| Commit message (Collapse) | Author | Age | Files | Lines |
|
|
|
| |
(cherry picked from commit a19de32095e4cdb18957e66609574ce2021a8d1c)
|
|
|
|
|
|
|
|
|
|
|
|
| |
The old version might be faster on EG (RECIP_IEEE is Trans only),
but it'd need extra corner case checks.
This gives correct corner case behaviour and saves a register.
Fixes OCL CTS sqrt test (1-thread, scalar) on Turks.
Reviewer: arsenm
Differential Revision: https://reviews.llvm.org/D74017
(cherry picked from commit e6686adf8a743564f0c455c34f04752ab08cf642)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
Due to the fact that kill is just a normal intrinsic, even though it's
supposed to terminate the thread, we can end up with provably infinite
loops that are actually supposed to end successfully. The
AMDGPUUnifyDivergentExitNodes pass breaks up these loops, but because
there's no obvious place to make the loop branch to, it just makes it
return immediately, which skips the exports that are supposed to happen
at the end and hangs the GPU if all the threads end up being killed.
While it would be nice if the fact that kill terminates the thread were
modeled in the IR, I think that the structurizer as-is would make a mess if we
did that when the kill is inside control flow. For now, we just add a null
export at the end to make sure that it always exports something, which fixes
the immediate problem without penalizing the more common case. This means that
we sometimes do two "done" exports when only some of the threads enter the
discard loop, but from tests the hardware seems ok with that.
This fixes dEQP-VK.graphicsfuzz.while-inside-switch with radv.
Reviewers: arsenm, nhaehnle
Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D70781
(cherry picked from commit 87d98c149504f9b0751189744472d7cc94883960)
|
|
|
|
|
|
|
|
|
|
| |
R600 relies on this behaviour.
Fixes: 6e18266aa4dd78953557b8614cb9ff260bad7c65 ('Partially revert D61491 "AMDGPU: Be explicit about whether the high-word in SI_PC_ADD_REL_OFFSET is 0"')
Fixes ~100 piglit regressions since 6e18266
Differential Revision: https://reviews.llvm.org/D72991
(cherry picked from commit 1b8eab179db46f25a267bb73c657009c0bb542cc)
|
|
|
|
|
|
|
|
|
| |
This reverts commit 0dc6c249bffac9f23a605ce4e42a84341da3ddbd.
The commit is reported to cause a regression in piglit/bin/glsl-vs-loop for
Mesa.
(cherry picked from commit a80291ce10ba9667352adcc895f9668144f5f616)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The current implementation of skip insertion (SIInsertSkip) makes it a
mandatory pass required for correctness. Initially, the idea was to
have an optional pass. This patch inserts the s_cbranch_execz upfront
during SILowerControlFlow to skip over the sections of code when no
lanes are active. Later, SIRemoveShortExecBranches removes the skips
for short branches, unless there is a sideeffect and the skip branch is
really necessary.
This new pass will replace the handling of skip insertion in the
existing SIInsertSkip Pass.
Differential revision: https://reviews.llvm.org/D68092
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
For builds with LLVM_BUILD_LLVM_DYLIB=ON and BUILD_SHARED_LIBS=OFF
this change makes all symbols in the target specific libraries hidden
by default.
A new macro called LLVM_EXTERNAL_VISIBILITY has been added to mark symbols in these
libraries public, which is mainly needed for the definitions of the
LLVMInitialize* functions.
This patch reduces the number of public symbols in libLLVM.so by about
25%. This should improve load times for the dynamic library and also
make abi checker tools, like abidiff require less memory when analyzing
libLLVM.so
One side-effect of this change is that for builds with
LLVM_BUILD_LLVM_DYLIB=ON and LLVM_LINK_LLVM_DYLIB=ON some unittests that
access symbols that are no longer public will need to be statically linked.
