GPU_PTX WWC+membar.cta+membar.gl-p0::p1:p2-xgys "Rf-c-g Mcta-d-Rg-Ws Rf-w-s Mgl-d-Rs-Wg Ws-c-g" {} P0 | P1 | P2 ; mov.s32 r0, 2 | ld.cg.s32 r0, [r1] | ld.cg.s32 r0, [r1] ; st.cg.s32 [r1], r0 | membar.cta | membar.gl ; | mov.s32 r2, 1 | mov.s32 r2, 1 ; | st.cg.s32 [r3], r2 | st.cg.s32 [r3], r2 ; exists (0::x=2 /\ 1:r0=2 /\ 2:r0=1) (device (kernel (cta (warp P0)) (cta (warp P1) (warp P2)))) x:global; y:local Generated assembler //START _litmus_P2 ld.cg.s32 sr02, [sr12] ; membar.gl ; 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 mov.s32 sr00, 2 ; st.cg.s32 [sr10], sr00 ; Binary '/tmp/dirad8576.tmp/WWC+membar.cta+membar.gl-p0::p1:p2-xgys-0.exe' successfully loaded Specification clusters: 3 Specification: [[(586, 3, 'R4'), (584, 2, 'R12')], [(644, 3, 'R4'), (642, 2, 'R8')], [(687, 2, 'R8')]] Cluster 0: OK Cluster 1: OK Cluster 2: OK !!SUCCESS!! Test WWC+membar.cta+membar.gl-p0::p1:p2-xgys Allowed Histogram (4 states) 26243 :>1:r0=0; 2:r0=0; 0::x=1; 18681 :>1:r0=2; 2:r0=0; 0::x=1; 4527 :>1:r0=0; 2:r0=1; 0::x=1; 549 :>1:r0=2; 2:r0=1; 0::x=1; No Witnesses Positive: 0, Negative: 50000 Condition exists (0::x=2 /\ 1:r0=2 /\ 2:r0=1) is NOT validated Observation WWC+membar.cta+membar.gl-p0::p1:p2-xgys Never 0 50000 Time WWC+membar.cta+membar.gl-p0::p1:p2-xgys 12.77 -- device info -- Name: GeForce GTX TITAN Major revision number: 3 Minor revision number: 5 Total global memory: 6442123264 Total shared memory per block: 49152 Number of multiprocessors: 14 Machine: formal Revision 1383, version 5.01 GPU_PTX experimental backend Command line: ./litmus -mach GTXTitan.cfg -a 8 -gpu-verf-comp true big_bucket/WWC+membar.cta+membar.gl-p0::p1:p2-xgys-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_35 */ /* 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: 14 */ /* gpu_min_ctas: 10 */ /* gpu_max_threads: 512 */ /* gpu_min_threads: 128 */