Cast matrix — astype src→dst × layout × dtype (NumSharp vs NumPy 2.4.2)

Full astype(dst, copy:true) sweep over every src→dst dtype pair × 8 memory layouts at 1M elements, best-of-3. ratio = NumPy_ms / NumSharp_ms — >1.0 = NumSharp faster. ✅≥1.0 🟡≥0.5 🟠≥0.2 🔴<0.2 · — = no NumPy counterpart (Decimal has no NumPy dtype).

Summary

• 381 / 1568 comparable cells lag (<1.0); 1187 win (≥1.0).
• 🔴 <0.2 — 26 cells. Top: 14× float/cplx → narrow-int (bool/u8/i8/i16/u16/char); 5× int → sub-word (narrow); 3× bool → f16
• 🟠 0.2–0.5 — 156 cells. Top: 67× int → sub-word (narrow); 24× float/cplx → narrow-int (bool/u8/i8/i16/u16/char); 15× * → bool
• 🟡 0.5–1.0 — 199 cells. Top: 32× int → sub-word (narrow); 27× float/cplx → narrow-int (bool/u8/i8/i16/u16/char); 8× f16 → u64

float/complex → narrow-int geomean by src (the historical cliff): f32→narrow 1.62, f64→narrow 1.16, f16→narrow 3.67, c128→narrow 0.88.

Geomean by layout (all src×dst, excl. Decimal)

C	F	T	sliced	negrow	negcol	strided	bcast
3.27 ✅	3.18 ✅	3.27 ✅	2.88 ✅	2.98 ✅	1.76 ✅	1.53 ✅	0.43 🟠

Geomean by src dtype (all layouts×dst)

bool	u8	i8	i16	u16	i32	u32	i64	u64	char	f16	f32	f64	dec	c128
1.98 ✅	3.30 ✅	3.17 ✅	3.43 ✅	3.49 ✅	1.97 ✅	1.99 ✅	1.36 ✅	1.31 ✅	3.01 ✅	2.38 ✅	1.56 ✅	1.32 ✅	nan ?	1.05 ✅

Geomean by dst dtype (all layouts×src)

bool	u8	i8	i16	u16	i32	u32	i64	u64	char	f16	f32	f64	dec	c128
1.94 ✅	1.68 ✅	1.68 ✅	2.27 ✅	2.33 ✅	2.41 ✅	1.85 ✅	2.44 ✅	2.01 ✅	2.27 ✅	1.59 ✅	1.96 ✅	2.39 ✅	nan ?	2.51 ✅

Layout: C (rows=src, cols=dst)

src\dst	bool	u8	i8	i16	u16	i32	u32	i64	u64	char	f16	f32	f64	dec	c128
bool	0.61🟡	7.31✅	7.34✅	8.93✅	9.52✅	7.84✅	7.83✅	7.55✅	7.11✅	7.15✅	0.25🟠	8.07✅	7.43✅	—	5.93✅
u8	5.00✅	0.74🟡	10.54✅	9.68✅	10.47✅	5.89✅	6.23✅	4.24✅	6.99✅	5.11✅	2.86✅	1.95✅	3.00✅	—	3.57✅
i8	11.65✅	8.73✅	1.64✅	6.04✅	7.70✅	4.82✅	4.67✅	8.25✅	3.93✅	7.74✅	2.88✅	1.95✅	3.01✅	—	3.45✅
i16	8.38✅	7.80✅	10.52✅	3.85✅	6.95✅	5.38✅	5.15✅	4.83✅	3.81✅	7.30✅	2.89✅	6.11✅	2.96✅	—	3.20✅
u16	8.43✅	10.58✅	9.20✅	4.36✅	3.71✅	9.34✅	4.58✅	4.74✅	5.03✅	3.92✅	2.88✅	5.91✅	2.96✅	—	3.42✅
i32	3.33✅	1.01✅	0.90🟡	4.16✅	5.39✅	3.42✅	5.44✅	4.23✅	4.31✅	4.91✅	3.00✅	2.43✅	4.11✅	—	2.51✅
u32	1.23✅	1.45✅	0.90🟡	4.33✅	5.37✅	5.22✅	3.59✅	4.23✅	4.34✅	5.08✅	2.73✅	1.87✅	2.88✅	—	2.90✅
i64	1.21✅	1.34✅	0.89🟡	1.79✅	1.86✅	3.07✅	6.35✅	2.63✅	4.49✅	2.23✅	1.43✅	1.66✅	2.97✅	—	2.45✅
u64	1.21✅	1.03✅	1.33✅	1.48✅	1.75✅	3.24✅	2.93✅	4.45✅	2.55✅	1.59✅	0.96🟡	1.50✅	1.77✅	—	2.30✅
char	8.37✅	10.77✅	10.72✅	7.39✅	4.61✅	2.32✅	2.13✅	2.21✅	2.29✅	3.58✅	10.67✅	3.28✅	2.30✅	—	5.38✅
f16	17.29✅	4.34✅	4.65✅	5.44✅	5.87✅	6.92✅	4.42✅	3.29✅	0.72🟡	5.71✅	3.47✅	3.16✅	0.88🟡	—	1.23✅
f32	4.93✅	2.75✅	2.71✅	5.25✅	6.18✅	4.65✅	0.71🟡	0.89🟡	0.57🟡	5.03✅	3.06✅	3.51✅	4.51✅	—	3.04✅
f64	2.26✅	2.62✅	2.60✅	3.28✅	2.91✅	3.26✅	0.97🟡	1.07✅	0.61🟡	2.53✅	4.95✅	5.40✅	3.06✅	—	1.88✅
dec	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
c128	0.86🟡	1.51✅	1.51✅	1.89✅	1.97✅	2.14✅	1.12✅	1.12✅	0.62🟡	2.05✅	1.52✅	1.66✅	1.77✅	—	6.39✅

Layout: F (rows=src, cols=dst)

