test_pass_storage_rewrite.py 17.6 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13
import tvm

def test_storage_share():
    m = tvm.var('m')
    l = tvm.var('l')
    A = tvm.placeholder((m, l), name='A')
    num_stage = 5
    B = A
    for t in range(num_stage):
        B = tvm.compute((m, l), lambda i, j: B[i, j] + (t+1), name='A%d' % t)

    s = tvm.create_schedule(B.op)
    bounds = tvm.schedule.InferBound(s)
14
    assert isinstance(bounds, tvm.container.Map)
15 16 17
    stmt = tvm.schedule.ScheduleOps(s, bounds)
    Ab = tvm.decl_buffer(A.shape, A.dtype, name='A')
    Bb = tvm.decl_buffer(B.shape, B.dtype, name='B')
18
    stmt = tvm.ir_pass.StorageFlatten(stmt, {A: Ab, B: Bb}, 64)
19 20 21
    stmt = tvm.ir_pass.CanonicalSimplify(stmt)
    stmt = tvm.ir_pass.Simplify(stmt)
    stmt = tvm.ir_pass.StorageRewrite(stmt)
22 23 24 25 26 27 28 29 30
    # verify only have one allocations.
    # verify inplace folding works
    num_alloc = [0]
    def verify(n):
        if isinstance(n, tvm.stmt.Allocate):
            num_alloc[0] += 1
    tvm.ir_pass.PostOrderVisit(stmt, verify)
    assert num_alloc[0] == 1

31 32 33 34 35 36 37 38 39 40
def register_mem(scope_tb, max_bits):
    #Register mem
    @tvm.register_func("tvm.info.mem.%s" % scope_tb)
    def mem_info_inp_buffer():
        return tvm.make.node("MemoryInfo",
                        unit_bits= 16,
                        max_simd_bits=32,
                        max_num_bits=max_bits,
                        head_address=None)

41
def test_alloc_seq():
42 43 44 45 46
    scope_tb = "local.L0A"
    max_bits = 1024 * 1024 * 1024

    register_mem(scope_tb, max_bits)

47 48 49 50
    ib = tvm.ir_builder.create()
    n = tvm.var("n")
    with ib.for_range(0, n, name="i") as i:
        with ib.for_range(0, 10, name="j") as j:
51
            A = ib.allocate("float32", 200, name="A", scope=scope_tb)
52 53
            A[j] = 1.2
        with ib.for_range(0, 10, name="j") as j:
54
            A = ib.allocate("float32", 200, name="B", scope=scope_tb)
55 56 57 58 59 60 61 62 63 64 65 66
            A[j] = 1.3

    body = ib.get()
    body = tvm.ir_pass.StorageRewrite(body)
    num_alloc = [0]
    def verify(n):
        if isinstance(n, tvm.stmt.Allocate):
            num_alloc[0] += 1
            assert n.extents[0].value == 200
    tvm.ir_pass.PostOrderVisit(body, verify)
    assert num_alloc[0] == 1

67 68 69 70 71
def test_alloc_different_dtypes():
    def stmt_generater(dtype_list, length):
        ib = tvm.ir_builder.create()
        base_dtype = dtype_list[0]
        global_a = tvm.placeholder((length,), name = "global_a", dtype = base_dtype)
72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92
        assert len(dtype_list) == 4
        with ib.for_range(0, length, name="j") as j:
            dtype = dtype_list[0]
            A = ib.allocate(dtype, length, name="A", scope="local.L0A")
            A[j] = tvm.const(1, dtype = dtype)
        with ib.for_range(0, length, name="j") as j:
            dtype = dtype_list[1]
            B = ib.allocate(dtype, length, name="B", scope="local.L0A")
            B[j] = tvm.const(1, dtype = dtype)
        with ib.for_range(0, length, name="j") as j:
            dtype = dtype_list[2]
            C = ib.allocate(dtype, length, name="C", scope="local.L0A")
            C[j] = tvm.const(1, dtype = dtype)
        with ib.for_range(0, length, name="j") as j:
            dtype = dtype_list[3]
            D = ib.allocate(dtype, length, name="D", scope="local.L0A")
            D[j] = tvm.const(1, dtype = dtype)
        with ib.for_range(0, length, name="j") as j:
            dtype = "int8"
            E = ib.allocate(dtype, length, name="E", scope="local.L0A")
            E[j] = A[j].astype(dtype) + B[j].astype(dtype) + C[j].astype(dtype) + D[j].astype(dtype)
93
        return ib.get()
94

