docs/namespacecutlass_1_1gemm_1_1threadblock.html
| | CUTLASS
CUDA Templates for Linear Algebra Subroutines and Solvers |
Namespaces | Classes | Functions
cutlass::gemm::threadblock Namespace Reference
|
| | | detail | | |
|
|
| struct | DefaultGemvCore |
| |
| struct | DefaultMma |
| |
| struct | DefaultMma< ElementA, LayoutA, kAlignmentA, ElementB, LayoutB, kAlignmentB, ElementAccumulator, layout::ColumnMajorInterleaved< InterleavedK >, OperatorClass, ArchTag, ThreadblockShape, WarpShape, InstructionShape, 2, Operator, true > |
| | Specialization for column-major-interleaved output. More...
|
| |
| struct | DefaultMma< ElementA, LayoutA, kAlignmentA, ElementB, LayoutB, kAlignmentB, ElementAccumulator, layout::RowMajor, arch::OpClassSimt, ArchTag, ThreadblockShape, WarpShape, InstructionShape, 2, Operator, false > |
| | Specialization for row-major output (OperatorClass Simt) More...
|
| |
| struct | DefaultMma< ElementA, LayoutA, kAlignmentA, ElementB, LayoutB, kAlignmentB, ElementAccumulator, layout::RowMajor, arch::OpClassTensorOp, ArchTag, ThreadblockShape, WarpShape, InstructionShape, 2, Operator, false > |
| | Specialization for row-major output (OperatorClass Simt) More...
|
| |
| struct | DefaultMma< int8_t, LayoutA, kAlignmentA, int8_t, LayoutB, kAlignmentB, ElementAccumulator, layout::RowMajor, arch::OpClassSimt, ArchTag, ThreadblockShape, WarpShape, GemmShape< 1, 1, 4 >, 2, Operator, false > |
| |
| struct | DefaultMmaCore |
| |
| struct | [DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmShab94a11a77dd0565102710907089acee0.html) |
| |
| struct | [DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmShafafd5c61db86cbfe90863578ddd11092.html) |
| |
| struct | [DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_, >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmSha46446d1e3871e31d2e728f710d78c8c1.html) |
| |
| struct | [DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmSha8da7a0cfbbe859b701fdd9f2b8566aa7.html) |
| |
| struct | [DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmSha84e9f8afb6a4ca9f5dcd219b182d16e7.html) |
| |
| struct | [DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::ColumnMajor, int8_t, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmSha2c0d0b7cdb5c4bcb11e83c058eb65345.html) |
| | Partial specialization: [More...](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmSha2c0d0b7cdb5c4bcb11e83c058eb65345.html#details)
|
| |
| struct | [DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::ColumnMajor, int8_t, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmSha34a52cc7b2942e8c290f0032b6779b52.html) |
| |
| struct | [DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::RowMajor, int8_t, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmShaaf312aafe9da92ea9d417bcc12a8e7dc.html) |
| | Partial specialization: [More...](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmShaaf312aafe9da92ea9d417bcc12a8e7dc.html#details)
|
| |
| struct | [DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::RowMajor, int8_t, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmSha863d4139ccaa713bc4bde32c425f4067.html) |
| | Partial specialization: [More...](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmSha863d4139ccaa713bc4bde32c425f4067.html#details)
|
| |
| struct | [DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmShaf03a122202ad10acdc96f280106d678b.html) |
| |
| struct | [DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmSha69bef08ea63dd930f99d9788105873dd.html) |
| |
| struct | [DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmSha3adf608332a8c9ee7014fced0da8a9ca.html) |
| |
| struct | [DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmShab7edfba3cdf43a07e3c4d719d87565a4.html) |
| |
| struct | [DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01Instruc803d38bc1e4618c07c47f54c87ae2678.html) |
| |
| struct | [DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01Instrucf60fe02fcdd80d28b7fd419133465dcc.html) |
| |
| struct | [DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajorInterleaved< InterleavedK >, ElementB_, layout::RowMajorInterleaved< InterleavedK >, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_, AccumulatorsInRowMajor >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01Instruc2bf00737f4ad0a9da9a8be6d3e66c152.html) |
| |
| struct | [DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01Instruc24092ddc01fc83dabb7db4c14880fe60.html) |
| |
| struct | [DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01Instruc4fee9f2965b8468bfb42b94a74527d22.html) |
| |
| struct | GemmBatchedIdentityThreadblockSwizzle |
| | Threadblock swizzling function for batched GEMMs. More...