src\dst	bool	u8	i8	i16	u16	i32	u32	i64	u64	char	f16	f32	f64	dec	c128
bool	4.39✅	15.91✅	8.64✅	8.94✅	15.51✅	7.49✅	6.23✅	5.36✅	5.38✅	9.29✅	0.29🟠	6.61✅	5.07✅	—	3.59✅
u8	10.68✅	1.43✅	12.29✅	10.07✅	8.19✅	5.91✅	5.77✅	4.41✅	4.46✅	9.37✅	2.87✅	1.88✅	2.50✅	—	2.23✅
i8	11.47✅	8.15✅	1.69✅	9.64✅	6.67✅	5.80✅	5.78✅	3.95✅	3.66✅	8.03✅	2.90✅	1.90✅	2.96✅	—	3.53✅
i16	8.39✅	3.52✅	3.61✅	3.40✅	6.73✅	5.65✅	5.11✅	4.70✅	5.08✅	6.12✅	2.81✅	6.46✅	2.22✅	—	3.41✅
u16	8.43✅	3.61✅	10.58✅	4.51✅	3.75✅	5.31✅	5.25✅	4.82✅	4.85✅	3.41✅	2.83✅	5.70✅	3.01✅	—	3.36✅
i32	3.37✅	1.03✅	0.90🟡	4.01✅	5.65✅	3.53✅	5.44✅	4.36✅	4.30✅	5.11✅	3.02✅	2.44✅	3.95✅	—	3.00✅
u32	3.33✅	1.31✅	0.90🟡	4.09✅	5.12✅	5.29✅	6.34✅	6.40✅	4.42✅	5.11✅	2.71✅	1.86✅	5.51✅	—	2.96✅
i64	1.21✅	1.35✅	0.47🟠	1.80✅	1.70✅	3.02✅	3.17✅	3.26✅	4.73✅	2.32✅	1.44✅	2.38✅	2.96✅	—	2.24✅
u64	1.21✅	1.03✅	1.30✅	1.46✅	1.15✅	2.05✅	2.16✅	4.56✅	3.30✅	2.34✅	1.80✅	1.52✅	1.79✅	—	2.12✅
char	3.41✅	10.38✅	11.62✅	5.90✅	6.66✅	2.37✅	2.29✅	3.37✅	3.44✅	3.37✅	2.84✅	1.90✅	2.78✅	—	1.40✅
f16	17.23✅	2.26✅	2.26✅	5.36✅	5.75✅	7.08✅	1.46✅	3.32✅	0.72🟡	5.72✅	3.65✅	3.19✅	0.93🟡	—	1.22✅
f32	4.93✅	2.74✅	2.71✅	4.76✅	4.99✅	4.64✅	0.72🟡	0.90🟡	0.58🟡	5.01✅	3.04✅	3.37✅	4.23✅	—	2.10✅
f64	2.23✅	2.63✅	2.62✅	3.28✅	2.65✅	3.19✅	0.96🟡	1.04✅	0.60🟡	2.61✅	4.64✅	2.87✅	5.74✅	—	1.69✅
dec	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
c128	0.72🟡	1.11✅	1.51✅	1.96✅	1.93✅	3.88✅	1.13✅	1.17✅	0.66🟡	1.93✅	1.50✅	1.78✅	2.06✅	—	3.15✅

Layout: T (rows=src, cols=dst)

src\dst	bool	u8	i8	i16	u16	i32	u32	i64	u64	char	f16	f32	f64	dec	c128
bool	2.23✅	9.99✅	11.36✅	9.60✅	7.85✅	6.26✅	6.66✅	5.41✅	9.87✅	8.71✅	0.30🟠	6.89✅	5.08✅	—	2.85✅
u8	10.79✅	2.28✅	11.33✅	9.68✅	8.06✅	5.78✅	5.86✅	4.55✅	4.26✅	13.74✅	10.38✅	1.90✅	2.97✅	—	3.66✅
i8	11.61✅	8.43✅	1.72✅	9.62✅	8.01✅	5.66✅	5.40✅	3.84✅	3.91✅	8.00✅	2.87✅	1.89✅	2.71✅	—	3.34✅
i16	8.32✅	6.75✅	9.36✅	3.54✅	7.24✅	5.83✅	5.59✅	4.80✅	4.88✅	6.31✅	2.88✅	5.78✅	2.91✅	—	3.23✅
u16	8.38✅	10.53✅	9.94✅	6.40✅	4.32✅	5.26✅	3.92✅	6.60✅	5.07✅	3.43✅	2.91✅	5.75✅	2.98✅	—	3.51✅
i32	3.30✅	0.95🟡	0.86🟡	4.18✅	5.56✅	3.66✅	5.45✅	4.19✅	4.29✅	5.09✅	1.57✅	2.53✅	4.16✅	—	3.09✅
u32	3.27✅	1.44✅	0.90🟡	4.22✅	10.09✅	5.72✅	3.82✅	3.28✅	3.57✅	4.80✅	2.70✅	1.87✅	2.92✅	—	2.91✅
i64	1.21✅	1.36✅	0.87🟡	1.76✅	1.81✅	2.72✅	2.73✅	3.17✅	4.53✅	2.14✅	1.46✅	2.24✅	2.56✅	—	3.00✅
u64	1.21✅	1.03✅	1.27✅	1.00🟡	1.15✅	3.27✅	3.00✅	4.49✅	3.17✅	2.28✅	1.83✅	1.51✅	1.79✅	—	2.22✅
char	8.36✅	10.71✅	9.34✅	6.52✅	4.13✅	2.44✅	2.35✅	6.94✅	3.54✅	3.52✅	2.89✅	1.86✅	2.64✅	—	2.17✅
f16	17.18✅	4.33✅	4.66✅	5.42✅	5.86✅	7.12✅	1.48✅	3.31✅	0.71🟡	5.72✅	3.90✅	3.18✅	0.95🟡	—	1.22✅
f32	2.46✅	2.69✅	2.72✅	5.31✅	9.91✅	4.80✅	0.70🟡	0.90🟡	0.57🟡	4.98✅	3.04✅	3.43✅	4.12✅	—	2.18✅
f64	2.19✅	2.75✅	2.45✅	3.34✅	2.87✅	3.14✅	0.99🟡	1.05✅	0.61🟡	2.70✅	1.70✅	3.19✅	3.20✅	—	2.29✅
dec	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
c128	0.88🟡	1.45✅	1.41✅	1.97✅	1.92✅	2.13✅	1.11✅	1.09✅	0.63🟡	1.91✅	1.51✅	1.69✅	1.99✅	—	3.07✅

Layout: sliced (rows=src, cols=dst)

