GPU_PTX WRC+membar.ctas-p0:p1:p2-xgys "Rf-w-g Mcta-d-Rg-Ws Rf-w-s Mcta-d-Rs-Rg Fr-w-g" {} P0 | P1 | P2 ; mov.s32 r0, 1 | ld.cg.s32 r0, [r1] | ld.cg.s32 r0, [r1] ; st.cg.s32 [r1], r0 | membar.cta | membar.cta ; | mov.s32 r2, 1 | ld.cg.s32 r2, [r3] ; | st.cg.s32 [r3], r2 | ; exists (1:r0=1 /\ 2:r0=1 /\ 2:r2=0) (device (kernel (cta (warp P0) (warp P1) (warp P2)))) x:global; y:local Generated assembler //START _litmus_P2 ld.cg.s32 sr02, [sr12] ; membar.cta ; ld.cg.s32 sr22, [sr32] ; //START _litmus_P1 ld.cg.s32 sr01, [sr11] ; membar.cta ; mov.s32 sr21, 1 ; st.cg.s32 [sr31], sr21 ; //START _litmus_P0 mov.s32 sr00, 1 ; st.cg.s32 [sr10], sr00 ; Binary '/tmp/dir863d04.tmp/WRC+membar.ctas-p0:p1:p2-xgys-0.exe' successfully loaded Specification clusters: 3 Specification: [[(675, 3, 'R0'), (676, 3, 'R4')], [(754, 3, 'R0'), (755, 2, 'R10')], [(810, 2, 'R8')]] Cluster 0: OK Cluster 1: OK Cluster 2: OK !!SUCCESS!! Test WRC+membar.ctas-p0:p1:p2-xgys Allowed Histogram (7 states) 6767 :>1:r0=0; 2:r0=0; 2:r2=0; 1877 :>1:r0=1; 2:r0=0; 2:r2=0; 5 :>1:r0=0; 2:r0=1; 2:r2=0; 15670 :>1:r0=0; 2:r0=0; 2:r2=1; 25137 :>1:r0=1; 2:r0=0; 2:r2=1; 423 :>1:r0=0; 2:r0=1; 2:r2=1; 121 :>1:r0=1; 2:r0=1; 2:r2=1; No Witnesses Positive: 0, Negative: 50000 Condition exists (1:r0=1 /\ 2:r0=1 /\ 2:r2=0) is NOT validated Observation WRC+membar.ctas-p0:p1:p2-xgys Never 0 50000 Time WRC+membar.ctas-p0:p1:p2-xgys 3.94 -- device info -- Name: GeForce GTX 750 Ti Major revision number: 5 Minor revision number: 0 Total global memory: 2147287040 Total shared memory per block: 49152 Number of multiprocessors: 5 Machine: formal Revision 1383, version 5.01 GPU_PTX experimental backend Command line: ./litmus -mach GTX750.cfg -a 8 -gpu-verf-comp true big_bucket/WRC+membar.ctas-p0:p1:p2-xgys-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_50 */ /* 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: 5 */ /* gpu_min_ctas: 4 */ /* gpu_max_threads: 256 */ /* gpu_min_threads: 128 */