• via Digitalmars-d-bugs (21/21) Sep 12 2016 https://issues.dlang.org/show_bug.cgi?id=16488

via Digitalmars-d-bugs <digitalmars-d-bugs puremagic.com> writes:

https://issues.dlang.org/show_bug.cgi?id=16488

          Issue ID: 16488
           Summary: [spec][optimization] broadcast scalar to simd vector
           Product: D
           Version: D2
          Hardware: All
                OS: All
            Status: NEW
          Severity: major
          Priority: P1
         Component: dmd
          Assignee: nobody puremagic.com
          Reporter: ilyayaroshenko gmail.com

Currently DMD is 10-20(!) times slower for GLAS matrix multiplication then LDC.
This is the largest DMD FE problem for GLAS [1].

float s = 3;
...
__vector(float[4]) e = 3; // OK
__vector(float[4]) e = s; // Fails for DMD, but OK for LDC


[1] http://docs.mir.dlang.io/latest/mir_glas_l3.html

--