9931b1f7a4785b6a17fb87b81a3546d61d0cbca1 switched this to checking for
the two specific subtargets, instead of the dedicated feature. This
broke supporting functions which force added the feature when emitting
targets that do not actually support them. This stil does not work for
the targets that use the gfx6/7 or gfx10 encodings.
The Linux kernel objtool diagnostic `call without frame pointer save/setup`
arise in multiple instrumentation passes (asan/tsan/gcov). With the mechanism
introduced in D100251, it's trivial to respect the command line
-m[no-]omit-leaf-frame-pointer/-f[no-]omit-frame-pointer, so let's do it.
Fix: https://github.com/ClangBuiltLinux/linux/issues/1236 (tsan)
Fix: https://github.com/ClangBuiltLinux/linux/issues/1238 (asan)
Also document the function attribute "frame-pointer" which is long overdue.
Differential Revision: https://reviews.llvm.org/D101016
Background:
CFGStackify's [[ 398f253400/llvm/lib/Target/WebAssembly/WebAssemblyCFGStackify.cpp (L1481-L1540) | fixEndsAtEndOfFunction ]] fixes block/loop/try's return
type when the end of function is unreachable and the function return
type is not void. So if a function returns i32 and `block`-`end` wraps the
whole function, i.e., the `block`'s `end` is the last instruction of the
function, the `block`'s return type should be i32 too:
```
block i32
...
end
end_function
```
If there are consecutive `end`s, this signature has to be propagate to
those blocks too, like:
```
block i32
...
block i32
...
end
end
end_function
```
This applies to `try`-`end` too:
```
try i32
...
catch
...
end
end_function
```
In case of `try`, we not only follow consecutive `end`s but also follow
`catch`, because for the type of the whole `try` to be i32, both `try`
and `catch` parts have to be i32:
```
try i32
...
block i32
...
end
catch
...
block i32
...
end
end
end_function
```
---
Previously we only handled consecutive `end`s or `end` before a `catch`.
But now we have `delegate`, which serves like `end` for
`try`-`delegate`. So we have to follow `delegate` too and mark its
corresponding `try` as i32 (the function's return type):
```
try i32
...
catch
...
try i32 ;; Here
...
delegate N
end
end_function
```
Reviewed By: tlively
Differential Revision: https://reviews.llvm.org/D101036
This adds support for YAML serialization of `Params` and `Results`
fields in `WebAssemblyMachineFunctionInfo`. Types are printed as `MVT`'s
string representation. This is for writing MIR tests easier.
The tests added are testing simple parsing and printing of `params` /
`results` fields under `machineFunctionInfo`.
Reviewed By: tlively
Differential Revision: https://reviews.llvm.org/D101029
This CL
1. Creates Utils/ directory under lib/Target/WebAssembly
2. Moves existing WebAssemblyUtilities.cpp|h into the Utils/ directory
3. Creates Utils/WebAssemblyTypeUtilities.cpp|h and put type
declarataions and type conversion functions scattered in various
places into this single place.
It has been suggested several times that it is not easy to share utility
functions between subdirectories (AsmParser, DIsassembler, MCTargetDesc,
...). Sometimes we ended up [[ https://reviews.llvm.org/D92840#2478863 | duplicating ]] the same function because of
this.
There are already other targets doing this: AArch64, AMDGPU, and ARM
have Utils/ subdirectory under their target directory.
This extracts the utility functions into a single directory Utils/ and
make them sharable among all passes in WebAssembly/ and its
subdirectories. Also I believe gathering all type-related conversion
functionalities into a single place makes it more usable. (Actually I
was working on another CL that uses various type conversion functions
scattered in multiple places, which became the motivation for this CL.)
Reviewed By: dschuff, aardappel
Differential Revision: https://reviews.llvm.org/D100995
Add PromoteIntOp_FP_TO_XINT_SAT to type legalize the bit width
operand from i32 to i64 for RV64.
Add test cases for the saturating intrinsics for half/float/double
and i32/i64. CodeGen is definitely not optimal. We can probably
make use of the native behavior of fcvt instructions in many cases.