95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126
    def dtype_bit_len(dtype):
        index = 0
        for i in dtype:
            if i.isdigit():
                break
            index += 1
        return int(dtype[index:])

    def offset_generater(dtype_list, length):
        dtype_len_list = [dtype_bit_len(i) for i in dtype_list]
        base_len = dtype_len_list[0]
        return sum([i * length / base_len for i in dtype_len_list])

    def dtype_test(dtype_list, length):
        def verify(n):
            if isinstance(n, tvm.stmt.Allocate):
                assert n.extents[0].value == offset

        body = stmt_generater(dtype_list, length)
        offset = offset_generater(dtype_list, length)
        body = tvm.ir_pass.StorageRewrite(body)
        tvm.ir_pass.PostOrderVisit(body, verify)

    length = 1024
    dtype_list = ["float16", "int32", "uint16", "int8"]
    dtype_test(dtype_list, length)

    dtype_list = ["float32", "int32", "uint16", "int8"]
    dtype_test(dtype_list, length)

    dtype_list = ["float64", "int32", "uint16", "int8"]
    dtype_test(dtype_list, length)
127

128 129
    dtype_list = ["int8", "int32", "uint16", "uint8"]
    dtype_test(dtype_list, length)
130

131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150

def test_inplace_rule():
    m = 10
    A = tvm.placeholder((m,), name='A')
    A0 = tvm.compute((m,), lambda i: A[i], name='A0')
    A1 = tvm.compute((m,), lambda i: A[i] + 1, name='A1')
    AA =  tvm.compute((m,), lambda i: A0[i] + A1[i] + A1[0], name='AA')
    B = tvm.compute((m,), lambda i: AA[i] + 1, name='B')
    s = tvm.create_schedule(B.op)
    bounds = tvm.schedule.InferBound(s)
    assert isinstance(bounds, tvm.container.Map)
    stmt = tvm.schedule.ScheduleOps(s, bounds)
    Ab = tvm.decl_buffer(A.shape, A.dtype, name='A')
    Bb = tvm.decl_buffer(B.shape, B.dtype, name='B')
    stmt = tvm.ir_pass.StorageFlatten(stmt, {A: Ab, B: Bb}, 64)
    stmt = tvm.ir_pass.CanonicalSimplify(stmt)
    stmt = tvm.ir_pass.Simplify(stmt)
    stmt = tvm.ir_pass.StorageRewrite(stmt)
    # verify only have one allocations.
    # verify inplace folding works
151 152 153 154 155 156 157
    num_alloc = [0]
    def verify(n):
        if isinstance(n, tvm.stmt.Allocate):
            num_alloc[0] += 1
    tvm.ir_pass.PostOrderVisit(stmt, verify)
    assert num_alloc[0] == 2

158 159 160 161 162 163 164 165

def test_storage_combine():
    n = 8
    A = tvm.placeholder((4,), name='A')
    num_stage = 5
    B = A
    stages = []
    for t in range(num_stage):
166
        B = tvm.compute((n, ), lambda i: B[i] + B[0] + (t+1), name='A%d' % t)
167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189
        stages.append(B)

