GPU_PTX Z6.2+membar.cta+addr+addr-p0:p1:p2-xsyszs "Mcta-d-Ws-Ws Rf-w-s Addr-d-s-Ws Rf-w-s Addr-d-s-Ws Ws-w-s" {} P0 | P1 | P2 ; mov.s32 r0, 2 | ld.cg.s32 r0, [r1] | ld.cg.s32 r0, [r1] ; st.cg.s32 [r1], r0 | and.b32 r2, r0 2147483648 | and.b32 r2, r0 2147483648 ; membar.cta | cvt.u64.u32 r3, r2 | cvt.u64.u32 r3, r2 ; mov.s32 r2, 1 | mov.s32 r4, 1 | mov.s32 r4, 1 ; st.cg.s32 [r3], r2 | add.u64 r5, r5 r3 | add.u64 r5, r5 r3 ; | st.cg.s32 [r5], r4 | st.cg.s32 [r5], r4 ; exists (0::x=2 /\ 1:r0=1 /\ 2:r0=1) (device (kernel (cta (warp P0) (warp P1) (warp P2)))) x:local; y:local; z:local 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 ld.cg.s32 sr01, [sr11] ; and.b32 sr21, sr01, 2147483648 ; cvt.u64.u32 sr31, sr21 ; mov.s32 sr41, 1 ; add.u64 sr51, sr51, sr31 ; st.cg.s32 [sr51], sr41 ; //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/dircd804e.tmp/Z6.2+membar.cta+addr+addr-p0:p1:p2-xsyszs-0.exe' successfully loaded Specification clusters: 3 Specification: [[(673, 3, 'R4'), (671, 2, 'R6')], [(740, 3, 'R4'), (738, 2, 'R6')], [(807, 2, 'R10'), (809, 2, 'R12')]] Cluster 0: OK Cluster 1: OK Cluster 2: OK !!SUCCESS!! Test Z6.2+membar.cta+addr+addr-p0:p1:p2-xsyszs Allowed Histogram (7 states) 19309 :>1:r0=0; 2:r0=0; 0::x=1; 6947 :>1:r0=1; 2:r0=0; 0::x=1; 8434 :>1:r0=0; 2:r0=1; 0::x=1; 1039 :>1:r0=1; 2:r0=1; 0::x=1; 12626 :>1:r0=0; 2:r0=0; 0::x=2; 502 :>1:r0=1; 2:r0=0; 0::x=2; 1143 :>1:r0=0; 2:r0=1; 0::x=2; No Witnesses Positive: 0, Negative: 50000 Condition exists (0::x=2 /\ 1:r0=1 /\ 2:r0=1) is NOT validated Observation Z6.2+membar.cta+addr+addr-p0:p1:p2-xsyszs Never 0 50000 Time Z6.2+membar.cta+addr+addr-p0:p1:p2-xsyszs 17.83 -- 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/Z6.2+membar.cta+addr+addr-p0:p1:p2-xsyszs-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 */