src\dst	bool	u8	i8	i16	u16	i32	u32	i64	u64	char	f16	f32	f64	dec	c128
bool	1.19✅	0.90🟡	1.05✅	1.26✅	1.43✅	1.74✅	1.72✅	4.18✅	2.96✅	1.29✅	0.16🔴	1.37✅	2.89✅	—	2.49✅
u8	8.17✅	1.35✅	11.60✅	9.18✅	7.42✅	5.47✅	5.77✅	2.96✅	2.97✅	9.10✅	2.76✅	1.89✅	2.97✅	—	3.85✅
i8	8.55✅	7.70✅	0.67🟡	9.53✅	8.06✅	5.78✅	6.02✅	3.02✅	3.04✅	7.57✅	2.81✅	1.90✅	2.95✅	—	3.65✅
i16	7.97✅	7.08✅	8.65✅	5.15✅	7.31✅	5.66✅	5.21✅	4.56✅	5.01✅	6.79✅	2.80✅	5.88✅	3.50✅	—	3.67✅
u16	8.03✅	8.86✅	9.19✅	6.80✅	4.52✅	4.76✅	4.91✅	4.65✅	4.50✅	4.87✅	1.74✅	5.91✅	3.76✅	—	3.36✅
i32	3.00✅	3.00✅	3.05✅	2.74✅	2.90✅	3.72✅	3.99✅	4.23✅	4.30✅	4.92✅	2.89✅	1.67✅	4.38✅	—	3.06✅
u32	3.16✅	4.32✅	3.05✅	3.93✅	4.99✅	4.43✅	4.22✅	4.08✅	3.09✅	4.88✅	2.66✅	2.31✅	3.67✅	—	3.23✅
i64	1.11✅	1.72✅	1.22✅	2.57✅	2.17✅	2.32✅	2.75✅	2.06✅	1.87✅	1.58✅	1.42✅	3.28✅	2.70✅	—	2.26✅
u64	1.18✅	1.22✅	1.76✅	2.27✅	2.30✅	2.98✅	2.73✅	2.79✅	2.83✅	2.18✅	0.96🟡	1.38✅	1.20✅	—	1.57✅
char	8.01✅	8.66✅	8.53✅	6.80✅	5.70✅	2.31✅	2.32✅	4.08✅	4.21✅	4.92✅	2.80✅	1.85✅	2.96✅	—	3.57✅
f16	16.46✅	4.15✅	4.37✅	5.06✅	5.45✅	6.17✅	1.52✅	3.11✅	0.72🟡	5.34✅	5.64✅	3.01✅	0.90🟡	—	1.15✅
f32	4.31✅	2.33✅	2.32✅	4.27✅	4.42✅	4.32✅	0.70🟡	0.89🟡	0.57🟡	4.25✅	3.03✅	3.82✅	4.21✅	—	2.84✅
f64	2.07✅	2.16✅	2.18✅	1.75✅	1.68✅	2.97✅	0.94🟡	1.02✅	0.62🟡	2.43✅	1.73✅	3.12✅	2.92✅	—	2.32✅
dec	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
c128	0.91🟡	1.38✅	1.40✅	1.86✅	1.80✅	1.89✅	1.01✅	1.10✅	0.63🟡	1.79✅	1.50✅	1.55✅	1.13✅	—	1.59✅

Layout: negrow (rows=src, cols=dst)

src\dst	bool	u8	i8	i16	u16	i32	u32	i64	u64	char	f16	f32	f64	dec	c128
bool	1.41✅	0.90🟡	1.04✅	1.34✅	1.06✅	1.26✅	1.67✅	2.88✅	2.81✅	1.29✅	0.15🔴	1.99✅	2.82✅	—	2.79✅
u8	8.62✅	1.53✅	17.94✅	9.60✅	10.05✅	5.65✅	8.86✅	2.96✅	7.78✅	9.41✅	2.75✅	1.91✅	2.92✅	—	2.28✅
i8	8.44✅	12.17✅	1.14✅	9.86✅	7.99✅	5.92✅	5.91✅	2.97✅	3.01✅	8.34✅	2.83✅	1.90✅	2.96✅	—	3.54✅
i16	7.46✅	6.76✅	9.40✅	5.20✅	4.25✅	5.39✅	5.28✅	4.41✅	4.22✅	7.03✅	2.80✅	5.55✅	3.31✅	—	3.54✅
u16	7.48✅	10.39✅	9.33✅	7.19✅	4.79✅	5.29✅	5.12✅	4.86✅	4.80✅	5.07✅	2.82✅	6.02✅	3.50✅	—	3.81✅
i32	2.85✅	2.90✅	2.88✅	4.15✅	8.52✅	3.74✅	3.95✅	4.15✅	4.33✅	5.01✅	2.89✅	1.71✅	4.10✅	—	2.88✅
u32	2.86✅	3.90✅	2.90✅	4.15✅	5.38✅	4.15✅	2.87✅	4.12✅	4.16✅	5.06✅	2.59✅	2.20✅	3.41✅	—	3.27✅
i64	1.15✅	1.70✅	1.25✅	2.79✅	2.39✅	3.00✅	2.88✅	2.43✅	2.67✅	2.09✅	1.41✅	1.71✅	2.35✅	—	1.85✅
u64	1.15✅	1.23✅	1.67✅	2.26✅	2.26✅	3.04✅	2.97✅	3.13✅	3.01✅	2.21✅	0.94🟡	0.77🟡	2.90✅	—	2.20✅
char	3.15✅	10.35✅	10.36✅	7.37✅	4.55✅	2.27✅	2.30✅	4.07✅	6.93✅	5.53✅	2.80✅	1.88✅	2.74✅	—	3.28✅
f16	15.60✅	4.11✅	4.27✅	4.99✅	5.21✅	6.69✅	1.52✅	3.24✅	0.72🟡	5.08✅	5.45✅	3.09✅	0.88🟡	—	1.22✅
f32	4.19✅	2.19✅	2.21✅	4.56✅	4.35✅	4.32✅	0.65🟡	0.83🟡	1.40✅	4.28✅	2.92✅	3.68✅	3.83✅	—	2.93✅
f64	2.00✅	2.22✅	2.23✅	3.20✅	2.80✅	3.34✅	0.95🟡	0.99🟡	0.62🟡	2.66✅	1.66✅	3.17✅	2.83✅	—	2.35✅
dec	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
c128	0.85🟡	1.35✅	1.34✅	1.80✅	1.93✅	1.96✅	1.06✅	1.06✅	0.64🟡	1.68✅	1.45✅	1.59✅	1.89✅	—	1.85✅

Layout: negcol (rows=src, cols=dst)

src\dst	bool	u8	i8	i16	u16	i32	u32	i64	u64	char	f16	f32	f64	dec	c128
bool	0.86🟡	0.90🟡	0.89🟡	1.31✅	1.34✅	1.67✅	1.67✅	2.90✅	2.84✅	1.26✅	0.30🟠	3.50✅	5.13✅	—	3.47✅
u8	0.68🟡	8.93✅	7.66✅	9.53✅	10.56✅	2.17✅	2.12✅	3.99✅	3.99✅	9.81✅	1.07✅	2.07✅	3.32✅	—	3.61✅
i8	1.08✅	11.79✅	9.13✅	7.96✅	7.28✅	2.00✅	2.16✅	3.59✅	3.62✅	9.62✅	1.04✅	1.43✅	3.28✅	—	3.51✅
i16	3.86✅	9.02✅	3.82✅	8.90✅	9.48✅	2.27✅	2.20✅	2.63✅	2.74✅	5.67✅	2.14✅	1.95✅	3.21✅	—	2.49✅
u16	3.83✅	5.18✅	5.21✅	7.24✅	8.55✅	2.59✅	1.95✅	4.22✅	3.83✅	8.73✅	2.15✅	2.00✅	3.23✅	—	3.62✅
i32	0.48🟠	0.55🟡	0.23🟠	0.46🟠	0.72🟡	1.79✅	1.77✅	3.61✅	3.61✅	0.64🟡	2.21✅	3.56✅	2.91✅	—	3.24✅
u32	0.48🟠	0.41🟠	0.23🟠	0.64🟡	0.50🟡	1.85✅	1.78✅	3.74✅	3.87✅	0.81🟡	2.11✅	1.91✅	2.33✅	—	2.87✅
i64	0.39🟠	0.40🟠	0.39🟠	0.56🟡	0.49🟠	0.69🟡	0.72🟡	2.33✅	2.35✅	0.45🟠	1.23✅	1.80✅	2.94✅	—	2.24✅
u64	0.39🟠	0.39🟠	0.39🟠	0.54🟡	4.29✅	1.04✅	0.72🟡	2.00✅	1.99✅	0.55🟡	1.49✅	1.16✅	1.86✅	—	2.21✅
char	3.86✅	5.25✅	5.24✅	7.23✅	9.19✅	2.46✅	2.46✅	2.94✅	3.89✅	8.81✅	2.08✅	1.88✅	2.67✅	—	2.39✅
f16	9.56✅	2.28✅	3.87✅	2.76✅	2.72✅	3.40✅	1.26✅	2.28✅	0.73🟡	2.66✅	5.81✅	3.49✅	0.82🟡	—	1.23✅
f32	0.82🟡	0.40🟠	0.54🟡	0.69🟡	0.66🟡	0.98🟡	0.41🟠	0.86🟡	0.48🟠	0.66🟡	2.17✅	1.74✅	2.27✅	—	2.84✅
f64	0.57🟡	0.30🟠	0.30🟠	0.58🟡	0.51🟡	2.93✅	0.57🟡	0.98🟡	0.58🟡	0.49🟠	1.36✅	1.37✅	2.55✅	—	2.30✅
dec	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
c128	1.00🟡	0.39🟠	0.40🟠	0.64🟡	0.62🟡	0.84🟡	0.69🟡	1.07✅	0.63🟡	0.60🟡	1.24✅	1.64✅	2.10✅	—	2.05✅