    s = tvm.create_schedule(B.op)
    for S in stages[:-1]:
        s[S].set_scope("global:tag")
    bounds = tvm.schedule.InferBound(s)
    assert isinstance(bounds, tvm.container.Map)
    stmt = tvm.schedule.ScheduleOps(s, bounds)
    Ab = tvm.decl_buffer(A.shape, A.dtype, name='A')
    Bb = tvm.decl_buffer(B.shape, B.dtype, name='B')
    stmt = tvm.ir_pass.StorageFlatten(stmt, {A: Ab, B: Bb}, 64)
    stmt = tvm.ir_pass.CanonicalSimplify(stmt)
    stmt = tvm.ir_pass.Simplify(stmt)
    stmt = tvm.ir_pass.StorageRewrite(stmt)
    num_alloc = [0]
    def verify(n):
        if isinstance(n, tvm.stmt.Allocate):
            num_alloc[0] += 1
            assert (n.extents[0].value == 16)
    tvm.ir_pass.PostOrderVisit(stmt, verify)
    assert num_alloc[0] == 1


190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206
def test_storage_share_gpu():
    m = tvm.var('m')
    A = [tvm.placeholder((m), name='A')]
    num_stage = 5
    for t in range(num_stage):
        A.append(tvm.compute((m,), lambda i: A[-1][i] + (t+1), name='A%d_s' % t))
        A.append(tvm.compute((m,), lambda i: A[-1][i], name='A%d' % t))
    s = tvm.create_schedule(A[-1].op)
    for t in range(num_stage):
        x = A[2*t+2].op.axis[0]
        bx, tx = s[A[2*t+2]].split(x, factor=32)
        s[A[2*t+2]].bind(bx, tvm.thread_axis("blockIdx.x"))
        s[A[2*t+2]].bind(tx, tvm.thread_axis("threadIdx.x"))
        s[A[2*t+1]].compute_at(s[A[2*t+2]], tx)
        s[A[2*t+1]].set_scope("shared")

    bounds = tvm.schedule.InferBound(s)
207
    assert isinstance(bounds, tvm.container.Map)
208 209 210
    stmt = tvm.schedule.ScheduleOps(s, bounds)
    Ab = tvm.decl_buffer(A[0].shape, A[0].dtype, name='A')
    Bb = tvm.decl_buffer(A[0].shape, A[0].dtype, name='B')
211
    stmt = tvm.ir_pass.StorageFlatten(stmt, {A[0]: Ab, A[-1]: Bb}, 64)
212 213 214 215 216 217 218 219 220 221 222 223 224
    stmt = tvm.ir_pass.CanonicalSimplify(stmt)
    stmt = tvm.ir_pass.Simplify(stmt)
    stmt = tvm.ir_pass.StorageRewrite(stmt)
    alloc_stats = {"global": 0, "shared": 0}

    def verify(n):
        if isinstance(n, tvm.stmt.AttrStmt):
            if n.attr_key == "storage_scope":
                alloc_stats[n.value.value] += 1
    tvm.ir_pass.PostOrderVisit(stmt, verify)
    assert alloc_stats["global"] == 2
    assert alloc_stats["shared"] == num_stage

225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247
def test_parallel_alloc():
    ib = tvm.ir_builder.create()
    n = tvm.var("n")
    with ib.for_range(0, n, name="i", for_type="parallel") as i:
        with ib.for_range(0, 10, name="j") as j:
            A = ib.allocate("float32", n, name="A", scope="global")
            A[j] = A[j] + 2

    body = ib.get()
    body = tvm.ir_pass.StorageRewrite(body)
    assert (isinstance(body.body.body, tvm.stmt.Allocate))

    ib = tvm.ir_builder.create()
    n = tvm.var("n")
    with ib.for_range(0, n, name="t") as i:
        ib.scope_attr(
            tvm.const(1) , "pragma_scope", tvm.make.StringImm("parallel_launch_point"))
        with ib.for_range(0, n, name="i", for_type="parallel") as i:
            with ib.for_range(0, 10, name="j") as j:
                A = ib.allocate("float32", n, name="A", scope="global")
                A[j] = A[j] + 2
    body = ib.get()
    body = tvm.ir_pass.StorageRewrite(body)
248

249
    assert(isinstance(body.body.body.body.body, tvm.stmt.Allocate))
250

251
def test_inplace_rule2(scope_tb = "local_TB2", max_bits = 1024 * 1024 * 1024):
252
    #Test Buffer
253
    register_mem(scope_tb, max_bits)
254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284
    m = 10
    A = tvm.placeholder((m,), name='A')
    C = tvm.placeholder((m,), name='C')
    D = tvm.placeholder((m,), name='D')
    A0 = tvm.compute((m,), lambda i: A[i] + C[i], name='A0')
    A1 = tvm.compute((m,), lambda i: D[i] * D[i], name='A1')
    A2 = tvm.compute((m,), lambda i: A0[i] + A1[i], name='A2')
    B = tvm.compute((m,), lambda i: A2[i], name='B')
    s = tvm.create_schedule(B.op)
    A0L = s.cache_read(A0, scope_tb, [A2])
    A1L = s.cache_read(A1, scope_tb, [A2])
    A2L = s.cache_read(A2, scope_tb, [B])
    bounds = tvm.schedule.InferBound(s)
    assert isinstance(bounds, tvm.container.Map)
    stmt = tvm.schedule.ScheduleOps(s, bounds)
    Ab = tvm.decl_buffer(A.shape, A.dtype, name='A')
    Bb = tvm.decl_buffer(B.shape, B.dtype, name='B')
    Cc = tvm.decl_buffer(C.shape, B.dtype, name='C')
    Dd = tvm.decl_buffer(D.shape, B.dtype, name='D')
    stmt = tvm.ir_pass.StorageFlatten(stmt, {A: Ab, B: Bb, C: Cc, D:Dd}, 64)
    stmt = tvm.ir_pass.CanonicalSimplify(stmt)
    stmt = tvm.ir_pass.Simplify(stmt)
    stmt = tvm.ir_pass.StorageRewrite(stmt)
    # verify only have one allocations.
    # verify inplace folding works
    num_alloc = [0]
    def verify(n):
        if isinstance(n, tvm.stmt.Allocate):
            num_alloc[0] += 1
    tvm.ir_pass.PostOrderVisit(stmt, verify)
    assert num_alloc[0] == 2
285

286 287 288 289 290 291 292 293 294 295 296
def test_exceed_mem():
    max_bits = 639
    # The critical max_num_bits is between 639 and 640
    loc = -1
    try:
        test_inplace_rule2("local_TEM", max_bits)
    except Exception as e:
        estr = str(e)
        loc = estr.find('Allocation exceed bound of memory')
        assert loc != -1

297 298 299
def test_inplace_rule3():
    #Test Buffer
    scope_tb = "local_TB3"
300 301 302
    max_bits=1024 * 1024 * 1024

    register_mem(scope_tb, max_bits)
303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330
    m = 10
    B0 = tvm.placeholder((m,), name='B0')
    B1 = tvm.placeholder((m,), name='B1')
    B2 = tvm.placeholder((m,), name='B2')
    B3 = tvm.placeholder((m,), name='B3')
    B4 = tvm.placeholder((m,), name='B4')
    B5 = tvm.placeholder((m,), name='B5')

    B6 = tvm.compute((m,), lambda i: B1[i] * B5[i], name='B6')
    B7 = tvm.compute((m,), lambda i: B2[i] * B4[i], name='B7')
    B8 = tvm.compute((m,), lambda i: B6[i] - B7[i], name='B8')

    B9 = tvm.compute((m,), lambda i: B2[i] * B3[i], name='B9')
    B10 = tvm.compute((m,), lambda i: B0[i] * B5[i], name='B10')
    B11 = tvm.compute((m,), lambda i: B9[i] - B10[i], name='B11')

    B12 = tvm.compute((m,), lambda i: B0[i] * B4[i], name='B12')
    B13 = tvm.compute((m,), lambda i: B1[i] * B3[i], name='B13')
    B14 = tvm.compute((m,), lambda i: B12[i] - B13[i], name='B14')

    B = tvm.compute((m,), lambda i: B8[i] * B11[i] + B14[i], name='B')
    s = tvm.create_schedule(B.op)

    B1L = s.cache_read(B1, scope_tb, [B6, B13])
    B5L = s.cache_read(B5, scope_tb, [B6, B10])
    B2L = s.cache_read(B2, scope_tb, [B7, B9])
    B4L = s.cache_read(B4, scope_tb, [B7, B12])
    B3L = s.cache_read(B3, scope_tb, [B9, B13])
331
    B0L = s.cache_read(B0, scope_tb, [B10, B12])
332 333 334 335 336 337 338 339 340 341

    B8L = s.cache_write(B8, scope_tb)
    B11L = s.cache_write(B11, scope_tb)
    B14L = s.cache_write(B14, scope_tb)
    B6L = s.cache_write(B6, scope_tb)
    B7L = s.cache_write(B7, scope_tb)
    B9L = s.cache_write(B9, scope_tb)
    B10L = s.cache_write(B10, scope_tb)
    B12L = s.cache_write(B12, scope_tb)
    B13L = s.cache_write(B13, scope_tb)
342

343 344 345 346 347 348 349 350 351
    s[B12].compute_inline()
    s[B13].compute_inline()
    s[B8].compute_inline()
    s[B11].compute_inline()
    s[B14].compute_inline()
    s[B6].compute_inline()
    s[B7].compute_inline()
    s[B9].compute_inline()
    s[B10].compute_inline()
352 353

    s = s.normalize()
354 355 356
    bounds = tvm.schedule.InferBound(s)
    assert isinstance(bounds, tvm.container.Map)
    stmt = tvm.schedule.ScheduleOps(s, bounds)
357

358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376
    B0a = tvm.decl_buffer(B0.shape, B0.dtype, name='B0')
    B1a = tvm.decl_buffer(B1.shape, B1.dtype, name='B1')
    B2a = tvm.decl_buffer(B2.shape, B2.dtype, name='B2')
    B3a = tvm.decl_buffer(B3.shape, B3.dtype, name='B3')
    B4a = tvm.decl_buffer(B4.shape, B4.dtype, name='B4')
    B5a = tvm.decl_buffer(B5.shape, B5.dtype, name='B5')

    Bb = tvm.decl_buffer(B.shape, B.dtype, name='B')
    stmt = tvm.ir_pass.StorageFlatten(stmt, {B0: B0a, B1: B1a, B2: B2a, B3: B2a, B4: B4a, B5: B5a, B: Bb}, 64)
    stmt = tvm.ir_pass.CanonicalSimplify(stmt)
    stmt = tvm.ir_pass.Simplify(stmt)
    stmt = tvm.ir_pass.StorageRewrite(stmt)
    # verify only have one allocations.
    # verify inplace folding works
    def verify(n):
        if isinstance(n, tvm.stmt.Allocate):
            assert n.extents[0].value == 70
    tvm.ir_pass.PostOrderVisit(stmt, verify)

377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405
def test_alloc_seq_type():
    ib = tvm.ir_builder.create()
    n = tvm.var("n")
    with ib.for_range(0, n, name="i") as i:
        with ib.for_range(0, 10, name="j") as j:
            A = ib.allocate("float32", 200, name="A", scope="local.L0A")
            A1 = ib.allocate("float32", 200, name="A1", scope="local.L0A")
            A[j] = 1.2
            A1[j] = 1.3
            B = ib.allocate("int16", 200, name="B", scope="local.L0A")
            B[j] = tvm.const(1, "int16")
            C = ib.allocate("int16", 200, name="C", scope="local.L0A")
            C[j] = tvm.const(1, "int16")
            D = ib.allocate("int16", 200, name="D", scope="local.L0A")
            D[j] = B[j] + C[j]
            A2 = ib.allocate("float32", 200, name="A2", scope="local.L0A")
            A2[j] = A[j]

    body = ib.get()
    body = tvm.ir_pass.StorageRewrite(body)
    num_alloc = [0]
    def verify(n):
        if isinstance(n, tvm.stmt.Allocate):
            num_alloc[0] += 1
            assert n.extents[0].value == 500
    tvm.ir_pass.PostOrderVisit(body, verify)
    assert num_alloc[0] == 1

def test_alloc_seq_type2():
406 407 408 409 410
    scope_tb = "local.L0A2"
    max_bits=1024 * 1024 * 1024

    register_mem(scope_tb, max_bits)

411 412 413 414
    ib = tvm.ir_builder.create()
    n = tvm.var("n")
    with ib.for_range(0, n, name="i") as i:
        with ib.for_range(0, 10, name="j") as j:
415
            A = ib.allocate("float32", 200, name="A", scope=scope_tb)
416 417
            A[j] = 1.2
        with ib.for_range(0, 20, name="j") as j:
418
            B = ib.allocate("int16", 400, name="B", scope=scope_tb)
419 420
            B[j] = tvm.const(1, "int16")
        with ib.for_range(0, 10, name="j") as j:
421
            C = ib.allocate("float32", 200, name="C", scope=scope_tb)
422 423 424 425 426 427 428 429 430 431 432 433
            C[j] = 1.2

    body = ib.get()
    body = tvm.ir_pass.StorageRewrite(body)
    num_alloc = [0]
    def verify(n):
        if isinstance(n, tvm.stmt.Allocate):
            num_alloc[0] += 1
            assert n.extents[0].value == 200
    tvm.ir_pass.PostOrderVisit(body, verify)
    assert num_alloc[0] == 1

434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464

def test_reuse_small_buffer():
    ib = tvm.ir_builder.create()
    n = tvm.var("n")
    with ib.for_range(0, n, name="i") as i:
        with ib.for_range(0, 10, name="j") as j:
            A = ib.allocate("int16", 200, name="A", scope="local.L0A")
            A[j] = tvm.const(1, "int16")
            B = ib.allocate("int16", 200, name="B", scope="local.L0A")
            B[j] = tvm.const(1, "int16")
            B1 = ib.allocate("int16", 200, name="B1", scope="local.L0A")
            B1[j] = A[j] + B[j]
            C = ib.allocate("int16", 400, name="C", scope="local.L0A")
            C[j] = tvm.const(1, "int16")
            D = ib.allocate("int16", 400, name="D", scope="local.L0A")
            D[j] = tvm.const(1, "int16")
            E = ib.allocate("int16", 400, name="E", scope="local.L0A")
            E[j] = C[j]

    body = ib.get()
    body = tvm.ir_pass.StorageRewrite(body)

    num_alloc = [0]

    def verify(n):
        if isinstance(n, tvm.stmt.Allocate):
            num_alloc[0] += 1
            assert n.extents[0].value == 800
    tvm.ir_pass.PostOrderVisit(body, verify)
    assert num_alloc[0] == 1

465 466 467 468 469 470 471 472 473 474 475 476 477
def test_replace_dataflow():
    shape = (255,)
    A = tvm.placeholder(shape, name = "A")
    B = tvm.compute(shape, lambda i: A[i] + A[i], name = "B")
    C = tvm.compute(shape, lambda i: A[i] + B[i], name = "C")
    D = tvm.compute(shape, lambda i: A[i] + C[i], name = "D")
    E = tvm.compute(shape, lambda i: A[i] + D[i], name = "E")

    s = tvm.create_schedule(E.op)
    s.cache_read(A, "local", [B, C, D, E])
    bounds = tvm.schedule.InferBound(s)
    assert isinstance(bounds, tvm.container.Map)

478

479
if __name__ == "__main__":
480
    test_alloc_seq()
481
    test_alloc_different_dtypes()
482 483
    test_inplace_rule()
    test_storage_share()
484
    test_parallel_alloc()
485
    test_storage_combine()
486
    test_storage_share_gpu()
487
    test_inplace_rule2()
488
    test_exceed_mem()
489
    test_inplace_rule3()
490 491
    test_alloc_seq_type()
    test_alloc_seq_type2()
492
    test_reuse_small_buffer()
493
    test_replace_dataflow()