{ "tile_sizes": { "M": 32, "K": 64, "N": 32 }, "engines": [ "pe_dma", "pe_fetch_store", "pe_gemm", "pe_math" ], "stages": [ "DMA_READ", "DMA_WRITE", "FETCH", "STORE", "GEMM", "MATH" ], "variants": [ "ref_ref", "load_ref", "load_load" ], "rows": [ { "M": 32, "K": 32, "N": 32, "variant": "ref_ref", "flops": 65536, "bytes_hbm": 6144, "arith_intensity": 10.666666666666666, "tile_count_expected": 1, "sim_wall_clock_s": 0.112, "engines": { "pe_dma": { "occupancy_ns": 79.0, "wall_ns": 79.0, "record_count": 3 }, "pe_fetch_store": { "occupancy_ns": 40.0, "wall_ns": 40.0, "record_count": 2 }, "pe_gemm": { "occupancy_ns": 16.384000000000015, "wall_ns": 16.384000000000015, "record_count": 1 }, "pe_math": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "stages": { "DMA_READ": { "occupancy_ns": 58.0, "wall_ns": 58.0, "record_count": 2 }, "DMA_WRITE": { "occupancy_ns": 21.0, "wall_ns": 21.0, "record_count": 1 }, "FETCH": { "occupancy_ns": 32.0, "wall_ns": 32.0, "record_count": 1 }, "STORE": { "occupancy_ns": 8.0, "wall_ns": 8.0, "record_count": 1 }, "GEMM": { "occupancy_ns": 16.384000000000015, "wall_ns": 16.384000000000015, "record_count": 1 }, "MATH": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "pe_window_ns": 135.38400000000001, "composite_window_ns": 135.38400000000001 }, { "M": 32, "K": 32, "N": 32, "variant": "load_ref", "flops": 65536, "bytes_hbm": 6144, "arith_intensity": 10.666666666666666, "tile_count_expected": 1, "sim_wall_clock_s": 0.108, "engines": { "pe_dma": { "occupancy_ns": 71.0, "wall_ns": 71.0, "record_count": 3 }, "pe_fetch_store": { "occupancy_ns": 40.0, "wall_ns": 40.0, "record_count": 2 }, "pe_gemm": { "occupancy_ns": 16.384000000000015, "wall_ns": 16.384000000000015, "record_count": 1 }, "pe_math": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "stages": { "DMA_READ": { "occupancy_ns": 29.0, "wall_ns": 29.0, "record_count": 1 }, "DMA_WRITE": { "occupancy_ns": 21.0, "wall_ns": 21.0, "record_count": 1 }, "FETCH": { "occupancy_ns": 32.0, "wall_ns": 32.0, "record_count": 1 }, "STORE": { "occupancy_ns": 8.0, "wall_ns": 8.0, "record_count": 1 }, "GEMM": { "occupancy_ns": 16.384000000000015, "wall_ns": 16.384000000000015, "record_count": 1 }, "MATH": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "pe_window_ns": 171.394, "composite_window_ns": 106.38400000000001 }, { "M": 32, "K": 32, "N": 32, "variant": "load_load", "flops": 65536, "bytes_hbm": 6144, "arith_intensity": 10.666666666666666, "tile_count_expected": 1, "sim_wall_clock_s": 0.105, "engines": { "pe_dma": { "occupancy_ns": 63.0, "wall_ns": 63.0, "record_count": 3 }, "pe_fetch_store": { "occupancy_ns": 40.0, "wall_ns": 40.0, "record_count": 2 }, "pe_gemm": { "occupancy_ns": 16.384000000000015, "wall_ns": 16.384000000000015, "record_count": 1 }, "pe_math": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "stages": { "DMA_READ": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 }, "DMA_WRITE": { "occupancy_ns": 21.0, "wall_ns": 21.0, "record_count": 1 }, "FETCH": { "occupancy_ns": 32.0, "wall_ns": 32.0, "record_count": 1 }, "STORE": { "occupancy_ns": 8.0, "wall_ns": 8.0, "record_count": 1 }, "GEMM": { "occupancy_ns": 16.384000000000015, "wall_ns": 16.384000000000015, "record_count": 1 }, "MATH": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "pe_window_ns": 