Pulse wave velocity (PWV) is a surrogate marker of arterial stiffness linked to cardiovascular morbidity. Pulse wave imaging (PWI) is a technique developed by our group for imaging the pulse wave propagation in vivo. PWI requires high temporal and spatial resolution, which conventional ultrasonic imaging is unable to simultaneously provide. Coherent compounding is known to address this tradeoff and provides full aperture images at high frame rates. This study aims to implement PWI using coherent compounding within a GPU-accelerated framework. The results of the implemented method were validated using a silicone phantom against static mechanical testing. Reproducibility of the measured PWVs was assessed in the right common carotid of six healthy subjects (n = 6) approximately 10-15 mm before the bifurcation during two cardiac cycles over the course of 1-3 d. Good agreement of the measured PWVs (3.97 ± 1.21 m s-1, 4.08 ± 1.15 m s-1, p = 0.74) was obtained. The effects of frame rate, transmission angle and number of compounded plane waves on PWI performance were investigated in the six healthy volunteers. Performance metrics such as the reproducibility of the PWVs, the coefficient of determination (r 2), the SNR of the PWI axial wall velocities ([Formula: see text]) and the percentage of lateral positions where the pulse wave appears to arrive at the same time-point, indicating inadequacy of the temporal resolution (i.e. temporal resolution misses) were used to evaluate the effect of each parameter. Compounding plane waves transmitted at 1° increments with a linear array yielded optimal performance, generating significantly higher r 2 and [Formula: see text] values (p ⩽ 0.05). Higher frame rates (⩾1667 Hz) produced improvements with significant gains in the r 2 coefficient (p ⩽ 0.05) and significant increase in both r 2 and [Formula: see text] from single plane wave imaging to 3-plane wave compounding (p ⩽ 0.05). Optimal performance was established at 2778 Hz with 3 plane waves and at 1667 Hz with 5 plane waves.