The rematerialized instruction may require a more constrained register class
than the register being spilled. In the test case, the spilled register has been
inflated to the DPR register class, but we are rematerializing a load of the
ssub_0 sub-register which only exists for DPR_VFP2 registers.
The register class is reinflated after spilling, so the conservative choice is
only temporary.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@128610 91177308-0d34-0410-b5e6-96231b3b80d8
{STR,LDC}{2}_PRE.
- Fixed the encoding in some places.
- Some of those instructions were using am2offset and now use addrmode2.
Codegen isn't affected, instructions which use SelectAddrMode2Offset were not
touched.
- Teach printAddrMode2Operand to check by the addressing mode which index
mode to print.
- This is a work in progress, more work to come. The idea is to change places
which use am2offset to use addrmode2 instead, as to unify assembly parser.
- Add testcases for assembly parser
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@128585 91177308-0d34-0410-b5e6-96231b3b80d8
that one of the numbers is signed while the other is unsigned. This could lead
to a wrong result when the signed was promoted to an unsigned int.
* Add the data layout line to the testcase so that it will test the appropriate
thing.
Patch by David Terei!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@128577 91177308-0d34-0410-b5e6-96231b3b80d8
StringMap was not properly updating NumTombstones after a clear or rehash.
This was not fatal until now because the table was growing faster than
NumTombstones could, but with the previous change of preventing infinite
growth of the table the invariant (NumItems + NumTombstones <= NumBuckets)
stopped being observed, causing infinite loops in certain situations.
Patch by José Fonseca!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@128567 91177308-0d34-0410-b5e6-96231b3b80d8
The rewriter can keep track of multiple stack slots in the same register if they
happen to have the same value. When an instruction modifies a stack slot by
defining a register that is mapped to a stack slot, other stack slots in that
register are no longer valid.
This is a very rare problem, and I don't have a simple test case. I get the
impression that VirtRegRewriter knows it is about to be deleted, inventing a
last opaque problem.
<rdar://problem/9204040>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@128562 91177308-0d34-0410-b5e6-96231b3b80d8
Some platforms may treat denormals as zero, on other platforms multiplication
with a subnormal is slower than dividing by a normal.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@128555 91177308-0d34-0410-b5e6-96231b3b80d8
The idea is, that if an ieee 754 float is divided by a power of two, we can
turn the division into a cheaper multiplication. This function sees if we can
get an exact multiplicative inverse for a divisor and returns it if possible.
This is the hard part of PR9587.
I tested many inputs against llvm-gcc's frotend implementation of this
optimization and didn't find any difference. However, floating point is the
land of weird edge cases, so any review would be appreciated.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@128545 91177308-0d34-0410-b5e6-96231b3b80d8
When DCE clones a live range because it separates into connected components,
make sure that the clones enter the same register allocator stage as the
register they were cloned from.
For instance, clones may be split even when they where created during spilling.
Other registers created during spilling are not candidates for splitting or even
(re-)spilling.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@128524 91177308-0d34-0410-b5e6-96231b3b80d8
was lowering them to sext / uxt + mul instructions. Unfortunately the
optimization passes may hoist the extensions out of the loop and separate them.
When that happens, the long multiplication instructions can be broken into
several scalar instructions, causing significant performance issue.
Note the vmla and vmls intrinsics are not added back. Frontend will codegen them
as intrinsics vmull* + add / sub. Also note the isel optimizations for catching
mul + sext / zext are not changed either.
First part of rdar://8832507, rdar://9203134
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@128502 91177308-0d34-0410-b5e6-96231b3b80d8
The STC_OPTION and STC2_OPTION instructions should have their coprocessor option enclosed in {}.
rdar://problem/9200661
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@128478 91177308-0d34-0410-b5e6-96231b3b80d8
the FailBB dominator is correctly calculated. Believe it or not, there isn't a
functionality change here.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@128455 91177308-0d34-0410-b5e6-96231b3b80d8
vector types. This helps a lot with inlined functions when using the ARM soft
float ABI. Fixes <rdar://problem/9184212>.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@128453 91177308-0d34-0410-b5e6-96231b3b80d8
The instruction to be rematerialized may not be the one defining the register
that is being spilled. The traceSiblingValue() function sees through sibling
copies to find the remat candidate.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@128449 91177308-0d34-0410-b5e6-96231b3b80d8
isel lowering to fold the zero-extend's and take advantage of no-stall
back to back vmul + vmla:
vmull q0, d4, d6
vmlal q0, d5, d6
is faster than
vaddl q0, d4, d5
vmovl q1, d6
vmul q0, q0, q1
This allows us to vmull + vmlal for:
f = vmull_u8( vget_high_u8(s), c);
f = vmlal_u8(f, vget_low_u8(s), c);
rdar://9197392
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@128444 91177308-0d34-0410-b5e6-96231b3b80d8
