GPU_PTX WRC+membar.ctas-p0:p1::p2-xgyg "Rf-w-gl2l2 Mcta-d-Rgl2-Wgl2 Rf-c-gl2l2 Mcta-d-Rgl2-Rgl2 Fr-c-gl2l2" {} 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)) (cta (warp P2)))) x:global; y:global 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/dir7cbe2e.tmp/WRC+membar.ctas-p0:p1::p2-xgyg-0.exe' successfully loaded Specification clusters: 3 Specification: [[(469, 3, 'R4'), (470, 3, 'R5')], [(526, 3, 'R4'), (525, 2, 'R12')], [(571, 2, 'R10')]] Cluster 0: OK Cluster 1: OK Cluster 2: OK !!SUCCESS!! Test WRC+membar.ctas-p0:p1::p2-xgyg Allowed Histogram (8 states) 21219 :>1:r0=0; 2:r0=0; 2:r2=0; 7211 :>1:r0=1; 2:r0=0; 2:r2=0; 3069 :>1:r0=0; 2:r0=1; 2:r2=0; 24 *>1:r0=1; 2:r0=1; 2:r2=0; 17957 :>1:r0=0; 2:r0=0; 2:r2=1; 28470 :>1:r0=1; 2:r0=0; 2:r2=1; 16759 :>1:r0=0; 2:r0=1; 2:r2=1; 5291 :>1:r0=1; 2:r0=1; 2:r2=1; Ok Witnesses Positive: 24, Negative: 99976 Condition exists (1:r0=1 /\ 2:r0=1 /\ 2:r2=0) is validated Observation WRC+membar.ctas-p0:p1::p2-xgyg Sometimes 24 99976 Time WRC+membar.ctas-p0:p1::p2-xgyg 38.65 -- 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/WRC+membar.ctas-p0:p1::p2-xgyg-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 */