GPU_PTX ISA2+membar.gl+membar.cta+ctrl-p0:p1:p2-xsyszg "Mgl-d-Ws-Ws Rf-w-s Mcta-d-Rs-Wg Rf-w-g Ctrl-d-g-Rs Fr-w-s" {} P0 | P1 | P2 ; mov.s32 r0, 1 | ld.cg.s32 r0, [r1] | ld.cg.s32 r0, [r1] ; st.cg.s32 [r1], r0 | membar.cta | and.b32 r2, r0 2147483648 ; membar.gl | mov.s32 r2, 1 | setp.eq.b32 p8, r2, 0 ; mov.s32 r2, 1 | st.cg.s32 [r3], r2 | @p8 bra LC00 ; st.cg.s32 [r3], r2 | | mov.s64 r4, 3494 ; | | LC00: ; | | ld.cg.s32 r3, [r4] ; exists (1:r0=1 /\ 2:r0=1 /\ 2:r3=0) (device (kernel (cta (warp P0) (warp P1) (warp P2)))) x:local; y:local; z:global Generated assembler //START _litmus_P2 ld.cg.s32 sr02, [sr12] ; and.b32 sr22, sr02, 2147483648 ; setp.eq.b32 sp82, sr22, 0 ; @sp82 bra LC00 ; mov.s64 sr42, 3494 ; LC00: ld.cg.s32 sr32, [sr42] ; //START _litmus_P1 ld.cg.s32 sr01, [sr11] ; membar.cta ; mov.s32 sr21, 1 ; st.cg.s32 [sr31], sr21 ; //START _litmus_P0 mov.s32 sr00, 1 ; st.cg.s32 [sr10], sr00 ; membar.gl ; mov.s32 sr20, 1 ; st.cg.s32 [sr30], sr20 ; Binary '/tmp/dircd1488.tmp/ISA2+membar.gl+membar.cta+ctrl-p0:p1:p2-xsyszg-0.exe' successfully loaded Specification clusters: 3 Specification: [[(831, 3, 'R0'), (832, 3, 'R4')], [(911, 3, 'R0'), (909, 2, 'R12')], [(996, 2, 'R8'), (998, 2, 'R10')]] Cluster 0: OK Cluster 1: OK Cluster 2: OK !!SUCCESS!! Test ISA2+membar.gl+membar.cta+ctrl-p0:p1:p2-xsyszg Allowed Histogram (5 states) 4175 :>1:r0=0; 2:r0=0; 2:r3=0; 169 :>1:r0=0; 2:r0=1; 2:r3=0; 36779 :>1:r0=0; 2:r0=0; 2:r3=1; 4268 :>1:r0=1; 2:r0=0; 2:r3=1; 4609 :>1:r0=0; 2:r0=1; 2:r3=1; No Witnesses Positive: 0, Negative: 50000 Condition exists (1:r0=1 /\ 2:r0=1 /\ 2:r3=0) is NOT validated Observation ISA2+membar.gl+membar.cta+ctrl-p0:p1:p2-xsyszg Never 0 50000 Time ISA2+membar.gl+membar.cta+ctrl-p0:p1:p2-xsyszg 4.29 -- 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/ISA2+membar.gl+membar.cta+ctrl-p0:p1:p2-xsyszg-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 */