| /freebsd/contrib/llvm-project/llvm/lib/Target/RISCV/ |
| H A D | RISCVSchedule.td | 20 def WriteIMul : SchedWrite; // 32-bit or 64-bit multiply 21 def WriteIMul32 : SchedWrite; // 32-bit multiply on RV64I 47 def WriteFMul16 : SchedWrite; // 16-bit floating point multiply 48 def WriteFMul32 : SchedWrite; // 32-bit floating point multiply 49 def WriteFMul64 : SchedWrite; // 64-bit floating point multiply 50 def WriteFMul128 : SchedWrite; // 128-bit floating point multiply 51 def WriteFMA16 : SchedWrite; // 16-bit floating point fused multiply-add 52 def WriteFMA32 : SchedWrite; // 32-bit floating point fused multiply-add 53 def WriteFMA64 : SchedWrite; // 64-bit floating point fused multiply-add 54 def WriteFMA128 : SchedWrite; // 128-bit floating point fused multiply-add [all …]
|
| H A D | RISCVVLOptimizer.cpp | 334 // Vector Single-Width Integer Multiply Instructions in getOperandLog2EEW() 354 // Vector Single-Width Integer Multiply-Add Instructions in getOperandLog2EEW() 402 // Vector Single-Width Fractional Multiply with Rounding and Saturation in getOperandLog2EEW() 449 // Vector Single-Width Floating-Point Multiply/Divide Instructions in getOperandLog2EEW() 455 // Vector Single-Width Floating-Point Fused Multiply-Add Instructions in getOperandLog2EEW() 522 // Vector Widening Integer Multiply Instructions in getOperandLog2EEW() 530 // Vector Widening Integer Multiply-Add Instructions in getOperandLog2EEW() 532 // A SEW-bit*SEW-bit multiply of the sources forms a 2*SEW-bit value, which in getOperandLog2EEW() 542 // Vector Widening Floating-Point Fused Multiply-Add Instructions in getOperandLog2EEW() 559 // Vector Widening Floating-Point Multiply in getOperandLog2EEW() [all …]
|
| H A D | RISCVScheduleV.td | 381 // 11.10. Vector Single-Width Integer Multiply Instructions 387 // 11.12. Vector Widening Integer Multiply Instructions 390 // 11.13. Vector Single-Width Integer Multiply-Add Instructions 393 // 11.14. Vector Widening Integer Multiply-Add Instructions 413 // 12.3. Vector Single-Width Fractional Multiply with Rounding and Saturation 432 // 13.4. Vector Single-Width Floating-Point Multiply/Divide Instructions 437 // 13.5. Vector Widening Floating-Point Multiply 440 // 13.6. Vector Single-Width Floating-Point Fused Multiply-Add Instructions 443 // 13.7. Vector Widening Floating-Point Fused Multiply-Add Instructions 613 // 11.10. Vector Single-Width Integer Multiply Instructions [all …]
|
| /freebsd/lib/libpmc/pmu-events/arch/x86/amdzen5/ |
| H A D | floating-point.json | 11 "BriefDescription": "Retired x87 floating-point multiply ops.", 35 "BriefDescription": "Retired SSE and AVX floating-point multiply ops.", 47 …"BriefDescription": "Retired SSE and AVX floating-point multiply-accumulate ops (each operation is… 143 "BriefDescription": "Retired scalar floating-point multiply ops.", 149 "BriefDescription": "Retired scalar floating-point multiply-accumulate ops.", 209 "BriefDescription": "Retired vector floating-point multiply ops.", 215 "BriefDescription": "Retired vector floating-point multiply-accumulate ops.", 293 "BriefDescription": "Retired MMX integer multiply ops.", 299 "BriefDescription": "Retired MMX integer multiply-accumulate ops.", 341 "BriefDescription": "Retired MMX integer multiply ops of other types.", [all …]
|
| /freebsd/lib/libpmc/pmu-events/arch/x86/amdzen1/ |
| H A D | floating-point.json | 94 "BriefDescription": "Multiply Ops.", 95 … Ops that have retired. The number of events logged per cycle can vary from 0 to 8. Multiply Ops.", 115 "BriefDescription": "Double precision multiply-add FLOPS. Multiply-add counts as 2 FLOPS.", 116 …from 0 to 64. This event can count above 15. Double precision multiply-add FLOPS. Multiply-add cou… 129 "BriefDescription": "Double precision multiply FLOPS.", 130 … per cycle can vary from 0 to 64. This event can count above 15. Double precision multiply FLOPS.", 143 "BriefDescription": "Single precision multiply-add FLOPS. Multiply-add counts as 2 FLOPS.", 144 …from 0 to 64. This event can count above 15. Single precision multiply-add FLOPS. Multiply-add cou… 157 "BriefDescription": "Single-precision multiply FLOPS.", 158 … per cycle can vary from 0 to 64. This event can count above 15. Single-precision multiply FLOPS.",
|
| /freebsd/lib/libpmc/pmu-events/arch/x86/amdzen6/ |
| H A D | floating-point.json | 11 "BriefDescription": "Retired x87 floating-point multiply uops.", 35 "BriefDescription": "Retired SSE and AVX multiply FLOPs.", 47 …"BriefDescription": "Retired SSE and AVX multiply-accumulate FLOPs (each operation is counted as 2… 155 "BriefDescription": "Retired scalar floating-point multiply uops.", 161 "BriefDescription": "Retired scalar floating-point multiply-accumulate uops.", 245 "BriefDescription": "Retired vector floating-point multiply uops.", 251 "BriefDescription": "Retired vector floating-point multiply-accumulate uops.", 341 "BriefDescription": "Retired MMX integer multiply uops.", 347 "BriefDescription": "Retired MMX integer multiply-accumulate uops.", 407 "BriefDescription": "Retired MMX integer multiply uops of other types.", [all …]
|
| /freebsd/contrib/llvm-project/clang/lib/Headers/ |
| H A D | fmaintrin.h | 21 /// Computes a multiply-add of 128-bit vectors of [4 x float]. 41 /// Computes a multiply-add of 128-bit vectors of [2 x double]. 61 /// Computes a scalar multiply-add of the single-precision values in the 90 /// Computes a scalar multiply-add of the double-precision values in the 119 /// Computes a multiply-subtract of 128-bit vectors of [4 x float]. 139 /// Computes a multiply-subtract of 128-bit vectors of [2 x double]. 159 /// Computes a scalar multiply-subtract of the single-precision values in 188 /// Computes a scalar multiply-subtract of the double-precision values in 217 /// Computes a negated multiply-add of 128-bit vectors of [4 x float]. 237 /// Computes a negated multiply-add of 128-bit vectors of [2 x double]. [all …]
|
| H A D | avxvnniint16intrin.h | 18 /// Multiply groups of 2 adjacent pairs of signed 16-bit integers in \a __A with 52 /// Multiply groups of 2 adjacent pairs of signed 16-bit integers in \a __A with 86 /// Multiply groups of 2 adjacent pairs of signed 16-bit integers in \a __A with 121 /// Multiply groups of 2 adjacent pairs of signed 16-bit integers in \a __A with 156 /// Multiply groups of 2 adjacent pairs of unsigned 16-bit integers in \a __A with 190 /// Multiply groups of 2 adjacent pairs of unsigned 16-bit integers in \a __A with 224 /// Multiply groups of 2 adjacent pairs of unsigned 16-bit integers in \a __A with 259 /// Multiply groups of 2 adjacent pairs of unsigned 16-bit integers in \a __A with 294 /// Multiply groups of 2 adjacent pairs of unsigned 16-bit integers in \a __A with 328 /// Multiply groups of 2 adjacent pairs of unsigned 16-bit integers in \a __A with [all …]
|
| H A D | avxvnniintrin.h | 46 /// Multiply groups of 4 adjacent pairs of unsigned 8-bit integers in \a __A with 69 /// Multiply groups of 4 adjacent pairs of unsigned 8-bit integers in \a __A with 92 /// Multiply groups of 2 adjacent pairs of signed 16-bit integers in \a __A with 113 /// Multiply groups of 2 adjacent pairs of signed 16-bit integers in \a __A with 134 /// Multiply groups of 4 adjacent pairs of unsigned 8-bit integers in \a __A with 157 /// Multiply groups of 4 adjacent pairs of unsigned 8-bit integers in \a __A with 180 /// Multiply groups of 2 adjacent pairs of signed 16-bit integers in \a __A with 201 /// Multiply groups of 2 adjacent pairs of signed 16-bit integers in \a __A with
|
| H A D | avxvnniint8intrin.h | 17 /// Multiply groups of 4 adjacent pairs of signed 8-bit integers in \a __A with 51 /// Multiply groups of 4 adjacent pairs of signed 8-bit integers in \a __A with 85 /// Multiply groups of 4 adjacent pairs of signed 8-bit integers in \a __A with 120 /// Multiply groups of 4 adjacent pairs of signed 8-bit integers in \a __A with 155 /// Multiply groups of 4 adjacent pairs of signed 8-bit integers in \a __A with 189 /// Multiply groups of 4 adjacent pairs of signed 8-bit integers in \a __A with 223 /// Multiply groups of 4 adjacent pairs of signed 8-bit integers in \a __A with 258 /// Multiply groups of 4 adjacent pairs of signed 8-bit integers in \a __A with 293 /// Multiply groups of 4 adjacent pairs of unsigned 8-bit integers in \a __A with 327 /// Multiply groups of 4 adjacent pairs of unsigned 8-bit integers in \a __A with [all …]
|
| /freebsd/crypto/openssl/crypto/ec/curve448/ |
| H A D | point_448.h | 138 * Multiply two scalars. |a|, |b| and |out| may alias each other. 211 * scalar (in): The scalar to multiply by. 224 * Multiply a point by X448_ENCODE_RATIO, then encode it like RFC 7748. 231 * This would multiply by the cofactor, but in fact internally points are always 251 * scalar (in): The scalar to multiply by. 257 * Multiply a precomputed base point by a scalar: out = scalar*base. 261 * scalar (in): The scalar to multiply by. 268 * Multiply two base points by two scalars: 275 * scalar1 (in): A first scalar to multiply by. 277 * scalar2 (in) A second scalar to multiply by.