Layout: strided (rows=src, cols=dst)

src\dst	bool	u8	i8	i16	u16	i32	u32	i64	u64	char	f16	f32	f64	dec	c128
bool	0.83🟡	0.88🟡	0.63🟡	0.58🟡	0.87🟡	1.73✅	1.91✅	2.96✅	2.84✅	0.87🟡	0.14🔴	2.02✅	2.92✅	—	4.93✅
u8	0.98🟡	6.38✅	5.43✅	5.78✅	5.12✅	1.85✅	2.57✅	4.44✅	3.15✅	2.79✅	0.89🟡	2.05✅	3.43✅	—	4.89✅
i8	0.98🟡	7.47✅	6.25✅	4.26✅	5.16✅	2.07✅	2.26✅	3.69✅	3.86✅	5.83✅	1.87✅	2.15✅	3.52✅	—	4.92✅
i16	2.92✅	3.87✅	2.79✅	5.38✅	4.66✅	2.17✅	2.47✅	3.85✅	2.70✅	5.36✅	1.92✅	2.03✅	3.58✅	—	4.75✅
u16	2.92✅	3.85✅	3.85✅	3.81✅	1.96✅	1.76✅	2.91✅	4.26✅	4.23✅	5.33✅	0.92🟡	2.14✅	3.63✅	—	4.65✅
i32	0.46🟠	0.21🟠	0.56🟡	0.57🟡	0.39🟠	1.83✅	1.32✅	3.49✅	3.50✅	0.39🟠	0.97🟡	1.58✅	2.85✅	—	3.66✅
u32	0.33🟠	0.39🟠	0.56🟡	0.23🟠	0.23🟠	1.82✅	2.87✅	3.71✅	3.99✅	0.59🟡	1.85✅	2.10✅	3.37✅	—	4.08✅
i64	0.41🟠	0.41🟠	0.19🔴	0.41🟠	0.32🟠	0.78🟡	0.83🟡	2.67✅	2.59✅	0.32🟠	0.54🟡	1.38✅	2.62✅	—	2.90✅
u64	0.42🟠	0.42🟠	0.41🟠	0.41🟠	0.41🟠	0.85🟡	0.81🟡	2.64✅	2.73✅	0.41🟠	1.33✅	1.20✅	2.05✅	—	2.66✅
char	2.91✅	3.83✅	7.51✅	3.75✅	4.73✅	2.70✅	2.81✅	4.33✅	4.21✅	5.29✅	1.93✅	1.89✅	2.98✅	—	4.29✅
f16	7.74✅	1.84✅	1.98✅	2.43✅	2.25✅	3.32✅	1.31✅	2.26✅	0.73🟡	2.25✅	5.31✅	1.99✅	0.86🟡	—	1.22✅
f32	0.82🟡	0.38🟠	0.54🟡	0.38🟠	0.38🟠	1.07✅	0.49🟠	0.85🟡	0.45🟠	0.38🟠	2.00✅	3.46✅	2.52✅	—	3.65✅
f64	0.60🟡	0.39🟠	0.37🟠	0.42🟠	0.38🟠	0.61🟡	0.64🟡	1.13✅	0.41🟠	0.19🔴	1.25✅	1.64✅	2.80✅	—	3.49✅
dec	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
c128	0.35🟠	0.61🟡	0.62🟡	0.57🟡	0.57🟡	1.04✅	0.71🟡	1.17✅	0.55🟡	0.57🟡	0.42🟠	1.08✅	1.96✅	—	2.53✅

Layout: bcast (rows=src, cols=dst)

src\dst	bool	u8	i8	i16	u16	i32	u32	i64	u64	char	f16	f32	f64	dec	c128
bool	0.03🔴	0.28🟠	0.27🟠	0.27🟠	0.27🟠	0.49🟠	0.50🟠	0.97🟡	0.88🟡	0.36🟠	0.30🟠	0.51🟡	0.97🟡	—	1.42✅
u8	0.29🟠	0.03🔴	0.25🟠	0.39🟠	0.39🟠	0.47🟠	0.50🟠	0.98🟡	0.99🟡	0.37🟠	0.59🟡	0.54🟡	0.92🟡	—	1.39✅
i8	0.29🟠	0.34🟠	0.03🔴	0.33🟠	0.38🟠	0.38🟠	0.50🟡	0.91🟡	0.92🟡	0.38🟠	0.58🟡	0.48🟠	0.98🟡	—	1.35✅
i16	0.27🟠	0.31🟠	0.23🟠	0.23🟠	0.25🟠	0.51🟡	0.49🟠	0.98🟡	0.98🟡	0.39🟠	0.57🟡	0.47🟠	0.91🟡	—	1.28✅
u16	0.56🟡	0.31🟠	0.31🟠	0.32🟠	0.25🟠	0.48🟠	0.51🟡	0.97🟡	0.99🟡	0.23🟠	0.59🟡	1.05✅	1.30✅	—	1.29✅
i32	0.25🟠	0.30🟠	0.29🟠	0.34🟠	0.30🟠	0.31🟠	0.32🟠	0.92🟡	0.96🟡	0.30🟠	0.62🟡	0.41🟠	0.98🟡	—	1.31✅
u32	0.19🔴	0.13🔴	0.30🟠	0.24🟠	0.41🟠	0.40🟠	0.41🟠	0.74🟡	1.00🟡	0.38🟠	0.59🟡	0.41🟠	0.98🟡	—	1.24✅
i64	0.29🟠	0.26🟠	0.26🟠	0.32🟠	0.25🟠	0.39🟠	0.46🟠	0.98🟡	0.99🟡	0.26🟠	0.54🟡	0.36🟠	0.98🟡	—	1.24✅
u64	0.29🟠	0.11🔴	0.11🔴	0.34🟠	0.34🟠	0.44🟠	0.47🟠	0.95🟡	1.00🟡	0.32🟠	0.54🟡	0.50🟡	1.12✅	—	1.12✅
char	0.26🟠	0.13🔴	0.31🟠	0.33🟠	0.25🟠	0.47🟠	0.47🟠	0.93🟡	0.80🟡	0.24🟠	0.58🟡	0.49🟠	0.97🟡	—	1.19✅
f16	0.77🟡	0.40🟠	0.41🟠	0.85🟡	0.45🟠	0.49🟠	0.51🟡	0.55🟡	0.67🟡	0.44🟠	0.26🟠	0.49🟠	0.77🟡	—	0.94🟡
f32	0.44🟠	0.11🔴	0.15🔴	0.19🔴	0.19🔴	0.33🟠	0.33🟠	0.75🟡	0.59🟡	0.18🔴	0.74🟡	0.37🟠	0.95🟡	—	1.30✅
f64	0.44🟠	0.12🔴	0.13🔴	0.24🟠	0.21🟠	0.37🟠	0.41🟠	0.85🟡	0.66🟡	0.19🔴	0.66🟡	0.36🟠	0.99🟡	—	1.27✅
dec	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
c128	0.36🟠	0.12🔴	0.08🔴	0.14🔴	0.17🔴	0.26🟠	0.27🟠	0.87🟡	0.40🟠	0.16🔴	0.66🟡	0.29🟠	0.97🟡	—	1.34✅

