Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Arm64/Sve: Implement SVE Math *Multiply* APIs #102007

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 30 commits into from
May 11, 2024
Merged

Arm64/Sve: Implement SVE Math *Multiply* APIs #102007

Changes from 1 commit
Commits
Show all changes
30 commits
Select commit Hold shift + click to select a range
97373ca
Add *Fused* APIs
kunalspathak May 6, 2024
4e14098
fix an assert in morph
kunalspathak May 7, 2024
3fb9dea
Map APIs to instructions
kunalspathak May 7, 2024
600391a
Add test cases
kunalspathak May 8, 2024
67e4d4d
handle fused* instructions
kunalspathak May 8, 2024
54899b2
jit format
kunalspathak May 8, 2024
e4a53ae
Added MultiplyAdd/MultiplySubtract
kunalspathak May 8, 2024
bfad7b7
Add mapping of API to instruction
kunalspathak May 8, 2024
100f289
Add test cases
kunalspathak May 8, 2024
8ac1840
Handle mov Z, Z instruction
kunalspathak May 9, 2024
9eb195e
Reuse GetResultOpNumForRmwIntrinsic() for arm64
kunalspathak May 9, 2024
c182d0d
Reuse HW_Flag_FmaIntrinsic for arm64
kunalspathak May 9, 2024
62ea159
Mark FMA APIs as HW_Flag_FmaIntrinsic
kunalspathak May 9, 2024
28a49cb
Handle FMA in LSRA and codegen
kunalspathak May 9, 2024
722dd55
Remove the SpecialCodeGen flag from selectedScalar
kunalspathak May 9, 2024
229f78f
address some more scenarios
kunalspathak May 10, 2024
a21439f
jit format
kunalspathak May 10, 2024
6a01ca4
Add MultiplyBySelectedScalar
kunalspathak May 10, 2024
318cbf3
Map the API to the instruction
kunalspathak May 10, 2024
e3fc830
fix a bug where *Indexed API used with ConditionalSelect were failing
kunalspathak May 10, 2024
1ca5539
unpredicated movprfx should not send opt
kunalspathak May 10, 2024
eb41e1d
Add the missing flags for Subtract/Multiply
kunalspathak May 10, 2024
7874f25
Added tests for MultiplyBySelectedScalar
kunalspathak May 10, 2024
f756afb
fixes to test cases
kunalspathak May 10, 2024
2904934
fix the parameter for selectedScalar test
kunalspathak May 10, 2024
53d29a0
Merge remote-tracking branch 'origin/main' into sve_math6
kunalspathak May 10, 2024
98ac0ce
jit format
kunalspathak May 10, 2024
0f89e10
Contain(op3) of CndSel if op1 is AllTrueMask
kunalspathak May 10, 2024
8e928ec
Handle FMA properly
kunalspathak May 10, 2024
c713d31
added assert
kunalspathak May 10, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
added assert
  • Loading branch information
@kunalspathak
kunalspathak committed May 10, 2024
commit c713d3155495ca390098e6d4853dbb74ab1f999c
1 change: 1 addition & 0 deletions src/coreclr/jit/hwintrinsiccodegenarm64.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -677,6 +677,7 @@ void CodeGen::genHWIntrinsic(GenTreeHWIntrinsic* node)
// destination using /Z.

assert(targetReg != embMaskOp2Reg);
assert(intrin.op3->isContained() || !intrin.op1->IsMaskAllBitsSet());
GetEmitter()->emitIns_R_R_R(INS_sve_movprfx, emitSize, targetReg, maskReg, embMaskOp1Reg, opt);
}
else
Expand Down