GPU_PTX cl_stale-p0::p1-agbgxgyg

{}

 P0                           | P1                     ;
 mov.u32 r0, 1                | ld.cg.u32 r0, [r1]     ;
 st.cg.u32 [r1], r0           | setp.eq.u32 r2, r0, 1  ;
 ld.cg.u32 r2, [r3]           | @r2 mov.u32 r3, 1      ;
 ld.cg.u32 r4, [r5]           | @r2 ld.cg.u32 r4, [r5] ;
 setp.eq.u32 r6, r2, r4       |                        ;
 @r6 atom.inc.u32 r7, [r8], 1 |                        ;
 membar.gl                    |                        ;

exists (1:r0=1 /\ 1:r4=0)
(device (kernel (cta (warp P0)) (cta (warp P1))))
y:global; x:global; a:global; b:global
Generated assembler
//START _litmus_P1
	ld.cg.u32 sr01, [sr11] ;
	setp.eq.u32 sr21, sr01, 1 ;
	@sr21 mov.u32 sr31, 1 ;
	@sr21 ld.cg.u32 sr41, [sr51] ;
//START _litmus_P0
	mov.u32 sr00, 1 ;
	st.cg.u32 [sr10], sr00 ;
	ld.cg.u32 sr20, [sr30] ;
	ld.cg.u32 sr40, [sr50] ;
	setp.eq.u32 sr60, sr20, sr40 ;
	@sr60 atom.inc.u32 sr70, [sr80], 1 ;
	membar.gl ;

Binary '/tmp/dira85d17.tmp/cl-stale.exe' successfully loaded
Specification clusters: 2
Specification: [[(884, 3, 'R4'), (887, 3, 'R0')], [(958, 2, 'R8'), (954, 3, 'R5'), (955, 3, 'R4'), (957, 7, 'R0')]]
Cluster 0: OK
Cluster 1: OK
!!SUCCESS!!
Test cl-stale Allowed
Histogram (3 states)
1     *>1:r0=1; 1:r4=0;
97821 :>1:r0=0; 1:r4=1;
2183  :>1:r0=1; 1:r4=1;
Ok

Witnesses
Positive: 1, Negative: 100004
Condition exists (1:r0=1 /\ 1:r4=0) is validated
Observation cl-stale Sometimes 1 100004
Time cl-stale 10.19

  -- 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 1521, version 5.01 GPU_PTX experimental backend
Command line: ./litmus -mach TeslaC2075.cfg ASPLOS/cl-stale.litmus -gpu-general-bc false
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_20 */
/* barrier: user */
/* speedcheck: no */
/* gpu_general_bc: false */
/* 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 */