Before and after public symbol counts (using gcc 8.2.1, ld.bfd 2.31.1):
nm before/libLLVM-9svn.so | grep ' [A-Zuvw] ' | wc -l
36221
nm after/libLLVM-9svn.so | grep ' [A-Zuvw] ' | wc -l
26278
Reviewers: chandlerc, beanz, mgorny, rnk, hans
Reviewed By: rnk, hans
Subscribers: merge_guards_bot, luismarques, smeenai, ldionne, lenary, s.egerton, pzheng, sameer.abuasal, MaskRay, wuzish, echristo, Jim, hiraditya, michaelplatings, chapuni, jholewinski, arsenm, dschuff, jyknight, dylanmckay, sdardis, nemanjai, jvesely, javed.absar, sbc100, jgravelle-google, aheejin, kbarton, fedor.sergeev, asb, rbar, johnrusso, simoncook, apazos, sabuasal, niosHD, jrtc27, zzheng, edward-jones, mgrang, atanasyan, rogfer01, MartinMosbeck, brucehoult, the_o, PkmX, jocewei, kristina, jsji, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D54439
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
- `dead-mi-elimination` assumes MIR in the SSA form and cannot be
arranged after phi elimination or DeSSA. It's enhanced to handle the
dead register definition by skipping use check on it. Once a register
def is `dead`, all its uses, if any, should be `undef`.
- Re-arrange the DIE in RA phase for AMDGPU by placing it directly after
`detect-dead-lanes`.
- Many relevant tests are refined due to different register assignment.
Reviewers: rampitec, qcolombet, sunfish
Subscribers: arsenm, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D72709
|
|
|
|
|
|
|
| |
This change allows to model the height of the instruction
within a bundle for latency adjustment purposes.
Differential Revision: https://reviews.llvm.org/D72669
|
|
|
|
|
|
|
|
| |
We do not have InstrItinerary so generic getInstLatency() was always
defaulting to return 1 cycle. We need to use TargetSchedModel instead
to compute an instruction's latency.
Differential Revision: https://reviews.llvm.org/D72655
|
| |
|
|
|
|
|
|
|
|
|
| |
The current users of the waterfall loop utility functions do not make
use of the restored original insert point. The insertion is either
done, or they set the insert point somewhere else. A future change
will want to insert instructions after the waterfall loop, but
figuring out the point after the loop is more difficult than ensuring
the insert point is there after the loop.
|
|
|
|
|
|
|
|
| |
The branch target needs to be changed depending on whether there is an
unconditional branch or not.
Loops also need to be similarly fixed, but compiling a simple testcase
end to end requires another set of patches that aren't upstream yet.
|
| |
|
|
|
|
|
| |
We don't use the xexec register classes for arbitrary values
anymore. Avoids a test variance beween GlobalISel and SelectionDAG>
|
|
|
|
|
| |
getDefIgnoringCopies will fail to find any def if no type is set if we
try to use it on the use's operand, so propagate the type.
|
|
|
|
|
|
|
|
|
|
| |
The argument is llvm::null() everywhere except llvm::errs() in
llvm-objdump in -DLLVM_ENABLE_ASSERTIONS=On builds. It is used by no
target but X86 in -DLLVM_ENABLE_ASSERTIONS=On builds.
If we ever have the needs to add verbose log to disassemblers, we can
record log with a member function, instead of passing it around as an
argument.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
- SI Whole Quad Mode phase is replacing WQM pseudo instructions with v_mov instructions.
While this is necessary for the special handling of moving results out of WWM live ranges,
it is not necessary for WQM live ranges. The result is a v_mov from a register to itself after every
WQM operation. This change uses a COPY psuedo in these cases, which allows the register
allocator to coalesce the moves away.
Reviewers: tpr, dstuttard, foad, nhaehnle
Reviewed By: nhaehnle
Subscribers: arsenm, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D71386
|
|
|
|
|
|
|
|
|
|
|
| |
This reverts the AMDGPU DAG mutation implemented in D72487 and gives
a more general way of adjusting BUNDLE operand latency.
It also replaces FixBundleLatencyMutation with adjustSchedDependency
callback in the AMDGPU, fixing not only successor latencies but
predecessors' as well.
Differential Revision: https://reviews.llvm.org/D72535
|
|
|
|
|
| |
Also clamps G_SEXT/G_ANYEXT, but the implementation is more limited so
fewer cases actually work.
|
|
|
|
|
| |
Doesn't try to do the fold into the base register of an add of a
constant in the index like the DAG path does.
|
|
|
|
|
|
| |
If an SGPR vector is indexed with a VGPR, the actual indexing will be
done on the SGPR and produce an SGPR. A copy needs to be inserted
inside the waterwall loop to the VGPR result.
|
|
|
|
|
|
|
| |
Bundles coming to scheduler considered free, i.e. zero latency.
