Support for Mixed Input TensorOp (#1084)
* Passing warp-level mixed input F16*(S8/U8) tests * passing device-level mixed input F16*(S8/U8) tests * add to profiler - I8 (111 TFLOPs), U (123 TFLOPs) * fast numeric conversions (I8 = 132 TFLOPs, U8 = 148 TFLOPs) * Speedup reference compilation (REVERT THIS COMMIT) * wider_add.u32_packed_sub.f16x2 (I8 = 132TFLOP/s, U8 = 170 TFLOP/s) * Improve s8->f16 cvt and support bf16*u8 @158 TFLOPs * BF16 * S8 (142 TFLOPs) * Handle mixed-input upcast on OperandA (Support [S8|U8]*[F16|BF16] * rename OpMultiplyAddMixedInput to OpMultiplyAddMixedInputUpcast * Add device-level test and profiler support for upcast on operand A * Move shfl before the cvt and reduce #shfls by 1/2 * fix smem_usage calculation for mixed_input types * uncomment the stuff (getting ready for merge) * profiler changes and mixed-input reference * mixed input reference are in a new file * use platform instead of std * comments and typo only * Use CreateGemmOperator and delete CreateMixedInputGemmOperator * copyright for new files * rebase follow-up
This commit is contained in:
@@ -103,16 +103,17 @@ struct TestbedUniversal {
|
||||
double scope_max, scope_min;
|
||||
int bits_input = cutlass::sizeof_bits<Element>::value;
|
||||
int bits_output = cutlass::sizeof_bits<typename Gemm::ElementC>::value;
|
||||
bool is_unsigned_int = std::numeric_limits<Element>::is_integer && !std::numeric_limits<Element>::is_signed;
|
||||
|
||||
if (bits_input == 1) {
|
||||
scope_max = 2;
|
||||
scope_min = 0;
|
||||
} else if (bits_input <= 8) {
|
||||
scope_max = 2;
|
||||
scope_min = -2;
|
||||
scope_max = is_unsigned_int ? 4 : 2;
|
||||
scope_min = is_unsigned_int ? 0 : -2;
|
||||
} else if (bits_output == 16) {
|
||||
scope_max = 5;
|
||||
scope_min = -5;
|
||||
scope_max = is_unsigned_int ? 10 : 5;
|
||||
scope_min = is_unsigned_int ? 0 : -5;
|
||||
} else {
|
||||
scope_max = 8;
|
||||
scope_min = -8;
|
||||
|
||||
Reference in New Issue
Block a user