Commit d711f974 authored by Bogdan Gligorijević's avatar Bogdan Gligorijević Committed by Luca Barbato
Browse files

ipred cfl functions

Benchmarks:

- Kendryte K230:
cfl_pred_cfl_128_w4_8bpc_c:         497.3 ( 1.00x)
cfl_pred_cfl_128_w4_8bpc_rvv:       369.6 ( 1.35x)
cfl_pred_cfl_128_w4_16bpc_c:        425.2 ( 1.00x)
cfl_pred_cfl_128_w4_16bpc_rvv:      385.5 ( 1.10x)
cfl_pred_cfl_128_w8_8bpc_c:        1544.2 ( 1.00x)
cfl_pred_cfl_128_w8_8bpc_rvv:       584.2 ( 2.64x)
cfl_pred_cfl_128_w8_16bpc_c:       1306.2 ( 1.00x)
cfl_pred_cfl_128_w8_16bpc_rvv:      608.8 ( 2.15x)
cfl_pred_cfl_128_w16_8bpc_c:       3085.6 ( 1.00x)
cfl_pred_cfl_128_w16_8bpc_rvv:      584.2 ( 5.28x)
cfl_pred_cfl_128_w16_16bpc_c:      2657.1 ( 1.00x)
cfl_pred_cfl_128_w16_16bpc_rvv:     608.9 ( 4.36x)
cfl_pred_cfl_128_w32_8bpc_c:       8405.6 ( 1.00x)
cfl_pred_cfl_128_w32_8bpc_rvv:     1416.1 ( 5.94x)
cfl_pred_cfl_128_w32_16bpc_c:      7199.9 ( 1.00x)
cfl_pred_cfl_128_w32_16bpc_rvv:    1479.8 ( 4.87x)
cfl_pred_cfl_left_w4_8bpc_c:        553.1 ( 1.00x)
cfl_pred_cfl_left_w4_8bpc_rvv:      395.6 ( 1.40x)
cfl_pred_cfl_left_w4_16bpc_c:       486.7 ( 1.00x)
cfl_pred_cfl_left_w4_16bpc_rvv:     409.1 ( 1.19x)
cfl_pred_cfl_left_w8_8bpc_c:       1610.8 ( 1.00x)
cfl_pred_cfl_left_w8_8bpc_rvv:      610.4 ( 2.64x)
cfl_pred_cfl_left_w8_16bpc_c:      1378.0 ( 1.00x)
cfl_pred_cfl_left_w8_16bpc_rvv:     636.2 ( 2.17x)
cfl_pred_cfl_left_w16_8bpc_c:      3154.4 ( 1.00x)
cfl_pred_cfl_left_w16_8bpc_rvv:     610.4 ( 5.17x)
cfl_pred_cfl_left_w16_16bpc_c:     2733.2 ( 1.00x)
cfl_pred_cfl_left_w16_16bpc_rvv:    636.3 ( 4.30x)
cfl_pred_cfl_left_w32_8bpc_c:      8451.7 ( 1.00x)
cfl_pred_cfl_left_w32_8bpc_rvv:    1442.5 ( 5.86x)
cfl_pred_cfl_left_w32_16bpc_c:     7267.2 ( 1.00x)
cfl_pred_cfl_left_w32_16bpc_rvv:   1509.4 ( 4.81x)
cfl_pred_cfl_top_w4_8bpc_c:         544.7 ( 1.00x)
cfl_pred_cfl_top_w4_8bpc_rvv:       395.8 ( 1.38x)
cfl_pred_cfl_top_w4_16bpc_c:        475.1 ( 1.00x)
cfl_pred_cfl_top_w4_16bpc_rvv:      406.7 ( 1.17x)
cfl_pred_cfl_top_w8_8bpc_c:        1599.3 ( 1.00x)
cfl_pred_cfl_top_w8_8bpc_rvv:       610.4 ( 2.62x)
cfl_pred_cfl_top_w8_16bpc_c:       1363.8 ( 1.00x)
cfl_pred_cfl_top_w8_16bpc_rvv:      630.3 ( 2.16x)
cfl_pred_cfl_top_w16_8bpc_c:       3161.0 ( 1.00x)
