diff --git a/results/B200/csv/interleave_autotune.csv b/results/B200/csv/interleave_autotune.csv
index ddec9b70..2c4d8e2b 100644
--- a/results/B200/csv/interleave_autotune.csv
+++ b/results/B200/csv/interleave_autotune.csv
@@ -1,81 +1,81 @@
-params,dtype,torch_ms,triton_ms,cutile_ms,speedup_triton,speedup_cutile,triton_vs_cutile,tilelang_ms,speedup_tilelang
-n=1000000,fp16,0.0088,0.0026,0.0027,3.38,3.28,1.0385,0.0028,3.11
-n=1000000,bf16,0.0087,0.0025,0.0026,3.42,3.32,1.0400,0.0026,3.34
-n=1000000,fp32,0.0090,0.0035,0.0038,2.57,2.34,1.0857,0.0036,2.49
-n=1000000,int8,0.0083,0.0021,0.0022,3.94,3.77,1.0476,0.0024,3.44
-n=2000000,fp16,0.0127,0.0037,0.0038,3.46,3.31,1.0270,0.0037,3.44
-n=2000000,bf16,0.0124,0.0034,0.0037,3.64,3.36,1.0882,0.0040,3.06
-n=2000000,fp32,0.0146,0.0064,0.0070,2.29,2.07,1.0938,0.0067,2.19
-n=2000000,int8,0.0117,0.0026,0.0027,4.56,4.26,1.0385,0.0033,3.60
-n=3000000,fp16,0.0171,0.0053,0.0057,3.24,3.00,1.0755,0.0054,3.16
-n=3000000,bf16,0.0167,0.0051,0.0054,3.26,3.11,1.0588,0.0056,2.99
-n=3000000,fp32,0.0219,0.0098,0.0098,2.24,2.25,1.0000,0.0096,2.28
-n=3000000,int8,0.0143,0.0029,0.0035,4.99,4.12,1.2069,0.0035,4.08
-n=4000000,fp16,0.0217,0.0069,0.0075,3.15,2.87,1.0870,0.0072,3.03
-n=4000000,bf16,0.0216,0.0066,0.0067,3.29,3.25,1.0152,0.0070,3.09
-n=4000000,fp32,0.0299,0.0117,0.0124,2.55,2.42,1.0598,0.0122,2.46
-n=4000000,int8,0.0181,0.0035,0.0037,5.18,4.91,1.0571,0.0042,4.35
-n=5000000,fp16,0.0266,0.0081,0.0085,3.28,3.15,1.0494,0.0087,3.04
-n=5000000,bf16,0.0266,0.0080,0.0081,3.32,3.27,1.0125,0.0086,3.09
-n=5000000,fp32,0.0373,0.0145,0.0150,2.57,2.49,1.0345,0.0151,2.46
-n=5000000,int8,0.0211,0.0056,0.0041,3.74,5.11,0.7321,0.0046,4.54
-n=6000000,fp16,0.0318,0.0103,0.0096,3.09,3.31,0.9320,0.0105,3.04
-n=6000000,bf16,0.0320,0.0095,0.0106,3.39,3.04,1.1158,0.0105,3.05
-n=6000000,fp32,0.0429,0.0170,0.0172,2.52,2.49,1.0118,0.0171,2.50
-n=6000000,int8,0.0256,0.0049,0.0052,5.24,4.95,1.0612,0.0053,4.79
-n=7000000,fp16,0.0369,0.0108,0.0108,3.41,3.42,1.0000,0.0110,3.35
-n=7000000,bf16,0.0374,0.0109,0.0110,3.44,3.40,1.0092,0.0111,3.38
-n=7000000,fp32,0.0493,0.0194,0.0194,2.54,2.54,1.0000,0.0193,2.56
-n=7000000,int8,0.0303,0.0056,0.0064,5.42,4.77,1.1429,0.0061,4.95
-n=8000000,fp16,0.0421,0.0123,0.0124,3.43,3.40,1.0081,0.0132,3.20
-n=8000000,bf16,0.0425,0.0132,0.0124,3.23,3.43,0.9394,0.0127,3.35
-n=8000000,fp32,0.0557,0.0216,0.0216,2.57,2.58,1.0000,0.0219,2.55
-n=8000000,int8,0.0348,0.0064,0.0067,5.44,5.18,1.0469,0.0074,4.72
-n=9000000,fp16,0.0475,0.0134,0.0137,3.53,3.47,1.0224,0.0146,3.24
-n=9000000,bf16,0.0470,0.0133,0.0137,3.54,3.44,1.0301,0.0137,3.44
-n=9000000,fp32,0.0621,0.0241,0.0242,2.58,2.57,1.0041,0.0246,2.53
-n=9000000,int8,0.0393,0.0071,0.0075,5.50,5.22,1.0563,0.0084,4.68
-n=10000000,fp16,0.0518,0.0145,0.0146,3.56,3.55,1.0069,0.0149,3.47
-n=10000000,bf16,0.0515,0.0145,0.0145,3.55,3.55,1.0000,0.0150,3.44
-n=10000000,fp32,0.0694,0.0263,0.0265,2.65,2.62,1.0076,0.0266,2.61
-n=10000000,int8,0.0442,0.0077,0.0081,5.72,5.43,1.0519,0.0086,5.13
-n=11000000,fp16,0.0560,0.0170,0.0160,3.30,3.51,0.9412,0.0173,3.24
-n=11000000,bf16,0.0561,0.0170,0.0159,3.29,3.53,0.9353,0.0164,3.42
-n=11000000,fp32,0.0796,0.0287,0.0287,2.77,2.78,1.0000,0.0287,2.77
-n=11000000,int8,0.0493,0.0088,0.0090,5.61,5.48,1.0227,0.0095,5.19
-n=12000000,fp16,0.0607,0.0170,0.0173,3.57,3.52,1.0176,0.0170,3.56
-n=12000000,bf16,0.0608,0.0169,0.0171,3.59,3.56,1.0118,0.0171,3.55
-n=12000000,fp32,0.0882,0.0310,0.0310,2.84,2.85,1.0000,0.0314,2.81
-n=12000000,int8,0.0540,0.0091,0.0105,5.96,5.16,1.1538,0.0105,5.16
-n=13000000,fp16,0.0654,0.0182,0.0182,3.59,3.59,1.0000,0.0184,3.56
-n=13000000,bf16,0.0652,0.0183,0.0184,3.57,3.54,1.0055,0.0184,3.54
