GPU_PTX IRIW+membar.cta+addr-p0:p1::p2:p3-xgyg "Rf-w-g Mcta-d-Rg-Rg Fr-c-g Rf-w-g Addr-d-g-Rg Fr-c-g" {} 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] | | cvt.u64.u32 r3, r2 ; | | | add.u64 r5, r5 r3 ; | | | ld.cg.s32 r4, [r5] ; exists (1:r0=1 /\ 1:r2=0 /\ 3:r0=1 /\ 3:r4=0) (device (kernel (cta (warp P0) (warp P1)) (cta (warp P2) (warp P3)))) x:global; y:global Generated assembler //START _litmus_P3 ld.cg.s32 sr03, [sr13] ; and.b32 sr23, sr03, 2147483648 ; cvt.u64.u32 sr33, sr23 ; add.u64 sr53, sr53, sr33 ; ld.cg.s32 sr43, [sr53] ; //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/dirf83df4.tmp/IRIW+membar.cta+addr-p0:p1::p2:p3-xgyg-0.exe' successfully loaded Specification clusters: 4 Specification: [[(528, 3, 'R5'), (526, 3, 'R4')], [(570, 2, 'R8')], [(615, 3, 'R4'), (613, 3, 'R5')], [(662, 2, 'R8')]] Cluster 0: OK Cluster 1: OK Cluster 2: OK Cluster 3: OK !!SUCCESS!! Test IRIW+membar.cta+addr-p0:p1::p2:p3-xgyg Allowed Histogram (15 states) 2810 :>1:r0=0; 1:r2=0; 3:r0=0; 3:r4=0; 10 :>1:r0=1; 1:r2=0; 3:r0=0; 3:r4=0; 2956 :>1:r0=0; 1:r2=1; 3:r0=0; 3:r4=0; 566 :>1:r0=1; 1:r2=1; 3:r0=0; 3:r4=0; 85 :>1:r0=0; 1:r2=0; 3:r0=1; 3:r4=0; 1036 :>1:r0=0; 1:r2=1; 3:r0=1; 3:r4=0; 149 :>1:r0=1; 1:r2=1; 3:r0=1; 3:r4=0; 9429 :>1:r0=0; 1:r2=0; 3:r0=0; 3:r4=1; 2990 :>1:r0=1; 1:r2=0; 3:r0=0; 3:r4=1; 5169 :>1:r0=0; 1:r2=1; 3:r0=0; 3:r4=1; 8178 :>1:r0=1; 1:r2=1; 3:r0=0; 3:r4=1; 3054 :>1:r0=0; 1:r2=0; 3:r0=1; 3:r4=1; 586 :>1:r0=1; 1:r2=0; 3:r0=1; 3:r4=1; 6631 :>1:r0=0; 1:r2=1; 3:r0=1; 3:r4=1; 6351 :>1:r0=1; 1:r2=1; 3:r0=1; 3:r4=1; No Witnesses Positive: 0, Negative: 50000 Condition exists (1:r0=1 /\ 1:r2=0 /\ 3:r0=1 /\ 3:r4=0) is NOT validated Observation IRIW+membar.cta+addr-p0:p1::p2:p3-xgyg Never 0 50000 Time IRIW+membar.cta+addr-p0:p1::p2:p3-xgyg 7.43 -- 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/IRIW+membar.cta+addr-p0:p1::p2:p3-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 */