GPU_PTX mp_volatile+membar.ctas-p0:p1-xsys

{}

 P0                       | P1                       ;
 mov.s32 r0, 1            | ld.volatile.s32 r0, [r1] ;
 st.volatile.s32 [r1], r0 | membar.cta               ;
 membar.cta               |                          ;
 mov.s32 r2, 1            | ld.volatile.s32 r2, [r3] ;
 st.volatile.s32 [r3], r2 |                          ;

exists (1:r0=1 /\ 1:r2=0)
(device (kernel (cta (warp P0) (warp P1))))
y:local; x:local
Generated assembler
//START _litmus_P1
	ld.volatile.s32 sr01, [sr11] ;
	membar.cta ;
	ld.volatile.s32 sr21, [sr31] ;
//START _litmus_P0
	mov.s32 sr00, 1 ;
	st.volatile.s32 [sr10], sr00 ;
	membar.cta ;
	mov.s32 sr20, 1 ;
	st.volatile.s32 [sr30], sr20 ;

Binary '/tmp/dir03db63.tmp/mp-volatile+membar.ctas.exe' successfully loaded
Specification clusters: 2
Specification: [[(438, 9, 'R4'), (439, 9, 'R5')], [(507, 8, 'R10'), (509, 8, 'R12')]]
Cluster 0: OK
Cluster 1: OK
!!SUCCESS!!
Test mp-volatile+membar.ctas Allowed
Histogram (3 states)
53628 :>1:r0=0; 1:r2=0;
36720 :>1:r0=0; 1:r2=1;
9652  :>1:r0=1; 1:r2=1;
No

Witnesses
Positive: 0, Negative: 100000
Condition exists (1:r0=1 /\ 1:r2=0) is NOT validated
Observation mp-volatile+membar.ctas Never 0 100000
Time mp-volatile+membar.ctas 24.83

  -- device info --
Name:                           GeForce GT 540M
Major revision number:          2
Minor revision number:          1
Total global memory:            1072889856
Total shared memory per block:  49152
Number of multiprocessors:      2

Machine: DeepThought3
Revision 1371, version 5.01 GPU_PTX experimental backend
Command line: ./litmus -mach GTX540m.cfg ASPLOS/mp-volatile+membar.ctas.litmus -a 2
Parameters
#ifndef SIZE_OF_TEST
#define SIZE_OF_TEST 100000
#endif
#ifndef NUMBER_OF_RUN
#define NUMBER_OF_RUN 1
#endif
/* cc options: -arch=sm_21 */
/* barrier: user */
/* speedcheck: no */
/* gpu_general_bc: true */
/* gpu_mem_stress: true */
/* gpu-rand-threads: true */
/* gpu_cuda: true */
/* gpu_gen_addr: true */
/* gpu_cvt_global_to_gen: true */
/* gpu_cvt_shared_to_gen: true */
/* gpu_max_ctas: 4 */
/* gpu_min_ctas: 4 */
/* gpu_max_threads: 128 */
/* gpu_min_threads: 128 */