This was introduced ~5yrs ago (by me), and has never really gotten
any adoption. By now, it's significantly out of sync with new/changed
poison propoagation rules. The idea is still reasonable, but the
imagined use case is largely covered by alive2 these days anyways.
https://github.com/llvm/llvm-project/pull/65972 introduced
-ubsan-unique-traps and -bounds-checking-unique-traps, which attach the
function size to the ubsantrap intrinsic.
https://github.com/llvm/llvm-project/pull/117651 changed
ubsan-unique-traps to use nomerge instead of the function size, but did
not update -bounds-checking-unique-traps. This patch adds nomerge to
bounds-checking-unique-traps.
This is a NFC.
Duplicate gfx12_asm_vop3_alias.s file to true16/fake16 version and
update `real-true16` flag on it.
This is preparing the upcoming changes for true16
This patch introduces IndexedCallstackIdConveter as a convenience
wrapper around FrameIdConverter and CallStackIdConverter just for
tests.
With the new wrapper, we get to replace idioms like:
FrameIdConverter<decltype(MemProfData.Frames)> FrameIdConv(
MemProfData.Frames);
CallStackIdConverter<decltype(MemProfData.CallStacks)> CSIdConv(
MemProfData.CallStacks, FrameIdConv);
with:
IndexedCallstackIdConveter CSIdConv(MemProfData);
Unfortunately, this exact pattern occurs in tests only; the
combinations of the frame ID converter and call stack ID converter are
diverse in production code.
- update `VectorUtils:isVectorIntrinsicWithScalarOpAtArg` to use TTI for
all uses, to allow specifiction of target specific intrinsics
- add TTI to the `isVectorIntrinsicWithStructReturnOverloadAtField` api
- update TTI api to provide `isTargetIntrinsicWith...` functions and
consistently name them
- move `isTriviallyScalarizable` to VectorUtils
- update all uses of the api and provide the TTI parameter
Resolves#117030
Prior to this patch, we required that all users had the same VL in order
to optimize. But as the FIXME said, we can use the largest VL to
optimize, as long as we can determine what the largest is. This patch
implements the FIXME.
Add tests for horizontal add patterns with missing/undemanded elements - which typically prevents folding to the (add (shuffle a, b),(shuffle a, b)) optimal pattern
This can be used with /llvmlibthin to create thin archives without an
index, which is a prerequisite for porting
https://reviews.llvm.org/D117284 to lld-link.
Creating files like this is already possible with `llvm-ar rcS`, so this
doesn't add additional problems.
This reverts commit e0526b0780f56eede09b05a859a93626ecdc6e4d.
The `v_minmax/maxmin_f16`(GFX11) needs to be updated to t16 with
`v_minmax/maxmin_num_f16`(GFX12) together since they share the same
codegen pattern. Revert the old patch and resubmit
SDNode::use_iterator now returns an SDUse& when dereferenced.
SDNode::user_iterator returns SDNode*. SDNode::use_begin/use_end/uses
work on use_iterator. SDNode::user_begin/user_end/users work on
user_iterator.
We can now write range based for loops using SDUse& and SDNode::uses().
I've converted many of these in this patch. I didn't update loops that
have additional variables updated in their for statement.
Some loops use SDNode::use_iterator::getOperandNo() which also prevents
using range based for loops. I plan to move this into SDUse in a follow
up patch.
Avoid introducing `ProxyReg` and `MOV` nodes during ISel when lowering
`bitconvert` or similar operations. These nodes are all erased by a
later pass but not introducing them in the first place is simpler and
likely saves compile time.
Also remove redundant `MOV` instruction definitions.
This tool is used for SPGO and is invoked directly by users as described
in the Clang User's Manual[^1].
This change will include llvm-profgen in installations configured with
LLVM_INSTALL_TOOLCHAIN_ONLY, such as those provided by LLVM's executable
Windows installers. This is useful now that LLVM can perform SPGO on
Windows.