Fixed.
Differential Revision: https://reviews.llvm.org/D72487
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The current implementation assumes there is an instruction associated
with the transform, but this is not the case for
timm/TargetConstant/immarg values. These transforms should directly
operate on a specific MachineOperand in the source
instruction. TableGen would assert if you attempted to define an
equivalent GISDNodeXFormEquiv using timm when it failed to find the
instruction matcher.
Specially recognize SDNodeXForms on timm, and pass the operand index
to the render function.
Ideally this would be a separate render function type that looks like
void renderFoo(MachineInstrBuilder, const MachineOperand&), but this
proved to be somewhat mechanically painful. Add an optional operand
index which will only be passed if the transform should only look at
the one source operand.
Theoretically it would also be possible to only ever pass the
MachineOperand, and the existing renderers would check the parent. I
think that would be somewhat ugly for the standard usage which may
want to inspect other operands, and I also think MachineOperand should
eventually not carry a pointer to the parent instruction.
Use it in one sample pattern. This isn't a great example, since the
transform exists to satisfy DAG type constraints. This could also be
avoided by just changing the MachineInstr's arbitrary choice of
operand type from i16 to i32. Other patterns have nontrivial uses, but
this serves as the simplest example.
One flaw this still has is if you try to use an SDNodeXForm defined
for imm, but the source pattern uses timm, you still see the "Failed
to lookup instruction" assert. However, there is now a way to avoid
it.
|
|
|
|
|
| |
Compared to the attempt in bdcc6d3d2638b3a2c99ab3b9bfaa9c02e584993a,
this uses intermediate generic instructions.
|
|
|
|
|
|
| |
Only PPC seems to be using it, and only checks some simple cases and
doesn't distinguish between FP. Just switch to using LLT to simplify
use from GlobalISel.
|
|
|
|
|
|
|
| |
When these arguments are broken down by the EVT based callbacks, the
pointer information is lost. Hack around this by coercing the register
types to be the expected pointer element type when building the
remerge operations.
|
|
|
|
|
|
| |
This should be legal, but will require future selection work. 16-bit
shift amounts were already removed from being legal, but this didn't
adjust the transformation rules.
|
|
|
|
|
| |
This isn't too useful now, since nothing is currently trying to form
min/max from cmp+select.
|
|
|
|
| |
These should now be limited to R600 code.
|
| |
|
| |
|
| |
|
|
|
|
| |
Partially fixes BFE pattern import.
|
|
|
|
|
|
| |
This doesn't enable any new imports yet, but moves the fmed patterns
from failing on this to hitting the "complex suboperand referenced
more than once" limitation in tablegen.
|
|
|
|
| |
Only partially fixes one pattern import.
|
| |
|
|
|
|
| |
Reduces diff for a future patch.
|
|
|
|
|
|
|
|
|
|
|
| |
`APFLoat::convertFromString` returns `Expected` result, which must be
"checked" if the LLVM_ENABLE_ABI_BREAKING_CHECKS preprocessor flag is
set.
To mark an `Expected` result as "checked" we must consume the `Error`
within.
In many cases, we are only interested in knowing if an error occured,
without the need to examine the error info. This is achieved, easily,
with the `errorToBool()` API.
|
| |
|
|
|
|
|
| |
This partially fixes GlobalISel import of the patterns, but removes a
lot of entriess from the end of the skipped pattern log.
|
|
|
|
|
| |
4e85ca9562a588eba491e44bcbf73cb2f419780f missed updating the legal
condition type set for pointers with any unrecognized address space.
|
|
|
|
|
| |
This was only applying the deeper nested zext pattern, and missing the
special case code size fold.
|
|
|
|
|
| |
Now that overridable default operands work, there's no reason to use
complex patterns to just produce 0s.
|
| |
|
| |
|
|
|
|
|
| |
We weren't treating i16->f16 casts as legal on targets with these
instructions, and always using a pair of casts through i32.
|
|
|
|
|
| |
The imm folding optimization pattern failed to import. The instruction
pattern was already working, but failing to fail on SGPR inputs.
|
| |
|
| |
|