|
| |
| struct | GemmHorizontalThreadblockSwizzle |
| | Threadblock swizzling function for GEMMs. More...
|
| |
| struct | GemmIdentityThreadblockSwizzle |
| | Threadblock swizzling function for GEMMs. More...
|
| |
| struct | GemmSplitKHorizontalThreadblockSwizzle |
| | Threadblock swizzling function for split-K GEMMs. More...
|
| |
| struct | GemmSplitKIdentityThreadblockSwizzle |
| | Threadblock swizzling function for split-K GEMMs. More...
|
| |
| class | Gemv |
| | Structure to compute the matrix-vector product using SIMT math instructions. More...
|
| |
| struct | GemvBatchedStridedThreadblockDefaultSwizzle |
| | Threadblock swizzling function for batched GEMVs. More...
|
| |
| class | MmaBase |
| |
| class | MmaPipelined |
| | Structure to compute the matrix product targeting CUDA cores and SIMT math instructions. More...
|
| |
| struct | MmaPolicy |
| | Policy object describing MmaTensorOp. More...
|
| |
| class | MmaSingleStage |
| | Structure to compute the matrix product targeting CUDA cores and SIMT math instructions. More...
|
| |
|
|
| CUTLASS_DEVICE int | RematerializeThreadIdxX () |
| | Helper to rematerialize block Idx. Reduces register liveness. More...
|
| |
| CUTLASS_DEVICE int | RematerializeThreadIdxY () |
| | Helper to rematerialize block Idx. Reduces register liveness. More...
|
| |
| CUTLASS_DEVICE int | RematerializeThreadIdxZ () |
| | Helper to rematerialize block Idx. Reduces register liveness. More...
|
| |
| CUTLASS_DEVICE int | RematerializeBlockIdxX () |
| | Helper to rematerialize block Idx. Reduces register liveness. More...
|
| |
| CUTLASS_DEVICE int | RematerializeBlockIdxY () |
| | Helper to rematerialize block Idx. Reduces register liveness. More...
|
| |
| CUTLASS_DEVICE int | RematerializeBlockIdxZ () |
| | Helper to rematerialize block Idx. Reduces register liveness. More...
|
| |
| CUTLASS_DEVICE int | RematerializeBlockDimX () |
| | Helper to rematerialize block Dim. Reduces register liveness. More...
|
| |
| CUTLASS_DEVICE int | RematerializeBlockDimY () |
| | Helper to rematerialize block Dim. Reduces register liveness. More...
|
| |
| CUTLASS_DEVICE int | RematerializeBlockDimZ () |
| | Helper to rematerialize block Dim. Reduces register liveness. More...
|
| |
| CUTLASS_DEVICE int cutlass::gemm::threadblock::RematerializeBlockDimX | ( | | ) | |
| CUTLASS_DEVICE int cutlass::gemm::threadblock::RematerializeBlockDimY | ( | | ) | |
| CUTLASS_DEVICE int cutlass::gemm::threadblock::RematerializeBlockDimZ | ( | | ) | |
| CUTLASS_DEVICE int cutlass::gemm::threadblock::RematerializeBlockIdxX | ( | | ) | |
| CUTLASS_DEVICE int cutlass::gemm::threadblock::RematerializeBlockIdxY | ( | | ) | |
| CUTLASS_DEVICE int cutlass::gemm::threadblock::RematerializeBlockIdxZ | ( | | ) | |
| CUTLASS_DEVICE int cutlass::gemm::threadblock::RematerializeThreadIdxX | ( | | ) | |
| CUTLASS_DEVICE int cutlass::gemm::threadblock::RematerializeThreadIdxY | ( | | ) | |
| CUTLASS_DEVICE int cutlass::gemm::threadblock::RematerializeThreadIdxZ | ( | | ) | |
Generated by 1.8.11