GPU_PTX Z6.2+membar.cta+addr+ctrl-p0:p1::p2-xgyszg "Mcta-d-Wg-Ws Rf-w-s Addr-d-s-Wg Rf-c-g Ctrl-d-g-Wg Ws-c-g" {} 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 | setp.eq.b32 p3, r2, 0 ; mov.s32 r2, 1 | mov.s32 r4, 1 | @p3 bra LC00 ; st.cg.s32 [r3], r2 | add.u64 r5, r5 r3 | mov.s64 r4, 3494 ; | st.cg.s32 [r5], r4 | LC00: ; | | mov.s32 r3, 1 ; | | st.cg.s32 [r4], r3 ; exists (0::x=2 /\ 1:r0=1 /\ 2:r0=1) (device (kernel (cta (warp P0) (warp P1)) (cta (warp P2)))) x:global; y:local; z:global Generated assembler //START _litmus_P2 ld.cg.s32 sr02, [sr12] ; and.b32 sr22, sr02, 2147483648 ; setp.eq.b32 sp32, sr22, 0 ; @sp32 bra LC00 ; mov.s64 sr42, 3494 ; LC00: mov.s32 sr32, 1 ; st.cg.s32 [sr42], sr32 ; //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/dirdbbe75.tmp/Z6.2+membar.cta+addr+ctrl-p0:p1::p2-xgyszg-0.exe' successfully loaded Specification clusters: 3 Specification: [[(818, 3, 'R0'), (819, 2, 'R10')], [(898, 3, 'R0'), (896, 2, 'R4')], [(975, 2, 'R8'), (977, 2, 'R10')]] Cluster 0: OK Cluster 1: OK Cluster 2: OK !!SUCCESS!! Test Z6.2+membar.cta+addr+ctrl-p0:p1::p2-xgyszg Allowed Histogram (7 states) 8807 :>1:r0=0; 2:r0=0; 0::x=1; 6962 :>1:r0=1; 2:r0=0; 0::x=1; 22525 :>1:r0=0; 2:r0=1; 0::x=1; 5752 :>1:r0=1; 2:r0=1; 0::x=1; 3200 :>1:r0=0; 2:r0=0; 0::x=2; 2082 :>1:r0=1; 2:r0=0; 0::x=2; 672 :>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+ctrl-p0:p1::p2-xgyszg Never 0 50000 Time Z6.2+membar.cta+addr+ctrl-p0:p1::p2-xgyszg 5.15 -- 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/Z6.2+membar.cta+addr+ctrl-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_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 */