If inline asm has a VGPR def, it must have come from a VGPR write
somewhere inside the asm. This should be further extended to all
read after write hazards.
This reverts commit 0148df8157f05ecf3b1064508e6f012aefb87dad.
Getting a lit test failures on AMDGPU but I can't reproduce it so far.
Reverting to investigate.
(sra X, BW-1) is either 0 or -1. So the multiply is a conditional
negate of Y.
This pattern shows up when type legalizing wide multiplies involving
a sign extended value.
Fixes PR57549.
Reviewed By: RKSimon
Differential Revision: https://reviews.llvm.org/D133399
Unfortunately, we have a broken handling of this in the runtime of rocm
5.3. The runtime is expected to handle this correctly when v5 becomes
the default.
Differential Revision: https://reviews.llvm.org/D134714
Reference: https://gcc.gnu.org/onlinedocs/gccint/Machine-Constraints.html
k: A memory operand whose address is formed by a base register and
(optionally scaled) index register.
m: A memory operand whose address is formed by a base register and
offset that is suitable for use in instructions with the same
addressing mode as st.w and ld.w.
ZB: An address that is held in a general-purpose register. The offset
is zero.
ZC: A memory operand whose address is formed by a base register and
offset that is suitable for use in instructions with the same
addressing mode as ll.w and sc.w.
Note:
The INLINEASM SDNode flags in below tests are updated because the new
introduced enum `Constraint_k` is added before `Constraint_m`.
llvm/test/CodeGen/AArch64/GlobalISel/irtranslator-inline-asm.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-inline-asm.ll
llvm/test/CodeGen/X86/callbr-asm-kill.mir
This patch passes `ninja check-all` on a X86 machine with all official
targets and the LoongArch target enabled.
Differential Revision: https://reviews.llvm.org/D134638
Apparently StackColoring depends on SlotIndexes, but not
LiveIntervals. If regalloc fast were manually requested, LiveIntervals
would be dropped before SILowerSGPRSpills but not SlotIndexes.
SILowerSGPRSpills preserved SlotIndexes, but only through
LiveIntervals. As a result, SILowerSGPRSpills was incorrectly
reporting it preserved SlotIndexes. Start updating these directly,
instead of depending on LiveIntervals also being available.
Similar to the current "Trunc/BuildVector" folding - which folds low element extracts of BuildVectors, folds hi element extracts done using bitshifts.
For D134354
Reviewed By: arsenm
Differential Revision: https://reviews.llvm.org/D135148
Register allocation is split into two passes, and the expected behavior is that the first pass only should only work on virtual SGPRs. Whereas the second pass works on virtual VGPRs. This adds a test case which breaks if the first pass allocates VGPRs.
Differential Revision: https://reviews.llvm.org/D135331
We can still get a NaN even if none of the operands are NaN,
e.g. from +inf/-inf. D50804 didn't catch that.
Reviewed By: arsenm
Differential Revision: https://reviews.llvm.org/D134854
Previously we would be unable to legalize V2S16 BUILD_VECTOR_TRUNC on GFX8 & below as the custom legalization was missing.
Reviewed By: arsenm
Differential Revision: https://reviews.llvm.org/D135149
Since SROA chooses promotion based on reaching load / stores of allocas, we may run into scenarios in which we alloca a vector, but promote it to an integer. The result of which is the familiar LoadCombine pattern (i.e. ZEXT, SHL, OR). However, instead of coming directly from distinct loads, the elements to be combined are coming from ExtractVectorElements which stem from a shared load.
This patch identifies such a pattern and combines it into a load.
Change-Id: I0bc06588f11e88a0a975cde1fd71e9143e6c42dd
The bitmask used to extract the bits assumed 16 bit elements and wasn't taking the size of the elements into account.
Reviewed By: arsenm
Differential Revision: https://reviews.llvm.org/D135156
Fix a crash in the FMA combine added by D132837 and amended by D134810.
In cases where the newly created node could be folded, the combiner
would fail this assertion:
llc: DAGCombiner.cpp:268: void (anonymous namespace)::DAGCombiner::AddToWorklist(llvm::SDNode *): Assertion `N->getOpcode() != ISD::DELETED_NODE && "Deleted Node added to Worklist"' failed.