183.394, "composite_window_ns": 77.38400000000001 }, { "M": 32, "K": 64, "N": 32, "variant": "ref_ref", "flops": 131072, "bytes_hbm": 10240, "arith_intensity": 12.8, "tile_count_expected": 1, "sim_wall_clock_s": 0.169, "engines": { "pe_dma": { "occupancy_ns": 79.0, "wall_ns": 79.0, "record_count": 3 }, "pe_fetch_store": { "occupancy_ns": 40.0, "wall_ns": 40.0, "record_count": 2 }, "pe_gemm": { "occupancy_ns": 16.384000000000015, "wall_ns": 16.384000000000015, "record_count": 1 }, "pe_math": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "stages": { "DMA_READ": { "occupancy_ns": 58.0, "wall_ns": 58.0, "record_count": 2 }, "DMA_WRITE": { "occupancy_ns": 21.0, "wall_ns": 21.0, "record_count": 1 }, "FETCH": { "occupancy_ns": 32.0, "wall_ns": 32.0, "record_count": 1 }, "STORE": { "occupancy_ns": 8.0, "wall_ns": 8.0, "record_count": 1 }, "GEMM": { "occupancy_ns": 16.384000000000015, "wall_ns": 16.384000000000015, "record_count": 1 }, "MATH": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "pe_window_ns": 135.38400000000001, "composite_window_ns": 135.38400000000001 }, { "M": 32, "K": 64, "N": 32, "variant": "load_ref", "flops": 131072, "bytes_hbm": 10240, "arith_intensity": 12.8, "tile_count_expected": 1, "sim_wall_clock_s": 0.163, "engines": { "pe_dma": { "occupancy_ns": 79.0, "wall_ns": 79.0, "record_count": 3 }, "pe_fetch_store": { "occupancy_ns": 40.0, "wall_ns": 40.0, "record_count": 2 }, "pe_gemm": { "occupancy_ns": 16.384000000000015, "wall_ns": 16.384000000000015, "record_count": 1 }, "pe_math": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "stages": { "DMA_READ": { "occupancy_ns": 29.0, "wall_ns": 29.0, "record_count": 1 }, "DMA_WRITE": { "occupancy_ns": 21.0, "wall_ns": 21.0, "record_count": 1 }, "FETCH": { "occupancy_ns": 32.0, "wall_ns": 32.0, "record_count": 1 }, "STORE": { "occupancy_ns": 8.0, "wall_ns": 8.0, "record_count": 1 }, "GEMM": { "occupancy_ns": 16.384000000000015, "wall_ns": 16.384000000000015, "record_count": 1 }, "MATH": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "pe_window_ns": 179.394, "composite_window_ns": 106.38400000000001 }, { "M": 32, "K": 64, "N": 32, "variant": "load_load", "flops": 131072, "bytes_hbm": 10240, "arith_intensity": 12.8, "tile_count_expected": 1, "sim_wall_clock_s": 0.104, "engines": { "pe_dma": { "occupancy_ns": 79.0, "wall_ns": 79.0, "record_count": 3 }, "pe_fetch_store": { "occupancy_ns": 40.0, "wall_ns": 40.0, "record_count": 2 }, "pe_gemm": { "occupancy_ns": 16.384000000000015, "wall_ns": 16.384000000000015, "record_count": 1 }, "pe_math": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "stages": { "DMA_READ": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 }, "DMA_WRITE": { "occupancy_ns": 21.0, "wall_ns": 21.0, "record_count": 1 }, "FETCH": { "occupancy_ns": 32.0, "wall_ns": 32.0, "record_count": 1 }, "STORE": { "occupancy_ns": 8.0, "wall_ns": 8.0, "record_count": 1 }, "GEMM": { "occupancy_ns": 16.384000000000015, "wall_ns": 16.384000000000015, "record_count": 1 }, "MATH": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "pe_window_ns": 191.394, "composite_window_ns": 77.38400000000001 }, { "M": 32, "K": 128, "N": 32, "variant": "ref_ref", "flops": 262144, "bytes_hbm": 18432, "arith_intensity": 14.222222222222221, "tile_count_expected": 2, "sim_wall_clock_s": 