leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 29 Packages Projects Releases Wiki Activity

CUTLASS 2.6.1 - functional and performance enhancements to strided DGRAD, fixes, and tuning

Browse Source 
* cutlass 2.6 update

* remove debug prints

* cutlass 2.6.1 (minor update)

* Updated CHANGELOG.

* Minor edit to readme to indicate patch version.

* Minor edit to readme.

Co-authored-by:  Haicheng Wu <haichengw@nvidia.com>, Andrew Kerr <akerr@nvidia.com>
This commit is contained in:
Manish Gupta
2021-09-03 10:26:15 -07:00
committed by GitHub
co-authored by Haicheng Wu <haichengw@nvidia.com>, Andrew Kerr <akerr@nvidia.com>
parent a01feb93d9
commit 6c2f8f2fb8
55 changed files with 317 additions and 315 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/cutlass/matrix.h
+3 -3
View File
@@ -14030,15 +14030,15 @@ struct Matrix<Element_, 4, 4> {
/// Returns a perspective projection matrix typical of OpenGL applications
CUTLASS_HOST_DEVICE
static Matrix perspective(Element near, Element far, Element fovH, Element fovV) {
static Matrix perspective(Element near_plane, Element far_plane, Element fovH, Element fovV) {
Element aspect = fovH / fovV;
Element f = Element(cos(fovV)) / Element(fovH);
Element Q = near - far;
Element Q = near_plane - far_plane;
return Matrix(
f / aspect, 0, 0, 0,
0, f, 0, 0,
0, 0, (near + far) / Q, Element(2) * far * near / Q,
0, 0, (near_plane + far_plane) / Q, Element(2) * far_plane * near_plane / Q,
0, 0, -1, 0
);
}