This patch allows `combineBinOp_VLToVWBinOp_VL` to handle patterns like
`(splat_vector (sext op))` or `(splat_vector (zext op))`. Then we can
use `vwadd.vx` and `vwadd.w` for such a case.
### Source code
```
define <vscale x 8 x i64> @vwadd_vx_splat_sext(<vscale x 8 x i32> %va, i32 %b) {
%sb = sext i32 %b to i64
%head = insertelement <vscale x 8 x i64> poison, i64 %sb, i32 0
%splat = shufflevector <vscale x 8 x i64> %head, <vscale x 8 x i64> poison, <vscale x 8 x i32> zeroinitializer
%vc = sext <vscale x 8 x i32> %va to <vscale x 8 x i64>
%ve = add <vscale x 8 x i64> %vc, %splat
ret <vscale x 8 x i64> %ve
}
```
### Before this patch
[Compiler Explorer](https://godbolt.org/z/sq191PsT4)
```
vwadd_vx_splat_sext:
sext.w a0, a0
vsetvli a1, zero, e64, m8, ta, ma
vmv.v.x v16, a0
vsetvli zero, zero, e32, m4, ta, ma
vwadd.wv v16, v16, v8
vmv8r.v v8, v16
ret
```
### After this patch
```
vwadd_vx_splat_sext
vsetvli a1, zero, e32, m4, ta, ma
vwadd.vx v16, v8, a0
vmv8r.v v8, v16
ret
```
Fixes#76623
Alive2 proof: https://alive2.llvm.org/ce/z/gX6znJ (I'm not sure how to
write a proof for such transform, maybe there are mistakes)
In most cases, `icmp(a, C1) && (other_cond && icmp(a, C2))` will be
reduced to `icmp(a, C1) & (other_cond && icmp(a, C2))`, since latter
icmp always implies the poison of the former. After reduction, it's
easier to simplify the icmp chain.
Similarly, this patch does the same thing for `(A && B) && C --> A && (B
& C)`. Maybe we could constraint such reduction only on icmps if there
is regression in benchmarks.
When moving an entire basic block after `InsertPoint`, currently we
check each instruction whether their users are dominated by
`InsertPoint`, however, this can be improved such that even a user is
not dominated by `InsertPoint`, as long as it appears as a subsequent
instruction in the same BB, it is safe to move.
This patch is similar to commit 751be2a064f119af74c7b9b1e52bc904d8aa114d
that enhanced hoisting an entire BB, and this patch enhances sinking an
entire BB. Please refer to the added functionality in test case
`llvm/unittests/Transforms/Utils/CodeMoverUtilsTest.cpp` that was not
supported without this patch.
Copy `nneg` flag when building `UINT_TO_FP` from `uitofp` and use
`nneg` flag in the one place we transform `UINT_TO_FP` -> `SINT_TO_FP`
if the operand is non-negative.
Improvements include
* Enable `ListeningSocket::accept` to timeout after a specified amount
of time or block indefinitely
* Enable `ListeningSocket::createUnix` to handle instances where the
target socket address already exists and differentiate between
situations where the existing file does and does not already have a
bound socket
* Doxygen comments
Functionality added for the module build daemon
---------
Co-authored-by: Michael Spencer <bigcheesegs@gmail.com>
As noted when #82404 was pushed (canonicalizing `sitofp` -> `uitofp`),
different signedness on fp casts can have dramatic performance
implications on different backends.
So, it makes to create a reliable means for the backend to pick its
cast signedness if either are correct.
Further, this allows us to start canonicalizing `sitofp`- > `uitofp`
which may easy middle end analysis.
Closes#86141
Restructures the cloning slightly to perform all cloning for each
allocation separately. The prior algorithm would sometimes miss cloning
opportunities in cases where trimmed cold contexts partially overlapped
with longer contexts for different allocations.
Most of the change is isolated to the helpers that move edges to new or
existing clones, which now support moving a subset of context ids.
Summary:
These entires are generic for offloading with the new driver now. Having
the `omp` prefix was a historical artifact and is confusing when used
for CUDA. This patch just renames them for now, future patches will
rework the binary format to make it more common.