-n=13000000,fp32,0.0952,0.0330,0.0333,2.88,2.86,1.0091,0.0335,2.84
-n=13000000,int8,0.0582,0.0104,0.0104,5.62,5.58,1.0000,0.0112,5.20
-n=14000000,fp16,0.0697,0.0193,0.0194,3.62,3.60,1.0052,0.0194,3.60
-n=14000000,bf16,0.0699,0.0193,0.0195,3.62,3.59,1.0104,0.0196,3.57
-n=14000000,fp32,0.1015,0.0354,0.0357,2.87,2.84,1.0085,0.0358,2.83
-n=14000000,int8,0.0632,0.0109,0.0113,5.80,5.59,1.0367,0.0113,5.59
-n=15000000,fp16,0.0739,0.0205,0.0207,3.60,3.58,1.0098,0.0204,3.62
-n=15000000,bf16,0.0743,0.0205,0.0206,3.63,3.61,1.0049,0.0206,3.61
-n=15000000,fp32,0.1080,0.0376,0.0380,2.87,2.84,1.0106,0.0378,2.86
-n=15000000,int8,0.0675,0.0125,0.0128,5.41,5.27,1.0240,0.0125,5.42
-n=16000000,fp16,0.0787,0.0218,0.0219,3.61,3.59,1.0046,0.0218,3.61
-n=16000000,bf16,0.0789,0.0218,0.0218,3.62,3.62,1.0000,0.0236,3.34
-n=16000000,fp32,0.1146,0.0399,0.0403,2.87,2.84,1.0100,0.0399,2.87
-n=16000000,int8,0.0716,0.0123,0.0124,5.82,5.76,1.0081,0.0131,5.46
-n=17000000,fp16,0.0835,0.0228,0.0229,3.66,3.65,1.0044,0.0229,3.64
-n=17000000,bf16,0.0835,0.0230,0.0231,3.64,3.62,1.0043,0.0234,3.56
-n=17000000,fp32,0.1217,0.0421,0.0426,2.89,2.86,1.0119,0.0432,2.82
-n=17000000,int8,0.0758,0.0129,0.0130,5.88,5.83,1.0078,0.0131,5.77
-n=18000000,fp16,0.0881,0.0241,0.0242,3.66,3.64,1.0041,0.0241,3.66
-n=18000000,bf16,0.0877,0.0239,0.0240,3.68,3.65,1.0042,0.0240,3.65
-n=18000000,fp32,0.1277,0.0443,0.0448,2.88,2.85,1.0113,0.0456,2.80
-n=18000000,int8,0.0799,0.0143,0.0146,5.58,5.45,1.0210,0.0141,5.68
-n=19000000,fp16,0.0931,0.0251,0.0252,3.70,3.69,1.0040,0.0251,3.71
-n=19000000,bf16,0.0930,0.0250,0.0251,3.73,3.70,1.0040,0.0251,3.71
-n=19000000,fp32,0.1344,0.0469,0.0473,2.87,2.84,1.0085,0.0475,2.83
-n=19000000,int8,0.0842,0.0149,0.0142,5.65,5.92,0.9530,0.0141,5.96
-n=20000000,fp16,0.0985,0.0263,0.0264,3.75,3.73,1.0038,0.0263,3.74
-n=20000000,bf16,0.0983,0.0262,0.0263,3.75,3.74,1.0038,0.0265,3.71
-n=20000000,fp32,0.1404,0.0489,0.0495,2.87,2.84,1.0123,0.0499,2.81
-n=20000000,int8,0.0882,0.0146,0.0148,6.05,5.94,1.0137,0.0147,5.99
+params,dtype,torch_ms,triton_ms,cutile_ms,speedup_triton,speedup_cutile,triton_vs_cutile,torch_nki_ms,nki_ms,speedup_nki
+n=1000000,fp16,0.0088,0.0026,0.0027,3.38,3.28,1.0385,0.0755,0.0277,2.73
+n=1000000,bf16,0.0087,0.0025,0.0026,3.42,3.32,1.0400,0.0754,0.0286,2.64
+n=1000000,fp32,0.0090,0.0035,0.0038,2.57,2.34,1.0857,0.1205,0.0382,3.16
+n=1000000,int8,0.0083,0.0021,0.0022,3.94,3.77,1.0476,0.0525,0.0236,2.22
+n=2000000,fp16,0.0127,0.0037,0.0038,3.46,3.31,1.0270,0.0777,0.0388,2.00
+n=2000000,bf16,0.0124,0.0034,0.0037,3.64,3.36,1.0882,0.0776,0.0389,1.99
+n=2000000,fp32,0.0146,0.0064,0.0070,2.29,2.07,1.0938,0.0922,0.0606,1.52
+n=2000000,int8,0.0117,0.0026,0.0027,4.56,4.26,1.0385,0.0723,0.0290,2.49
+n=3000000,fp16,0.0171,0.0053,0.0057,3.24,3.00,1.0755,0.1936,0.0503,3.85
+n=3000000,bf16,0.0167,0.0051,0.0054,3.26,3.11,1.0588,0.1940,0.0506,3.83
+n=3000000,fp32,0.0219,0.0098,0.0098,2.24,2.25,1.0000,0.3324,0.0844,3.94
+n=3000000,int8,0.0143,0.0029,0.0035,4.99,4.12,1.2069,0.1588,0.0343,4.64
+n=4000000,fp16,0.0217,0.0069,0.0075,3.15,2.87,1.0870,0.1326,0.0605,2.19
+n=4000000,bf16,0.0216,0.0066,0.0067,3.29,3.25,1.0152,0.1327,0.0610,2.17
+n=4000000,fp32,0.0299,0.0117,0.0124,2.55,2.42,1.0598,0.1752,0.1063,1.65
+n=4000000,int8,0.0181,0.0035,0.0037,5.18,4.91,1.0571,0.1303,0.0373,3.49
+n=5000000,fp16,0.0266,0.0081,0.0085,3.28,3.15,1.0494,0.3018,0.0736,4.10
+n=5000000,bf16,0.0266,0.0080,0.0081,3.32,3.27,1.0125,0.3020,0.0766,3.94
+n=5000000,fp32,0.0373,0.0145,0.0150,2.57,2.49,1.0345,0.5474,0.1340,4.08
+n=5000000,int8,0.0211,0.0056,0.0041,3.74,5.11,0.7321,0.2655,0.0461,5.76
+n=6000000,fp16,0.0318,0.0103,0.0096,3.09,3.31,0.9320,0.1850,0.0847,2.18
+n=6000000,bf16,0.0320,0.0095,0.0106,3.39,3.04,1.1158,0.1849,0.0846,2.18