cfl_pred_cfl_top_w16_8bpc_rvv:      610.5 ( 5.18x)
cfl_pred_cfl_top_w16_16bpc_c:      2735.9 ( 1.00x)
cfl_pred_cfl_top_w16_16bpc_rvv:     634.3 ( 4.31x)
cfl_pred_cfl_top_w32_8bpc_c:       8564.4 ( 1.00x)
cfl_pred_cfl_top_w32_8bpc_rvv:     1442.8 ( 5.94x)
cfl_pred_cfl_top_w32_16bpc_c:      7294.9 ( 1.00x)
cfl_pred_cfl_top_w32_16bpc_rvv:    1511.5 ( 4.83x)
cfl_pred_cfl_w4_8bpc_c:             571.5 ( 1.00x)
cfl_pred_cfl_w4_8bpc_rvv:           421.0 ( 1.36x)
cfl_pred_cfl_w4_16bpc_c:            499.1 ( 1.00x)
cfl_pred_cfl_w4_16bpc_rvv:          462.8 ( 1.08x)
cfl_pred_cfl_w8_8bpc_c:            1642.0 ( 1.00x)
cfl_pred_cfl_w8_8bpc_rvv:           635.8 ( 2.58x)
cfl_pred_cfl_w8_16bpc_c:           1401.4 ( 1.00x)
cfl_pred_cfl_w8_16bpc_rvv:          686.1 ( 2.04x)
cfl_pred_cfl_w16_8bpc_c:           3204.3 ( 1.00x)
cfl_pred_cfl_w16_8bpc_rvv:          635.8 ( 5.04x)
cfl_pred_cfl_w16_16bpc_c:          2784.8 ( 1.00x)
cfl_pred_cfl_w16_16bpc_rvv:         686.1 ( 4.06x)
cfl_pred_cfl_w32_8bpc_c:           8623.9 ( 1.00x)
cfl_pred_cfl_w32_8bpc_rvv:         1465.9 ( 5.88x)
cfl_pred_cfl_w32_16bpc_c:          7357.8 ( 1.00x)
cfl_pred_cfl_w32_16bpc_rvv:        1556.3 ( 4.73x)

- Banana Pi BPI-F3:
cfl_pred_cfl_128_w4_8bpc_c:         485.5 ( 1.00x)
cfl_pred_cfl_128_w4_8bpc_rvv:       366.4 ( 1.33x)
cfl_pred_cfl_128_w4_16bpc_c:        393.5 ( 1.00x)
cfl_pred_cfl_128_w4_16bpc_rvv:      378.7 ( 1.04x)
cfl_pred_cfl_128_w8_8bpc_c:        1507.9 ( 1.00x)
cfl_pred_cfl_128_w8_8bpc_rvv:       577.4 ( 2.61x)
cfl_pred_cfl_128_w8_16bpc_c:       1205.7 ( 1.00x)
cfl_pred_cfl_128_w8_16bpc_rvv:      605.1 ( 1.99x)
cfl_pred_cfl_128_w16_8bpc_c:       3019.3 ( 1.00x)
cfl_pred_cfl_128_w16_8bpc_rvv:      577.4 ( 5.23x)
cfl_pred_cfl_128_w16_16bpc_c:      2506.5 ( 1.00x)
cfl_pred_cfl_128_w16_16bpc_rvv:     605.1 ( 4.14x)
cfl_pred_cfl_128_w32_8bpc_c:       8170.0 ( 1.00x)
cfl_pred_cfl_128_w32_8bpc_rvv:      715.6 (11.42x)
cfl_pred_cfl_128_w32_16bpc_c:      6686.7 ( 1.00x)
cfl_pred_cfl_128_w32_16bpc_rvv:     749.7 ( 8.92x)
cfl_pred_cfl_left_w4_8bpc_c:        539.4 ( 1.00x)
cfl_pred_cfl_left_w4_8bpc_rvv:      393.2 ( 1.37x)
cfl_pred_cfl_left_w4_16bpc_c:       452.0 ( 1.00x)
cfl_pred_cfl_left_w4_16bpc_rvv:     401.2 ( 1.13x)
cfl_pred_cfl_left_w8_8bpc_c:       1572.4 ( 1.00x)
