|
Revision tags: llvmorg-21-init, llvmorg-19.1.7, llvmorg-19.1.6, llvmorg-19.1.5, llvmorg-19.1.4 |
|
| #
9122c523 |
| 15-Nov-2024 |
Pengcheng Wang <wangpengcheng.pp@bytedance.com> |
[RISCV] Enable bidirectional scheduling and tracking register pressure (#115445)
This is based on other targets like PPC/AArch64 and some experiments.
This PR will only enable bidirectional schedu
[RISCV] Enable bidirectional scheduling and tracking register pressure (#115445)
This is based on other targets like PPC/AArch64 and some experiments.
This PR will only enable bidirectional scheduling and tracking register
pressure.
Disclaimer: I haven't tested it on many cores, maybe we should make
some options being features. I believe downstreams must have tried
this before, so feedbacks are welcome.
show more ...
|
|
Revision tags: llvmorg-19.1.3, llvmorg-19.1.2, llvmorg-19.1.1, llvmorg-19.1.0, llvmorg-19.1.0-rc4 |
|
| #
9a1eded9 |
| 03-Sep-2024 |
Craig Topper <craig.topper@sifive.com> |
[RISCV] Custom legalize f16/bf16 FCOPYSIGN with Zfhmin/Zbfmin. (#107039)
The LegalizeDAG expansion will go through memory since i16 isn't a legal
type. Avoid this by using FMV nodes.
Similar to
[RISCV] Custom legalize f16/bf16 FCOPYSIGN with Zfhmin/Zbfmin. (#107039)
The LegalizeDAG expansion will go through memory since i16 isn't a legal
type. Avoid this by using FMV nodes.
Similar to what we did for #106886 for FNEG and FABS. Special care is
needed to handle the Sign operand being a different type.
show more ...
|
| #
dc19b59e |
| 03-Sep-2024 |
Craig Topper <craig.topper@sifive.com> |
[RISCV] Rename test cases in bfloat-arith.ll and half-arith.ll. NFC
Use _bf16 or _h instead of _s. The _s was copied from float-arith.ll
|
| #
3bdec313 |
| 01-Sep-2024 |
Craig Topper <craig.topper@sifive.com> |
[RISCV] Custom legalize f16/bf16 FNEG/FABS with Zfhmin/Zbfmin. (#106886)
The LegalizeDAG expansion will go through memory since i16 isn't a legal
type. Avoid this by using FMV nodes.
|
| #
a9ffb719 |
| 29-Aug-2024 |
Craig Topper <craig.topper@sifive.com> |
[RISCV] Don't promote f16 FNEG/FABS with Zfhmin/Zhinxmin. (#106474)
fneg/fabs are not supposed to canonicalize nans. Promoting to f32 will
go through an fp_extend which will canonicalize. The gener
[RISCV] Don't promote f16 FNEG/FABS with Zfhmin/Zhinxmin. (#106474)
fneg/fabs are not supposed to canonicalize nans. Promoting to f32 will
go through an fp_extend which will canonicalize. The generic Promote
handler needs to be removed from LegalizeDAG.
We need to use integer bit manip to clear the bit instead.
Unfortunately, this is going through the stack due to i16 not being a
legal type. Fixing that will require custom legalization or some other
generic SelectionDAG change.
show more ...
|
|
Revision tags: llvmorg-19.1.0-rc3, llvmorg-19.1.0-rc2, llvmorg-19.1.0-rc1, llvmorg-20-init |
|
| #
32597685 |
| 09-Jul-2024 |
Jianjian Guan <jacquesguan@me.com> |
[RISCV] Remove experimental for bf16 extensions (#97996)
They are already ratified now.
|
|
Revision tags: llvmorg-18.1.8, llvmorg-18.1.7, llvmorg-18.1.6, llvmorg-18.1.5, llvmorg-18.1.4, llvmorg-18.1.3, llvmorg-18.1.2, llvmorg-18.1.1, llvmorg-18.1.0, llvmorg-18.1.0-rc4, llvmorg-18.1.0-rc3, llvmorg-18.1.0-rc2, llvmorg-18.1.0-rc1, llvmorg-19-init, llvmorg-17.0.6, llvmorg-17.0.5, llvmorg-17.0.4, llvmorg-17.0.3, llvmorg-17.0.2, llvmorg-17.0.1, llvmorg-17.0.0, llvmorg-17.0.0-rc4, llvmorg-17.0.0-rc3, llvmorg-17.0.0-rc2 |
|
| #
8a71f44e |
| 03-Aug-2023 |
Alex Bradbury <asb@igalia.com> |
[RISCV] Expand test coverage of bf16 operations with Zfbfmin and fix gaps
This doesn't bring us to parity with the test/CodeGen/RISCV/half-* test
cases, it simply picks off an initial set that can b
[RISCV] Expand test coverage of bf16 operations with Zfbfmin and fix gaps
This doesn't bring us to parity with the test/CodeGen/RISCV/half-* test
cases, it simply picks off an initial set that can be supported
especially easy. In order to make the review more manageable, I'll
follow up with other cases.
There is zero innovation in the test cases - they simply take the
existing half/float cases and replace f16->bf16 and half->bfloat.
Differential Revision: https://reviews.llvm.org/D156895
show more ...
|