GPU_PTX Z6.1+membar.gl+membar.cta+po-p0:p1:p2-xgyszs "Mgl-d-Wgl2-Wsl2 Ws-w-sl2l2 Mcta-d-Wsl2-Wsl2 Rf-w-sl2l2 Po-d-Rsl2-Wgl2 Ws-w-gl2l2" {} P0 | P1 | P2 ; mov.s32 r0, 2 | mov.s32 r0, 2 | ld.cg.s32 r0, [r1] ; st.cg.s32 [r1], r0 | st.cg.s32 [r1], r0 | mov.s32 r2, 1 ; membar.gl | membar.cta | st.cg.s32 [r3], r2 ; mov.s32 r2, 1 | mov.s32 r2, 1 | ; st.cg.s32 [r3], r2 | st.cg.s32 [r3], r2 | ; exists (0::x=2 /\ 0::y=2 /\ 2:r0=1) (device (kernel (cta (warp P0) (warp P1) (warp P2)))) x:global; y:local; z:local Generated assembler //START _litmus_P2 ld.cg.s32 sr02, [sr12] ; mov.s32 sr22, 1 ; st.cg.s32 [sr32], sr22 ; //START _litmus_P1 mov.s32 sr01, 2 ; st.cg.s32 [sr11], sr01 ; membar.cta ; mov.s32 sr21, 1 ; st.cg.s32 [sr31], sr21 ; //START _litmus_P0 mov.s32 sr00, 2 ; st.cg.s32 [sr10], sr00 ; membar.gl ; mov.s32 sr20, 1 ; st.cg.s32 [sr30], sr20 ; Binary '/tmp/dir730a38.tmp/Z6.1+membar.gl+membar.cta+po-p0:p1:p2-xgyszs-0.exe' successfully loaded Specification clusters: 3 Specification: [[(637, 3, 'R4'), (636, 2, 'R12')], [(700, 2, 'R10'), (702, 2, 'R12')], [(754, 2, 'R10'), (759, 2, 'R12')]] Cluster 0: OK Cluster 1: OK Cluster 2: OK !!SUCCESS!! Test Z6.1+membar.gl+membar.cta+po-p0:p1:p2-xgyszs Allowed Histogram (4 states) 42568 :>2:r0=0; 0::x=1; 0::y=1; 10833 :>2:r0=1; 0::x=1; 0::y=1; 43364 :>2:r0=0; 0::x=2; 0::y=1; 3235 :>2:r0=1; 0::x=2; 0::y=1; No Witnesses Positive: 0, Negative: 100000 Condition exists (0::x=2 /\ 0::y=2 /\ 2:r0=1) is NOT validated Observation Z6.1+membar.gl+membar.cta+po-p0:p1:p2-xgyszs Never 0 100000 Time Z6.1+membar.gl+membar.cta+po-p0:p1:p2-xgyszs 37.32 -- 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/Z6.1+membar.gl+membar.cta+po-p0:p1:p2-xgyszs-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 */