Fixes PR50083
This patch is supposed to solve: https://bugs.llvm.org/show_bug.cgi?id=50075
The function `__dfsan_mem_transfer_callback` takes a `Len` argument of type `i64`; however, when processing a `MemTransferInst` such as `llvm.memcpy.p0i8.p0i8.i32`, the `len` argument has type `i32`. In order to make the type of `len` compatible with the one of the callback argument, this change zero-extends it when necessary.
Reviewed By: stephan.yichao.zhao, gbalats
Differential Revision: https://reviews.llvm.org/D101048
'not' expands to checking for an xor with a -1 constant. Since
this looks for a ConstantSDNode it will never match for a vector.
Co-authored-by: Craig Topper <craig.topper@sifive.com>
Differential Revision: https://reviews.llvm.org/D100687
Both the alias and aliasee linkage are important.
PR27866 provides some background.
Reviewed By: rnk
Differential Revision: https://reviews.llvm.org/D99629
This improves the lowering of v8i16 and v16i8 vector reverse shuffles.
Instead of going via a generic tbl it uses a rev64; ext pair, as already
happens for v4i32.
Differential Revision: https://reviews.llvm.org/D100882
lookupTarget() can update the passed triple argument. This happens
when no triple is given on the command line, and the architecture
argument does not match the architecture in the default triple.
For example, passing -march=aarch64 on the command line, and the
default triple being x86_64-windows-msvc, the triple is changed
to aarch64-windows-msvc.
However, this triple is not saved, and later in the code, the
triple is constructed again from the triple name, which is the
default triple at this point. Thus the default triple is passed
to constructor of MCSubtargetInfo instance.
The triple is only used determine the object file format, and by
chance, the AArch64 target also uses the COFF file format, and
all is fine. Obviously, the AArch64 target does not support all
available binary file formats, e.g. XCOFF and GOFF, and llvm-mca
crashes in this case.
The fix is to update the triple name with the changed triple
name for the target lookup. Then the default object file format
for the architecture is used, in the example ELF.
Reviewed By: andreadb, abhina.sreeskantharajan
Differential Revision: https://reviews.llvm.org/D100992
This change effectively reverts 86664638, but since there have been some changes on top and I wanted to leave the tests in, it's not a mechanical revert.
Why revert this now? Two main reasons:
1) There are continuing discussion around what the semantics of nofree. I am getting increasing uncomfortable with the seeming possibility we might redefine nofree in a way incompatible with these changes.
2) There was a reported miscompile triggered by this change (https://github.com/emscripten-core/emscripten/issues/9443). At first, I was making good progress on tracking down the issues exposed and those issues appeared to be unrelated latent bugs. Now that we've found at least one bug in the original change, and the investigation has stalled, I'm no longer comfortable leaving this in tree. In retrospect, I probably should have reverted this earlier and investigated the issues once the triggering change was out of tree.
These instructions don't really exist, but we have ways we can
emulate them.
.vv will swap operands and use vmsle().vv. .vi will adjust the
immediate and use .vmsgt(u).vi when possible. For .vx we need to
use some of the multiple instruction sequences from the V extension
spec.
For unmasked vmsge(u).vx we use:
vmslt{u}.vx vd, va, x; vmnand.mm vd, vd, vd
For cases where mask and maskedoff are the same value then we have
vmsge{u}.vx v0, va, x, v0.t which is the vd==v0 case that
requires a temporary so we use:
vmslt{u}.vx vt, va, x; vmandnot.mm vd, vd, vt
For other masked cases we use this sequence:
vmslt{u}.vx vd, va, x, v0.t; vmxor.mm vd, vd, v0
We trust that register allocation will prevent vd in vmslt{u}.vx
from being v0 since v0 is still needed by the vmxor.
Differential Revision: https://reviews.llvm.org/D100925
Refactor to use new multiclass instead of individual patterns.
We already supported this due to SEW=64 on RV32, but we didn't have
test cases for all the types we supported.
Part of D100925
We don't have instructions for these, but can swap the operands
to use vmle/vmflt. This makes the IR interface more consistent and
simplifies the frontend implementation.