cfl_pred_cfl_left_w8_8bpc_rvv:      604.1 ( 2.60x)
cfl_pred_cfl_left_w8_16bpc_c:      1274.5 ( 1.00x)
cfl_pred_cfl_left_w8_16bpc_rvv:     629.0 ( 2.03x)
cfl_pred_cfl_left_w16_8bpc_c:      3096.0 ( 1.00x)
cfl_pred_cfl_left_w16_8bpc_rvv:     604.1 ( 5.13x)
cfl_pred_cfl_left_w16_16bpc_c:     2591.4 ( 1.00x)
cfl_pred_cfl_left_w16_16bpc_rvv:    629.0 ( 4.12x)
cfl_pred_cfl_left_w32_8bpc_c:      8266.0 ( 1.00x)
cfl_pred_cfl_left_w32_8bpc_rvv:     742.4 (11.13x)
cfl_pred_cfl_left_w32_16bpc_c:     6758.0 ( 1.00x)
cfl_pred_cfl_left_w32_16bpc_rvv:    773.9 ( 8.73x)
cfl_pred_cfl_top_w4_8bpc_c:         532.3 ( 1.00x)
cfl_pred_cfl_top_w4_8bpc_rvv:       392.6 ( 1.36x)
cfl_pred_cfl_top_w4_16bpc_c:        440.4 ( 1.00x)
cfl_pred_cfl_top_w4_16bpc_rvv:      399.6 ( 1.10x)
cfl_pred_cfl_top_w8_8bpc_c:        1563.3 ( 1.00x)
cfl_pred_cfl_top_w8_8bpc_rvv:       603.6 ( 2.59x)
cfl_pred_cfl_top_w8_16bpc_c:       1271.6 ( 1.00x)
cfl_pred_cfl_top_w8_16bpc_rvv:      626.1 ( 2.03x)
cfl_pred_cfl_top_w16_8bpc_c:       3098.6 ( 1.00x)
cfl_pred_cfl_top_w16_8bpc_rvv:      603.6 ( 5.13x)
cfl_pred_cfl_top_w16_16bpc_c:      2562.8 ( 1.00x)
cfl_pred_cfl_top_w16_16bpc_rvv:     626.0 ( 4.09x)
cfl_pred_cfl_top_w32_8bpc_c:       8278.1 ( 1.00x)
cfl_pred_cfl_top_w32_8bpc_rvv:      741.8 (11.16x)
cfl_pred_cfl_top_w32_16bpc_c:      6799.1 ( 1.00x)
cfl_pred_cfl_top_w32_16bpc_rvv:     775.0 ( 8.77x)
cfl_pred_cfl_w4_8bpc_c:             559.8 ( 1.00x)
cfl_pred_cfl_w4_8bpc_rvv:           421.7 ( 1.33x)
cfl_pred_cfl_w4_16bpc_c:            470.2 ( 1.00x)
cfl_pred_cfl_w4_16bpc_rvv:          451.3 ( 1.04x)
cfl_pred_cfl_w8_8bpc_c:            1605.5 ( 1.00x)
cfl_pred_cfl_w8_8bpc_rvv:           632.8 ( 2.54x)
cfl_pred_cfl_w8_16bpc_c:           1308.5 ( 1.00x)
cfl_pred_cfl_w8_16bpc_rvv:          677.9 ( 1.93x)
cfl_pred_cfl_w16_8bpc_c:           3135.0 ( 1.00x)
cfl_pred_cfl_w16_8bpc_rvv:          632.9 ( 4.95x)
cfl_pred_cfl_w16_16bpc_c:          2625.9 ( 1.00x)
cfl_pred_cfl_w16_16bpc_rvv:         677.9 ( 3.87x)
cfl_pred_cfl_w32_8bpc_c:           8376.6 ( 1.00x)
cfl_pred_cfl_w32_8bpc_rvv:          770.4 (10.87x)
cfl_pred_cfl_w32_16bpc_c:          6866.4 ( 1.00x)
cfl_pred_cfl_w32_16bpc_rvv:         822.7 ( 8.35x)
parent 2f5bfc37
Loading
Loading
Loading
Loading
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment