MCPcopy Create free account

hub / github.com/KnowingNothing/MatmulTutorial / functions

Functions541 in github.com/KnowingNothing/MatmulTutorial

⨍ Functions 541◇ Types & classes 125
↓ 1 callersFunctiontest_correctness
(M=TEST_SIZE, N=TEST_SIZE, K=TEST_SIZE, atol=1e-2, rtol=1e-2)
examples/matmul/this-sm90/test_v1.py:30
↓ 1 callersFunctiontest_matmul
()
examples/matmul/this-sm100/test_this_perf.py:245
↓ 1 callersFunctiontest_swizzle
()
cutlass.py/swizzle.py:30
↓ 1 callersFunctionto_CUtensorMapSwizzle
include/tma.h:142
↓ 1 callersMethodto_underlying_arguments
( problem_shape_mnkl, tile_shape, cluster_shape, hw_info, arguments,
cutlass.py/tile_scheduler.py:275
↓ 1 callersFunctiontorch_c64_bwd_impl
(q, k, v, o, go)
examples/attention/triton/fused_linear_attention_complex_bwd_bind_bhm.py:382
↓ 1 callersFunctiontorch_c64_bwd_impl
(q, k, v, o, go)
examples/attention/triton/fused_linear_attention_complex_bwd_bind_bhm_v2.py:444
↓ 1 callersFunctiontorch_c64_fwd_impl
(q, k, v, r_scale, i_scale)
examples/attention/triton/fused_linear_attention_complex_bwd_bind_bhm.py:367
↓ 1 callersFunctiontorch_c64_fwd_impl
(q, k, v, r_scale, i_scale)
examples/attention/triton/fused_linear_attention_complex_bwd_bind_bhm_v2.py:426
↓ 1 callersFunctiontorch_impl
(rq, iq, rk, ik, rv, iv, r_scale, i_scale)
examples/attention/triton/fused_linear_attention_complex.py:232
↓ 1 callersFunctiontorch_impl
(rq, iq, rk, ik, rv, iv, r_scale, i_scale)
examples/attention/triton/fused_linear_attention_complex_tile_k_tile_n.py:270
↓ 1 callersFunctiontorch_impl
(rq, iq, rk, ik, rv, iv, rgo, igo, r_scale, i_scale)
examples/attention/triton/fused_linear_attention_complex_bwd_bind_bhm.py:347
↓ 1 callersFunctiontorch_impl
(rq, iq, rk, ik, rv, iv, rgo, igo, r_scale, i_scale)
examples/attention/triton/fused_linear_attention_complex_bwd_bind_bh.py:413
↓ 1 callersFunctiontorch_impl
(rq, iq, rk, ik, rv, iv, r_scale, i_scale)
examples/attention/triton/fused_linear_attention_complex_tile_k.py:247
↓ 1 callersFunctiontorch_impl
(rq, iq, rk, ik, rv, iv, rgo, igo, r_scale, i_scale)
examples/attention/triton/fused_linear_attention_complex_bwd_bind_bhm_v2.py:401
↓ 1 callersFunctiontune
(out_dtype)
examples/matmul/tvm/tensorir_meta_schedule.py:105
↓ 1 callersMethoduint16_t
(cls)
cutlass.py/dtype.py:76
↓ 1 callersMethoduint32_t
(cls)
cutlass.py/dtype.py:80
↓ 1 callersMethoduint4_t
(cls)
cutlass.py/dtype.py:68
↓ 1 callersMethoduint64_t
(cls)
cutlass.py/dtype.py:84
↓ 1 callersMethoduint8_t
(cls)
cutlass.py/dtype.py:72
↓ 1 callersFunctionverify_matmul
( func, M, N, K, ref_target="cuda", sm=80, atol=1e-5, rtol=1e-5 )
examples/matmul/tvm/relay_matmul_cutlass.py:56
↓ 1 callersFunctionwarp_id_in_block
Returns the warp id in block
include/common.h:444
MethodArrivalToken
include/pipeline.h:14
MethodClusterBarrier
include/barrier.h:34
MethodClusterTransactionBarrier
include/barrier.h:310
FunctionConsumerToken consumer_try_wait
/////////////// Consumer APIs ///////////////
include/pipeline.h:203
FunctionGmmaDescriptor
include/descriptor.h:23
FunctionGmmaDescriptor make_smem_desc_major_k
include/descriptor.h:75
MethodGpuTimer
Constructor
examples/matmul/cutlass/helper.h:74
MethodOrderedSequenceBarrier
include/barrier.h:252
MethodPipelineState
include/barrier.h:174
FunctionProducerToken producer_try_acquire
include/pipeline.h:172
FunctionSmemSwizzleBits get_tma_swizzle_bits
include/tma.h:124
MethodTileScheduler
include/scheduler.h:24
Method__add__
(self, other)
util/simulator/kernel.py:85
Method__add__
(self, other: Any)
util/simulator/data_math.py:22
Method__and__
(self, other: Any)
util/simulator/data_math.py:193
Method__call__
(self, dividend)
cutlass.py/fast_math.py:30
Method__call__
(self, x)
cutlass.py/fast_math.py:41
Method__call__
(self, offset)
cutlass.py/swizzle.py:26
Method__div__
(self, other)
util/simulator/kernel.py:94
Method__enter__
(self)
examples/matmul/this-sm100/test_this_perf.py:30
Method__enter__
(self)
examples/matmul/this-sm100/test_this_perf.py:38
Method__exit__
(self, *_)
