GPU_PTX 3.LB+membar.cta+membar.gl+ctrl-p0::p1:p2-xgygzs
"Mcta-d-Rg-Wg Rf-c-g Mgl-d-Rg-Ws Rf-w-s Ctrl-d-s-Wg Rf-c-g"

{}

 P0                 | P1                 | P2                        ;
 ld.cg.s32 r0, [r1] | ld.cg.s32 r0, [r1] | ld.cg.s32 r0, [r1]        ;
 membar.cta         | membar.gl          | and.b32 r2, r0 2147483648 ;
 mov.s32 r2, 1      | mov.s32 r2, 1      | setp.eq.b32 p4, r2, 0     ;
 st.cg.s32 [r3], r2 | st.cg.s32 [r3], r2 | @p4 bra LC00              ;
                    |                    | mov.s64 r4, 3494          ;
                    |                    | LC00:                     ;
                    |                    | mov.s32 r3, 1             ;
                    |                    | st.cg.s32 [r4], r3        ;

exists (0:r0=1 /\ 1:r0=1 /\ 2:r0=1)
(device (kernel (cta (warp P0)) (cta (warp P1) (warp P2))))
x:global; y:global; z:local
Generated assembler
//START _litmus_P2
	ld.cg.s32 sr02, [sr12] ;
	and.b32 sr22, sr02, 2147483648 ;
	setp.eq.b32 sp42, sr22, 0 ;
	@sp42 bra LC00 ;
	mov.s64 sr42, 3494 ;
LC00:
	mov.s32 sr32, 1 ;
	st.cg.s32 [sr42], sr32 ;
//START _litmus_P1
	ld.cg.s32 sr01, [sr11] ;
	membar.gl ;
	mov.s32 sr21, 1 ;
	st.cg.s32 [sr31], sr21 ;
//START _litmus_P0
	ld.cg.s32 sr00, [sr10] ;
	membar.cta ;
	mov.s32 sr20, 1 ;
	st.cg.s32 [sr30], sr20 ;

Binary '/tmp/dir66b044.tmp/3.LB+membar.cta+membar.gl+ctrl-p0::p1:p2-xgygzs-0.exe' successfully loaded
Specification clusters: 3
Specification: [[(635, 3, 'R0'), (633, 2, 'R10')], [(694, 3, 'R0'), (691, 2, 'R8')], [(748, 3, 'R0'), (745, 2, 'R10')]]
Cluster 0: OK
Cluster 1: OK
Cluster 2: OK
!!SUCCESS!!
Test 3.LB+membar.cta+membar.gl+ctrl-p0::p1:p2-xgygzs Allowed
Histogram (7 states)
32298 :>0:r0=0; 1:r0=0; 2:r0=0;
9719  :>0:r0=1; 1:r0=0; 2:r0=0;
4170  :>0:r0=0; 1:r0=1; 2:r0=0;
274   :>0:r0=1; 1:r0=1; 2:r0=0;
3513  :>0:r0=0; 1:r0=0; 2:r0=1;
19    :>0:r0=1; 1:r0=0; 2:r0=1;
7     :>0:r0=0; 1:r0=1; 2:r0=1;
No

Witnesses
Positive: 0, Negative: 50000
Condition exists (0:r0=1 /\ 1:r0=1 /\ 2:r0=1) is NOT validated
Observation 3.LB+membar.cta+membar.gl+ctrl-p0::p1:p2-xgygzs Never 0 50000
Time 3.LB+membar.cta+membar.gl+ctrl-p0::p1:p2-xgygzs 15.38

  -- device info --
Name:                           Tesla C2075
Major revision number:          2
Minor revision number:          0
Total global memory:            5636554752
Total shared memory per block:  49152
Number of multiprocessors:      14

Machine: fractus
Revision 1365M, version 5.01 GPU_PTX experimental backend
Command line: ./litmus -mach TeslaC2075.cfg -a 8 -gpu-verf-comp true big_bucket/3.LB+membar.cta+membar.gl+ctrl-p0::p1:p2-xgygzs-0.litmus -s 50000
Parameters
#ifndef SIZE_OF_TEST
#define SIZE_OF_TEST 50000
#endif
#ifndef NUMBER_OF_RUN
#define NUMBER_OF_RUN 1
#endif
/* cc options: -arch=sm_20 */
/* 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: 12 */
/* gpu_min_ctas: 9 */
/* gpu_max_threads: 512 */
/* gpu_min_threads: 128 */