+n=6000000,fp32,0.0429,0.0170,0.0172,2.52,2.49,1.0118,0.2369,0.1581,1.50
+n=6000000,int8,0.0256,0.0049,0.0052,5.24,4.95,1.0612,0.1675,0.0506,3.31
+n=7000000,fp16,0.0369,0.0108,0.0108,3.41,3.42,1.0000,0.4157,0.0965,4.31
+n=7000000,bf16,0.0374,0.0109,0.0110,3.44,3.40,1.0092,0.4161,0.1019,4.08
+n=7000000,fp32,0.0493,0.0194,0.0194,2.54,2.54,1.0000,0.7504,0.1852,4.05
+n=7000000,int8,0.0303,0.0056,0.0064,5.42,4.77,1.1429,0.3461,0.0569,6.08
+n=8000000,fp16,0.0421,0.0123,0.0124,3.43,3.40,1.0081,0.2431,0.1099,2.21
+n=8000000,bf16,0.0425,0.0132,0.0124,3.23,3.43,0.9394,0.2430,0.1127,2.16
+n=8000000,fp32,0.0557,0.0216,0.0216,2.57,2.58,1.0000,0.3154,0.2075,1.52
+n=8000000,int8,0.0348,0.0064,0.0067,5.44,5.18,1.0469,0.2300,0.0605,3.80
+n=9000000,fp16,0.0475,0.0134,0.0137,3.53,3.47,1.0224,0.5377,0.1221,4.40
+n=9000000,bf16,0.0470,0.0133,0.0137,3.54,3.44,1.0301,0.5376,0.1310,4.10
+n=9000000,fp32,0.0621,0.0241,0.0242,2.58,2.57,1.0041,0.9769,0.2307,4.24
+n=9000000,int8,0.0393,0.0071,0.0075,5.50,5.22,1.0563,0.4223,0.0677,6.24
+n=10000000,fp16,0.0518,0.0145,0.0146,3.56,3.55,1.0069,0.2982,0.1343,2.22
+n=10000000,bf16,0.0515,0.0145,0.0145,3.55,3.55,1.0000,0.2983,0.1346,2.22
+n=10000000,fp32,0.0694,0.0263,0.0265,2.65,2.62,1.0076,0.4032,0.2610,1.54
+n=10000000,int8,0.0442,0.0077,0.0081,5.72,5.43,1.0519,0.2807,0.0735,3.82
+n=11000000,fp16,0.0560,0.0170,0.0160,3.30,3.51,0.9412,0.6431,0.1464,4.39
+n=11000000,bf16,0.0561,0.0170,0.0159,3.29,3.53,0.9353,0.6434,0.1464,4.39
+n=11000000,fp32,0.0796,0.0287,0.0287,2.77,2.78,1.0000,1.1971,0.2781,4.30
+n=11000000,int8,0.0493,0.0088,0.0090,5.61,5.48,1.0227,0.5630,0.0791,7.11
+n=12000000,fp16,0.0607,0.0170,0.0173,3.57,3.52,1.0176,0.3536,0.1580,2.24
+n=12000000,bf16,0.0608,0.0169,0.0171,3.59,3.56,1.0118,0.3536,0.1619,2.18
+n=12000000,fp32,0.0882,0.0310,0.0310,2.84,2.85,1.0000,0.4807,0.3038,1.58
+n=12000000,int8,0.0540,0.0091,0.0105,5.96,5.16,1.1538,0.3242,0.0834,3.89
+n=13000000,fp16,0.0654,0.0182,0.0182,3.59,3.59,1.0000,0.7870,0.1713,4.60
+n=13000000,bf16,0.0652,0.0183,0.0184,3.57,3.54,1.0055,0.7880,0.1793,4.39
+n=13000000,fp32,0.0952,0.0330,0.0333,2.88,2.86,1.0091,1.4637,0.3262,4.49
+n=13000000,int8,0.0582,0.0104,0.0104,5.62,5.58,1.0000,0.6391,0.0903,7.08
+n=14000000,fp16,0.0697,0.0193,0.0194,3.62,3.60,1.0052,0.4033,0.1851,2.18
+n=14000000,bf16,0.0699,0.0193,0.0195,3.62,3.59,1.0104,0.4034,0.1873,2.15
+n=14000000,fp32,0.1015,0.0354,0.0357,2.87,2.84,1.0085,0.5679,0.3532,1.61
+n=14000000,int8,0.0632,0.0109,0.0113,5.80,5.59,1.0367,0.3812,0.0966,3.95
+n=15000000,fp16,0.0739,0.0205,0.0207,3.60,3.58,1.0098,0.8741,0.1984,4.41
+n=15000000,bf16,0.0743,0.0205,0.0206,3.63,3.61,1.0049,0.8740,0.2005,4.36
+n=15000000,fp32,0.1080,0.0376,0.0380,2.87,2.84,1.0106,1.6289,0.3748,4.35
+n=15000000,int8,0.0675,0.0125,0.0128,5.41,5.27,1.0240,0.7064,0.1074,6.58
+n=16000000,fp16,0.0787,0.0218,0.0219,3.61,3.59,1.0046,0.4686,0.2074,2.26
+n=16000000,bf16,0.0789,0.0218,0.0218,3.62,3.62,1.0000,0.4686,0.2094,2.24
+n=16000000,fp32,0.1146,0.0399,0.0403,2.87,2.84,1.0100,0.6551,0.3915,1.67
+n=16000000,int8,0.0716,0.0123,0.0124,5.82,5.76,1.0081,0.4268,0.1126,3.79
+n=17000000,fp16,0.0835,0.0228,0.0229,3.66,3.65,1.0044,0.9881,0.2232,4.43
+n=17000000,bf16,0.0835,0.0230,0.0231,3.64,3.62,1.0043,0.9878,0.2261,4.37
+n=17000000,fp32,0.1217,0.0421,0.0426,2.89,2.86,1.0119,1.8419,0.4226,4.36
+n=17000000,int8,0.0758,0.0129,0.0130,5.88,5.83,1.0078,0.8645,0.1212,7.13
+n=18000000,fp16,0.0881,0.0241,0.0242,3.66,3.64,1.0041,0.5239,0.2348,2.23
+n=18000000,bf16,0.0877,0.0239,0.0240,3.68,3.65,1.0042,0.5239,0.2357,2.22
+n=18000000,fp32,0.1277,0.0443,0.0448,2.88,2.85,1.0113,0.6857,0.4461,1.54
+n=18000000,int8,0.0799,0.0143,0.0146,5.58,5.45,1.0210,0.4956,0.1267,3.91