|
| /freebsd/crypto/openssl/doc/man3/ |
| H A D | OPENSSL_s390xcap.pod | 159 # 64 1<<63 PCC-Scalar-Multiply-P256 160 # 65 1<<62 PCC-Scalar-Multiply-P384 161 # 66 1<<61 PCC-Scalar-Multiply-P521 162 # 72 1<<55 PCC-Scalar-Multiply-Ed25519 163 # 73 1<<54 PCC-Scalar-Multiply-Ed448 164 # 80 1<<47 PCC-Scalar-Multiply-X25519 165 # 81 1<<46 PCC-Scalar-Multiply-X448
|
| /freebsd/secure/lib/libcrypto/man/man3/ |
| H A D | OPENSSL_s390xcap.3 | 216 \& # 64 1<<63 PCC\-Scalar\-Multiply\-P256 217 \& # 65 1<<62 PCC\-Scalar\-Multiply\-P384 218 \& # 66 1<<61 PCC\-Scalar\-Multiply\-P521 219 \& # 72 1<<55 PCC\-Scalar\-Multiply\-Ed25519 220 \& # 73 1<<54 PCC\-Scalar\-Multiply\-Ed448 221 \& # 80 1<<47 PCC\-Scalar\-Multiply\-X25519 222 \& # 81 1<<46 PCC\-Scalar\-Multiply\-X448
|
| /freebsd/lib/msun/man/ |
| H A D | fma.3 | 32 .Nd fused multiply-add 62 The fused multiply-add operation is often used to improve the 78 (respectively) have comparable or faster speed than a multiply 102 A fused multiply-add operation with virtually identical
|
| /freebsd/contrib/llvm-project/llvm/lib/Target/AArch64/ |
| H A D | AArch64Schedule.td | 36 def WriteIM32 : SchedWrite; // 32-bit Multiply 37 def WriteIM64 : SchedWrite; // 64-bit Multiply 38 def ReadIM : SchedRead; // 32/64-bit Multiply 39 def ReadIMA : SchedRead; // 32/64-bit Multiply Accumulate 77 def WriteFMul : SchedWrite; // Floating-point multiply.
