GPU_PTX 3.LB-p0::p1::p2-xgygzg "PodRW Rfe PodRW Rfe PodRW Rfe" {} P0 | P1 | P2 ; ld.cg.s32 r0, [r1] | ld.cg.s32 r0, [r1] | ld.cg.s32 r0, [r1] ; 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)) (cta (warp P1)) (cta (warp P2)))) z:global; y:global; x:global 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] ; mov.s32 sr21, 1 ; st.cg.s32 [sr31], sr21 ; //START _litmus_P0 ld.cg.s32 sr00, [sr10] ; mov.s32 sr20, 1 ; st.cg.s32 [sr30], sr20 ; Binary '/tmp/dir91106a.tmp/3.LB-0.exe' successfully loaded Specification clusters: 3 Specification: [[(789, 3, 'R0'), (786, 2, 'R10')], [(841, 3, 'R0'), (838, 2, 'R8')], [(895, 3, 'R0'), (892, 2, 'R10')]] Cluster 0: OK Cluster 1: OK Cluster 2: OK !!SUCCESS!! Test 3.LB Allowed Histogram (8 states) 37208 :>0:r0=0; 1:r0=0; 2:r0=0; 20955 :>0:r0=1; 1:r0=0; 2:r0=0; 19031 :>0:r0=0; 1:r0=1; 2:r0=0; 2713 :>0:r0=1; 1:r0=1; 2:r0=0; 16170 :>0:r0=0; 1:r0=0; 2:r0=1; 2017 :>0:r0=1; 1:r0=0; 2:r0=1; 1898 :>0:r0=0; 1:r0=1; 2:r0=1; 8 *>0:r0=1; 1:r0=1; 2:r0=1; Ok Witnesses Positive: 8, Negative: 99992 Condition exists (0:r0=1 /\ 1:r0=1 /\ 2:r0=1) is validated Observation 3.LB Sometimes 8 99992 Time 3.LB 17.30 -- 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 -gpu-verf-comp true -gpu-general-bc true -gpu-mem-stress true -barrier user -gpu-rand-threads true incantation_benchmarks/D:warp-S:cta-Global/3.LB-0.litmus -gpu-conc-scope s2 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: 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 */