[^1]:
https://clang.llvm.org/docs/UsersManual.html#using-sampling-profilers
This patch introduces a scheduling model for the MIPS p8700, an
out-of-order
RISC-V processor. The model includes pipelines for the following units:
- 2 Integer Arithmetic/Logical Units (ALU and AL2)
- Multiply/Divide Unit (MDU)
- Branch Unit (CTI)
- Load/Store Unit (LSU)
- Short Floating-Point Pipe (FPUS)
- Long Floating-Point Pipe (FPUL)
For additional details, refer to the official product page:
https://mips.com/products/hardware/p8700/.
Also adds `UnsupportedSchedZfhmin` to handle cases like
`WriteFCvtF16ToF32` that
previously caused build failures.
In streaming[-compatible] functions, use SVE for scalar FP conversions
to/from integer types. This can help avoid moves between FPRs and GRPs,
which could be costly.
This patch also updates definitions of SCVTF_ZPmZ_StoD and
UCVTF_ZPmZ_StoD to disallow lowering to them from ISD nodes, as doing so
requires creating a [U|S]INT_TO_FP_MERGE_PASSTHRU node with inconsistent
types.
Follow up to #112213.
Note: This PR does not include support for f64 <-> i32 conversions (like
#112564), which needs a bit more work to support.
If the shuffle split results in referencing a single legalised whole vector (i.e. no permutation), then this can be treated as free.
We already do something similar for broadcasts / whole subvector insertion + extraction - its purely an issue for register allocation.
Because these registers require an extra byte to encode in certain
memory form. Putting them later in the list will reduce code size when
EGPR is enabled. And align the same order in GR8, GR16 and GR32 lists.
Example:
movq (%r20), %r11 # encoding: [0xd5,0x1c,0x8b,0x1c,0x24]
movq (%r22), %r11 # encoding: [0xd5,0x1c,0x8b,0x1e]
Following on from https://github.com/llvm/llvm-project/pull/94499, this
patch adds support to the Loop Vectorizer to emit the partial reduction
intrinsics where they may be beneficial for the target.
---------
Co-authored-by: Samuel Tebbs <samuel.tebbs@arm.com>
== We were previously returning an invalid cost when truncating
anything to <vscale x 2 x i1>, which is incorrect since we can
generate perfectly good code for this.
== The costs for truncating legal or unpacked types to predicates
seemed overly optimistic. For example, when truncating
<vscale x 8 x i16> to <vscale x 8 x i1> we typically do
something like
and z0.h, z0.h, #0x1
cmpne p0.h, p0/z, z0.h, #0
I guess it might depend upon whether the input value is
generated in the same block or not and if we can avoid the
inreg zero-extend. However, it feels safe to take the more
conservative cost here.
== The costs for some truncates such as
trunc <vscale x 2 x i32> %a to <vscale x 2 x i16>
were 1, whereas in actual fact they are free and no instructions
are required.
== Also, for this
trunc <vscale x 8 x i32> %a to <vscale x 8 x i16>
it's just a single uzp1 instruction so I reduced the cost to 1.
In general, I've added costs for all cases where the destination
type is legal or unpacked. One unfortunate side effect of this
is the costs for some fixed-width truncates when using SVE now
look too optimistic.
Support the following relocations and assembly operators:
- `R_AARCH64_AUTH_TLSDESC_ADR_PAGE21` (`:tlsdesc_auth:` for `adrp`)
- `R_AARCH64_AUTH_TLSDESC_LD64_LO12` (`:tlsdesc_auth_lo12:` for `ldr`)
- `R_AARCH64_AUTH_TLSDESC_ADD_LO12` (`:tlsdesc_auth_lo12:` for `add`)
ZPR2StridedOrContiguous loads used by a FORM_TRANSPOSED_REG_TUPLE
pseudo should attempt to assign a strided register to avoid unnecessary
copies, even though this may overlap with the list of SVE callee-saved registers.
