GPU_PTX IRIW+membar.cta+ctrl-p0:p1:p2:p3-xsys "Rf-w-s Mcta-d-Rs-Rs Fr-w-s Rf-w-s Ctrl-d-s-Rs Fr-w-s" {} P0 | P1 | P2 | P3 ; mov.s32 r0, 1 | ld.cg.s32 r0, [r1] | mov.s32 r0, 1 | ld.cg.s32 r0, [r1] ; st.cg.s32 [r1], r0 | membar.cta | st.cg.s32 [r1], r0 | and.b32 r2, r0 2147483648 ; | ld.cg.s32 r2, [r3] | | setp.eq.b32 p7, r2, 0 ; | | | @p7 bra LC00 ; | | | mov.s64 r4, 3494 ; | | | LC00: ; | | | ld.cg.s32 r3, [r4] ; exists (1:r0=1 /\ 1:r2=0 /\ 3:r0=1 /\ 3:r3=0) (device (kernel (cta (warp P0) (warp P1) (warp P2) (warp P3)))) x:local; y:local Generated assembler //START _litmus_P3 ld.cg.s32 sr03, [sr13] ; and.b32 sr23, sr03, 2147483648 ; setp.eq.b32 sp73, sr23, 0 ; @sp73 bra LC00 ; mov.s64 sr43, 3494 ; LC00: ld.cg.s32 sr33, [sr43] ; //START _litmus_P2 mov.s32 sr02, 1 ; st.cg.s32 [sr12], sr02 ; //START _litmus_P1 ld.cg.s32 sr01, [sr11] ; membar.cta ; ld.cg.s32 sr21, [sr31] ; //START _litmus_P0 mov.s32 sr00, 1 ; st.cg.s32 [sr10], sr00 ; Binary '/tmp/dir3c25f5.tmp/IRIW+membar.cta+ctrl-p0:p1:p2:p3-xsys-0.exe' successfully loaded Specification clusters: 4 Specification: [[(808, 3, 'R4'), (809, 3, 'R5')], [(870, 2, 'R8')], [(945, 3, 'R4'), (946, 3, 'R5')], [(1012, 2, 'R8')]] Cluster 0: OK Cluster 1: OK Cluster 2: OK Cluster 3: OK !!SUCCESS!! Test IRIW+membar.cta+ctrl-p0:p1:p2:p3-xsys Allowed Histogram (15 states) 1245 :>1:r0=0; 1:r2=0; 3:r0=0; 3:r3=0; 16 :>1:r0=1; 1:r2=0; 3:r0=0; 3:r3=0; 2813 :>1:r0=0; 1:r2=1; 3:r0=0; 3:r3=0; 1062 :>1:r0=1; 1:r2=1; 3:r0=0; 3:r3=0; 20 :>1:r0=0; 1:r2=0; 3:r0=1; 3:r3=0; 918 :>1:r0=0; 1:r2=1; 3:r0=1; 3:r3=0; 522 :>1:r0=1; 1:r2=1; 3:r0=1; 3:r3=0; 1563 :>1:r0=0; 1:r2=0; 3:r0=0; 3:r3=1; 759 :>1:r0=1; 1:r2=0; 3:r0=0; 3:r3=1; 6083 :>1:r0=0; 1:r2=1; 3:r0=0; 3:r3=1; 11462 :>1:r0=1; 1:r2=1; 3:r0=0; 3:r3=1; 843 :>1:r0=0; 1:r2=0; 3:r0=1; 3:r3=1; 433 :>1:r0=1; 1:r2=0; 3:r0=1; 3:r3=1; 9072 :>1:r0=0; 1:r2=1; 3:r0=1; 3:r3=1; 13189 :>1:r0=1; 1:r2=1; 3:r0=1; 3:r3=1; No Witnesses Positive: 0, Negative: 50000 Condition exists (1:r0=1 /\ 1:r2=0 /\ 3:r0=1 /\ 3:r3=0) is NOT validated Observation IRIW+membar.cta+ctrl-p0:p1:p2:p3-xsys Never 0 50000 Time IRIW+membar.cta+ctrl-p0:p1:p2:p3-xsys 3.70 -- device info -- Name: GeForce GTX 750 Ti Major revision number: 5 Minor revision number: 0 Total global memory: 2147287040 Total shared memory per block: 49152 Number of multiprocessors: 5 Machine: formal Revision 1383, version 5.01 GPU_PTX experimental backend Command line: ./litmus -mach GTX750.cfg -a 8 -gpu-verf-comp true big_bucket/IRIW+membar.cta+ctrl-p0:p1:p2:p3-xsys-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_50 */ /* 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: 5 */ /* gpu_min_ctas: 4 */ /* gpu_max_threads: 256 */ /* gpu_min_threads: 128 */