examples/matmul/this-sm100/test_this_perf.py:33
Method__exit__
(self, *_)
examples/matmul/this-sm100/test_this_perf.py:58
Method__floordiv__
(self, other: Any)
util/simulator/data_math.py:70
Method__ge__
(self, other: Any)
util/simulator/data_math.py:169
Method__getitem__
(self, key: int)
cutlass.py/tiling.py:26
Method__getitem__
(self, key: int)
cutlass.py/tiling.py:108
Method__gt__
(self, other: Any)
util/simulator/data_math.py:161
Method__hash__
(self)
util/simulator/data_math.py:19
Method__init__
(self, config: LlamaConfig)
examples/attention/triton/model.py:90
Method__init__
(self)
examples/matmul/this-sm90/test_v2.py:40
Method__init__
(self)
examples/matmul/this-sm90/test_v3.py:34
Method__init__
(self)
examples/matmul/this-sm90/test_v4.py:34
Method__init__
(self)
util/simulator/kernel.py:10
Method__init__
(self, start, end, step: int = 1, binding_name=None)
util/simulator/kernel.py:27
Method__init__
grid: grid config (how many blocks in grid) cluster: cluster config (how many blocks in cluster) block: block config (how man
util/simulator/kernel.py:159
Method__init__
(self, num_sm)
util/simulator/gpu.py:2
Method__init__
(self, blocks_per_problem=0, log_swizzle_size=0, raster_order=None)
util/simulator/tile_scheduler.py:23
Method__init__
(self, gpu_kernel: GPUKernel)
util/simulator/tile_scheduler.py:32
Method__init__
(self, value)
util/simulator/data_math.py:13
Method__init__
(self, mma_op: MMA_OP)
cutlass.py/mma.py:92
Method__init__
(self, functions: Optional[List[Function]] = None)
cutlass.py/mapping.py:14
Method__init__
(self, divisor=0)
cutlass.py/fast_math.py:15
Method__init__
(self, divisor)
cutlass.py/fast_math.py:35
Method__init__
( self, blocks_per_problem=0, log_swizzle_size=0, raster_order=RasterOrder.AlongN )
cutlass.py/tile_scheduler.py:18
Method__init__
(self, params: TileParams, dev_coord: DeviceCoord)
cutlass.py/tile_scheduler.py:258
Method__init__
(self, num_bits: int, num_base: int, num_shft: int)
cutlass.py/swizzle.py:2
Method__init__
dimensions: each item: if item is IntegerType, it's dynamic, else it's static int value.
cutlass.py/tiling.py:7
Method__init__
dimensions: each item: if item is IntegerType, it's dynamic, else it's static int value.
cutlass.py/tiling.py:92
Method__le__
(self, other: Any)
util/simulator/data_math.py:185
Method__len__
(self)
cutlass.py/tiling.py:37
Method__len__
(self)
cutlass.py/tiling.py:116
Method__lshift__
(self, other: Any)
util/simulator/data_math.py:134
Method__lt__
(self, other: Any)
util/simulator/data_math.py:177
Method__mod__
(self, other)
util/simulator/kernel.py:97
Method__mod__
(self, other: Any)
util/simulator/data_math.py:102
Method__mul__
(self, other)
util/simulator/kernel.py:91
Method__mul__
(self, other: Any)
util/simulator/data_math.py:54
Method__ne__
(self, other: Any)
util/simulator/data_math.py:158
Method__or__
(self, other: Any)
util/simulator/data_math.py:209
Method__post_init__
(self)
cutlass.py/mapping.py:24
Method__pow__
(self, other: Any)
util/simulator/data_math.py:241
Method__radd__
(self, other)
util/simulator/kernel.py:100
Method__radd__
(self, other: Any)
util/simulator/data_math.py:30
Method__rand__
(self, other: Any)
util/simulator/data_math.py:201
Method__rdiv__
(self, other)
util/simulator/kernel.py:109
Method__repr__
(self)
cutlass.py/tiling.py:82
Method__rfloordiv__
(self, other: Any)
util/simulator/data_math.py:78
Method__rlshift__
(self, other: Any)
util/simulator/data_math.py:142
Method__rmod__
(self, other)
util/simulator/kernel.py:112
Method__rmod__
(self, other: Any)
util/simulator/data_math.py:110
Method__rmul__
(self, other)
util/simulator/kernel.py:106
Method__rmul__
(self, other: Any)
util/simulator/data_math.py:62
Method__ror__
(self, other: Any)
util/simulator/data_math.py:217
Method__rpow__
(self, other: Any)
util/simulator/data_math.py:249
Method__rrshift__
(self, other: Any)
util/simulator/data_math.py:126
Method__rshift__
(self, other: Any)
util/simulator/data_math.py:118
← previousnext →301–400 of 541, ranked by callers