+n=19000000,fp16,0.0931,0.0251,0.0252,3.70,3.69,1.0040,1.0995,0.2429,4.53
+n=19000000,bf16,0.0930,0.0250,0.0251,3.73,3.70,1.0040,1.0996,0.2462,4.47
+n=19000000,fp32,0.1344,0.0469,0.0473,2.87,2.84,1.0085,2.0164,0.4697,4.29
+n=19000000,int8,0.0842,0.0149,0.0142,5.65,5.92,0.9530,0.9226,0.1300,7.10
+n=20000000,fp16,0.0985,0.0263,0.0264,3.75,3.73,1.0038,0.5843,0.2567,2.28
+n=20000000,bf16,0.0983,0.0262,0.0263,3.75,3.74,1.0038,0.5843,0.2608,2.24
+n=20000000,fp32,0.1404,0.0489,0.0495,2.87,2.84,1.0123,0.8081,0.4942,1.64
+n=20000000,int8,0.0882,0.0146,0.0148,6.05,5.94,1.0137,0.5361,0.1315,4.08
diff --git a/results/B200/csv/interleave_default.csv b/results/B200/csv/interleave_default.csv
index 1f9ce2df..dd01fcf9 100644
--- a/results/B200/csv/interleave_default.csv
+++ b/results/B200/csv/interleave_default.csv
@@ -1,81 +1,81 @@
-params,dtype,torch_ms,triton_ms,cutile_ms,speedup_triton,speedup_cutile,triton_vs_cutile,tilelang_ms,speedup_tilelang
-n=1000000,fp16,0.0088,0.0026,0.0027,3.36,3.28,1.0385,0.0026,3.34
-n=1000000,bf16,0.0087,0.0025,0.0026,3.52,3.35,1.0400,0.0026,3.38
-n=1000000,fp32,0.0089,0.0037,0.0039,2.44,2.31,1.0541,0.0039,2.28
-n=1000000,int8,0.0081,0.0021,0.0024,3.78,3.37,1.1429,0.0023,3.53
-n=2000000,fp16,0.0129,0.0038,0.0038,3.42,3.37,1.0000,0.0038,3.43
-n=2000000,bf16,0.0126,0.0036,0.0037,3.49,3.41,1.0278,0.0038,3.27
-n=2000000,fp32,0.0147,0.0064,0.0071,2.29,2.08,1.1094,0.0068,2.15
-n=2000000,int8,0.0117,0.0026,0.0029,4.42,3.99,1.1154,0.0028,4.11
-n=3000000,fp16,0.0169,0.0052,0.0053,3.26,3.20,1.0192,0.0053,3.18
-n=3000000,bf16,0.0165,0.0053,0.0054,3.10,3.07,1.0189,0.0052,3.17
-n=3000000,fp32,0.0224,0.0096,0.0107,2.33,2.10,1.1146,0.0104,2.15
-n=3000000,int8,0.0143,0.0034,0.0037,4.19,3.86,1.0882,0.0037,3.89
-n=4000000,fp16,0.0218,0.0068,0.0069,3.22,3.16,1.0147,0.0068,3.22
-n=4000000,bf16,0.0213,0.0067,0.0068,3.17,3.15,1.0149,0.0068,3.14
-n=4000000,fp32,0.0304,0.0122,0.0135,2.48,2.25,1.1066,0.0128,2.37
-n=4000000,int8,0.0175,0.0039,0.0042,4.50,4.14,1.0769,0.0039,4.51
-n=5000000,fp16,0.0267,0.0084,0.0085,3.18,3.15,1.0119,0.0086,3.11
-n=5000000,bf16,0.0268,0.0084,0.0085,3.20,3.16,1.0119,0.0086,3.12
-n=5000000,fp32,0.0373,0.0146,0.0164,2.56,2.28,1.1233,0.0149,2.50
-n=5000000,int8,0.0211,0.0046,0.0050,4.54,4.24,1.0870,0.0046,4.56
-n=6000000,fp16,0.0321,0.0098,0.0101,3.26,3.18,1.0306,0.0098,3.27
-n=6000000,bf16,0.0320,0.0098,0.0099,3.25,3.23,1.0102,0.0099,3.22
-n=6000000,fp32,0.0438,0.0170,0.0191,2.58,2.29,1.1235,0.0174,2.52
-n=6000000,int8,0.0256,0.0056,0.0058,4.59,4.39,1.0357,0.0057,4.50
-n=7000000,fp16,0.0373,0.0111,0.0111,3.37,3.35,1.0000,0.0114,3.28
-n=7000000,bf16,0.0368,0.0110,0.0110,3.34,3.33,1.0000,0.0111,3.33
-n=7000000,fp32,0.0498,0.0192,0.0219,2.60,2.27,1.1406,0.0199,2.51
-n=7000000,int8,0.0297,0.0064,0.0067,4.68,4.47,1.0469,0.0065,4.54
-n=8000000,fp16,0.0421,0.0123,0.0124,3.43,3.40,1.0081,0.0122,3.47
-n=8000000,bf16,0.0421,0.0123,0.0124,3.43,3.41,1.0081,0.0121,3.47
-n=8000000,fp32,0.0560,0.0217,0.0248,2.59,2.26,1.1429,0.0221,2.54
-n=8000000,int8,0.0353,0.0074,0.0076,4.79,4.61,1.0270,0.0072,4.88
-n=9000000,fp16,0.0471,0.0136,0.0136,3.47,3.45,1.0000,0.0136,3.47
-n=9000000,bf16,0.0473,0.0138,0.0139,3.43,3.41,1.0072,0.0137,3.45
-n=9000000,fp32,0.0618,0.0240,0.0275,2.57,2.25,1.1458,0.0245,2.52
-n=9000000,int8,0.0395,0.0079,0.0082,4.99,4.82,1.0380,0.0082,4.79
-n=10000000,fp16,0.0518,0.0145,0.0145,3.57,3.57,1.0000,0.0149,3.48
-n=10000000,bf16,0.0515,0.0148,0.0148,3.49,3.48,1.0000,0.0147,3.50
-n=10000000,fp32,0.0692,0.0264,0.0302,2.63,2.30,1.1439,0.0267,2.59
-n=10000000,int8,0.0446,0.0088,0.0091,5.06,4.91,1.0341,0.0092,4.87
-n=11000000,fp16,0.0561,0.0158,0.0159,3.54,3.54,1.0063,0.0159,3.52
-n=11000000,bf16,0.0558,0.0159,0.0160,3.51,3.48,1.0063,0.0156,3.57
