create such symbols for relocatable output, we don't need to call this
function.
llvm-svn: 265154
assignAddressesRelocatable function did not set addresses to sections
despite its name. What it actually did is to set file offsets to sections.
assignAddresses function assigned addresses and file offsets to sections.
So there was a confusion what they were doing, and they had duplicate code.
This patch separates file offset assignments from address assignments.
A new function, assignFileOffsets assign file offsets. assignAddresses
do not care about file offsets anymore.
llvm-svn: 265151
The extra fix is to note that it still requires copy relocations.
Original message:
Change how we handle R_MIPS_LO16.
Mips aligns PT_LOAD to 16 bits (0x10000). That means that the lower 16
bits are always the same, so we can, effectively, say that the
relocation is relative.
P.S.: Suggestions for a better name for the predicate are welcome :-)
llvm-svn: 265150
Refactor the code that gets and creates PGOFuncName meta data so that it can be
used in clang's value profile annotation.
Differential Revision: http://reviews.llvm.org/D18623
llvm-svn: 265149
Follow-up to D18566 - where we noticed that an intermediate splat was being
generated for memsets of non-zero chars.
That was because we told getMemsetStores() to use a 32-bit vector element type,
and it happily obliged by producing that constant using an integer multiply.
The tests that were added in the last patch are now equivalent for AVX1 and AVX2
(no splats, just a vector load), but we have PR27141 to track that splat difference.
In the new tests, the splat via shuffling looks ok to me, but there might be some
room for improvement depending on uarch there.
Note that the SSE1/2 paths are not changed in this patch. That can be a follow-up.
This patch should resolve PR27100.
Differential Revision: http://reviews.llvm.org/D18676
llvm-svn: 265148
This avoids undefined behavior when casting pointers to it. Also make
sure that we don't cast to a derived StringMapEntry before checking for
tombstone, as that may have different alignment requirements.
llvm-svn: 265145
Summary: The assembler was picking the wrong JR variant because the pre-R6 one was still enabled at R6.
Author: nitesh.jain
Reviewers: vkalintiris, dsanders
Subscribers: dsanders, llvm-commits, mohit.bhakkad, sagar, bhushan, jaydeep
Differential: D18387
llvm-svn: 265134
If a non-affine region PHI is generated we should not move the insert
point prior to the synthezised value in the same block as we might
split that block at the insert point later on. Only if the incoming
value should be placed in a different block we should change the
insertion point.
llvm-svn: 265132
That is consistent with other symbols: _edata, _etext
and can help to avoid duplicate code.
Differential revision: http://reviews.llvm.org/D18655
llvm-svn: 265129
This can happen as we look for '<<<<' while scanning tokens but then expect
'<<<<\n' to tell apart perforce from diff3 conflict markers. Just harden
the pointer arithmetic.
Found by libfuzzer + asan!
llvm-svn: 265125
Sanjay Patel