Part of D100925
This partially reverts commit 77ac823fd285973cfb3517932c09d82e6a32f46d.
Halide uses le32/le64 (https://github.com/halide/Halide/pull/5934).
Temporarily brings back the code part to give them some time for migration.
Implementations are allowed to optimize an x0 stride to perform
less memory accesses. This is the case in SiFive cores.
No idea if this is the case in other implementations. We might
need a tuning flag for this.
Reviewed By: frasercrmck, arcbbb
Differential Revision: https://reviews.llvm.org/D100815
Rather than doing splatting each separately and doing bit manipulation
to merge them in the vector domain, copy the data to the stack
and splat it using a strided load with x0 stride. At least on
some implementations this vector load is optimized to not do
a load for each element.
This is equivalent to how we move i64 to f64 on RV32.
I've only implemented this for the intrinsic fallbacks in this
patch. I think we do similar splatting/shifting/oring in other
places. If this is approved, I'll refactor the others to share
the code.
Differential Revision: https://reviews.llvm.org/D101002
Intrinsics for the following instructions are added. The intrinsic
name is "int_hexagon_<inst>[_128B]", e.g.
int_hexagon_V6_vL32b_pred_ai for 64-byte version
int_hexagon_V6_vL32b_pred_ai_128B for 128-byte version
V6_vL32b_pred_ai if (Pv4) Vd32 = vmem(Rt32+#s4)
V6_vL32b_pred_pi if (Pv4) Vd32 = vmem(Rx32++#s3)
V6_vL32b_pred_ppu if (Pv4) Vd32 = vmem(Rx32++Mu2)
V6_vL32b_npred_ai if (!Pv4) Vd32 = vmem(Rt32+#s4)
V6_vL32b_npred_pi if (!Pv4) Vd32 = vmem(Rx32++#s3)
V6_vL32b_npred_ppu if (!Pv4) Vd32 = vmem(Rx32++Mu2)
V6_vL32b_nt_pred_ai if (Pv4) Vd32 = vmem(Rt32+#s4):nt
V6_vL32b_nt_pred_pi if (Pv4) Vd32 = vmem(Rx32++#s3):nt
V6_vL32b_nt_pred_ppu if (Pv4) Vd32 = vmem(Rx32++Mu2):nt
V6_vL32b_nt_npred_ai if (!Pv4) Vd32 = vmem(Rt32+#s4):nt
V6_vL32b_nt_npred_pi if (!Pv4) Vd32 = vmem(Rx32++#s3):nt
V6_vL32b_nt_npred_ppu if (!Pv4) Vd32 = vmem(Rx32++Mu2):nt
V6_vS32b_pred_ai if (Pv4) vmem(Rt32+#s4) = Vs32
V6_vS32b_pred_pi if (Pv4) vmem(Rx32++#s3) = Vs32
V6_vS32b_pred_ppu if (Pv4) vmem(Rx32++Mu2) = Vs32
V6_vS32b_npred_ai if (!Pv4) vmem(Rt32+#s4) = Vs32
V6_vS32b_npred_pi if (!Pv4) vmem(Rx32++#s3) = Vs32
V6_vS32b_npred_ppu if (!Pv4) vmem(Rx32++Mu2) = Vs32
V6_vS32Ub_pred_ai if (Pv4) vmemu(Rt32+#s4) = Vs32
V6_vS32Ub_pred_pi if (Pv4) vmemu(Rx32++#s3) = Vs32
V6_vS32Ub_pred_ppu if (Pv4) vmemu(Rx32++Mu2) = Vs32
V6_vS32Ub_npred_ai if (!Pv4) vmemu(Rt32+#s4) = Vs32
V6_vS32Ub_npred_pi if (!Pv4) vmemu(Rx32++#s3) = Vs32
V6_vS32Ub_npred_ppu if (!Pv4) vmemu(Rx32++Mu2) = Vs32
V6_vS32b_nt_pred_ai if (Pv4) vmem(Rt32+#s4):nt = Vs32
V6_vS32b_nt_pred_pi if (Pv4) vmem(Rx32++#s3):nt = Vs32
V6_vS32b_nt_pred_ppu if (Pv4) vmem(Rx32++Mu2):nt = Vs32
V6_vS32b_nt_npred_ai if (!Pv4) vmem(Rt32+#s4):nt = Vs32
V6_vS32b_nt_npred_pi if (!Pv4) vmem(Rx32++#s3):nt = Vs32
V6_vS32b_nt_npred_ppu if (!Pv4) vmem(Rx32++Mu2):nt = Vs32
The buffer we turn into a std::string here is malloc'd and should be
free'd before we return from this function.