0.162, "engines": { "pe_dma": { "occupancy_ns": 158.995, "wall_ns": 98.0, "record_count": 5 }, "pe_fetch_store": { "occupancy_ns": 72.0, "wall_ns": 56.0, "record_count": 3 }, "pe_gemm": { "occupancy_ns": 33.152000000000044, "wall_ns": 32.76800000000003, "record_count": 2 }, "pe_math": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "stages": { "DMA_READ": { "occupancy_ns": 137.995, "wall_ns": 77.0, "record_count": 4 }, "DMA_WRITE": { "occupancy_ns": 21.0, "wall_ns": 21.0, "record_count": 1 }, "FETCH": { "occupancy_ns": 64.0, "wall_ns": 48.0, "record_count": 2 }, "STORE": { "occupancy_ns": 8.0, "wall_ns": 8.0, "record_count": 1 }, "GEMM": { "occupancy_ns": 33.152000000000044, "wall_ns": 32.76800000000003, "record_count": 2 }, "MATH": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "pe_window_ns": 154.76800000000003, "composite_window_ns": 154.76800000000003 }, { "M": 32, "K": 128, "N": 32, "variant": "load_ref", "flops": 262144, "bytes_hbm": 18432, "arith_intensity": 14.222222222222221, "tile_count_expected": 2, "sim_wall_clock_s": 0.183, "engines": { "pe_dma": { "occupancy_ns": 139.995, "wall_ns": 111.0, "record_count": 4 }, "pe_fetch_store": { "occupancy_ns": 72.0, "wall_ns": 56.0, "record_count": 3 }, "pe_gemm": { "occupancy_ns": 33.152000000000044, "wall_ns": 32.76800000000003, "record_count": 2 }, "pe_math": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "stages": { "DMA_READ": { "occupancy_ns": 73.995, "wall_ns": 45.0, "record_count": 2 }, "DMA_WRITE": { "occupancy_ns": 21.0, "wall_ns": 21.0, "record_count": 1 }, "FETCH": { "occupancy_ns": 64.0, "wall_ns": 48.0, "record_count": 2 }, "STORE": { "occupancy_ns": 8.0, "wall_ns": 8.0, "record_count": 1 }, "GEMM": { "occupancy_ns": 33.152000000000044, "wall_ns": 32.76800000000003, "record_count": 2 }, "MATH": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "pe_window_ns": 211.77800000000002, "composite_window_ns": 122.76800000000003 }, { "M": 32, "K": 128, "N": 32, "variant": "load_load", "flops": 262144, "bytes_hbm": 18432, "arith_intensity": 14.222222222222221, "tile_count_expected": 2, "sim_wall_clock_s": 0.106, "engines": { "pe_dma": { "occupancy_ns": 112.0, "wall_ns": 107.0, "record_count": 3 }, "pe_fetch_store": { "occupancy_ns": 87.995, "wall_ns": 56.0, "record_count": 3 }, "pe_gemm": { "occupancy_ns": 33.152000000000044, "wall_ns": 32.76800000000003, "record_count": 2 }, "pe_math": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "stages": { "DMA_READ": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 }, "DMA_WRITE": { "occupancy_ns": 21.0, "wall_ns": 21.0, "record_count": 1 }, "FETCH": { "occupancy_ns": 79.995, "wall_ns": 48.0, "record_count": 2 }, "STORE": { "occupancy_ns": 8.0, "wall_ns": 8.0, "record_count": 1 }, "GEMM": { "occupancy_ns": 33.152000000000044, "wall_ns": 32.76800000000003, "record_count": 2 }, "MATH": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "pe_window_ns": 223.77800000000002, "composite_window_ns": 93.76800000000003 }, { "M": 32, "K": 128, "N": 128, "variant": "ref_ref", "flops": 1048576, "bytes_hbm": 49152, "arith_intensity": 21.333333333333332, "tile_count_expected": 8, "sim_wall_clock_s": 0.177, "engines": { "pe_dma": { "occupancy_ns": 1798.8600000000001, "wall_ns": 339.0, "record_count": 20 }, "pe_fetch_store": { "occupancy_ns": 341.3119999999999, "wall_ns": 