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

Skip to content

Expose various Convert intrinsics for Avx512F, Avx512BW, and Avx512DQ #85281

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 14 commits into from
Apr 25, 2023
Merged

Expose various Convert intrinsics for Avx512F, Avx512BW, and Avx512DQ #85281

Changes from 1 commit
Commits
Show all changes
14 commits
Select commit Hold shift + click to select a range
414d0c0
Expose various Convert intrinsics for Avx512F and Avx512DQ
tannergooding Apr 24, 2023
14cc465
Expose various integer conversion APIs for Avx512F and Avx512BW
tannergooding Apr 24, 2023
f6cce6c
Ensure special instructions are handled in codegen
tannergooding Apr 24, 2023
e3f3d88
Apply formatting patch
tannergooding Apr 24, 2023
d7de182
Ensure the AVX512F_VL variant is picked for simdSize=16/32
tannergooding Apr 25, 2023
3a68518
Ensure conversion instructions are handled in PERFSCORE
tannergooding Apr 25, 2023
29220d8
Ensure instructions use the right tuple type
tannergooding Apr 25, 2023
469284a
Removing an invalid API and fix more PERFSCORE entries
tannergooding Apr 25, 2023
d729776
Resolve additional failures masked by #85056
tannergooding Apr 25, 2023
6e77772
Ensure TieredCompilation=0 is also passing
tannergooding Apr 25, 2023
a1e2ace
Apply formatting patch
tannergooding Apr 25, 2023
8145ce2
Fixing some more test edge cases
tannergooding Apr 25, 2023
a7bbdf5
Merge remote-tracking branch 'dotnet/main' into avx512-4
tannergooding Apr 25, 2023
c0bd337
Ensure uint64->double and uint64->Float masks the input
tannergooding Apr 25, 2023
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
Next Next commit
Ensure the AVX512F_VL variant is picked for simdSize=16/32
  • Loading branch information
@tannergooding
tannergooding committed Apr 25, 2023
commit d7de182de2c4350905e2fd69668ad4db24afc7bd
4 changes: 2 additions & 2 deletions src/coreclr/jit/gentree.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22764,7 +22764,7 @@ GenTree* Compiler::gtNewSimdNarrowNode(
}
else
{
intrinsicId = NI_AVX512F_ConvertToVector128Int16;
intrinsicId = NI_AVX512F_VL_ConvertToVector128Int16;
}

opBaseJitType = CORINFO_TYPE_INT;
Expand All @@ -22779,7 +22779,7 @@ GenTree* Compiler::gtNewSimdNarrowNode(
}
else
{
intrinsicId = NI_AVX512F_ConvertToVector128UInt16;
intrinsicId = NI_AVX512F_VL_ConvertToVector128UInt16;
}

opBaseJitType = CORINFO_TYPE_UINT;
Expand Down