cessen/psychopath
1
0
Fork 0
Code Issues 1 Pull Requests Projects Releases Wiki Activity

Fix bug resulting in cracks between triangles in some cases.

Browse Source
This commit is contained in:
Nathan Vegdahl 2022-08-03 10:23:26 -07:00
parent 9569f772f0
commit 15cd261026
2 changed files with 40 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
sub_crates/rmath/src/wide4/mod.rs
View File

@ -748,4 +748,38 @@ mod tests {
assert_eq!(all ^ all, none); assert_eq!(all ^ all, none);
assert_eq!(none ^ none, none); assert_eq!(none ^ none, none);
} }
#[test]
fn matches_fallback() {
fn tf1(n: Float4) -> [f32; 4] {
[n.a(), n.b(), n.c(), n.d()]
}
fn tf2(n: fallback::Float4) -> [f32; 4] {
[n.a(), n.b(), n.c(), n.d()]
}
let a1 = Float4::new(1.53245, 5.4234523, -424.432, 0.0004231);
let b1 = Float4::new(74.63, -9.65436, 3.0, -1003.3);
let c1 = Float4::new(-0.4216, -132.52, 8.9452, 42.0);
let a2 = fallback::Float4::new(1.53245, 5.4234523, -424.432, 0.0004231);
let b2 = fallback::Float4::new(74.63, -9.65436, 3.0, -1003.3);
let c2 = fallback::Float4::new(-0.4216, -132.52, 8.9452, 42.0);
assert_eq!(tf1(a1), tf2(a2));
assert_eq!(tf1(b1), tf2(b2));
assert_eq!(tf1(c1), tf2(c2));
assert_eq!(tf1(a1 + b1), tf2(a2 + b2));
assert_eq!(tf1(a1 - b1), tf2(a2 - b2));
assert_eq!(tf1(a1 * b1), tf2(a2 * b2));
assert_eq!(tf1(a1 / b1), tf2(a2 / b2));
assert_eq!(tf1(a1.mul_add(b1, c1)), tf2(a2.mul_add(b2, c2)));
assert_eq!(tf1(a1.min(b1)), tf2(a2.min(b2)));
assert_eq!(tf1(a1.max(b1)), tf2(a2.max(b2)));
assert_eq!(a1.min_element(), a2.min_element());
assert_eq!(a1.max_element(), a2.max_element());
assert_eq!(tf1(a1.recip()), tf2(a2.recip()));
assert_eq!(tf1(a1.abs()), tf2(a2.abs()));
}
} }

9
sub_crates/rmath/src/wide4/sse.rs
View File

@ -3,8 +3,8 @@ use std::ops::{Add, BitAnd, BitOr, BitXor, Div, Index, Mul, Neg, Not, Sub};
use std::arch::x86_64::{ use std::arch::x86_64::{
__m128, _mm_add_ps, _mm_and_ps, _mm_castsi128_ps, _mm_cmpeq_ps, _mm_cmpge_ps, _mm_cmpgt_ps, __m128, _mm_add_ps, _mm_and_ps, _mm_castsi128_ps, _mm_cmpeq_ps, _mm_cmpge_ps, _mm_cmpgt_ps,
_mm_cmple_ps, _mm_cmplt_ps, _mm_div_ps, _mm_fmadd_ps, _mm_max_ps, _mm_min_ps, _mm_movemask_ps, _mm_cmple_ps, _mm_cmplt_ps, _mm_div_ps, _mm_fmadd_ps, _mm_max_ps, _mm_min_ps, _mm_movemask_ps,
_mm_mul_ps, _mm_or_ps, _mm_rcp_ps, _mm_set1_epi32, _mm_set1_ps, _mm_set_epi32, _mm_set_ps, _mm_mul_ps, _mm_or_ps, _mm_set1_epi32, _mm_set1_ps, _mm_set_epi32, _mm_set_ps, _mm_setzero_ps,
_mm_setzero_ps, _mm_shuffle_ps, _mm_storeu_ps, _mm_sub_ps, _mm_xor_ps, _mm_shuffle_ps, _mm_storeu_ps, _mm_sub_ps, _mm_xor_ps,
}; };
use crate::FMulAdd; use crate::FMulAdd;
@ -77,7 +77,10 @@ impl Float4 {
/// 1.0 / self /// 1.0 / self
#[inline(always)] #[inline(always)]
pub fn recip(self) -> Self { pub fn recip(self) -> Self {
Self(unsafe { _mm_rcp_ps(self.0) }) // The reciprocal intrinsic is not precise enough.
// Self(unsafe { std::arch::x86_64::_mm_rcp_ps(self.0) })
Self::splat(1.0) / self
} }
#[inline(always)] #[inline(always)]