-n=11000000,fp32,0.0785,0.0288,0.0329,2.73,2.39,1.1424,0.0289,2.72
-n=11000000,int8,0.0492,0.0098,0.0100,5.03,4.90,1.0204,0.0100,4.92
-n=12000000,fp16,0.0607,0.0170,0.0170,3.58,3.56,1.0000,0.0173,3.50
-n=12000000,bf16,0.0607,0.0170,0.0171,3.57,3.55,1.0059,0.0171,3.55
-n=12000000,fp32,0.0873,0.0310,0.0356,2.81,2.46,1.1484,0.0312,2.80
-n=12000000,int8,0.0537,0.0104,0.0107,5.19,5.03,1.0288,0.0104,5.16
-n=13000000,fp16,0.0656,0.0181,0.0182,3.62,3.60,1.0055,0.0184,3.56
-n=13000000,bf16,0.0652,0.0181,0.0182,3.60,3.59,1.0055,0.0182,3.57
-n=13000000,fp32,0.0948,0.0334,0.0382,2.84,2.48,1.1437,0.0338,2.81
-n=13000000,int8,0.0584,0.0109,0.0112,5.33,5.20,1.0275,0.0112,5.19
-n=14000000,fp16,0.0698,0.0194,0.0195,3.60,3.59,1.0052,0.0193,3.61
-n=14000000,bf16,0.0697,0.0193,0.0194,3.60,3.59,1.0052,0.0194,3.60
-n=14000000,fp32,0.1019,0.0357,0.0406,2.85,2.51,1.1373,0.0361,2.82
-n=14000000,int8,0.0631,0.0114,0.0118,5.51,5.34,1.0351,0.0119,5.28
-n=15000000,fp16,0.0742,0.0206,0.0207,3.61,3.59,1.0049,0.0205,3.61
-n=15000000,bf16,0.0741,0.0207,0.0207,3.59,3.57,1.0000,0.0206,3.59
-n=15000000,fp32,0.1077,0.0380,0.0434,2.83,2.48,1.1421,0.0383,2.81
-n=15000000,int8,0.0671,0.0126,0.0130,5.33,5.18,1.0317,0.0126,5.32
-n=16000000,fp16,0.0786,0.0217,0.0217,3.62,3.62,1.0000,0.0216,3.63
-n=16000000,bf16,0.0789,0.0216,0.0216,3.66,3.65,1.0000,0.0218,3.62
-n=16000000,fp32,0.1148,0.0404,0.0460,2.85,2.49,1.1386,0.0408,2.81
-n=16000000,int8,0.0717,0.0132,0.0136,5.43,5.29,1.0303,0.0132,5.42
-n=17000000,fp16,0.0833,0.0227,0.0227,3.67,3.67,1.0000,0.0228,3.65
-n=17000000,bf16,0.0833,0.0229,0.0229,3.64,3.63,1.0000,0.0229,3.63
-n=17000000,fp32,0.1211,0.0426,0.0486,2.85,2.49,1.1408,0.0430,2.82
-n=17000000,int8,0.0759,0.0134,0.0139,5.65,5.47,1.0373,0.0140,5.41
-n=18000000,fp16,0.0882,0.0241,0.0241,3.67,3.66,1.0000,0.0242,3.64
-n=18000000,bf16,0.0884,0.0241,0.0241,3.67,3.67,1.0000,0.0243,3.63
-n=18000000,fp32,0.1282,0.0450,0.0513,2.85,2.50,1.1400,0.0452,2.83
-n=18000000,int8,0.0800,0.0145,0.0148,5.51,5.39,1.0207,0.0145,5.52
-n=19000000,fp16,0.0933,0.0252,0.0253,3.70,3.69,1.0040,0.0254,3.68
-n=19000000,bf16,0.0932,0.0251,0.0252,3.70,3.70,1.0040,0.0256,3.64
-n=19000000,fp32,0.1347,0.0474,0.0538,2.84,2.50,1.1350,0.0478,2.82
-n=19000000,int8,0.0842,0.0151,0.0156,5.57,5.41,1.0331,0.0152,5.56
-n=20000000,fp16,0.0984,0.0264,0.0264,3.73,3.73,1.0000,0.0268,3.67
-n=20000000,bf16,0.0983,0.0265,0.0265,3.72,3.71,1.0000,0.0263,3.74
-n=20000000,fp32,0.1404,0.0496,0.0564,2.83,2.49,1.1371,0.0502,2.80
-n=20000000,int8,0.0883,0.0155,0.0160,5.71,5.53,1.0323,0.0156,5.66
+params,dtype,torch_ms,triton_ms,cutile_ms,speedup_triton,speedup_cutile,triton_vs_cutile,tilelang_ms,speedup_tilelang,torch_nki_ms,nki_ms,speedup_nki
+n=1000000,fp16,0.0088,0.0026,0.0027,3.36,3.28,1.0385,0.0026,3.34,0.0754,0.0277,2.72
+n=1000000,bf16,0.0087,0.0025,0.0026,3.52,3.35,1.0400,0.0026,3.38,0.0754,0.0277,2.72
+n=1000000,fp32,0.0089,0.0037,0.0039,2.44,2.31,1.0541,0.0039,2.28,0.1201,0.0390,3.08
+n=1000000,int8,0.0081,0.0021,0.0024,3.78,3.37,1.1429,0.0023,3.53,0.0524,0.0236,2.22
+n=2000000,fp16,0.0129,0.0038,0.0038,3.42,3.37,1.0000,0.0038,3.43,0.0776,0.0388,2.00
+n=2000000,bf16,0.0126,0.0036,0.0037,3.49,3.41,1.0278,0.0038,3.27,0.0776,0.0388,2.00
+n=2000000,fp32,0.0147,0.0064,0.0071,2.29,2.08,1.1094,0.0068,2.15,0.0923,0.0612,1.51
+n=2000000,int8,0.0117,0.0026,0.0029,4.42,3.99,1.1154,0.0028,4.11,0.0723,0.0322,2.25
+n=3000000,fp16,0.0169,0.0052,0.0053,3.26,3.20,1.0192,0.0053,3.18,0.1937,0.0503,3.85
+n=3000000,bf16,0.0165,0.0053,0.0054,3.10,3.07,1.0189,0.0052,3.17,0.1937,0.0503,3.85
+n=3000000,fp32,0.0224,0.0096,0.0107,2.33,2.10,1.1146,0.0104,2.15,0.3323,0.0846,3.93
+n=3000000,int8,0.0143,0.0034,0.0037,4.19,3.86,1.0882,0.0037,3.89,0.1587,0.0403,3.94
