Removed the HasT2ExtractPack feature and replaced its references
with HasDSP. This then allows the Thumb2 extend instructions to be
selected for ARMv8M +dsp. These instruction descriptions have also
been refactored and more target tests have been added for their isel.
Differential Revision: https://reviews.llvm.org/D29623
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295452 91177308-0d34-0410-b5e6-96231b3b80d8
Return invalid opcodes when some of the helpers in the instruction selection
pass can't handle a given combination.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295446 91177308-0d34-0410-b5e6-96231b3b80d8
Add some asserts to make sure we're using the mappings that we think we're
using. This is to keep us from accidentally breaking functionality while moving
to TableGen'erated mappings.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295441 91177308-0d34-0410-b5e6-96231b3b80d8
Start using the Subtarget to make decisions about what's legal. In particular,
we only mark floating point operations as legal if we have VFP2, which is
something we should've done from the very start.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295439 91177308-0d34-0410-b5e6-96231b3b80d8
The original commit was reverted in r283329 due to a miscompile in
Chromium. That turned out to be the same issue as PR31257, which was
fixed in r295262.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295357 91177308-0d34-0410-b5e6-96231b3b80d8
Defining nodes should not alias with one another, while clobbering
nodes can. When pushing defs on stacks, push clobbers first, link
non-clobbering defs, then push the defs.
The data flow in a statement is now: uses -> clobbers -> defs.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295356 91177308-0d34-0410-b5e6-96231b3b80d8
The existing code always saves the xmm registers for 64-bit targets even if the
target doesn't support SSE (which is common for kernels). Thus, the compiler
inserts movaps instructions which lead to CPU exceptions when an interrupt
handler is invoked.
This commit fixes this bug by returning a register set without xmm registers
from getCalleeSavedRegs and getCallPreservedMask for such targets.
Patch by Philipp Oppermann.
Differential Revision: https://reviews.llvm.org/D29959
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295347 91177308-0d34-0410-b5e6-96231b3b80d8
Regression test neon-diagnostics.s needed changing because it now
produces a more specific diagnostic about the immediate ranges. One
change in the expected error message is not obvious, but there multiple
candidate and it happens to pick the immediate diagnostic.
Differential Revision: https://reviews.llvm.org/D29939
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295331 91177308-0d34-0410-b5e6-96231b3b80d8
Since they're only used for passing around double precision floating point
values into the general purpose registers, we'll lower them to VMOVDRR and
VMOVRRD.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295310 91177308-0d34-0410-b5e6-96231b3b80d8
Support G_SEQUENCE and G_EXTRACT as needed for passing double precision floating
point values in the soft-fp float mode.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295306 91177308-0d34-0410-b5e6-96231b3b80d8
For now we just mark them as legal all the time and let the other passes bail
out if they can't handle it. In the future, we'll want to move more of the
brains into the legalizer.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295300 91177308-0d34-0410-b5e6-96231b3b80d8
For the hard float calling convention, we just use the D registers.
For the soft-fp calling convention, we use the R registers and move values
to/from the D registers by means of G_SEQUENCE/G_EXTRACT. While doing so, we
make sure to honor the endianness of the target, since the CCAssignFn doesn't do
that for us.
For pure soft float targets, we still bail out because we don't support the
libcalls yet.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295295 91177308-0d34-0410-b5e6-96231b3b80d8
The new 512-bit unmasked intrinsics will make it easy to handle these with the SSE/AVX intrinsics in InstCombine where we currently have a TODO.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295290 91177308-0d34-0410-b5e6-96231b3b80d8
This reverts r294348, which removed support for conditional tail calls
due to the PR above. It fixes the PR by marking live registers as
implicitly used and defined by the now predicated tailcall. This is
similar to how IfConversion predicates instructions.
Differential Revision: https://reviews.llvm.org/D29856
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295262 91177308-0d34-0410-b5e6-96231b3b80d8
Uses a Custom implementation because the slot sizes being a multiple of the
pointer size isn't really universal, even for the architectures that do have a
simple "void *" va_list.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295255 91177308-0d34-0410-b5e6-96231b3b80d8
Minor performance speedup - if any call to getShuffleScalarElt fails to get a result, don't both calling for the remaining elements as EltsFromConsecutiveLoads will fail anyhow.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295235 91177308-0d34-0410-b5e6-96231b3b80d8
am_ldrlit diverged from am_brcond in r207105, but kept the OtherVT
operand type. It made sense for branch targets, as those are
represented as MVT::Other in SDAG. But loads operate on pointers.
This shouldn't have an observable effect on any in-tree code, but helps
make the patterns consistent for external users.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295229 91177308-0d34-0410-b5e6-96231b3b80d8
Only do this for integer types currently - floats types (in particular insertps) load folding often fails with this.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295208 91177308-0d34-0410-b5e6-96231b3b80d8
This patch reverts region's scheduling to the original untouched state
in case if we have have decreased occupancy.
In addition it switches to use TargetRegisterInfo occupancy callback
for pressure limits instead of gradually increasing limits which were
just passed by. We are going to stay with the best schedule so we do
not need to tolerate worsened scheduling anymore.
Differential Revision: https://reviews.llvm.org/D29971
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295206 91177308-0d34-0410-b5e6-96231b3b80d8
Add support for specifying an UNPCK input as ZERO, particularly improves ZEXT cases with non-zero offsets
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295169 91177308-0d34-0410-b5e6-96231b3b80d8
Summary: Adds support for xray instrumentation on mips for both 32-bit and 64-bit.
Reviewed by sdardis, dberris
Differential: D27697
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295164 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
We don't seem to have great rules on what a valid VBROADCAST node looks like. And as a consequence we end up with a lot of patterns to try to catch everything. We have patterns with scalar inputs, 128-bit vector inputs, 256-bit vector inputs, and 512-bit vector inputs.
As you can see from the things improved here we are currently missing patterns for 128-bit loads being extended to 256-bit before the vbroadcast.
I'd like to propose that VBROADCAST should always take a 128-bit vector type as input. As a first step towards that this patch adds an EXTRACT_SUBVECTOR in front of VBROADCAST when the input is 256 or 512-bits. In the future I would like to add scalar_to_vector around all the scalar operations. And maybe we should consider adding a VBROADCAST+load node to avoid separating loads from the broadcasting operation when the load itself isn't foldable.
This requires an additional change in target shuffle combining to look for the extract subvector and look through it to find the original operand. I'm sure this change isn't perfect but was enough to fix a few test failures that were being caused.
Another interesting thing I noticed is that the changes in masked_gather_scatter.ll show cases were we don't remove a useless insert into element 1 before broadcasting element 0.
Reviewers: delena, RKSimon, zvi
Reviewed By: zvi
Subscribers: igorb, llvm-commits
Differential Revision: https://reviews.llvm.org/D28747
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295155 91177308-0d34-0410-b5e6-96231b3b80d8
This patch corrects the maximum workgroups per CU if we have big
workgroups (more than 128). This calculation contributes to the
occupancy calculation in respect to LDS size.
Differential Revision: https://reviews.llvm.org/D29974
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295134 91177308-0d34-0410-b5e6-96231b3b80d8
Correct the definition of MIPS16 instructions that act as return instructions
so that isReturn = 1 as expected.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295109 91177308-0d34-0410-b5e6-96231b3b80d8