Lagging cells (<1.0) — the worklist (381 cells)

key	NumSharp ms	NumPy ms	ratio
bool|bcast|bool	1.4941	0.0471	0.03 🔴
u8|bcast|u8	1.4360	0.0487	0.03 🔴
i8|bcast|i8	1.4392	0.0488	0.03 🔴
c128|bcast|i8	3.1701	0.2452	0.08 🔴
u64|bcast|u8	1.8771	0.1978	0.11 🔴
u64|bcast|i8	1.8710	0.1982	0.11 🔴
f32|bcast|u8	3.1493	0.3548	0.11 🔴
c128|bcast|u8	3.0778	0.3567	0.12 🔴
f64|bcast|u8	2.8647	0.3550	0.12 🔴
f64|bcast|i8	2.8382	0.3550	0.13 🔴
char|bcast|u8	1.5715	0.2004	0.13 🔴
u32|bcast|u8	1.6123	0.2092	0.13 🔴
bool|strided|f16	5.3589	0.7299	0.14 🔴
c128|bcast|i16	3.2484	0.4548	0.14 🔴
bool|negrow|f16	11.2341	1.6957	0.15 🔴
f32|bcast|i8	3.1514	0.4795	0.15 🔴
bool|sliced|f16	10.7603	1.6681	0.16 🔴
c128|bcast|char	3.5035	0.5628	0.16 🔴
c128|bcast|u16	3.6305	0.6166	0.17 🔴
f32|bcast|char	3.1652	0.5588	0.18 🔴
u32|bcast|bool	1.6259	0.3021	0.19 🔴
i64|strided|i8	0.6632	0.1242	0.19 🔴
f64|bcast|char	2.9148	0.5615	0.19 🔴
f32|bcast|i16	3.1536	0.6089	0.19 🔴
f64|strided|char	0.6744	0.1303	0.19 🔴
f32|bcast|u16	3.1549	0.6132	0.19 🔴
f64|bcast|u16	2.8638	0.5966	0.21 🟠
i32|strided|u8	0.4569	0.0975	0.21 🟠
u32|strided|i16	0.4546	0.1028	0.23 🟠
u32|strided|u16	0.4547	0.1029	0.23 🟠
i32|negcol|i8	0.9034	0.2052	0.23 🟠
u32|negcol|i8	0.9032	0.2058	0.23 🟠
u16|bcast|char	1.7865	0.4086	0.23 🟠
i16|bcast|i8	1.5473	0.3549	0.23 🟠
i16|bcast|i16	1.7875	0.4120	0.23 🟠
f64|bcast|i16	2.8660	0.6834	0.24 🟠
u32|bcast|i16	1.8290	0.4414	0.24 🟠
char|bcast|char	1.7404	0.4233	0.24 🟠
char|bcast|u16	1.7612	0.4327	0.25 🟠
bool|C|f16	6.7123	1.6517	0.25 🟠
u8|bcast|i8	1.4393	0.3546	0.25 🟠
i64|bcast|u16	2.2411	0.5613	0.25 🟠
u16|bcast|u16	1.7871	0.4508	0.25 🟠
i32|bcast|bool	1.6313	0.4128	0.25 🟠
i16|bcast|u16	1.7805	0.4534	0.25 🟠
i64|bcast|u8	1.8659	0.4796	0.26 🟠
c128|bcast|i32	3.5397	0.9135	0.26 🟠
f16|bcast|f16	1.7593	0.4543	0.26 🟠
i64|bcast|i8	1.8528	0.4794	0.26 🟠
i64|bcast|char	2.1941	0.5704	0.26 🟠
char|bcast|bool	1.5623	0.4127	0.26 🟠
c128|bcast|u32	3.2429	0.8621	0.27 🟠
i16|bcast|bool	1.5287	0.4127	0.27 🟠
bool|bcast|i16	1.8070	0.4909	0.27 🟠
bool|bcast|i8	1.5112	0.4129	0.27 🟠
bool|bcast|u16	1.8610	0.5089	0.27 🟠
bool|bcast|u8	1.5005	0.4129	0.28 🟠
bool|F|f16	10.9523	3.1945	0.29 🟠
u8|bcast|bool	1.6394	0.4790	0.29 🟠
u64|bcast|bool	1.6370	0.4792	0.29 🟠
i64|bcast|bool	1.6368	0.4793	0.29 🟠
i8|bcast|bool	1.6353	0.4792	0.29 🟠
i32|bcast|i8	1.6298	0.4797	0.29 🟠
c128|bcast|f32	2.9914	0.8814	0.29 🟠
i32|bcast|u16	2.1051	0.6210	0.30 🟠
i32|bcast|u8	1.6245	0.4794	0.30 🟠
bool|bcast|f16	10.7720	3.1954	0.30 🟠
f64|negcol|i8	1.3202	0.3919	0.30 🟠
u32|bcast|i8	1.6031	0.4786	0.30 🟠
bool|negcol|f16	10.7650	3.2144	0.30 🟠
bool|T|f16	10.8092	3.2278	0.30 🟠
f64|negcol|u8	1.3199	0.3972	0.30 🟠
i32|bcast|char	1.8444	0.5605	0.30 🟠
i32|bcast|i32	2.7475	0.8479	0.31 🟠
char|bcast|i8	1.5396	0.4797	0.31 🟠
u16|bcast|i8	1.5372	0.4798	0.31 🟠
u16|bcast|u8	1.5318	0.4785	0.31 🟠
i16|bcast|u8	1.5279	0.4797	0.31 🟠
u16|bcast|i16	1.7396	0.5516	0.32 🟠
i64|strided|u16	0.6776	0.2150	0.32 🟠
i64|strided|char	0.6775	0.2158	0.32 🟠
i64|bcast|i16	2.1528	0.6862	0.32 🟠
u64|bcast|char	2.1580	0.6934	0.32 🟠
i32|bcast|u32	2.7680	0.8899	0.32 🟠
i8|bcast|i16	1.7830	0.5826	0.33 🟠
f32|bcast|i32	2.5413	0.8367	0.33 🟠
u32|strided|bool	0.4525	0.1494	0.33 🟠
char|bcast|i16	1.7562	0.5854	0.33 🟠
f32|bcast|u32	2.5479	0.8505	0.33 🟠
i8|bcast|u8	1.4281	0.4784	0.34 🟠
u64|bcast|i16	2.1845	0.7408	0.34 🟠
i32|bcast|i16	2.0800	0.7092	0.34 🟠
u64|bcast|u16	2.1781	0.7474	0.34 🟠
c128|strided|bool	1.3592	0.4746	0.35 🟠