160.0, "record_count": 12 }, "pe_gemm": { "occupancy_ns": 135.29600000000028, "wall_ns": 131.07200000000012, "record_count": 8 }, "pe_math": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "stages": { "DMA_READ": { "occupancy_ns": 1703.8600000000001, "wall_ns": 269.0, "record_count": 16 }, "DMA_WRITE": { "occupancy_ns": 95.0, "wall_ns": 94.0, "record_count": 4 }, "FETCH": { "occupancy_ns": 272.0, "wall_ns": 152.0, "record_count": 8 }, "STORE": { "occupancy_ns": 69.3119999999999, "wall_ns": 69.3119999999999, "record_count": 4 }, "GEMM": { "occupancy_ns": 135.29600000000028, "wall_ns": 131.07200000000012, "record_count": 8 }, "MATH": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "pe_window_ns": 354.384, "composite_window_ns": 354.384 }, { "M": 32, "K": 128, "N": 128, "variant": "load_ref", "flops": 1048576, "bytes_hbm": 49152, "arith_intensity": 21.333333333333332, "tile_count_expected": 8, "sim_wall_clock_s": 0.22, "engines": { "pe_dma": { "occupancy_ns": 819.8600000000001, "wall_ns": 256.0, "record_count": 13 }, "pe_fetch_store": { "occupancy_ns": 341.3119999999999, "wall_ns": 160.0, "record_count": 12 }, "pe_gemm": { "occupancy_ns": 135.29600000000028, "wall_ns": 131.07200000000012, "record_count": 8 }, "pe_math": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "stages": { "DMA_READ": { "occupancy_ns": 679.8600000000001, "wall_ns": 141.0, "record_count": 8 }, "DMA_WRITE": { "occupancy_ns": 95.0, "wall_ns": 94.0, "record_count": 4 }, "FETCH": { "occupancy_ns": 272.0, "wall_ns": 152.0, "record_count": 8 }, "STORE": { "occupancy_ns": 69.3119999999999, "wall_ns": 69.3119999999999, "record_count": 4 }, "GEMM": { "occupancy_ns": 135.29600000000028, "wall_ns": 131.07200000000012, "record_count": 8 }, "MATH": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "pe_window_ns": 315.394, "composite_window_ns": 226.38400000000001 }, { "M": 32, "K": 128, "N": 128, "variant": "load_load", "flops": 1048576, "bytes_hbm": 49152, "arith_intensity": 21.333333333333332, "tile_count_expected": 8, "sim_wall_clock_s": 0.112, "engines": { "pe_dma": { "occupancy_ns": 283.0, "wall_ns": 238.07200000000012, "record_count": 6 }, "pe_fetch_store": { "occupancy_ns": 839.252, "wall_ns": 152.0, "record_count": 12 }, "pe_gemm": { "occupancy_ns": 141.82400000000052, "wall_ns": 131.07200000000012, "record_count": 8 }, "pe_math": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "stages": { "DMA_READ": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 }, "DMA_WRITE": { "occupancy_ns": 96.0, "wall_ns": 56.072000000000116, "record_count": 4 }, "FETCH": { "occupancy_ns": 703.8600000000001, "wall_ns": 144.0, "record_count": 8 }, "STORE": { "occupancy_ns": 135.39199999999983, "wall_ns": 87.23199999999997, "record_count": 4 }, "GEMM": { "occupancy_ns": 141.82400000000052, "wall_ns": 131.07200000000012, "record_count": 8 }, "MATH": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "pe_window_ns": 418.0820000000001, "composite_window_ns": 192.07200000000012 }, { "M": 32, "K": 3072, "N": 32, "variant": "ref_ref", "flops": 6291456, "bytes_hbm": 395264, "arith_intensity": 15.917098445595855, "tile_count_expected": 48, "sim_wall_clock_s": 0.2, "engines": { "pe_dma": { "occupancy_ns": 56319.35999999987, "wall_ns": 1569.9999999999998, "record_count": 97 }, "pe_fetch_store": { "occupancy_ns": 