GPU_PTX LB+data+ctrl-p0:p1-xgyg "Data-d-g-Wg Rf-w-g Ctrl-d-g-Wg Rf-w-g" {} P0 | P1 ; ld.cg.s32 r0, [r1] | ld.cg.s32 r0, [r1] ; and.b32 r2, r0 2147483648 | and.b32 r2, r0 2147483648 ; add.s32 r2, r2 1 | setp.eq.b32 p7, r2, 0 ; st.cg.s32 [r3], r2 | @p7 bra LC00 ; | mov.s64 r4, 3494 ; | LC00: ; | mov.s32 r3, 1 ; | st.cg.s32 [r4], r3 ; exists (0:r0=1 /\ 1:r0=1) (device (kernel (cta (warp P0) (warp P1)))) x:global; y:global Generated assembler //START _litmus_P1 ld.cg.s32 sr01, [sr11] ; and.b32 sr21, sr01, 2147483648 ; setp.eq.b32 sp71, sr21, 0 ; @sp71 bra LC00 ; mov.s64 sr41, 3494 ; LC00: mov.s32 sr31, 1 ; st.cg.s32 [sr41], sr31 ; //START _litmus_P0 ld.cg.s32 sr00, [sr10] ; and.b32 sr20, sr00, 2147483648 ; add.s32 sr20, sr20, 1 ; st.cg.s32 [sr30], sr20 ; Binary '/tmp/dire19f3b.tmp/LB+data+ctrl-p0:p1-xgyg-0.exe' successfully loaded Specification clusters: 2 Specification: [[(422, 3, 'R4'), (419, 2, 'R10')], [(474, 3, 'R4'), (473, 2, 'R10')]] Cluster 0: OK Cluster 1: OK !!SUCCESS!! Test LB+data+ctrl-p0:p1-xgyg Allowed Histogram (3 states) 39767 :>0:r0=0; 1:r0=0; 4815 :>0:r0=1; 1:r0=0; 5418 :>0:r0=0; 1:r0=1; No Witnesses Positive: 0, Negative: 50000 Condition exists (0:r0=1 /\ 1:r0=1) is NOT validated Observation LB+data+ctrl-p0:p1-xgyg Never 0 50000 Time LB+data+ctrl-p0:p1-xgyg 3.74 -- device info -- Name: GeForce GT 540M Major revision number: 2 Minor revision number: 1 Total global memory: 1072889856 Total shared memory per block: 49152 Number of multiprocessors: 2 Machine: DeepThought3 Revision 1371, version 5.01 GPU_PTX experimental backend Command line: ./litmus -mach GTX540m.cfg -a 8 -gpu-verf-comp true big_bucket/LB+data+ctrl-p0:p1-xgyg-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_21 */ /* 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: 4 */ /* gpu_min_ctas: 4 */ /* gpu_max_threads: 128 */ /* gpu_min_threads: 128 */