[PATCH 1/2] amdgcn/fmin: fcanonicalize operands

Runtimes OpenCL
1

v_min instruction needs canonicalized operands.
Passes CTS on carrizo
Fixes minmag CTS on carrizo

Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

2

v_max instruction needs canonicalized operands.
Passes CTS on carrizo
Fixes maxmag CTS on carrizo

Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

3

Looks ok to me.

fmin/fmax float/double now pass on Polaris against CL 1.2 CTS as well.

--Aaron