GPU_PTX ISA2+po+po+membar.gl-p0:p1:p2-xsyszs "Po-d-Ws-Ws Rf-w-s Po-d-Rs-Ws Rf-w-s Mgl-d-Rs-Rs Fr-w-s" {} P0 | P1 | P2 ; mov.s32 r0, 1 | ld.cg.s32 r0, [r1] | ld.cg.s32 r0, [r1] ; st.cg.s32 [r1], r0 | mov.s32 r2, 1 | membar.gl ; mov.s32 r2, 1 | st.cg.s32 [r3], r2 | 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:local; y:local; z:local Generated assembler //START _litmus_P2 ld.cg.s32 sr02, [sr12] ; membar.gl ; ld.cg.s32 sr22, [sr32] ; //START _litmus_P1 ld.cg.s32 sr01, [sr11] ; mov.s32 sr21, 1 ; st.cg.s32 [sr31], sr21 ; //START _litmus_P0 mov.s32 sr00, 1 ; st.cg.s32 [sr10], sr00 ; mov.s32 sr20, 1 ; st.cg.s32 [sr30], sr20 ; Binary '/tmp/dir966bee.tmp/ISA2+po+po+membar.gl-p0:p1:p2-xsyszs-0.exe' successfully loaded Specification clusters: 3 Specification: [[(670, 3, 'R0'), (671, 3, 'R4')], [(738, 3, 'R0'), (736, 2, 'R14')], [(802, 2, 'R8'), (804, 2, 'R14')]] Cluster 0: OK Cluster 1: OK Cluster 2: OK !!SUCCESS!! Test ISA2+po+po+membar.gl-p0:p1:p2-xsyszs Allowed Histogram (7 states) 8899 :>1:r0=0; 2:r0=0; 2:r2=0; 66 :>1:r0=1; 2:r0=0; 2:r2=0; 848 :>1:r0=0; 2:r0=1; 2:r2=0; 21584 :>1:r0=0; 2:r0=0; 2:r2=1; 8160 :>1:r0=1; 2:r0=0; 2:r2=1; 9742 :>1:r0=0; 2:r0=1; 2:r2=1; 701 :>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 ISA2+po+po+membar.gl-p0:p1:p2-xsyszs Never 0 50000 Time ISA2+po+po+membar.gl-p0:p1:p2-xsyszs 18.57 -- 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_bucket2/ISA2+po+po+membar.gl-p0:p1:p2-xsyszs-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 */