weird numba behavior when assigning to an array - numpy

Question

I have a function I'm jitting with #jit(nopython=True).
Inside it has a loop that does a bunch of stuff, calculates a correlation and then assigns that to a preallocated output array. Both the target array and the correlation have the same type (np.float32), but for some reason the assignment makes the function take 100X as long.
To make things even more strange, if i instead assign a meaningless float np.float32(i*1.01) instead of my correlation value, the function runs at an appropriate speed.
Given that everything is the same type, they should both run at the same speed no?
corrs = np.zeros(a.shape[0], dtype=np.float32)
for i in range(lb, a.shape[0]):
#a bunch of calculations happens here
correl = np.float32(covar/(a_std*b_std))
testval = np.float32(i*1.01)
#doing this makes the function take FOREVER
#corrs[i] = correl
#but doing this runs very quickly, even though it is also a np.float32
#corrs[i] = testval
here is a runable example. I added an argument called "assign" that if true will assign what I want to assign, and if false will assign my useless test value.
#jit(nopython=True)
def hist_corr_loop(a, b, lb = 1000, assign=True):
flb = np.float32(lb)
a_mu, b_mu = a[0], b[0]
for i in range(1, lb):
a_mu+=a[i]
b_mu+=b[i]
a_mu = a_mu/flb
b_mu = b_mu/flb
a_var, b_var = np.float32(0.0), np.float32(0.0)
for i in range(lb):
a_var += np.square(a[i] - a_mu)
b_var += np.square(b[i] - b_mu)
a_var = a_var/flb
b_var = b_var/flb
corrs = np.zeros(a.shape[0], dtype=np.float32)
for i in range(lb, a.shape[0]):
#calculate new means and stdevs
_a_mu = a_mu
_b_mu = b_mu
a_mu = _a_mu + (a[i] - a[i-lb])/flb
b_mu = _b_mu + (b[i] - b[i-lb])/flb
a_var += (a[i] - a[i-lb])*(a[i] - a_mu + a[i-lb] - _a_mu)/flb
b_var += (b[i] - b[i-lb])*(b[i] - b_mu + b[i-lb] - _b_mu)/flb
a_std = np.sqrt(a_var)#**0.5
b_std = np.sqrt(b_var)#**0.5
covar = np.float32(0.0)
for j in range(i-lb+1,i+1):
covar += (a[j] - a_mu)*(b[j] - b_mu)
covar = covar/flb
correl = np.float32(covar/(a_std*b_std))
testval = np.float32(i*1.01)
if assign:
corrs[i] = correl
else:
corrs[i] = testval
return corrs
to run:
n = 10000000
a = np.random.random(n)
b = np.random.random(n)
%timeit hist_corr_loop(a,b,1000, True)
%timeit hist_corr_loop(a,b, 1000, False)
I get
%timeit hist_corr_loop(a,b,1000, True)
10.5 s ± 52.3 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
%timeit hist_corr_loop(a,b, 1000, False)
220 ms ± 1.05 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
10 seconds vs 220 ms.