Follow up to LLDB leak fixes such as D100806.
Reviewed By: mstorsjo, rupprecht, MaskRay
Differential Revision: https://reviews.llvm.org/D100843
The first version of origin tracking tracks only memory stores. Although
this is sufficient for understanding correct flows, it is hard to figure
out where an undefined value is read from. To find reading undefined values,
we still have to do a reverse binary search from the last store in the chain
with printing and logging at possible code paths. This is
quite inefficient.
Tracking memory load instructions can help this case. The main issues of
tracking loads are performance and code size overheads.
With tracking only stores, the code size overhead is 38%,
memory overhead is 1x, and cpu overhead is 3x. In practice #load is much
larger than #store, so both code size and cpu overhead increases. The
first blocker is code size overhead: link fails if we inline tracking
loads. The workaround is using external function calls to propagate
metadata. This is also the workaround ASan uses. The cpu overhead
is ~10x. This is a trade off between debuggability and performance,
and will be used only when debugging cases that tracking only stores
is not enough.
Reviewed By: gbalats
Differential Revision: https://reviews.llvm.org/D100967
This patch adds semantic checks for the General Restrictions of the
Allocate Directive.
Since the requires directive is not yet implemented in Flang, the
restriction:
```
allocate directives that appear in a target region must
specify an allocator clause unless a requires directive with the
dynamic_allocators clause is present in the same compilation unit
```
will need to be updated at a later time.
A different patch will be made with the Fortran specific restrictions of
this directive.
I have used the code from https://reviews.llvm.org/D89395 for the
CheckObjectListStructure function.
Co-authored-by: Isaac Perry <isaac.perry@arm.com>
Reviewed By: clementval, kiranchandramohan
Differential Revision: https://reviews.llvm.org/D91159
We can skip check for undefs trying to find perfect/shuffled tree
entries matching, they can be ignored completely improving the final
cost/vectorization results.
Differential Revision: https://reviews.llvm.org/D101061
There are no patterns for the AArch64ISD::BSP ISD node for anything
other than NEON vectors at the moment. As a result, if we hit these
combines for vectors wider than a NEON vector (such as what we might get
with fixed length SVE) we will fail to lower.
This patch simply prevents us from attempting the combines if the input
vector type is too wide.
Reviewed By: peterwaller-arm
Differential Revision: https://reviews.llvm.org/D100961
This commit fixes a bug where the loop vectoriser fails to predicate
loads/stores when interleaving for targets that support masked
loads and stores.
Code such as:
1 void foo(int *restrict data1, int *restrict data2)
2 {
3 int counter = 1024;
4 while (counter--)
5 if (data1[counter] > data2[counter])
6 data1[counter] = data2[counter];
7 }
... could previously be transformed in such a way that the predicated
store implied by:
if (data1[counter] > data2[counter])
data1[counter] = data2[counter];
... was lost, resulting in miscompiles.
This bug was causing some tests in llvm-test-suite to fail when built
for SVE.
Differential Revision: https://reviews.llvm.org/D99569
1. No need to call `areAllUsersVectorized` as later the cost is
calculated only if the instruction has one use and gets vectorized.
2. Need to calculate the cost of the dead extractelement more precisely,
taking the vector type of the vector operand, not the resulting
vector type.
Part of D57059.
Differential Revision: https://reviews.llvm.org/D99980
This patch adds strings content checking to printf-2.ll via --check-globals flag.
Split off from D100724.
Reviewed By: xbolva00
Differential Revision: https://reviews.llvm.org/D101034
