diff --git a/examples/matrix-multiply.py b/examples/matrix-multiply.py index 142591f14e7bbeb568c9558386c87a64fd7bf10a..c8fab12e19b5d4499bd241e53c7433049ad7e642 100644 --- a/examples/matrix-multiply.py +++ b/examples/matrix-multiply.py @@ -161,8 +161,12 @@ h_c = numpy.empty((c_height, c_width)).astype(numpy.float32) kernel_params = {"block_size": block_size, "w_a":a_width, "h_a":a_height, "w_b":b_width} +if "NVIDIA" in queue.device.vendor: + options = "-cl-mad-enable -cl-fast-relaxed-math" +else: + options = None prg = cl.Program(ctx, KERNEL_CODE % kernel_params, - ).build(options="-cl-mad-enable -cl-fast-relaxed-math") + ).build(options=options) kernel = prg.matrixMul #print prg.binaries[0]