GPU_PTX IRIW+membar.cta+ctrl-p0:p1:p2::p3-xgyg "Rf-w-g Mcta-d-Rg-Rg Fr-w-g Rf-c-g Ctrl-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] | | setp.eq.b32 p7, r2, 0 ; | | | @p7 bra LC00 ; | | | mov.s64 r4, 3494 ; | | | LC00: ; | | | ld.cg.s32 r3, [r4] ; exists (1:r0=1 /\ 1:r2=0 /\ 3:r0=1 /\ 3:r3=0) (device (kernel (cta (warp P0) (warp P1) (warp P2)) (cta (warp P3)))) x:global; y:global Generated assembler //START _litmus_P3 ld.cg.s32 sr03, [sr13] ; and.b32 sr23, sr03, 2147483648 ; setp.eq.b32 sp73, sr23, 0 ; @sp73 bra LC00 ; mov.s64 sr43, 3494 ; LC00: ld.cg.s32 sr33, [sr43] ; //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/dira1a287.tmp/IRIW+membar.cta+ctrl-p0:p1:p2::p3-xgyg-0.exe' successfully loaded Specification clusters: 4 Specification: [[(610, 3, 'R4'), (608, 3, 'R5')], [(653, 2, 'R10')], [(698, 3, 'R4'), (696, 3, 'R5')], [(745, 2, 'R10')]] Cluster 0: OK Cluster 1: OK Cluster 2: OK Cluster 3: OK !!SUCCESS!! Test IRIW+membar.cta+ctrl-p0:p1:p2::p3-xgyg Allowed Histogram (15 states) 704 :>1:r0=0; 1:r2=0; 3:r0=0; 3:r3=0; 89 :>1:r0=1; 1:r2=0; 3:r0=0; 3:r3=0; 934 :>1:r0=0; 1:r2=1; 3:r0=0; 3:r3=0; 438 :>1:r0=1; 1:r2=1; 3:r0=0; 3:r3=0; 29 :>1:r0=0; 1:r2=0; 3:r0=1; 3:r3=0; 249 :>1:r0=0; 1:r2=1; 3:r0=1; 3:r3=0; 29 :>1:r0=1; 1:r2=1; 3:r0=1; 3:r3=0; 7565 :>1:r0=0; 1:r2=0; 3:r0=0; 3:r3=1; 1830 :>1:r0=1; 1:r2=0; 3:r0=0; 3:r3=1; 6587 :>1:r0=0; 1:r2=1; 3:r0=0; 3:r3=1; 7070 :>1:r0=1; 1:r2=1; 3:r0=0; 3:r3=1; 5232 :>1:r0=0; 1:r2=0; 3:r0=1; 3:r3=1; 925 :>1:r0=1; 1:r2=0; 3:r0=1; 3:r3=1; 10054 :>1:r0=0; 1:r2=1; 3:r0=1; 3:r3=1; 8265 :>1:r0=1; 1:r2=1; 3:r0=1; 3:r3=1; No Witnesses Positive: 0, Negative: 50000 Condition exists (1:r0=1 /\ 1:r2=0 /\ 3:r0=1 /\ 3:r3=0) is NOT validated Observation IRIW+membar.cta+ctrl-p0:p1:p2::p3-xgyg Never 0 50000 Time IRIW+membar.cta+ctrl-p0:p1:p2::p3-xgyg 18.14 -- device info -- Name: GeForce GTX TITAN Major revision number: 3 Minor revision number: 5 Total global memory: 6442123264 Total shared memory per block: 49152 Number of multiprocessors: 14 Machine: formal Revision 1383, version 5.01 GPU_PTX experimental backend Command line: ./litmus -mach GTXTitan.cfg -a 8 -gpu-verf-comp true big_bucket/IRIW+membar.cta+ctrl-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_35 */ /* 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: 14 */ /* gpu_min_ctas: 10 */ /* gpu_max_threads: 512 */ /* gpu_min_threads: 128 */