GPU_PTX Z6.1+membar.cta+po+addr-p0:p1:p2-xgyszg "Mcta-d-Wg-Ws Ws-w-s Po-d-Ws-Wg Rf-w-g Addr-d-g-Wg Ws-w-g" {} 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 | and.b32 r2, r0 2147483648 ; membar.cta | mov.s32 r2, 1 | cvt.u64.u32 r3, r2 ; mov.s32 r2, 1 | st.cg.s32 [r3], r2 | mov.s32 r4, 1 ; st.cg.s32 [r3], r2 | | add.u64 r5, r5 r3 ; | | st.cg.s32 [r5], r4 ; exists (0::x=2 /\ 0::y=2 /\ 2:r0=1) (device (kernel (cta (warp P0) (warp P1) (warp P2)))) x:global; y:local; z:global Generated assembler //START _litmus_P2 ld.cg.s32 sr02, [sr12] ; and.b32 sr22, sr02, 2147483648 ; cvt.u64.u32 sr32, sr22 ; mov.s32 sr42, 1 ; add.u64 sr52, sr52, sr32 ; st.cg.s32 [sr52], sr42 ; //START _litmus_P1 mov.s32 sr01, 2 ; st.cg.s32 [sr11], sr01 ; mov.s32 sr21, 1 ; st.cg.s32 [sr31], sr21 ; //START _litmus_P0 mov.s32 sr00, 2 ; st.cg.s32 [sr10], sr00 ; membar.cta ; mov.s32 sr20, 1 ; st.cg.s32 [sr30], sr20 ; Binary '/tmp/dir9fa91e.tmp/Z6.1+membar.cta+po+addr-p0:p1:p2-xgyszg-0.exe' successfully loaded Specification clusters: 3 Specification: [[(661, 3, 'R4'), (658, 2, 'R6')], [(716, 2, 'R10'), (718, 2, 'R12')], [(772, 2, 'R10'), (775, 2, 'R12')]] Cluster 0: OK Cluster 1: OK Cluster 2: OK !!SUCCESS!! Test Z6.1+membar.cta+po+addr-p0:p1:p2-xgyszg Allowed Histogram (7 states) 33809 :>2:r0=0; 0::x=1; 0::y=1; 5220 :>2:r0=1; 0::x=1; 0::y=1; 3099 :>2:r0=0; 0::x=2; 0::y=1; 76 :>2:r0=1; 0::x=2; 0::y=1; 7739 :>2:r0=0; 0::x=1; 0::y=2; 46 :>2:r0=1; 0::x=1; 0::y=2; 11 :>2:r0=0; 0::x=2; 0::y=2; No Witnesses Positive: 0, Negative: 50000 Condition exists (0::x=2 /\ 0::y=2 /\ 2:r0=1) is NOT validated Observation Z6.1+membar.cta+po+addr-p0:p1:p2-xgyszg Never 0 50000 Time Z6.1+membar.cta+po+addr-p0:p1:p2-xgyszg 22.54 -- 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_bucket/Z6.1+membar.cta+po+addr-p0:p1:p2-xgyszg-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 */