You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Work on #8298 revealed that correctness_float16_t fails when arm_fp16 is enabled in the target.
HL_TARGET=host
HL_JIT_TARGET=host
#CTEST_RESOURCE_GROUP_COUNT=
/home/halidenightly/build_bot/worker/halide-testbranch-main-llvm19-arm-64-linux-cmake/halide-build/test/correctness/correctness_float16_t
Result 4 is 0 instead of 1
float16_t test failed!
Testing float16_t...
Required regular expression not found. Regex=[Success!]
The text was updated successfully, but these errors were encountered:
Adds feature detection for ARM CPUs to the runtime library and to
the host target feature computation. Supports Windows, macOS,
Linux, iOS, and Android.
Also fix bug in Type::max() and Type::min() for float16.
Fixes#4727Fixes#6106Fixes#7901Fixes#7979Fixes#8340
…elease/18.x) (#8343)
Detect ARM CPU features for host target and in runtime (#8298)
Adds feature detection for ARM CPUs to the runtime library and to
the host target feature computation. Supports Windows, macOS,
Linux, iOS, and Android.
Also fix bug in Type::max() and Type::min() for float16.
Fixes#4727Fixes#6106Fixes#7901Fixes#7979Fixes#8340
Co-authored-by: Alex Reinking <[email protected]>
Work on #8298 revealed that
correctness_float16_t
fails whenarm_fp16
is enabled in the target.The text was updated successfully, but these errors were encountered: