test_loopy.py

            ],
            [
                "a[i] = 5+i+j",
                ],
            [
                lp.GlobalArg("a", np.float32),
                lp.ValueArg("n", np.int32, approximately=1000),
                ],
            assumptions="n>=1")

    knl = lp.tag_inames(knl, dict(j="ilp"))

    from loopy.check import WriteRaceConditionError
    import pytest
    with pytest.raises(WriteRaceConditionError):
        list(lp.generate_loop_schedules(knl))




def test_ilp_write_race_avoidance_local(ctx_factory):
    ctx = ctx_factory()

    knl = lp.make_kernel(ctx.devices[0],
            "{[i,j]: 0<=i<16 and 0<=j<17 }",
            [
                "<> a[i] = 5+i+j",
                ],
            [])

    knl = lp.tag_inames(knl, dict(i="l.0", j="ilp"))

    for k in lp.generate_loop_schedules(knl):
        assert k.temporary_variables["a"].shape == (16,17)




def test_ilp_write_race_avoidance_private(ctx_factory):
    ctx = ctx_factory()

    knl = lp.make_kernel(ctx.devices[0],
            "{[j]: 0<=j<16 }",
            [
                "<> a = 5+j",
                ],
            [])

    knl = lp.tag_inames(knl, dict(j="ilp"))

    for k in lp.generate_loop_schedules(knl):
        assert k.temporary_variables["a"].shape == (16,)

# }}}




def test_write_parameter(ctx_factory):
    dtype = np.float32
    ctx = ctx_factory()

    knl = lp.make_kernel(ctx.devices[0], [
            "{[i,j]: 0<=i,j<n }",
            ],
            """
                a = sum((i,j), i*j)
                b = sum(i, sum(j, i*j))
                n = 15
                """,
            [
                lp.GlobalArg("a", dtype, shape=()),
                lp.GlobalArg("b", dtype, shape=()),
                lp.ValueArg("n", np.int32, approximately=1000),
                ],
            assumptions="n>=1")

    import pytest
    with pytest.raises(RuntimeError):
        lp.CompiledKernel(ctx, knl).get_code()




# {{{ arg guessing

def test_arg_shape_guessing(ctx_factory):
    ctx = ctx_factory()

    knl = lp.make_kernel(ctx.devices[0], [
            "{[i,j]: 0<=i,j<n }",
            ],
            """
                a = 1.5 + sum((i,j), i*j)
                b[i, j] = i*j
                c[i+j, j] = b[j,i]
                """,
            [
                lp.GlobalArg("a", shape=lp.auto),
                lp.GlobalArg("b", shape=lp.auto),
                lp.GlobalArg("c", shape=lp.auto),
                lp.ValueArg("n"),
                ],
            assumptions="n>=1")

    print knl
    print lp.CompiledKernel(ctx, knl).get_highlighted_code()




def test_arg_guessing(ctx_factory):
    ctx = ctx_factory()

    knl = lp.make_kernel(ctx.devices[0], [
            "{[i,j]: 0<=i,j<n }",
            ],
            """
                a = 1.5 + sum((i,j), i*j)
                b[i, j] = i*j
                c[i+j, j] = b[j,i]
                """,
            assumptions="n>=1")

    print knl
    print lp.CompiledKernel(ctx, knl).get_highlighted_code()

def test_arg_guessing_with_reduction(ctx_factory):
    #logging.basicConfig(level=logging.DEBUG)
    ctx = ctx_factory()

    knl = lp.make_kernel(ctx.devices[0], [
            "{[i,j]: 0<=i,j<n }",
            ],
            """
                a = 1.5 + sum((i,j), i*j)
                d = 1.5 + sum((i,j), b[i,j])
                b[i, j] = i*j
                c[i+j, j] = b[j,i]
                """,
            assumptions="n>=1")

    print knl
    print lp.CompiledKernel(ctx, knl).get_highlighted_code()

# }}}

def test_nonlinear_index(ctx_factory):
    ctx = ctx_factory()

    knl = lp.make_kernel(ctx.devices[0], [
            "{[i,j]: 0<=i,j<n }",
            ],
            """
                a[i*i] = 17
                """,
            [
                lp.GlobalArg("a", shape="n"),
                lp.ValueArg("n"),
                ],
            assumptions="n>=1")

    print knl
    print lp.CompiledKernel(ctx, knl).get_highlighted_code()


def test_triangle_domain(ctx_factory):
    ctx = ctx_factory()

    knl = lp.make_kernel(ctx.devices[0], [
            "{[i,j]: 0<=i,j<n and i <= j}",
            ],
            "a[i,j] = 17",
            assumptions="n>=1")

    print knl
    print lp.CompiledKernel(ctx, knl).get_highlighted_code()





def test_array_with_offset(ctx_factory):
    ctx = ctx_factory()
    queue = cl.CommandQueue(ctx)

    n = 5

    knl = lp.make_kernel(ctx.devices[0], [
            "{[i,j]: 0<=i<n and 0<=j<m }",
            ],
            """
                b[i,j] = 2*a[i,j]
                """,
            assumptions="n>=1 and m>=1",
            default_offset=lp.auto)

    cknl = lp.CompiledKernel(ctx, knl)

    a_full = cl.clrandom.rand(queue, (n, n), np.float64)
    a = a_full[3:10]

    print cknl.get_highlighted_code({"a": a.dtype}, {"a": True, "b": False})
    evt, (b,) = cknl(queue, a=a)

    import numpy.linalg as la
    assert la.norm(b.get() - 2*a.get()) < 1e-13




if __name__ == "__main__":
    import sys
    if len(sys.argv) > 1:
        exec(sys.argv[1])
    else:
        from py.test.cmdline import main
        main([__file__])

# vim: foldmethod=marker