1543.9999999999995, "wall_ns": 791.9999999999998, "record_count": 49 }, "pe_gemm": { "occupancy_ns": 1219.5840000000169, "wall_ns": 786.4320000000005, "record_count": 48 }, "pe_math": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "stages": { "DMA_READ": { "occupancy_ns": 56298.35999999987, "wall_ns": 1548.9999999999998, "record_count": 96 }, "DMA_WRITE": { "occupancy_ns": 21.0, "wall_ns": 21.0, "record_count": 1 }, "FETCH": { "occupancy_ns": 1535.9999999999995, "wall_ns": 783.9999999999998, "record_count": 48 }, "STORE": { "occupancy_ns": 8.0, "wall_ns": 8.0, "record_count": 1 }, "GEMM": { "occupancy_ns": 1219.5840000000169, "wall_ns": 786.4320000000005, "record_count": 48 }, "MATH": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "pe_window_ns": 1644.4320000000005, "composite_window_ns": 1644.4320000000005 }, { "M": 32, "K": 3072, "N": 32, "variant": "load_ref", "flops": 6291456, "bytes_hbm": 395264, "arith_intensity": 15.917098445595855, "tile_count_expected": 48, "sim_wall_clock_s": 0.237, "engines": { "pe_dma": { "occupancy_ns": 20236.359999999866, "wall_ns": 1582.9999999999998, "record_count": 50 }, "pe_fetch_store": { "occupancy_ns": 1543.9999999999998, "wall_ns": 791.9999999999998, "record_count": 49 }, "pe_gemm": { "occupancy_ns": 1219.584000000017, "wall_ns": 786.4320000000007, "record_count": 48 }, "pe_math": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "stages": { "DMA_READ": { "occupancy_ns": 19434.359999999866, "wall_ns": 780.9999999999998, "record_count": 48 }, "DMA_WRITE": { "occupancy_ns": 21.0, "wall_ns": 21.0, "record_count": 1 }, "FETCH": { "occupancy_ns": 1535.9999999999998, "wall_ns": 783.9999999999998, "record_count": 48 }, "STORE": { "occupancy_ns": 8.0, "wall_ns": 8.0, "record_count": 1 }, "GEMM": { "occupancy_ns": 1219.584000000017, "wall_ns": 786.4320000000007, "record_count": 48 }, "MATH": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "pe_window_ns": 1701.4420000000007, "composite_window_ns": 876.4320000000005 }, { "M": 32, "K": 3072, "N": 32, "variant": "load_load", "flops": 6291456, "bytes_hbm": 395264, "arith_intensity": 15.917098445595855, "tile_count_expected": 48, "sim_wall_clock_s": 0.208, "engines": { "pe_dma": { "occupancy_ns": 2310.0, "wall_ns": 1569.9999999999998, "record_count": 3 }, "pe_fetch_store": { "occupancy_ns": 19586.359999999877, "wall_ns": 792.0, "record_count": 49 }, "pe_gemm": { "occupancy_ns": 1219.584000000017, "wall_ns": 786.4320000000007, "record_count": 48 }, "pe_math": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "stages": { "DMA_READ": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 }, "DMA_WRITE": { "occupancy_ns": 21.0, "wall_ns": 21.0, "record_count": 1 }, "FETCH": { "occupancy_ns": 19578.359999999877, "wall_ns": 784.0, "record_count": 48 }, "STORE": { "occupancy_ns": 8.0, "wall_ns": 8.0, "record_count": 1 }, "GEMM": { "occupancy_ns": 1219.584000000017, "wall_ns": 786.4320000000007, "record_count": 48 }, "MATH": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "pe_window_ns": 2440.442000000001, "composite_window_ns": 847.4320000000007 }, { "M": 8, "K": 128, "N": 128, "variant": "ref_ref", "flops": 262144, "bytes_hbm": 36864, "arith_intensity": 7.111111111111111, "tile_count_expected": 8, "sim_wall_clock_s": 0.089, "engines": { "pe_dma": { "occupancy_ns": 