Saves several MB of memory in larger applications after linking finishes
by clearing DenseMap storage that is empty. This does not attempt to
shrink partially full materialization infos. The assumption is that
adding more after linking finishes is rare.
rdar://126145336
This removes the old legacy PM "intervals" analysis pass (aka
IntervalPartition). It also removes the associated Interval and
IntervalIterator help classes.
Reasons for removal:
1) The pass is not used by llvm-project (not even being tested by
any regression tests).
2) Pass has not been ported to new pass manager, which at least
indicates that it isn't used by the middle-end.
3) ASan reports heap-use-after-free on
++I; // After the first one...
even if false is passed to intervals_begin. Not sure if that is
a false positive, but it makes the code a bit less trustworthy.
`getDebugNamesBucketAndHashCount` lures users to provide an array to
compute the bucket count using an O(n log n) sort. This is inefficient
as hash table based uniquifying is faster.
The performance issue matters less for Clang as the number of names is
relatively small. For `ld.lld --debug-names`, I plan to compute the
unique hash count as a side product of parallel entry pool computation,
and I just need a function to suggest a bucket count.
Need to improve detection of number of bits, required for the operand,
before doing a reduction. If the instruction is incoming operand of the
signed compare, need to consider adding an extra bit for signedness.
Update the remaining uses of `std::begin`/`end` functions to
`adl_beging`/`end`. This is to make the behavior all the utility
functions consistent, rather than trying to fix a specific usecase.
Currently the bitwise NOT instruction is not recognized. Add support for
using NOT on data registers. This is a partial implementation that puts
NOT at the same level of support as NEG currently enjoys.
Using not rather than eori cuts the length of the encoded instruction
in half or in thirds, leading to a reduction of 4-10 cycles per
instruction, on the original 68000.
This change includes tests for both bitwise and arithmetic negation.
Need to use vectorized operands, not the vecop of the extractelement
instructions, to avoid false detection of the extra vector operand in
the extractelements shuffling.
This tries to add some costs for the shuffle in a ST3/ST4 instruction,
which are represented in LLVM IR as store(interleaving shuffle). In
order to detect the store, it needs to add a CxtI context instruction to
check the users of the shuffle. LD3 and LD4 are added, LD2 should be a
zip1 shuffle, which will be added in another patch.
It should help fix some of the regressions from #87510.
7dc20ab introduced an extra COPY when spilling and filling a PNR
register, which can't be elided as the input (PNR predicate) and output
(PPR predicate) register classes differ. The patch adds a new register
class that covers both PPR and PNR so that STR_PXI and LDR_PXI can
take either of them, removing the need for the copy.
This PR fixes issue https://github.com/llvm/llvm-project/issues/87763
and preserves valid CFG in cases when previous scheme failed to generate
valid code for a switch statement. The PR hardens one existing test case
and adds one more test case as a validation of a new switch generation.
Tests are passing spirv-val now.
This PR also improves validation of forward calls.
SPIR-V intsruction selection was mapping the LLVM float min/max
intrinsics to FMin and FMax respectively for GL/Vulkan environments,
which does not match the intrinsics' documented treatment of NaN
operands. This patch switches the mapping to the correctly matched NMin
and NMax operations.
Fixes#87072
Allows us to match insert_subvector(insert_subvector(undef, insert_subvector(insert_subvector(undef, x, 0), y, 1), 0), 0),
insert_subvector(insert_subvector(undef, z, 0), w, 1), 2)
Create PatFrags for fadd, fmul, fsub, mul, smulh and umulh so that a
single set of patterns can be used. Patch then removes unused classes
and some redundant whitespace.
VPBlendRecipe does not use the first mask operand. Removing it allows
VPlan-based DCE to remove unused mask computations.
This also fixes#87410, where unused Not VPInstructions are considered
having only their first lane demanded, but some of their operands
providing a vector value due to other users.
Fixes https://github.com/llvm/llvm-project/issues/87410
PR: https://github.com/llvm/llvm-project/pull/87770
