GPU_PTX WRW+WR+membar.cta+membar.gl-p0:p1:p2-xsyg "Rf-w-s Mcta-d-Rs-Wg Ws-w-g Mgl-d-Wg-Rs Fr-w-s" {} P0 | P1 | P2 ; mov.s32 r0, 1 | ld.cg.s32 r0, [r1] | mov.s32 r0, 2 ; st.cg.s32 [r1], r0 | membar.cta | st.cg.s32 [r1], r0 ; | mov.s32 r2, 1 | membar.gl ; | st.cg.s32 [r3], r2 | ld.cg.s32 r2, [r3] ; exists (1::y=2 /\ 1:r0=1 /\ 2:r2=0) (device (kernel (cta (warp P0) (warp P1) (warp P2)))) x:local; y:global Generated assembler //START _litmus_P2 mov.s32 sr02, 2 ; st.cg.s32 [sr12], sr02 ; membar.gl ; 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/dire09eab.tmp/WRW+WR+membar.cta+membar.gl-p0:p1:p2-xsyg-0.exe' successfully loaded Specification clusters: 3 Specification: [[(562, 2, 'R8'), (565, 3, 'R0')], [(624, 3, 'R0'), (622, 2, 'R10')], [(672, 2, 'R8')]] Cluster 0: OK Cluster 1: OK Cluster 2: OK !!SUCCESS!! Test WRW+WR+membar.cta+membar.gl-p0:p1:p2-xsyg Allowed Histogram (7 states) 314 :>1:r0=0; 2:r2=0; 1::y=1; 7 :>1:r0=1; 2:r2=0; 1::y=1; 18328 :>1:r0=0; 2:r2=1; 1::y=1; 11442 :>1:r0=1; 2:r2=1; 1::y=1; 50 :>1:r0=0; 2:r2=0; 1::y=2; 17735 :>1:r0=0; 2:r2=1; 1::y=2; 2124 :>1:r0=1; 2:r2=1; 1::y=2; No Witnesses Positive: 0, Negative: 50000 Condition exists (1::y=2 /\ 1:r0=1 /\ 2:r2=0) is NOT validated Observation WRW+WR+membar.cta+membar.gl-p0:p1:p2-xsyg Never 0 50000 Time WRW+WR+membar.cta+membar.gl-p0:p1:p2-xsyg 16.45 -- 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/WRW+WR+membar.cta+membar.gl-p0:p1:p2-xsyg-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 */