bool|bcast|char	1.8310	0.6576	0.36 🟠
c128|bcast|bool	1.9800	0.7128	0.36 🟠
i64|bcast|f32	2.4956	0.9095	0.36 🟠
f64|bcast|f32	2.3416	0.8545	0.36 🟠
f32|bcast|f32	2.1590	0.7983	0.37 🟠
f64|bcast|i32	2.1736	0.8047	0.37 🟠
f64|strided|i8	0.6602	0.2449	0.37 🟠
u8|bcast|char	1.8215	0.6793	0.37 🟠
f32|strided|u8	0.4733	0.1775	0.38 🟠
f64|strided|u16	0.6748	0.2536	0.38 🟠
u32|bcast|char	1.8217	0.6860	0.38 🟠
i8|bcast|u16	1.8106	0.6838	0.38 🟠
i8|bcast|i32	1.8346	0.6994	0.38 🟠
f32|strided|i16	0.4639	0.1779	0.38 🟠
f32|strided|char	0.4639	0.1780	0.38 🟠
i8|bcast|char	1.7790	0.6844	0.38 🟠
f32|strided|u16	0.4639	0.1786	0.38 🟠
i16|bcast|char	1.7640	0.6795	0.39 🟠
u8|bcast|i16	1.7906	0.6901	0.39 🟠
u8|bcast|u16	1.8441	0.7146	0.39 🟠
c128|negcol|u8	1.3321	0.5168	0.39 🟠
f64|strided|u8	0.6603	0.2580	0.39 🟠
u64|negcol|i8	1.3261	0.5191	0.39 🟠
i32|strided|u16	0.4548	0.1786	0.39 🟠
i32|strided|char	0.4551	0.1789	0.39 🟠
u64|negcol|u8	1.3242	0.5212	0.39 🟠
i64|negcol|bool	1.3547	0.5341	0.39 🟠
i64|negcol|i8	1.3272	0.5235	0.39 🟠
u64|negcol|bool	1.3559	0.5349	0.39 🟠
u32|strided|u8	0.4564	0.1802	0.39 🟠
i64|bcast|i32	2.1195	0.8372	0.39 🟠
i64|negcol|u8	1.3262	0.5239	0.40 🟠
c128|negcol|i8	1.3337	0.5278	0.40 🟠
f16|bcast|u8	4.5833	1.8157	0.40 🟠
c128|bcast|u64	4.0657	1.6189	0.40 🟠
u32|bcast|i32	2.0450	0.8154	0.40 🟠
f32|negcol|u8	0.9269	0.3698	0.40 🟠
f64|bcast|u32	2.1256	0.8662	0.41 🟠
u32|bcast|u16	1.8552	0.7565	0.41 🟠
u32|bcast|u32	2.0508	0.8370	0.41 🟠
u32|negcol|u8	0.9033	0.3687	0.41 🟠
i64|strided|i16	0.6773	0.2768	0.41 🟠
i64|strided|bool	0.6739	0.2757	0.41 🟠
f64|strided|u64	1.6374	0.6715	0.41 🟠
u64|strided|i16	0.6774	0.2786	0.41 🟠
i64|strided|u8	0.6642	0.2734	0.41 🟠
f32|negcol|u32	2.2645	0.9331	0.41 🟠
f16|bcast|i8	4.5715	1.8849	0.41 🟠
u64|strided|char	0.6777	0.2800	0.41 🟠
u64|strided|u16	0.6772	0.2801	0.41 🟠
u32|bcast|f32	2.1745	0.8995	0.41 🟠
i32|bcast|f32	2.1462	0.8881	0.41 🟠
u64|strided|i8	0.6635	0.2751	0.41 🟠
u64|strided|u8	0.6635	0.2760	0.42 🟠
u64|strided|bool	0.6739	0.2816	0.42 🟠
c128|strided|f16	1.6986	0.7116	0.42 🟠
f64|strided|i16	0.6746	0.2858	0.42 🟠
f64|bcast|bool	1.6365	0.7126	0.44 🟠
f32|bcast|bool	1.6281	0.7124	0.44 🟠
u64|bcast|i32	1.9583	0.8683	0.44 🟠
f16|bcast|char	4.5725	2.0314	0.44 🟠
f32|strided|u64	2.0005	0.8941	0.45 🟠
f16|bcast|u16	4.6025	2.0777	0.45 🟠
i64|negcol|char	1.3523	0.6147	0.45 🟠
i32|strided|bool	0.4522	0.2075	0.46 🟠
i64|bcast|u32	2.0154	0.9318	0.46 🟠
i32|negcol|i16	0.9188	0.4249	0.46 🟠
u8|bcast|i32	1.8453	0.8648	0.47 🟠
char|bcast|i32	1.9353	0.9074	0.47 🟠
u64|bcast|u32	1.9509	0.9219	0.47 🟠
i64|F|i8	0.4027	0.1905	0.47 🟠
i16|bcast|f32	2.0267	0.9604	0.47 🟠
char|bcast|u32	1.9708	0.9349	0.47 🟠
u32|negcol|bool	0.9065	0.4309	0.48 🟠
i8|bcast|f32	2.0448	0.9735	0.48 🟠
i32|negcol|bool	0.9054	0.4323	0.48 🟠
u16|bcast|i32	1.8803	0.8989	0.48 🟠
f32|negcol|u64	3.5822	1.7257	0.48 🟠
f16|bcast|i32	4.7029	2.2863	0.49 🟠
f64|negcol|char	1.3556	0.6593	0.49 🟠
i16|bcast|u32	1.9314	0.9394	0.49 🟠
f16|bcast|f32	3.8049	1.8519	0.49 🟠
char|bcast|f32	1.9226	0.9368	0.49 🟠
bool|bcast|i32	1.8616	0.9108	0.49 🟠
i64|negcol|u16	1.3539	0.6627	0.49 🟠
f32|strided|u32	1.1334	0.5557	0.49 🟠
bool|bcast|u32	1.8413	0.9134	0.50 🟠
u8|bcast|u32	1.7389	0.8658	0.50 🟠
i8|bcast|u32	1.8755	0.9395	0.50 🟡
u32|negcol|u16	0.9183	0.4601	0.50 🟡
u64|bcast|f32	2.2217	1.1154	0.50 🟡
i16|bcast|i32	1.8713	0.9480	0.51 🟡
bool|bcast|f32	1.9075	0.9676	0.51 🟡
f16|bcast|u32	4.5027	2.2950	0.51 🟡
f64|negcol|u16	1.3549	0.6929	0.51 🟡
