GPU_PTX 3.LB+membar.cta+membar.cta+po-p0:p1:p2-xgygzs "Mcta-d-Rgl2-Wgl2 Rf-w-gl2l2 Mcta-d-Rgl2-Wsl2 Rf-w-sl2l2 Po-d-Rsl2-Wgl2 Rf-w-gl2l2" {} P0 | P1 | P2 ; ld.cg.s32 r0, [r1] | ld.cg.s32 r0, [r1] | ld.cg.s32 r0, [r1] ; membar.cta | membar.cta | mov.s32 r2, 1 ; mov.s32 r2, 1 | mov.s32 r2, 1 | st.cg.s32 [r3], r2 ; st.cg.s32 [r3], r2 | st.cg.s32 [r3], r2 | ; exists (0:r0=1 /\ 1:r0=1 /\ 2:r0=1) (device (kernel (cta (warp P0) (warp P1) (warp P2)))) x:global; y:global; z:local Generated assembler //START _litmus_P2 ld.cg.s32 sr02, [sr12] ; mov.s32 sr22, 1 ; st.cg.s32 [sr32], sr22 ; //START _litmus_P1 ld.cg.s32 sr01, [sr11] ; membar.cta ; 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/dirad9485.tmp/3.LB+membar.cta+membar.cta+po-p0:p1:p2-xgygzs-0.exe' successfully loaded Specification clusters: 3 Specification: [[(608, 3, 'R4'), (607, 2, 'R12')], [(663, 3, 'R4'), (662, 2, 'R12')], [(715, 3, 'R4'), (714, 2, 'R14')]] Cluster 0: OK Cluster 1: OK Cluster 2: OK !!SUCCESS!! Test 3.LB+membar.cta+membar.cta+po-p0:p1:p2-xgygzs Allowed Histogram (7 states) 36187 :>0:r0=0; 1:r0=0; 2:r0=0; 31193 :>0:r0=1; 1:r0=0; 2:r0=0; 13742 :>0:r0=0; 1:r0=1; 2:r0=0; 3548 :>0:r0=1; 1:r0=1; 2:r0=0; 12451 :>0:r0=0; 1:r0=0; 2:r0=1; 2403 :>0:r0=1; 1:r0=0; 2:r0=1; 476 :>0:r0=0; 1:r0=1; 2:r0=1; No Witnesses Positive: 0, Negative: 100000 Condition exists (0:r0=1 /\ 1:r0=1 /\ 2:r0=1) is NOT validated Observation 3.LB+membar.cta+membar.cta+po-p0:p1:p2-xgygzs Never 0 100000 Time 3.LB+membar.cta+membar.cta+po-p0:p1:p2-xgygzs 40.18 -- device info -- Name: GeForce GTX 660 Major revision number: 3 Minor revision number: 0 Total global memory: 2147155968 Total shared memory per block: 49152 Number of multiprocessors: 5 Machine: csu8975 Revision 967, version 5.01 GPU_PTX experimental backend Command line: ./litmus -gpu -ccopts -arch=sm_30 -gpu-max-ctas 8 -gpu-min-ctas 4 tests-sm30/3.LB+membar.cta+membar.cta+po-p0:p1:p2-xgygzs-0.litmus 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_30 */ /* 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: 8 */ /* gpu_min_ctas: 4 */ /* gpu_max_threads: 512 */ /* gpu_min_threads: 128 */