Differential Revision: https://reviews.llvm.org/D135150
If we can not prove that f16 operands of a buildvector are canonicalized, then we can not lower into a V_PACK. In this scenario, we would previously lower into some combination of and(sdwa), shr, or. This patch allows for matching into V_PERM instead.
Change-Id: Ifa4a74fdb81ef44f22ba490c7fdf81ec8aebc945
VALU use of an SGPR (pair) as mask followed by SALU write to the
same SGPR can cause incorrect execution of subsequent SALU reads
of the SGPR.
Reviewed By: foad, rampitec
Differential Revision: https://reviews.llvm.org/D134151
Recognize more opcodes in the function.
Fixes some regressions introduced in D134857 for fdiv.f16 too.
Depends on D134857
Reviewed By: arsenm, foad
Differential Revision: https://reviews.llvm.org/D134862
Preparation patch for D134354 to make V2S16 G_BUILD_VECTOR legal.
Also removes RegBankInfo's scalarization of small BUILD_VECTORs,
replacing it with InstructionSelector logic instead.
This allows for V2S16 BUILD_VECTOR instructions to survive
all the way to ISel so we can select FMA/MAD_MIX instructions
in D134354.
Reviewed By: arsenm
Differential Revision: https://reviews.llvm.org/D134433
In D132837, an existing v_fma combine was extended to regard nested
fma instructions. Originally, the inner FMA was checked for being used
only once. In its current state, this check is missing, which causes
some regressions.
In this patch, this check was added.
Reviewed By: foad
Differential Revision: https://reviews.llvm.org/D134856
- Use `fneg %a` instead of `fsub -0.0, %a`
- This is for D134354 as we don't currently support folding `fsub -0.0, %a` into `fneg` on GISel.
Also, `fneg` is the canonical way to do the negation.
- Switch to `update_llc_test_checks`-generated tests.
- Better test coverage
- Easier to update
- Easier to see changes in future diffs
- Remove unnecessary CL arguments in RUN lines
Motive for the patch: Preparation for D134354 - we would like to
put GISel tests in this file as well. Fixing the lack of `fneg` and
switching to generated testing makes it much easier.
Reviewed By: arsenm
Differential Revision: https://reviews.llvm.org/D134793
This change sets
-amdgpu-assume-{external-call-stack-size | dynamic-stack-object-size}
options to zero by default for code object v5 and later. The runtime is
expected to adjust the scratch size if the amdhsa_uses_dynamic_stack bit
in the kernel descriptor is set.
Differential Revision: https://reviews.llvm.org/D128346
Given something like this:
```
declare signext i16 @signext_callee()
define i32 @caller() {
%res = call i16 @signext_callee()
...
}
```
CallLowering would miss that signext_callee's return value is sign extended,
because it isn't on the call.
Use hasRetAttr on the CallBase to allow us to catch this.
(This now inserts G_ASSERT_SEXT/G_ASSERT_ZEXT like in the original review.)
Differential Revision: https://reviews.llvm.org/D86228
D132837 introduced a new DAG combine that used MorphNodeTo to morph an
FMUL into an FMA. It turns out that MorphNodeTo does not properly update
the divergence bit for users of the morphed node, causing an assertion
failure on the new test case:
llc: SelectionDAG.cpp:10486: void llvm::SelectionDAG::VerifyDAGDivergence(): Assertion `calculateDivergence(N) == N->isDivergent() && "Divergence bit inconsistency detected"' failed.
Fixing MorphNodeTo to propagate the divergence bit is tricky because of
the way it is used to select machine instructions, so use getNode and
ReplaceAllUsesOfValueWith instead.
Differential Revision: https://reviews.llvm.org/D134810
One of the conditions to flush the vmcnt counter in loop preheaders is: The loop
contains a use of a vgpr that is defined out of the loop. The code currently
checks if a waitcnt is needed by looking at the score of that vgpr in the score
brackets. This is not enough and may cause the generation of an unnecessary
vmcnt flush. This patch fixes that case.
