is descrypt slow after ocl v1.31?

[atom]

I'm testing with the following system:

Device #1: GeForce GTX 980, 4095MB, 1215Mhz, 16MCU
Device #2: GeForce GTX 750 Ti, 2047MB, 1110Mhz, 5MCU
Device #3: GeForce GTX 560 Ti, 1023MB, 1660Mhz, 8MCU

From benchmark -b speed is OK:

1.31:

Speed.GPU.#1.: 96327.5 kH/s
Speed.GPU.#2.: 28080.3 kH/s
Speed.GPU.#3.: 18439.4 kH/s

1.36 (beta 30):

Speed.GPU.#1.: 95496.5 kH/s
Speed.GPU.#2.: 28245.5 kH/s
Speed.GPU.#3.: 18851.3 kH/s

And with -a0 (wordlist based attack) speed is OK:

command used:

$ ./mp64.bin ?a?a?a?a?a?a?a | ./cudaHashcat64.bin w8GvlER3.Xkj6 -m 1500 -r rules/generated2.rule -u 1024 -n 16 --potfile-disable --runtime 60 --status --status-timer 2 -d 1

1.31:

Progress.......: 5435817984

1.36 (beta 30):

Progress.......: 5838471168

That means latest version is fastest (more progress in the same time)