Merge remote-tracking branch 'origin/master'

README.md

@@ -19,8 +19,8 @@ The point of this package is to provide operations that are accelerated by SIMD.
 
 # FAQ
 
-### Why are there so many `a = a[:len(a)]` lines?
-This is mainly done to eliminate bounds checking in a loop. The idea is the bounds of the slice is checked early on, and if need be, panics early. Then if everything is normal, there won't be bounds checking while in the loop.
+### Why are there so many `b = b[:len(a)]` lines?
+This is mainly done to eliminate bounds checking in a loop. The idea is the bounds of the slice is checked early on, and if need be, panics early. Then if everything is normal, there won't be bounds checking while in the loop. This also means that `b` must be at least `len(a)`, otherwise a panic will occur.
 
 To check for boundschecking and bounds check elimination (an amazing feature that landed in Go 1.7), compile your programs with `-gcflags='-d=ssa/check_bce/debug=1'`. 
 

arith.go

@@ -5,7 +5,6 @@ import "github.com/chewxy/math32"
 // Pow performs  elementwise
 //		a̅ ^ b̅
 func Pow(a, b []float32) {
-	a = a[:len(a)]
 	b = b[:len(a)]
 	for i, v := range a {
 		switch b[i] {
@@ -24,7 +23,6 @@ func Pow(a, b []float32) {
 }
 
 func Mod(a, b []float32) {
-	a = a[:len(a)]
 	b = b[:len(a)]
 	for i, v := range a {
 		a[i] = math32.Mod(v, b[i])
@@ -93,7 +91,6 @@ func PowOfR(a []float32, s float32) {
 
 // Max takes two slices, a̅ + b̅, and compares them elementwise. The highest value is put into a̅.
 func Max(a, b []float32) {
-	a = a[:len(a)]
 	b = b[:len(a)]
 
 	for i, v := range a {
@@ -106,7 +103,6 @@ func Max(a, b []float32) {
 
 // Min takes two slices, a̅ + b̅ and compares them elementwise. The lowest value is put into a̅.
 func Min(a, b []float32) {
-	a = a[:len(a)]
 	b = b[:len(a)]
 
 	for i, v := range a {

go.go

@@ -6,7 +6,6 @@ import "github.com/chewxy/math32"
 
 // Add performs a̅ + b̅. a̅ will be clobbered
 func Add(a, b []float32) {
-	a = a[:len(a)]
 	b = b[:len(a)]
 	for i, v := range a {
 		a[i] = v + b[i]
@@ -15,7 +14,6 @@ func Add(a, b []float32) {
 
 // Sub performs a̅ - b̅. a̅ will be clobbered
 func Sub(a, b []float32) {
-	a = a[:len(a)]
 	b = b[:len(a)]
 	for i, v := range a {
 		a[i] = v - b[i]
@@ -24,7 +22,6 @@ func Sub(a, b []float32) {
 
 // Mul performs a̅ × b̅. a̅ will be clobbered
 func Mul(a, b []float32) {
-	a = a[:len(a)]
 	b = b[:len(a)]
 	for i, v := range a {
 		a[i] = v * b[i]
@@ -33,7 +30,6 @@ func Mul(a, b []float32) {
 
 // Div performs a̅ ÷ b̅. a̅ will be clobbered
 func Div(a, b []float32) {
-	a = a[:len(a)]
 	b = b[:len(a)]
 	for i, v := range a {
 		if b[i] == 0 {

incr.go

@@ -4,7 +4,6 @@ import "github.com/chewxy/math32"
 
 // IncrAdd performs a̅ + b̅ and then adds it elementwise to the incr slice
 func IncrAdd(a, b, incr []float32) {
-	a = a[:len(a)]
 	b = b[:len(a)]
 	incr = incr[:len(a)]
 	for i, v := range a {
@@ -14,7 +13,6 @@ func IncrAdd(a, b, incr []float32) {
 
