GPU_PTX ISA2+membar.cta+ctrl+addr-p0:p1::p2-xgyszg "Mcta-d-Wg-Ws Rf-w-s Ctrl-d-s-Wg Rf-c-g Addr-d-g-Rg Fr-c-g" {} P0 | P1 | P2 ; mov.s32 r0, 1 | 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 | setp.eq.b32 p1, r2, 0 | cvt.u64.u32 r3, r2 ; mov.s32 r2, 1 | @p1 bra LC00 | add.u64 r5, r5 r3 ; st.cg.s32 [r3], r2 | mov.s64 r4, 3494 | ld.cg.s32 r4, [r5] ; | LC00: | ; | mov.s32 r3, 1 | ; | st.cg.s32 [r4], r3 | ; exists (1:r0=1 /\ 2:r0=1 /\ 2:r4=0) (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 ; cvt.u64.u32 sr32, sr22 ; add.u64 sr52, sr52, sr32 ; ld.cg.s32 sr42, [sr52] ; //START _litmus_P1 ld.cg.s32 sr01, [sr11] ; and.b32 sr21, sr01, 2147483648 ; setp.eq.b32 sp11, sr21, 0 ; @sp11 bra LC00 ; mov.s64 sr41, 3494 ; LC00: mov.s32 sr31, 1 ; st.cg.s32 [sr41], sr31 ; //START _litmus_P0 mov.s32 sr00, 1 ; st.cg.s32 [sr10], sr00 ; membar.cta ; mov.s32 sr20, 1 ; st.cg.s32 [sr30], sr20 ; Binary '/tmp/dir4b70fc.tmp/ISA2+membar.cta+ctrl+addr-p0:p1::p2-xgyszg-0.exe' successfully loaded Specification clusters: 3 Specification: [[(625, 3, 'R4'), (623, 3, 'R0')], [(689, 3, 'R0'), (687, 2, 'R10')], [(748, 2, 'R8'), (751, 2, 'R10')]] Cluster 0: OK Cluster 1: OK Cluster 2: OK !!SUCCESS!! Test ISA2+membar.cta+ctrl+addr-p0:p1::p2-xgyszg Allowed Histogram (7 states) 2911 :>1:r0=0; 2:r0=0; 2:r4=0; 11 :>1:r0=1; 2:r0=0; 2:r4=0; 99 :>1:r0=0; 2:r0=1; 2:r4=0; 35343 :>1:r0=0; 2:r0=0; 2:r4=1; 6592 :>1:r0=1; 2:r0=0; 2:r4=1; 4879 :>1:r0=0; 2:r0=1; 2:r4=1; 165 :>1:r0=1; 2:r0=1; 2:r4=1; No Witnesses Positive: 0, Negative: 50000 Condition exists (1:r0=1 /\ 2:r0=1 /\ 2:r4=0) is NOT validated Observation ISA2+membar.cta+ctrl+addr-p0:p1::p2-xgyszg Never 0 50000 Time ISA2+membar.cta+ctrl+addr-p0:p1::p2-xgyszg 22.08 -- 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_bucket2/ISA2+membar.cta+ctrl+addr-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_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 */