Dev on .NET Libraries team working on Hardware Intrinsics and Numerics. He/Him.
-
Microsoft
- Redmond, WA
- https://blog.tagoo.dev/
- @tannergooding
Highlights
- 7 discussions answered
Block or Report
Block or report tannergooding
Report abuse
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abusePinned
-
dotnet/runtime Public
.NET is a cross-platform runtime for cloud, mobile, desktop, and IoT apps.
-
-
-
-
1,720 contributions in the last year
Less
More
Activity overview
Contributed to
terrafx/terrafx.interop.windows,
dotnet/runtime,
dotnet/ClangSharp
and 5 other
repositories
Contribution activity
February 2022
Created 10 commits in 3 repositories
Created a pull request in dotnet/runtime that received 6 comments
Fixing a runtime check and test to match the EnableISA flag behavior
This resolves #63859
+26
−6
•
6
comments
Opened 1 other pull request in 1 repository
terrafx/terrafx.interop.vulkan
1
merged
Reviewed 38 pull requests in 5 repositories
dotnet/runtime
34 pull requests
- Faster Math.Max/Min on arm64
- Remove S.R.CS.Unsafe and Intrinsify Unsafe
- [WIP] ARM64 - Optimizing a % b operations
- Add Nullable.GetValueRefOrDefaultRef API
- Fix Vector256.IsHardwareAccelerated in R2R binaries
- Disable R2R code for all associated components of a composite image
- [JIT] More ARM64 comparison instruction optimizations with Vector.Zero
- Include IsNetCoreAppRef in assembly version calculation for servicing
- Convert non-blittable delegate usage in System.DirectoryServices to function pointers.
- [Mono] Add SIMD intrinsic for Vector64/128 comparisons
- [Mono] Add arm64 SIMD intrinsic for Vector64/128 Abs
- [release/6.0] Expand System.Runtime.InteropServices.NFloat to support the APIs required by Xamarin
- Use generic math in System.Numerics.Vectors (#60365)
- Optimize Math.Round(x, MidpointRounding.AwayFromZero/ToEven)
- Allow constant propagation of Vector.Zero.
- [WIP] Heuristic change for double constant adjustment
- Make System.Math/MathF.Truncate an intrinsic
- Implement LoadPairVector64 and LoadPairVector128
-
Optimize
StringBuilder.Insert. - Limit number of JIT/HardwareIntrinsics/* under GCStress
- Treat TZCNT/POPCNT/LZCNT as never negative
-
Morph
Vector.Create(0)toVector.Zero - JIT: fix containment safety check in LowerHWIntrinsicGetElement
- Add vectorized paths for Span<T>.Reverse
- Improve backport.yml to only check start of line and instructions for team visibility
- Some pull request reviews not shown.
dotnet/core
1 pull request
dotnet/machinelearning
1 pull request
dotnet/dotnet-api-docs
1 pull request
dotnet/docs
1 pull request
Created an issue in dotnet/runtime that received 4 comments
Update the HWIntrinsics to allow removal where no side-effects exist
For simplicity when the hardware intrinsics were first being brought up we marked all GT_HWINTRINSIC as "having side-effects" and therefore not all…
4
comments