+n=4000000,fp16,0.0218,0.0068,0.0069,3.22,3.16,1.0147,0.0068,3.22,0.1327,0.0631,2.10
+n=4000000,bf16,0.0213,0.0067,0.0068,3.17,3.15,1.0149,0.0068,3.14,0.1326,0.0631,2.10
+n=4000000,fp32,0.0304,0.0122,0.0135,2.48,2.25,1.1066,0.0128,2.37,0.1753,0.1126,1.56
+n=4000000,int8,0.0175,0.0039,0.0042,4.50,4.14,1.0769,0.0039,4.51,0.1303,0.0475,2.74
+n=5000000,fp16,0.0267,0.0084,0.0085,3.18,3.15,1.0119,0.0086,3.11,0.3021,0.0765,3.95
+n=5000000,bf16,0.0268,0.0084,0.0085,3.20,3.16,1.0119,0.0086,3.12,0.3021,0.0765,3.95
+n=5000000,fp32,0.0373,0.0146,0.0164,2.56,2.28,1.1233,0.0149,2.50,0.5474,0.1348,4.06
+n=5000000,int8,0.0211,0.0046,0.0050,4.54,4.24,1.0870,0.0046,4.56,0.2654,0.0576,4.60
+n=6000000,fp16,0.0321,0.0098,0.0101,3.26,3.18,1.0306,0.0098,3.27,0.1850,0.0891,2.08
+n=6000000,bf16,0.0320,0.0098,0.0099,3.25,3.23,1.0102,0.0099,3.22,0.1852,0.0890,2.08
+n=6000000,fp32,0.0438,0.0170,0.0191,2.58,2.29,1.1235,0.0174,2.52,0.2369,0.1609,1.47
+n=6000000,int8,0.0256,0.0056,0.0058,4.59,4.39,1.0357,0.0057,4.50,0.1673,0.0652,2.56
+n=7000000,fp16,0.0373,0.0111,0.0111,3.37,3.35,1.0000,0.0114,3.28,0.4157,0.1018,4.08
+n=7000000,bf16,0.0368,0.0110,0.0110,3.34,3.33,1.0000,0.0111,3.33,0.4159,0.1020,4.08
+n=7000000,fp32,0.0498,0.0192,0.0219,2.60,2.27,1.1406,0.0199,2.51,0.7508,0.1866,4.02
+n=7000000,int8,0.0297,0.0064,0.0067,4.68,4.47,1.0469,0.0065,4.54,0.3461,0.0719,4.82
+n=8000000,fp16,0.0421,0.0123,0.0124,3.43,3.40,1.0081,0.0122,3.47,0.2430,0.1123,2.16
+n=8000000,bf16,0.0421,0.0123,0.0124,3.43,3.41,1.0081,0.0121,3.47,0.2430,0.1120,2.17
+n=8000000,fp32,0.0560,0.0217,0.0248,2.59,2.26,1.1429,0.0221,2.54,0.3154,0.2130,1.48
+n=8000000,int8,0.0353,0.0074,0.0076,4.79,4.61,1.0270,0.0072,4.88,0.2301,0.0792,2.91
+n=9000000,fp16,0.0471,0.0136,0.0136,3.47,3.45,1.0000,0.0136,3.47,0.5375,0.1293,4.16
+n=9000000,bf16,0.0473,0.0138,0.0139,3.43,3.41,1.0072,0.0137,3.45,0.5378,0.1293,4.16
+n=9000000,fp32,0.0618,0.0240,0.0275,2.57,2.25,1.1458,0.0245,2.52,0.9773,0.2361,4.14
+n=9000000,int8,0.0395,0.0079,0.0082,4.99,4.82,1.0380,0.0082,4.79,0.4224,0.0889,4.75
+n=10000000,fp16,0.0518,0.0145,0.0145,3.57,3.57,1.0000,0.0149,3.48,0.2982,0.1388,2.15
+n=10000000,bf16,0.0515,0.0148,0.0148,3.49,3.48,1.0000,0.0147,3.50,0.2982,0.1389,2.15
+n=10000000,fp32,0.0692,0.0264,0.0302,2.63,2.30,1.1439,0.0267,2.59,0.4032,0.2622,1.54
+n=10000000,int8,0.0446,0.0088,0.0091,5.06,4.91,1.0341,0.0092,4.87,0.2807,0.0972,2.89
+n=11000000,fp16,0.0561,0.0158,0.0159,3.54,3.54,1.0063,0.0159,3.52,0.6432,0.1545,4.16
+n=11000000,bf16,0.0558,0.0159,0.0160,3.51,3.48,1.0063,0.0156,3.57,0.6433,0.1546,4.16
+n=11000000,fp32,0.0785,0.0288,0.0329,2.73,2.39,1.1424,0.0289,2.72,1.1971,0.2863,4.18
+n=11000000,int8,0.0492,0.0098,0.0100,5.03,4.90,1.0204,0.0100,4.92,0.5630,0.1040,5.41
+n=12000000,fp16,0.0607,0.0170,0.0170,3.58,3.56,1.0000,0.0173,3.50,0.3536,0.1621,2.18
+n=12000000,bf16,0.0607,0.0170,0.0171,3.57,3.55,1.0059,0.0171,3.55,0.3536,0.1621,2.18
+n=12000000,fp32,0.0873,0.0310,0.0356,2.81,2.46,1.1484,0.0312,2.80,0.4812,0.3083,1.56
+n=12000000,int8,0.0537,0.0104,0.0107,5.19,5.03,1.0288,0.0104,5.16,0.3241,0.1097,2.95
+n=13000000,fp16,0.0656,0.0181,0.0182,3.62,3.60,1.0055,0.0184,3.56,0.7874,0.1789,4.40
+n=13000000,bf16,0.0652,0.0181,0.0182,3.60,3.59,1.0055,0.0182,3.57,0.7877,0.1789,4.40
+n=13000000,fp32,0.0948,0.0334,0.0382,2.84,2.48,1.1437,0.0338,2.81,1.4638,0.3389,4.32
+n=13000000,int8,0.0584,0.0109,0.0112,5.33,5.20,1.0275,0.0112,5.19,0.6391,0.1236,5.17
+n=14000000,fp16,0.0698,0.0194,0.0195,3.60,3.59,1.0052,0.0193,3.61,0.4033,0.1873,2.15
+n=14000000,bf16,0.0697,0.0193,0.0194,3.60,3.59,1.0052,0.0194,3.60,0.4033,0.1872,2.15
+n=14000000,fp32,0.1019,0.0357,0.0406,2.85,2.51,1.1373,0.0361,2.82,0.5679,0.3649,1.56