u16|bcast|u32	1.8897	0.9725	0.51 🟡
f32|strided|i8	0.4734	0.2537	0.54 🟡
u64|bcast|f16	6.2618	3.3806	0.54 🟡
i64|strided|f16	1.2818	0.6929	0.54 🟡
f32|negcol|i8	0.9277	0.5027	0.54 🟡
i64|bcast|f16	5.6754	3.0787	0.54 🟡
u8|bcast|f32	1.7622	0.9567	0.54 🟡
u64|negcol|i16	1.3524	0.7343	0.54 🟡
c128|strided|u64	2.2039	1.2023	0.55 🟡
i32|negcol|u8	0.9032	0.4992	0.55 🟡
u64|negcol|char	1.3517	0.7476	0.55 🟡
f16|bcast|i64	4.8163	2.6670	0.55 🟡
u32|strided|i8	0.4563	0.2543	0.56 🟡
i64|negcol|i16	1.3536	0.7559	0.56 🟡
u16|bcast|bool	0.7389	0.4127	0.56 🟡
i32|strided|i8	0.4567	0.2551	0.56 🟡
f64|negcol|bool	1.3556	0.7664	0.57 🟡
i16|bcast|f16	5.4506	3.0827	0.57 🟡
f32|sliced|u64	3.0199	1.7097	0.57 🟡
f32|T|u64	3.0152	1.7090	0.57 🟡
f32|C|u64	3.0135	1.7103	0.57 🟡
c128|strided|u16	0.7347	0.4170	0.57 🟡
i32|strided|i16	0.4548	0.2586	0.57 🟡
f64|negcol|u32	1.7397	0.9948	0.57 🟡
c128|strided|char	0.7280	0.4178	0.57 🟡
c128|strided|i16	0.7276	0.4178	0.57 🟡
i8|bcast|f16	5.4668	3.1439	0.58 🟡
char|bcast|f16	5.3379	3.0822	0.58 🟡
bool|strided|i16	0.2695	0.1561	0.58 🟡
f64|negcol|u64	3.1539	1.8355	0.58 🟡
f32|F|u64	3.0336	1.7665	0.58 🟡
f64|negcol|i16	1.3547	0.7917	0.58 🟡
u8|bcast|f16	5.2612	3.0841	0.59 🟡
u32|bcast|f16	5.3163	3.1225	0.59 🟡
u32|strided|char	0.4546	0.2674	0.59 🟡
u16|bcast|f16	5.3294	3.1352	0.59 🟡
f32|bcast|u64	2.7264	1.6141	0.59 🟡
c128|negcol|char	1.4568	0.8674	0.60 🟡
f64|strided|bool	0.6747	0.4057	0.60 🟡
f64|F|u64	2.9212	1.7660	0.60 🟡
f64|T|u64	2.9211	1.7783	0.61 🟡
f64|strided|i32	0.9748	0.5941	0.61 🟡
c128|strided|u8	0.6754	0.4130	0.61 🟡
f64|C|u64	2.9233	1.7945	0.61 🟡
bool|C|bool	0.0236	0.0145	0.61 🟡
c128|negcol|u16	1.4550	0.8954	0.62 🟡
i32|bcast|f16	4.9837	3.0758	0.62 🟡
f64|negrow|u64	2.9567	1.8273	0.62 🟡
c128|strided|i8	0.6741	0.4167	0.62 🟡
c128|C|u64	3.2339	2.0020	0.62 🟡
f64|sliced|u64	2.9367	1.8185	0.62 🟡
c128|T|u64	3.2350	2.0368	0.63 🟡
c128|sliced|u64	3.2747	2.0622	0.63 🟡
bool|strided|i8	0.2349	0.1487	0.63 🟡
c128|negcol|u64	3.3406	2.1150	0.63 🟡
c128|negcol|i16	1.4549	0.9240	0.64 🟡
f64|strided|u32	0.8517	0.5437	0.64 🟡
u32|negcol|i16	0.9193	0.5895	0.64 🟡
i32|negcol|char	0.9179	0.5891	0.64 🟡
c128|negrow|u64	3.3556	2.1623	0.64 🟡
f32|negrow|u32	1.3383	0.8680	0.65 🟡
f64|bcast|f16	5.4475	3.5734	0.66 🟡
f64|bcast|u64	2.4326	1.5958	0.66 🟡
c128|bcast|f16	5.7581	3.7818	0.66 🟡
c128|F|u64	3.2345	2.1316	0.66 🟡
f32|negcol|u16	0.9102	0.6006	0.66 🟡
f32|negcol|char	0.9092	0.6016	0.66 🟡
i8|sliced|i8	0.0456	0.0306	0.67 🟡
f16|bcast|u64	4.6871	3.1504	0.67 🟡
u8|negcol|bool	0.4497	0.3037	0.68 🟡
i64|negcol|i32	1.3612	0.9355	0.69 🟡
f32|negcol|i16	0.9095	0.6264	0.69 🟡
c128|negcol|u32	1.7738	1.2236	0.69 🟡
f32|T|u32	1.3157	0.9193	0.70 🟡
f32|sliced|u32	1.3321	0.9339	0.70 🟡
f16|T|u64	4.0011	2.8231	0.71 🟡
c128|strided|u32	0.9967	0.7079	0.71 🟡
f32|C|u32	1.3165	0.9400	0.71 🟡
f16|negrow|u64	4.0182	2.8741	0.72 🟡
f32|F|u32	1.3157	0.9411	0.72 🟡
f16|C|u64	3.9940	2.8596	0.72 🟡
f16|F|u64	4.0070	2.8742	0.72 🟡
i32|negcol|u16	0.9187	0.6591	0.72 🟡
f16|sliced|u64	3.9947	2.8694	0.72 🟡
i64|negcol|u32	1.3587	0.9775	0.72 🟡
c128|F|bool	0.8137	0.5865	0.72 🟡
u64|negcol|u32	1.3581	0.9813	0.72 🟡
f16|strided|u64	2.1976	1.6060	0.73 🟡
f16|negcol|u64	4.3789	3.2042	0.73 🟡
f32|bcast|f16	4.0202	2.9592	0.74 🟡
u32|bcast|i64	1.5893	1.1785	0.74 🟡
u8|C|u8	0.0419	0.0311	0.74 🟡
f32|bcast|i64	2.1225	1.5817	0.75 🟡
f16|bcast|bool	1.5366	1.1786	0.77 🟡
u64|negrow|f32	1.0318	0.7941	0.77 🟡
f16|bcast|f64	2.6438	2.0363	0.77 🟡