1798.8600000000001, "wall_ns": 339.0, "record_count": 20 }, "pe_fetch_store": { "occupancy_ns": 341.3119999999999, "wall_ns": 160.0, "record_count": 12 }, "pe_gemm": { "occupancy_ns": 135.29600000000028, "wall_ns": 131.07200000000012, "record_count": 8 }, "pe_math": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "stages": { "DMA_READ": { "occupancy_ns": 1703.8600000000001, "wall_ns": 269.0, "record_count": 16 }, "DMA_WRITE": { "occupancy_ns": 95.0, "wall_ns": 94.0, "record_count": 4 }, "FETCH": { "occupancy_ns": 272.0, "wall_ns": 152.0, "record_count": 8 }, "STORE": { "occupancy_ns": 69.3119999999999, "wall_ns": 69.3119999999999, "record_count": 4 }, "GEMM": { "occupancy_ns": 135.29600000000028, "wall_ns": 131.07200000000012, "record_count": 8 }, "MATH": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "pe_window_ns": 354.384, "composite_window_ns": 354.384 }, { "M": 8, "K": 128, "N": 128, "variant": "load_ref", "flops": 262144, "bytes_hbm": 36864, "arith_intensity": 7.111111111111111, "tile_count_expected": 8, "sim_wall_clock_s": 0.155, "engines": { "pe_dma": { "occupancy_ns": 795.8600000000001, "wall_ns": 232.0, "record_count": 13 }, "pe_fetch_store": { "occupancy_ns": 341.3119999999999, "wall_ns": 160.0, "record_count": 12 }, "pe_gemm": { "occupancy_ns": 135.29600000000028, "wall_ns": 131.07200000000012, "record_count": 8 }, "pe_math": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "stages": { "DMA_READ": { "occupancy_ns": 679.8600000000001, "wall_ns": 141.0, "record_count": 8 }, "DMA_WRITE": { "occupancy_ns": 95.0, "wall_ns": 94.0, "record_count": 4 }, "FETCH": { "occupancy_ns": 272.0, "wall_ns": 152.0, "record_count": 8 }, "STORE": { "occupancy_ns": 69.3119999999999, "wall_ns": 69.3119999999999, "record_count": 4 }, "GEMM": { "occupancy_ns": 135.29600000000028, "wall_ns": 131.07200000000012, "record_count": 8 }, "MATH": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "pe_window_ns": 291.394, "composite_window_ns": 226.38400000000001 }, { "M": 8, "K": 128, "N": 128, "variant": "load_load", "flops": 262144, "bytes_hbm": 36864, "arith_intensity": 7.111111111111111, "tile_count_expected": 8, "sim_wall_clock_s": 0.234, "engines": { "pe_dma": { "occupancy_ns": 258.0, "wall_ns": 218.07200000000012, "record_count": 6 }, "pe_fetch_store": { "occupancy_ns": 839.252, "wall_ns": 152.0, "record_count": 12 }, "pe_gemm": { "occupancy_ns": 141.82400000000052, "wall_ns": 131.07200000000012, "record_count": 8 }, "pe_math": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "stages": { "DMA_READ": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 }, "DMA_WRITE": { "occupancy_ns": 96.0, "wall_ns": 56.072000000000116, "record_count": 4 }, "FETCH": { "occupancy_ns": 703.8600000000001, "wall_ns": 144.0, "record_count": 8 }, "STORE": { "occupancy_ns": 135.39199999999983, "wall_ns": 87.23199999999997, "record_count": 4 }, "GEMM": { "occupancy_ns": 141.82400000000052, "wall_ns": 131.07200000000012, "record_count": 8 }, "MATH": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "pe_window_ns": 418.0820000000001, "composite_window_ns": 192.07200000000012 }, { "M": 128, "K": 8, "N": 128, "variant": "ref_ref", "flops": 262144, "bytes_hbm": 36864, "arith_intensity": 7.111111111111111, "tile_count_expected": 16, "sim_wall_clock_s": 