+n=14000000,int8,0.0631,0.0114,0.0118,5.51,5.34,1.0351,0.0119,5.28,0.3812,0.1290,2.96
+n=15000000,fp16,0.0742,0.0206,0.0207,3.61,3.59,1.0049,0.0205,3.61,0.8740,0.2048,4.27
+n=15000000,bf16,0.0741,0.0207,0.0207,3.59,3.57,1.0000,0.0206,3.59,0.8742,0.2048,4.27
+n=15000000,fp32,0.1077,0.0380,0.0434,2.83,2.48,1.1421,0.0383,2.81,1.6274,0.3898,4.17
+n=15000000,int8,0.0671,0.0126,0.0130,5.33,5.18,1.0317,0.0126,5.32,0.7062,0.1372,5.15
+n=16000000,fp16,0.0786,0.0217,0.0217,3.62,3.62,1.0000,0.0216,3.63,0.4686,0.2094,2.24
+n=16000000,bf16,0.0789,0.0216,0.0216,3.66,3.65,1.0000,0.0218,3.62,0.4686,0.2094,2.24
+n=16000000,fp32,0.1148,0.0404,0.0460,2.85,2.49,1.1386,0.0408,2.81,0.6556,0.4141,1.58
+n=16000000,int8,0.0717,0.0132,0.0136,5.43,5.29,1.0303,0.0132,5.42,0.4269,0.1439,2.97
+n=17000000,fp16,0.0833,0.0227,0.0227,3.67,3.67,1.0000,0.0228,3.65,0.9882,0.2270,4.35
+n=17000000,bf16,0.0833,0.0229,0.0229,3.64,3.63,1.0000,0.0229,3.63,0.9881,0.2268,4.36
+n=17000000,fp32,0.1211,0.0426,0.0486,2.85,2.49,1.1408,0.0430,2.82,1.8417,0.4333,4.25
+n=17000000,int8,0.0759,0.0134,0.0139,5.65,5.47,1.0373,0.0140,5.41,0.8646,0.1517,5.70
+n=18000000,fp16,0.0882,0.0241,0.0241,3.67,3.66,1.0000,0.0242,3.64,0.5239,0.2381,2.20
+n=18000000,bf16,0.0884,0.0241,0.0241,3.67,3.67,1.0000,0.0243,3.63,0.5240,0.2383,2.20
+n=18000000,fp32,0.1282,0.0450,0.0513,2.85,2.50,1.1400,0.0452,2.83,0.6857,0.4668,1.47
+n=18000000,int8,0.0800,0.0145,0.0148,5.51,5.39,1.0207,0.0145,5.52,0.4955,0.1612,3.07
+n=19000000,fp16,0.0933,0.0252,0.0253,3.70,3.69,1.0040,0.0254,3.68,1.0996,0.2532,4.34
+n=19000000,bf16,0.0932,0.0251,0.0252,3.70,3.70,1.0040,0.0256,3.64,1.0997,0.2532,4.34
+n=19000000,fp32,0.1347,0.0474,0.0538,2.84,2.50,1.1350,0.0478,2.82,2.0164,0.4939,4.08
+n=19000000,int8,0.0842,0.0151,0.0156,5.57,5.41,1.0331,0.0152,5.56,0.9225,0.1688,5.47
+n=20000000,fp16,0.0984,0.0264,0.0264,3.73,3.73,1.0000,0.0268,3.67,0.5842,0.2584,2.26
+n=20000000,bf16,0.0983,0.0265,0.0265,3.72,3.71,1.0000,0.0263,3.74,0.5842,0.2584,2.26
+n=20000000,fp32,0.1404,0.0496,0.0564,2.83,2.49,1.1371,0.0502,2.80,0.8081,0.5077,1.59
+n=20000000,int8,0.0883,0.0155,0.0160,5.71,5.53,1.0323,0.0156,5.66,0.5361,0.1749,3.07
diff --git a/tilebench/benchmarks/operators/interleave/impl_nki.py b/tilebench/benchmarks/operators/interleave/impl_nki.py
new file mode 100644
index 00000000..20c066be
--- /dev/null
+++ b/tilebench/benchmarks/operators/interleave/impl_nki.py
@@ -0,0 +1,98 @@
+import functools
+import os
+import re
+import subprocess
+from types import SimpleNamespace
+
+import torch
+
+from tilebench.core.nki_autotune import NkiAutotuner
+
+try:
+    import nki
+    import nki.isa as nisa
+    import nki.language as nl
+    PMAX = nl.tile_size.pmax
+except ImportError:
+    nki = None
+    PMAX = 128
+
+
+@functools.lru_cache(maxsize=1)
+def _lnc_degree() -> int:
+    explicit = os.environ.get("NEURON_LOGICAL_NC_CONFIG", "")
+    if explicit.strip().isdigit():
+        return int(explicit.strip())
+    match = re.search(r"--lnc[=\s]+(\d+)", os.environ.get("NEURON_CC_FLAGS", ""))
+    if match:
+        return int(match.group(1))
+    try:
+        out = subprocess.run(["neuron-ls"], capture_output=True, text=True, timeout=10).stdout
+        lnc = re.search(r"logical-neuroncore-config:\s*(\d+)", out)
+        if lnc:
+            return int(lnc.group(1))
+    except (OSError, subprocess.SubprocessError):
+        pass
+    return 1
+
+
+if nki is not None:
+    @nki.jit
+    def interleave_kernel(a_input, b_input, block_size):
+        n = a_input.shape[0]
+        out = nl.ndarray((2 * n,), dtype=a_input.dtype, buffer=nl.shared_hbm)
+
+        num_programs = nl.num_programs()
+        per_core = (n + num_programs - 1) // num_programs
