We can have a v_mac with an immediate src0.
We can still fold if it's an inline immediate,
otherwise it already uses the constant bus.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@313852 91177308-0d34-0410-b5e6-96231b3b80d8
These write to the low and high half of the destination
register and leave the other 16-bits unchanged. This is true
for most 16-bit instructions on gfx9, but we don't use that
now.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@313812 91177308-0d34-0410-b5e6-96231b3b80d8
Also add some tests that should be able to use v_mad_mixhi_f16,
but do not yet. This is trickier because we don't really model
the partial update of the register done by 16-bit instructions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@313806 91177308-0d34-0410-b5e6-96231b3b80d8
Also starts selecting global loads for constant address
in some cases. Some end up selecting to mubuf still, which
requires investigation.
We still get sub-optimal regalloc and extra waitcnts inserted
due to not really tracking the liveness of the separate register
halves.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@313716 91177308-0d34-0410-b5e6-96231b3b80d8
The relocations used for externally visible functions
aren't supported, so the direct call emitted ends
up hitting a linker error.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@313616 91177308-0d34-0410-b5e6-96231b3b80d8
Because the stack growth direction and addressing is done
in the same direction, modifying SP at the beginning of the
call sequence was incorrect. If we had a stack passed argument,
we would end up skipping that number of bytes before pushing
arguments, leaving unused/inconsistent space.
The callee creates fixed stack objects in its frame, so
the space necessary for these is already logically allocated
in the callee, so we just let the callee increment SP if
it really requires it.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@313279 91177308-0d34-0410-b5e6-96231b3b80d8
Using SplitCSR for the frame register was very broken. Often
the copies in the prolog and epilog were optimized out, in addition
to them being inserted after the true prolog where the FP
was clobbered.
I have a hacky solution which works that continues to use
split CSR, but for now this is simpler and will get to working
programs.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@313274 91177308-0d34-0410-b5e6-96231b3b80d8
MachineScheduler when clustering loads or stores checks if base
pointers point to the same memory. This check is done through
comparison of base registers of two memory instructions. This
works fine when instructions have separate offset operand. If
they require a full calculated pointer such instructions can
never be clustered according to such logic.
Changed shouldClusterMemOps to accept base registers as well and
let it decide what to do about it.
Differential Revision: https://reviews.llvm.org/D37698
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@313208 91177308-0d34-0410-b5e6-96231b3b80d8
A mrt exp with vm=1 must be in exact (non-WQM) mode, as it also exports
the exec mask as the valid mask to determine which pixels to render.
This commit marks any exp as needing to be in exact mode.
Actually, if there are multiple mrt exps, only one needs to have vm=1,
and only that one needs to be in exact mode. But that is an optimization
for another day.
Differential Revision: https://reviews.llvm.org/D36305
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@312915 91177308-0d34-0410-b5e6-96231b3b80d8
We have a lot of operand definition work essentially producing
every valid permutation of operands to workaround builiding
operand lists based on the instruction features. Apparently tablegen
already has a mostly undocumented operator to concat dags which
simplies this.
Convert one simple place to use this. The BUF instruction definitions
have much more complicated logic that can be totally rewritten now.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@312822 91177308-0d34-0410-b5e6-96231b3b80d8
The various scalar bit operations set SCC,
so one is erased or moved it needs to be recomputed.
Not sure why the existing tests don't fail on this.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@312819 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
Mesa still uses a hack where empty inline assembly is used as a kind of
optimization barrier. This exposed a problem where not enough wait states
were inserted, because the hazard recognizer implicitly assumed that each
inline assembly "instruction" has at least one wait state.
Reviewers: arsenm
Subscribers: kzhuravl, wdng, yaxunl, dstuttard, tpr, llvm-commits, t-tye
Differential Revision: https://reviews.llvm.org/D37205
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@312635 91177308-0d34-0410-b5e6-96231b3b80d8
If the only call in a function is a tail call, the
function isn't considered to have a call since it's a
type of return.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@312561 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
This fixes a bug that was exposed on gfx9 in various
GL45-CTS.shaders.loops.*_iterations.select_iteration_count_fragment tests,
e.g. GL45-CTS.shaders.loops.do_while_uniform_iterations.select_iteration_count_fragment
Reviewers: arsenm
Subscribers: kzhuravl, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D36193
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@312337 91177308-0d34-0410-b5e6-96231b3b80d8
