approxEqAbs comparison type changed to f64

[Nefistofeles]

const orthographics = math.orthographicLh(1366.0, 768.0, -1000.0, 1000.0) 
const inv = math.inverse(orthographics);

Ortographics matrix is:

0.0014641288, 0,            0,      0
0,            0.0026041667, 0,      0
0,            0,            0.0005, 0
0,            0,            0.5,    1

Determinant result is: 0.00000000190641773273548
f32 epsilon is math.floatEps(f32) = 0.0000001192092900
f64 epsilon is math.floatEps(f64) = 0.0000000000000002

Inverse matrix result give all column 0 because of this lines:

zmath/src/root.zig

Lines 2622 to 2629 in 634ffd6

	if (math.approxEqAbs(f32, det[0], 0.0, math.floatEps(f32))) {
	return .{
	f32x4(0.0, 0.0, 0.0, 0.0),
	f32x4(0.0, 0.0, 0.0, 0.0),
	f32x4(0.0, 0.0, 0.0, 0.0),
	f32x4(0.0, 0.0, 0.0, 0.0),
	};
	}

Increasing approxEqAbs type to f64 solve the problem.

[Srekel]

We had a similar problem with this line on Tides recently and simply removed it. Might be worth checking if this works better. What is the reason for it in the first place @michal-z ?

[hazeycode]

Looks good to me. Lots of error can be accumulated calculating determinants so making the epsilon smaller to mitigate this seems reasonable.

[Copilot]

Pull Request Overview

This PR improves the determinant near-zero check in the matrix inversion function by using double-precision tolerance to avoid falsely detecting non-singular matrices as singular.

• Switched math.approxEqAbs from f32 to f64 when comparing the determinant against epsilon
• Updated epsilon argument to math.floatEps(f64) for higher precision

Comments suppressed due to low confidence (2)

src/root.zig:2620

• [nitpick] Add a comment above this check explaining why f64 precision is needed for the determinant comparison to help future maintainers understand the rationale.

    }

src/root.zig:2622

• Add a unit test for inverseDet using a near-singular matrix (like the orthographic example) to verify that the new f64 comparison correctly avoids returning a zero matrix.

    if (math.approxEqAbs(f64, det[0], 0.0, math.floatEps(f64))) {