Differential Revision: https://reviews.llvm.org/D130313
The association between kernel and struct is done by symbol name.
This doesn't work robustly for anonymous kernels as shown by the modified
test case.
An alternative association between function and struct can be constructed
if necessary, probably though metadata, but on the basis that we currently
miscompile anonymous kernels and that they are difficult to construct from
application code and difficult to call from the runtime, this patch makes
it a fatal error for now.
Reviewed By: arsenm
Differential Revision: https://reviews.llvm.org/D134741
A User like the PHINode may be visited multiple times for the same pointer along
different def-use edges. The uninitialized state of OffsetInfo at the first
visit needs to be distinct from the Unknown value that may be assigned after
processing the PHINode. Without that, a PHINode with all inputs Unknown is never
followed to its uses. This results in incorrect optimization because some
interfering accessess are missed.
Differential Revision: https://reviews.llvm.org/D134704
Surprisingly these were getting legalized to something
zero initialized.
This fixes an infinite loop when combining some vector types.
Also fixes zero initializing some undef values.
SimplifyDemandedVectorElts / SimplifyDemandedBits are not checking
for the legality of the output undefs they are replacing unused
operations with. This resulted in turning vectors into undefs
that were later re-legalized back into zero vectors.
A kernel may have an associated struct for laying out LDS variables.
This patch puts that instance, if present, at a deterministic address by
allocating it at the same time as the module scope instance.
This is relatively likely to be where the instance was allocated anyway (~NFC)
but will allow later patches to calculate where a given field can be found,
which means a function which is only reachable from a single kernel will be
able to access a LDS variable with zero overhead. That will be particularly
helpful for applications that instantiate a function template containing LDS
variables once per kernel.
Reviewed By: arsenm
Differential Revision: https://reviews.llvm.org/D127052
Make MIMG NSA minimum addresses threshold an attribute that can
be set on a function or configured via command line.
This enables frontend tuning which allows increased NSA usage
where beneficial.
Reviewed By: foad
Differential Revision: https://reviews.llvm.org/D134780
Summary:
With opaque pointer support, the "ptr" type is introduced and thus BitCast is not necessary in some cases.
This work takes care of this change, and recognizes the new address patterns to do appropriate optimizations.
Reviewers:
arsenm
Differential Revision:
https://reviews.llvm.org/D134596
During structurization process, we may place non-predecessor blocks
between the predecessors of a block in the structurized CFG. Take
the typical while-break case as an example:
```
/---A(v=...)
| / \
^ B C
| \ /|
\---L |
\ /
E (r = phi (v:C)...)
```
After structurization, the CFG would be look like:
```
/---A
| |\
| | C
| |/
| F1
^ |\
| | B
| |/
| F2
| |\
| | L
\ |/
\--F3
|
E
```
We can see that block B is placed between the predecessors(C/L) of E.
During phi reconstruction, to achieve the same sematics as before, we
are reconstructing the PHIs as:
F1: v1 = phi (v:C), (undef:A)
F3: r = phi (v1:F2), ...
But this is also saying that `v1` would be live through B, which is not
quite necessary. The idea in the change is to say the incoming value
from B is Undef for the PHI in E. With this change, the reconstructed
PHI would be:
F1: v1 = phi (v:C), (undef:A)
F2: v2 = phi (v1:F1), (undef:B)
F3: r = phi (v2:F2), ...
Reviewed by: sameerds
Differential Revision: https://reviews.llvm.org/D132450
The instruction simplification will try to simplify the affected phis.
In some cases, this might extend the liveness of values. For example:
BB0:
| \
| BB1
| /
BB2:phi (BB0, v), (BB1, undef)
The phi in BB2 will be simplified to v as v dominates BB2, but this is
increasing the number of active values in BB1. By setting CanUseUndef
to false, we will not simplify the phi in this way, this would help
register pressure. This is mandatory for the later change to help
reducing VGPR pressure for AMDGPU.
Reviewed by: foad, sameerds
Differential Revision: https://reviews.llvm.org/D132449