 // IncrSub performs a̅ = b̅ and then adds it elementwise to the incr slice
 func IncrSub(a, b, incr []float32) {
-	a = a[:len(a)]
 	b = b[:len(a)]
 	incr = incr[:len(a)]
 	for i, v := range a {
@@ -24,7 +22,6 @@ func IncrSub(a, b, incr []float32) {
 
 // IncrMul performs a̅ × b̅ and then adds it elementwise to the incr slice
 func IncrMul(a, b, incr []float32) {
-	a = a[:len(a)]
 	b = b[:len(a)]
 	incr = incr[:len(a)]
 	for i, v := range a {
@@ -33,7 +30,6 @@ func IncrMul(a, b, incr []float32) {
 }
 
 func IncrDiv(a, b, incr []float32) {
-	a = a[:len(a)]
 	b = b[:len(a)]
 	incr = incr[:len(a)]
 	for i, v := range a {
@@ -47,7 +43,6 @@ func IncrDiv(a, b, incr []float32) {
 
 // IncrDiv performs a̅ ÷ b̅. then adds it to incr
 func IncrPow(a, b, incr []float32) {
-	a = a[:len(a)]
 	b = b[:len(a)]
 	incr = incr[:len(a)]
 	for i, v := range a {
@@ -68,7 +63,6 @@ func IncrPow(a, b, incr []float32) {
 
 // IncrMod performs a̅ % b̅ then adds it to incr
 func IncrMod(a, b, incr []float32) {
-	a = a[:len(a)]
 	b = b[:len(a)]
 	incr = incr[:len(a)]
 
@@ -80,7 +74,6 @@ func IncrMod(a, b, incr []float32) {
 // Scale multiplies all values in the slice by the scalar and then increments the incr slice
 // 		incr += a̅ * s
 func IncrScale(a []float32, s float32, incr []float32) {
-	a = a[:len(a)]
 	incr = incr[:len(a)]
 	for i, v := range a {
 		incr[i] += v * s
@@ -96,7 +89,6 @@ func IncrScaleInv(a []float32, s float32, incr []float32) {
 /// IncrScaleInvR divides all numbers in the slice by a scalar and then increments the incr slice
 // 		incr += s / a̅
 func IncrScaleInvR(a []float32, s float32, incr []float32) {
-	a = a[:len(a)]
 	incr = incr[:len(a)]
 	for i, v := range a {
 		incr[i] += s / v
@@ -106,7 +98,6 @@ func IncrScaleInvR(a []float32, s float32, incr []float32) {
 // IncrTrans adds all the values in the slice by a scalar and then increments the incr slice
 // 		incr += a̅ + s
 func IncrTrans(a []float32, s float32, incr []float32) {
-	a = a[:len(a)]
 	incr = incr[:len(a)]
 	for i, v := range a {
 		incr[i] += v + s
@@ -122,7 +113,6 @@ func IncrTransInv(a []float32, s float32, incr []float32) {
 // IncrTransInvR subtracts all the numbers in a slice from a scalar and then increments the incr slice
 //	 incr += s - a̅
 func IncrTransInvR(a []float32, s float32, incr []float32) {
-	a = a[:len(a)]
 	incr = incr[:len(a)]
 	for i, v := range a {
 		incr[i] += s - v
@@ -132,7 +122,6 @@ func IncrTransInvR(a []float32, s float32, incr []float32) {
 // IncrPowOf performs elementwise power function and then increments the incr slice
 //		incr += a̅ ^ s
 func IncrPowOf(a []float32, s float32, incr []float32) {
-	a = a[:len(a)]
 	incr = incr[:len(a)]
 	for i, v := range a {
 		incr[i] += math32.Pow(v, s)
@@ -142,7 +131,6 @@ func IncrPowOf(a []float32, s float32, incr []float32) {
 // PowOfR performs elementwise power function below and then increments the incr slice.
 //		incr += s ^ a̅
 func IncrPowOfR(a []float32, s float32, incr []float32) {
-	a = a[:len(a)]
 	incr = incr[:len(a)]
 	for i, v := range a {
 		incr[i] += math32.Pow(s, v)