|
| H A D | AArch64SchedNeoverseN3.td | 618 // Divide and Multiply Instructions 642 // Multiply 643 // Multiply accumulate, W-form 644 // Multiply accumulate, X-form 645 // Multiply accumulate long 646 // Multiply long 651 // Multiply high 834 // FP multiply 837 // FP multiply accumulate 989 // ASIMD matrix multiply-accumulate [all …]
|
| H A D | AArch64SchedA510.td | 76 def : WriteRes<WriteIM32, [CortexA510UnitMAC]> { let Latency = 3; } // 32-bit Multiply 77 …WriteIM64, [CortexA510UnitMAC]> { let Latency = 5; let ReleaseAtCycles = [2];} // 64-bit Multiply 444 // ASIMD multiply, by element 447 // ASIMD multiply 450 // ASIMD multiply accumulate 454 // ASIMD multiply accumulate half 456 // ASIMD multiply accumulate long 458 // ASIMD multiply accumulate long #2 465 // ASIMD multiply long 467 // ASIMD polynomial (8x8) multiply long [all …]
|
| H A D | AArch64SchedA320.td | 65 def : WriteRes<WriteIM32, [CortexA320UnitMAC]> { let Latency = 3; } // 32-bit Multiply 66 …WriteIM64, [CortexA320UnitMAC]> { let Latency = 5; let ReleaseAtCycles = [2];} // 64-bit Multiply 466 // ASIMD multiply, by element 469 // ASIMD multiply 472 // ASIMD multiply accumulate 476 // ASIMD multiply accumulate half 478 // ASIMD multiply accumulate long 480 // ASIMD multiply accumulate long #2 487 // ASIMD multiply long 489 // ASIMD polynomial (8x8) multiply long [all …]
|
| H A D | AArch64SchedNeoverseN2.td | 719 // Divide and Multiply Instructions 729 // Multiply high 855 // FP multiply 858 // FP multiply accumulate 1024 // ASIMD matrix multiply-accumulate 1038 // ASIMD multiply 1041 // ASIMD multiply accumulate 1044 // ASIMD multiply accumulate high 1047 // ASIMD multiply accumulate long 1050 // ASIMD multiply accumulate saturating long [all …]
|
| H A D | AArch64SchedNeoverseV2.td | 970 // consumers of 64 bit multiply high operations? 1037 // NOTE: SOG p. 43: Complex multiply-add B, H, S element size: How to reduce 1167 // §3.5 Divide and multiply instructions 1177 // Multiply 1178 // Multiply accumulate, W-form 1179 // Multiply accumulate, X-form 1183 // Multiply accumulate long 1184 // Multiply long 1188 // Multiply high 1319 // FP multiply [all …]
|
| H A D | AArch64SchedNeoverseN1.td | 324 // Divide and multiply instructions 331 // Multiply accumulate 332 // Multiply accumulate, long 336 // Multiply high 431 // FP multiply 434 // FP multiply accumulate 612 // ASIMD multiply, D-form 613 // ASIMD multiply accumulate, D-form 614 // ASIMD multiply accumulate high, D-form 615 // ASIMD multiply accumulat [all...] |
| H A D | AArch64SchedNeoverseV1.td | 477 // consumers of 64 bit multiply high operations? 633 // Divide and multiply instructions 643 // Multiply 644 // Multiply accumulate, W-form 645 // Multiply accumulate, X-form 649 // Multiply accumulate long 650 // Multiply long 653 // Multiply high 769 // FP multiply 772 // FP multiply accumulate [all …]
|
| /freebsd/contrib/llvm-project/llvm/lib/Target/ARM/ |
| H A D | ARMISelLowering.h | 227 // Vector multiply long: 246 VMLAVs, // sign- or zero-extend the elements of two vectors to i32, multiply 263 SMULWB, // Signed multiply word by half word, bottom 264 SMULWT, // Signed multiply word by half word, top 265 UMLAL, // 64bit Unsigned Accumulate Multiply 266 SMLAL, // 64bit Signed Accumulate Multiply 267 UMAAL, // 64-bit Unsigned Accumulate Accumulate Multiply 268 SMLALBB, // 64-bit signed accumulate multiply bottom, bottom 16 269 SMLALBT, // 64-bit signed accumulate multiply bottom, top 16 270 SMLALTB, // 64-bit signed accumulate multiply top, bottom 16 [all …]
|
| /freebsd/contrib/llvm-project/llvm/include/llvm/Support/ |
| H A D | CheckedArithmetic.h | 60 /// Multiply two signed integers \p LHS and \p RHS. 69 /// Multiply A and B, and add C to the resulting product. 89 /// Multiply two unsigned integers \p LHS and \p RHS. 98 /// Multiply unsigned integers A and B, and add C to the resulting product.
|
| /freebsd/contrib/llvm-project/llvm/lib/Target/PowerPC/ |
| H A D | P10InstrResources.td | 1462 // 10 Cycles SIMD Matrix Multiply Engine operations, 0 input operands 1468 // 10 Cycles SIMD Matrix Multiply Engine operations, 2 input operands 1481 // 10 Cycles SIMD Matrix Multiply Engine operations, 3 input operands 1507 // 10 Cycles SIMD Matrix Multiply Engine operations, 2 input operands 1520 // 10 Cycles SIMD Matrix Multiply Engine operations, 3 input operands 1547 // 10 Cycles SIMD Matrix Multiply Engine operations, and 3 Cycles ALU operations, 1 input operands 1554 // 10 Cycles SIMD Matrix Multiply Engine operations, 3 Cycles ALU operations, 10 Cycles SIMD Matrix… 1560 // 5 Cycles GPR Multiply operations, 1 input operands 1566 // 5 Cycles GPR Multiply operations, 2 input operands 1582 // 5 Cycles GPR Multiply operations, 3 input operands [all …]
|