i64|strided|i32	0.6772	0.5280	0.78 🟡
char|bcast|u64	1.9775	1.5897	0.80 🟡
u64|strided|u32	0.6767	0.5474	0.81 🟡
u32|negcol|char	0.9199	0.7447	0.81 🟡
f16|negcol|f64	2.5426	2.0858	0.82 🟡
f32|negcol|bool	0.8970	0.7375	0.82 🟡
f32|strided|bool	0.4502	0.3705	0.82 🟡
f32|negrow|i64	1.9434	1.6091	0.83 🟡
i64|strided|u32	0.6769	0.5626	0.83 🟡
bool|strided|bool	0.2465	0.2057	0.83 🟡
c128|negcol|i32	1.4319	1.2056	0.84 🟡
c128|negrow|bool	0.8742	0.7391	0.85 🟡
u64|strided|i32	0.6775	0.5767	0.85 🟡
f64|bcast|i64	1.8789	1.6027	0.85 🟡
f32|strided|i64	0.9461	0.8073	0.85 🟡
f16|bcast|i16	2.4768	2.1173	0.85 🟡
f16|strided|f64	1.2617	1.0841	0.86 🟡
f32|negcol|i64	1.9531	1.6792	0.86 🟡
bool|negcol|bool	0.4863	0.4193	0.86 🟡
c128|C|bool	0.8218	0.7095	0.86 🟡
i32|T|i8	0.4088	0.3535	0.86 🟡
c128|bcast|i64	1.8134	1.5776	0.87 🟡
bool|strided|u16	0.2694	0.2351	0.87 🟡
i64|T|i8	0.4090	0.3570	0.87 🟡
bool|strided|char	0.2692	0.2350	0.87 🟡
c128|T|bool	0.8127	0.7115	0.88 🟡
bool|strided|u8	0.2350	0.2058	0.88 🟡
f16|negrow|f64	2.5575	2.2402	0.88 🟡
f16|C|f64	2.5232	2.2257	0.88 🟡
bool|bcast|u64	1.6358	1.4462	0.88 🟡
i64|C|i8	0.4026	0.3574	0.89 🟡
f32|sliced|i64	1.8989	1.6893	0.89 🟡
f32|C|i64	1.8728	1.6669	0.89 🟡
bool|negcol|i8	0.4657	0.4158	0.89 🟡
u8|strided|f16	0.7678	0.6859	0.89 🟡
f32|T|i64	1.8737	1.6776	0.90 🟡
i32|F|i8	0.3947	0.3533	0.90 🟡
u32|C|i8	0.3943	0.3531	0.90 🟡
bool|negcol|u8	0.4642	0.4158	0.90 🟡
bool|negrow|u8	0.4646	0.4162	0.90 🟡
f32|F|i64	1.8767	1.6815	0.90 🟡
i32|C|i8	0.3943	0.3533	0.90 🟡
u32|T|i8	0.3944	0.3535	0.90 🟡
u32|F|i8	0.3942	0.3536	0.90 🟡
bool|sliced|u8	0.4582	0.4112	0.90 🟡
f16|sliced|f64	2.5141	2.2656	0.90 🟡
i8|bcast|i64	1.6156	1.4696	0.91 🟡
c128|sliced|bool	0.7833	0.7135	0.91 🟡
i16|bcast|f64	1.6389	1.4968	0.91 🟡
i32|bcast|i64	1.5835	1.4494	0.92 🟡
u8|bcast|f64	1.7224	1.5850	0.92 🟡
i8|bcast|u64	1.5858	1.4630	0.92 🟡
u16|strided|f16	0.7439	0.6875	0.92 🟡
f16|F|f64	2.4132	2.2400	0.93 🟡
char|bcast|i64	1.6684	1.5591	0.93 🟡
u64|negrow|f16	1.9400	1.8196	0.94 🟡
f64|sliced|u32	1.0641	1.0005	0.94 🟡
f16|bcast|c128	3.5628	3.3579	0.94 🟡
i32|T|u8	0.3735	0.3536	0.95 🟡
u64|bcast|i64	1.6390	1.5547	0.95 🟡
f32|bcast|f64	1.6309	1.5473	0.95 🟡
f16|T|f64	2.3716	2.2520	0.95 🟡
f64|negrow|u32	1.0785	1.0264	0.95 🟡
i32|bcast|u64	1.6317	1.5597	0.96 🟡
u64|sliced|f16	1.8987	1.8166	0.96 🟡
f64|F|u32	1.0542	1.0102	0.96 🟡
u64|C|f16	1.8664	1.7950	0.96 🟡
f64|C|u32	1.0543	1.0174	0.97 🟡
bool|bcast|i64	1.6615	1.6041	0.97 🟡
bool|bcast|f64	1.5764	1.5300	0.97 🟡
i32|strided|f16	0.7054	0.6857	0.97 🟡
c128|bcast|f64	1.6403	1.5960	0.97 🟡
u16|bcast|i64	1.6091	1.5658	0.97 🟡
char|bcast|f64	1.6014	1.5610	0.97 🟡
u8|strided|bool	0.2461	0.2405	0.98 🟡
i16|bcast|u64	1.6098	1.5743	0.98 🟡
i8|strided|bool	0.2458	0.2405	0.98 🟡
i64|bcast|f64	1.5806	1.5487	0.98 🟡
i8|bcast|f64	1.5900	1.5581	0.98 🟡
i32|bcast|f64	1.5886	1.5573	0.98 🟡
f32|negcol|i32	0.9468	0.9285	0.98 🟡
u8|bcast|i64	1.6199	1.5892	0.98 🟡
f64|negcol|i64	1.7569	1.7243	0.98 🟡
u32|bcast|f64	1.6055	1.5768	0.98 🟡
i64|bcast|i64	1.6563	1.6281	0.98 🟡
i16|bcast|i64	1.6036	1.5782	0.98 🟡
i64|bcast|u64	1.6060	1.5873	0.99 🟡
f64|bcast|f64	1.6164	1.5989	0.99 🟡
u8|bcast|u64	1.5978	1.5839	0.99 🟡
u16|bcast|u64	1.5788	1.5677	0.99 🟡
f64|T|u32	1.0535	1.0469	0.99 🟡
f64|negrow|i64	1.7433	1.7328	0.99 🟡
c128|negcol|bool	0.8538	0.8498	1.00 🟡
u64|bcast|u64	1.6033	1.5959	1.00 🟡
u64|T|i16	0.4115	0.4099	1.00 🟡
u32|bcast|u64	1.5699	1.5676	1.00 🟡

1568 comparable cells (1800 NumSharp rows; 381 lagging <1.0).