+        lo = nl.program_id(0) * per_core
+        hi = min(n, lo + per_core)
+
+        chunk = PMAX * block_size
+        for j in range(max(0, (hi - lo + chunk - 1) // chunk)):
+            start = lo + j * chunk
+            count = min(chunk, hi - start)
+            q = count // PMAX
+            r = count - q * PMAX
+            if q > 0:
+                _tile_body(PMAX, q, start, a_input, b_input, out)
+            if r > 0:
+                _tile_body(1, r, start + q * PMAX, a_input, b_input, out)
+        return out
+
+    def _tile_body(p, f, start, a_input, b_input, out):
+        a_tile = nl.ndarray((p, f), dtype=a_input.dtype, buffer=nl.sbuf)
+        nisa.dma_copy(dst=a_tile, src=a_input.ap(pattern=[[f, p], [1, f]], offset=start))
+        b_tile = nl.ndarray((p, f), dtype=b_input.dtype, buffer=nl.sbuf)
+        nisa.dma_copy(dst=b_tile, src=b_input.ap(pattern=[[f, p], [1, f]], offset=start))
+        out_tile = nl.ndarray((p, 2 * f), dtype=a_input.dtype, buffer=nl.sbuf)
+        nisa.tensor_copy(dst=out_tile[0:p, 0:2 * f:2], src=a_tile)
+        nisa.tensor_copy(dst=out_tile[0:p, 1:2 * f:2], src=b_tile)
+        nisa.dma_copy(dst=out.ap(pattern=[[2 * f, p], [1, 2 * f]], offset=2 * start), src=out_tile)
+
+
+_DEFAULT_CONFIG = SimpleNamespace(block_size=1024)
+_SEARCH_SPACE = [SimpleNamespace(block_size=b) for b in (1024, 2048, 4096, 8192)]
+_kernel = interleave_kernel[_lnc_degree()] if nki is not None else None
+_tuner = NkiAutotuner(_kernel) if nki is not None else None
+_last_autotune_config: dict = {}
+
+
+def run(A: torch.Tensor, B: torch.Tensor, N: int, block_size: int = 1024,
+        autotune: bool = False, **kwargs) -> torch.Tensor:
+    a_flat, b_flat = A.reshape(-1), B.reshape(-1)
+    n = a_flat.numel()
+    if autotune:
+        cfg = _tuner.tune_or_cached(
+            shape_key=(n, str(a_flat.dtype)),
+            search_space=_SEARCH_SPACE,
+            args_fn=lambda cfg: (a_flat, b_flat, cfg.block_size),
+        )
+        _last_autotune_config.clear()
+        _last_autotune_config.update(vars(cfg))
+    else:
+        cfg = _DEFAULT_CONFIG
+    return _kernel(a_flat, b_flat, cfg.block_size)
+
+
+def get_last_config() -> dict | None:
+    return dict(_last_autotune_config) or None
diff --git a/tilebench/benchmarks/operators/interleave/impl_torch.py b/tilebench/benchmarks/operators/interleave/impl_torch.py
index 572bd07a..b8e405fa 100644
--- a/tilebench/benchmarks/operators/interleave/impl_torch.py
+++ b/tilebench/benchmarks/operators/interleave/impl_torch.py
@@ -1,8 +1,29 @@
 import torch
+import torch.nn.functional as F
 
 
-def run(A: torch.Tensor, B: torch.Tensor, N: int, **kwargs):
-    output = torch.empty(2 * N, dtype=A.dtype, device=A.device)
-    output[0::2] = A
-    output[1::2] = B
+def _view_cols(n: int, lo: int = 128, hi: int = 8192) -> int | None:
+    for c in range(hi, lo - 1, -1):
+        if n % c == 0:
+            return c
+    return None
+
+
+def _interleave(a: torch.Tensor, b: torch.Tensor, n: int) -> torch.Tensor:
+    output = torch.empty(2 * n, dtype=a.dtype, device=a.device)
+    output[0::2] = a
+    output[1::2] = b
     return output
+
+
+def run(A: torch.Tensor, B: torch.Tensor, N: int, **kwargs):
+    if A.device.type == "xla" and N % 128 != 0:
+        cols = _view_cols(N)
+        if cols is not None:
+            rows = N // cols
+            pad = (-cols) % 128
+            a2 = F.pad(A.reshape(rows, cols), (0, pad)).reshape(-1)
+            b2 = F.pad(B.reshape(rows, cols), (0, pad)).reshape(-1)
+            out = _interleave(a2, b2, a2.numel()).reshape(rows, 2 * (cols + pad))
+            return out[:, :2 * cols].reshape(-1)
+    return _interleave(A, B, N)