gammaln — Compute the natural logarithm of the gamma function element-wise in MATLAB and RunMat.

Y = gammaln(A) evaluates log(gamma(A)) for real nonnegative inputs while avoiding the overflow that can occur when computing gamma(A) first.

Syntax

Y = gammaln(A)

Inputs

Returns

Errors

How gammaln works

• gammaln(A) applies the log-gamma function element-by-element while preserving the input tensor shape.
• Double inputs return double results; single tensors preserve single dtype metadata with single-rounded output values.
• gammaln(0) returns Inf; gammaln(Inf) returns Inf; gammaln(NaN) returns NaN.
• Scalar integer, logical, and character inputs are promoted through RunMat's ordinary numeric coercion path for compatibility with existing elementwise builtins.
• Negative, complex, string, and sparse inputs produce stable typed errors.
• Real GPU tensors stay on device when the provider implements unary_gammaln; otherwise RunMat gathers the tensor, evaluates on the host, and returns a host value with the computed results.

GPU memory and residency

Yes when the active provider implements unary_gammaln for real-valued gpuArray inputs. Providers without that hook trigger a host fallback, so the computed result is returned as a host tensor rather than a resident gpuArray.

Examples

Evaluate the log-gamma function at a scalar

y = gammaln(5)

Expected output:

y = 3.1781

Evaluate a half-integer input

y = gammaln(0.5)

Expected output:

y = 0.5724

Apply gammaln element-wise to an array

A = [0.5 1 2 5];
Y = gammaln(A)

Expected output:

Y = [0.5724 0 0 3.1781]

Avoid gamma overflow for large inputs

y = gammaln(171)

Expected output:

y = 706.5731

Run gammaln on GPU data

G = gpuArray([0.5 1 5]);
out = gammaln(G);
result = gather(out)

Expected output:

result = [0.5724 0 3.1781]

Using gammaln with coding agents

Open a RunMat example with live inputs, then ask the agent to explain how gammaln changes the result.

FAQ

Related Math functions

About RunMat

RunMat is an open-source runtime that executes MATLAB-syntax code blazing on any GPU. It is licensed under the Apache 2.0 license.

• RunMat automatically optimizes your math for GPU execution on Apple, Nvidia, and AMD hardware. No code changes needed. Simulations that took hours now take minutes.
• Start running code in seconds. RunMat runs in the browser, on the desktop, or from the CLI. No license server, no IT ticket.

Getting started · Benchmarks · Pricing