0.119, "engines": { "pe_dma": { "occupancy_ns": 7854.6320000000005, "wall_ns": 653.0, "record_count": 48 }, "pe_fetch_store": { "occupancy_ns": 1367.9359999999997, "wall_ns": 328.384, "record_count": 32 }, "pe_gemm": { "occupancy_ns": 264.83200000000033, "wall_ns": 262.14400000000023, "record_count": 16 }, "pe_math": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "stages": { "DMA_READ": { "occupancy_ns": 6479.400000000001, "wall_ns": 525.0, "record_count": 32 }, "DMA_WRITE": { "occupancy_ns": 1375.232, "wall_ns": 296.0, "record_count": 16 }, "FETCH": { "occupancy_ns": 804.0, "wall_ns": 316.0, "record_count": 16 }, "STORE": { "occupancy_ns": 563.9359999999997, "wall_ns": 280.0, "record_count": 16 }, "GEMM": { "occupancy_ns": 264.83200000000033, "wall_ns": 262.14400000000023, "record_count": 16 }, "MATH": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "pe_window_ns": 653.0, "composite_window_ns": 653.0 }, { "M": 128, "K": 8, "N": 128, "variant": "load_ref", "flops": 262144, "bytes_hbm": 36864, "arith_intensity": 7.111111111111111, "tile_count_expected": 16, "sim_wall_clock_s": 0.183, "engines": { "pe_dma": { "occupancy_ns": 3779.6320000000005, "wall_ns": 418.0, "record_count": 33 }, "pe_fetch_store": { "occupancy_ns": 1367.9359999999997, "wall_ns": 328.384, "record_count": 32 }, "pe_gemm": { "occupancy_ns": 264.83200000000033, "wall_ns": 262.14400000000023, "record_count": 16 }, "pe_math": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "stages": { "DMA_READ": { "occupancy_ns": 2383.4000000000005, "wall_ns": 269.0, "record_count": 16 }, "DMA_WRITE": { "occupancy_ns": 1375.232, "wall_ns": 296.0, "record_count": 16 }, "FETCH": { "occupancy_ns": 804.0, "wall_ns": 316.0, "record_count": 16 }, "STORE": { "occupancy_ns": 563.9359999999997, "wall_ns": 280.0, "record_count": 16 }, "GEMM": { "occupancy_ns": 264.83200000000033, "wall_ns": 262.14400000000023, "record_count": 16 }, "MATH": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "pe_window_ns": 462.01, "composite_window_ns": 397.0 }, { "M": 128, "K": 8, "N": 128, "variant": "load_load", "flops": 262144, "bytes_hbm": 36864, "arith_intensity": 7.111111111111111, "tile_count_expected": 16, "sim_wall_clock_s": 0.179, "engines": { "pe_dma": { "occupancy_ns": 858.0, "wall_ns": 183.0, "record_count": 18 }, "pe_fetch_store": { "occupancy_ns": 4395.175999999999, "wall_ns": 324.0, "record_count": 32 }, "pe_gemm": { "occupancy_ns": 308.224000000002, "wall_ns": 262.14400000000023, "record_count": 16 }, "pe_math": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "stages": { "DMA_READ": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 }, "DMA_WRITE": { "occupancy_ns": 816.0, "wall_ns": 141.0, "record_count": 16 }, "FETCH": { "occupancy_ns": 2431.4000000000005, "wall_ns": 272.0, "record_count": 16 }, "STORE": { "occupancy_ns": 1963.775999999998, "wall_ns": 275.616, "record_count": 16 }, "GEMM": { "occupancy_ns": 308.224000000002, "wall_ns": 262.14400000000023, "record_count": 16 }, "MATH": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "pe_window_ns": 511.01, "composite_window_ns": 405.0 }, { "M": 512, "K": 512, "N": 512, "variant": "ref_ref", "flops": 268435456, "bytes_hbm": 1572864, "arith_intensity": 170.66666666666666, "tile_count_expected": 2048, "sim_wall_clock_s": 1.241, "engines": { "pe_dma": { "occupancy_ns": 