Comparing
aarch64_neon_stable
(4967e1b
) withmain
(868600f
)0%
- Untouched
- 168
Benchmarks
168 total
avx2_f16_argmin_in
benches/bench_f16_ignore_nan.rs::benches::argminmax_in_f16_random_array_long0%
121 µs120.9 µs
sse_f16_argminmax_in
benches/bench_f16_ignore_nan.rs::benches::argminmax_in_f16_random_array_long0%
183.5 µs183.4 µs
impl_f16_argmin_in
benches/bench_f16_ignore_nan.rs::benches::argminmax_in_f16_random_array_long0%
121.2 µs121.1 µs
sse_u8_argmin
benches/bench_u8.rs::benches::argminmax_u8_random_array_long0%
68.8 µs68.8 µs
sse_u8_argmax
benches/bench_u8.rs::benches::argminmax_u8_random_array_long0%
69.3 µs69.3 µs
avx2_f32_argmax_rn
benches/bench_f32_return_nan.rs::benches::argminmax_rn_f32_random_array_long0%
241 µs240.9 µs
impl_f32_argminmax_rn
benches/bench_f32_return_nan.rs::benches::argminmax_rn_f32_random_array_long0%
241.1 µs241 µs
impl_f32_argmin_rn
benches/bench_f32_return_nan.rs::benches::argminmax_rn_f32_random_array_long0%
241.1 µs241.1 µs
impl_f32_argmax_rn
benches/bench_f32_return_nan.rs::benches::argminmax_rn_f32_random_array_long0%
241.2 µs241.1 µs
sse_i8_argminmax
benches/bench_i8.rs::benches::argminmax_i8_random_array_long0%
84.8 µs84.7 µs
avx2_u32_argminmax
benches/bench_u32.rs::benches::argminmax_u32_random_array_long0%
230.1 µs230.1 µs
avx2_f64_argmin_rn
benches/bench_f64_return_nan.rs::benches::argminmax_rn_f64_random_array_long0%
488 µs487.9 µs
impl_f64_argminmax_rn
benches/bench_f64_return_nan.rs::benches::argminmax_rn_f64_random_array_long0%
488.1 µs488 µs
avx2_f32_argminmax_rn
benches/bench_f32_return_nan.rs::benches::argminmax_rn_f32_random_array_long0%
240.9 µs240.9 µs
avx2_f32_argmin_rn
benches/bench_f32_return_nan.rs::benches::argminmax_rn_f32_random_array_long0%
241 µs240.9 µs
avx2_f16_argminmax_in
benches/bench_f16_ignore_nan.rs::benches::argminmax_in_f16_random_array_long0%
128.4 µs128.3 µs
impl_f16_argminmax_in
benches/bench_f16_ignore_nan.rs::benches::argminmax_in_f16_random_array_long0%
128.5 µs128.5 µs
impl_u64_argmin
benches/bench_u64.rs::benches::argminmax_u64_random_array_long0%
431 µs430.9 µs
sse_f16_argmax_in
benches/bench_f16_ignore_nan.rs::benches::argminmax_in_f16_random_array_long0%
158.2 µs158.2 µs
sse_u32_argminmax
benches/bench_u32.rs::benches::argminmax_u32_random_array_long0%
294 µs293.9 µs
avx2_f64_argminmax_rn
benches/bench_f64_return_nan.rs::benches::argminmax_rn_f64_random_array_long0%
487.9 µs487.8 µs
avx2_f64_argmax_rn
benches/bench_f64_return_nan.rs::benches::argminmax_rn_f64_random_array_long0%
488 µs487.9 µs
impl_f64_argmin_rn
benches/bench_f64_return_nan.rs::benches::argminmax_rn_f64_random_array_long0%
488.1 µs488 µs
impl_f64_argmax_rn
benches/bench_f64_return_nan.rs::benches::argminmax_rn_f64_random_array_long0%
488.1 µs488 µs
scalar_i8_argminmax
benches/bench_i8.rs::benches::argminmax_i8_random_array_long0%
359.8 µs359.8 µs
Commits
Click on a commit to change the comparison rangeBase
main
868600f
0%
remove simd_nightly feature flag for aarch64 for i16
51d821d
2 years ago
by jvdd0%
add aarch64 target_arch to imports
468c83e
2 years ago
by jvdd0%
add aarch64 target_arch to imports in generic.rs
03c0863
2 years ago
by jvdd0%
remove nightly_simd flag for impl_SIMDArgMinMax macro
03b03e1
2 years ago
by jvdd0%
remove nightly_simd feature flag for aarch64 for i8 and i32
6f48cc7
2 years ago
by jvdd0%
wrap up ints and uints
098661e
2 years ago
by jvdd0%
add f32 support
d3e19fd
2 years ago
by jvdd0%
fix arm
641b1b0
2 years ago
by jvdd0%
:see_no_evil:
1e12aa6
2 years ago
by jvdd0%
update other float types
81842be
2 years ago
by jvdd0%
restrict cfg to arm and nightly_simd for floats
75d619d
2 years ago
by jvdd0%
restrict imports to arm & nightly_simd
d575a56
2 years ago
by jvdd0%
:recycle:
773f08d
2 years ago
by jvdd0%
build aarch64 as stable
15ac377
2 years ago
by jvdd0%
use scalar implementation for 64 bit integers on aarch64
ecc035f
2 years ago
by jvdd0%
:broom: review code
aa4220b
2 years ago
by jvdd0%
:broom: remove fixed TODO
cacfb3c
2 years ago
by jvdd0%
:lotus_position: review code
4967e1b
2 years ago
by jvdd