104867178.97599977, "wall_ns": 67597.00000000001, "record_count": 4352 }, "pe_fetch_store": { "occupancy_ns": 1206911.5840000017, "wall_ns": 33800.00000000001, "record_count": 2304 }, "pe_gemm": { "occupancy_ns": 36417.40799998986, "wall_ns": 33554.43199999787, "record_count": 2048 }, "pe_math": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "stages": { "DMA_READ": { "occupancy_ns": 100695823.35999978, "wall_ns": 65549.00000000001, "record_count": 4096 }, "DMA_WRITE": { "occupancy_ns": 4171355.616000002, "wall_ns": 34616.00000000001, "record_count": 256 }, "FETCH": { "occupancy_ns": 1076760.0000000005, "wall_ns": 33776.00000000001, "record_count": 2048 }, "STORE": { "occupancy_ns": 130151.58400000134, "wall_ns": 31914.784000000276, "record_count": 256 }, "GEMM": { "occupancy_ns": 36417.40799998986, "wall_ns": 33554.43199999787, "record_count": 2048 }, "MATH": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "pe_window_ns": 67597.00000000001, "composite_window_ns": 67597.00000000001 }, { "M": 512, "K": 512, "N": 512, "variant": "load_ref", "flops": 268435456, "bytes_hbm": 1572864, "arith_intensity": 170.66666666666666, "tile_count_expected": 2048, "sim_wall_clock_s": 0.742, "engines": { "pe_dma": { "occupancy_ns": 37760375.97599977, "wall_ns": 36890.0, "record_count": 2305 }, "pe_fetch_store": { "occupancy_ns": 1206911.5840000017, "wall_ns": 33800.0, "record_count": 2304 }, "pe_gemm": { "occupancy_ns": 36417.40799998891, "wall_ns": 33554.43199999761, "record_count": 2048 }, "pe_math": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "stages": { "DMA_READ": { "occupancy_ns": 33586959.359999776, "wall_ns": 32781.0, "record_count": 2048 }, "DMA_WRITE": { "occupancy_ns": 4171355.616000001, "wall_ns": 34616.0, "record_count": 256 }, "FETCH": { "occupancy_ns": 1076760.0000000002, "wall_ns": 33776.0, "record_count": 2048 }, "STORE": { "occupancy_ns": 130151.58400000146, "wall_ns": 31914.784000000003, "record_count": 256 }, "GEMM": { "occupancy_ns": 36417.40799998891, "wall_ns": 33554.43199999761, "record_count": 2048 }, "MATH": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "pe_window_ns": 36934.01, "composite_window_ns": 34829.0 }, { "M": 512, "K": 512, "N": 512, "variant": "load_load", "flops": 268435456, "bytes_hbm": 1572864, "arith_intensity": 170.66666666666666, "tile_count_expected": 2048, "sim_wall_clock_s": 0.406, "engines": { "pe_dma": { "occupancy_ns": 142065.0, "wall_ns": 6170.0, "record_count": 258 }, "pe_fetch_store": { "occupancy_ns": 37794382.84800001, "wall_ns": 33796.0, "record_count": 2304 }, "pe_gemm": { "occupancy_ns": 838467.5839981049, "wall_ns": 33554.43199999738, "record_count": 2048 }, "pe_math": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "stages": { "DMA_READ": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 }, "DMA_WRITE": { "occupancy_ns": 135936.0, "wall_ns": 2061.0, "record_count": 256 }, "FETCH": { "occupancy_ns": 33593103.359999776, "wall_ns": 32784.0, "record_count": 2048 }, "STORE": { "occupancy_ns": 4201279.488000238, "wall_ns": 33632.928, "record_count": 256 }, "GEMM": { "occupancy_ns": 838467.5839981049, "wall_ns": 33554.43199999738, "record_count": 2048 }, "MATH": { "occupancy_ns": 0, "wall_ns": 0.0, "record_count": 0 } }, "pe_window_ns": 38990.01, "composite_window_ns": 34837.0 } ] }