diff options
Diffstat (limited to 'gcc/doc/extend.texi')
| -rw-r--r-- | gcc/doc/extend.texi | 95 |
1 files changed, 95 insertions, 0 deletions
diff --git a/gcc/doc/extend.texi b/gcc/doc/extend.texi index 10dc32e..95f7192 100644 --- a/gcc/doc/extend.texi +++ b/gcc/doc/extend.texi @@ -13858,6 +13858,7 @@ instructions, but allow the compiler to schedule those calls. * PowerPC AltiVec/VSX Built-in Functions:: * PowerPC Hardware Transactional Memory Built-in Functions:: * PowerPC Atomic Memory Operation Functions:: +* PowerPC Matrix-Multiply Assist Built-in Functions:: * RX Built-in Functions:: * S/390 System z Built-in Functions:: * SH Built-in Functions:: @@ -21359,6 +21360,100 @@ void amo_stdat_smax (int64_t *, int64_t); void amo_stdat_smin (int64_t *, int64_t); @end smallexample +@node PowerPC Matrix-Multiply Assist Built-in Functions +@subsection PowerPC Matrix-Multiply Assist Built-in Functions +ISA 3.1 of the PowerPC added new Matrix-Multiply Assist (MMA) instructions. +GCC provides support for these instructions through the following built-in +functions which are enabled with the @code{-mmma} option. The vec_t type +below is defined to be a normal vector unsigned char type. The uint2, uint4 +and uint8 parameters are 2-bit, 4-bit and 8-bit unsigned integer constants +respectively. The compiler will verify that they are constants and that +their values are within range. + +The built-in functions supported are: + +@smallexample +void __builtin_mma_xvi4ger8 (__vector_quad *, vec_t, vec_t); +void __builtin_mma_xvi8ger4 (__vector_quad *, vec_t, vec_t); +void __builtin_mma_xvi16ger2 (__vector_quad *, vec_t, vec_t); +void __builtin_mma_xvi16ger2s (__vector_quad *, vec_t, vec_t); +void __builtin_mma_xvf16ger2 (__vector_quad *, vec_t, vec_t); +void __builtin_mma_xvbf16ger2 (__vector_quad *, vec_t, vec_t); +void __builtin_mma_xvf32ger (__vector_quad *, vec_t, vec_t); + +void __builtin_mma_xvi4ger8pp (__vector_quad *, vec_t, vec_t); +void __builtin_mma_xvi8ger4pp (__vector_quad *, vec_t, vec_t); +void __builtin_mma_xvi8ger4spp(__vector_quad *, vec_t, vec_t); +void __builtin_mma_xvi16ger2pp (__vector_quad *, vec_t, vec_t); +void __builtin_mma_xvi16ger2spp (__vector_quad *, vec_t, vec_t); +void __builtin_mma_xvf16ger2pp (__vector_quad *, vec_t, vec_t); +void __builtin_mma_xvf16ger2pn (__vector_quad *, vec_t, vec_t); +void __builtin_mma_xvf16ger2np (__vector_quad *, vec_t, vec_t); +void __builtin_mma_xvf16ger2nn (__vector_quad *, vec_t, vec_t); +void __builtin_mma_xvbf16ger2pp (__vector_quad *, vec_t, vec_t); +void __builtin_mma_xvbf16ger2pn (__vector_quad *, vec_t, vec_t); +void __builtin_mma_xvbf16ger2np (__vector_quad *, vec_t, vec_t); +void __builtin_mma_xvbf16ger2nn (__vector_quad *, vec_t, vec_t); +void __builtin_mma_xvf32gerpp (__vector_quad *, vec_t, vec_t); +void __builtin_mma_xvf32gerpn (__vector_quad *, vec_t, vec_t); +void __builtin_mma_xvf32gernp (__vector_quad *, vec_t, vec_t); +void __builtin_mma_xvf32gernn (__vector_quad *, vec_t, vec_t); + +void __builtin_mma_pmxvi4ger8 (__vector_quad *, vec_t, vec_t, uint4, uint4, uint8); +void __builtin_mma_pmxvi4ger8pp (__vector_quad *, vec_t, vec_t, uint4, uint4, uint8); + +void __builtin_mma_pmxvi8ger4 (__vector_quad *, vec_t, vec_t, uint4, uint4, uint4); +void __builtin_mma_pmxvi8ger4pp (__vector_quad *, vec_t, vec_t, uint4, uint4, uint4); +void __builtin_mma_pmxvi8ger4spp(__vector_quad *, vec_t, vec_t, uint4, uint4, uint4); + +void __builtin_mma_pmxvi16ger2 (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2); +void __builtin_mma_pmxvi16ger2s (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2); +void __builtin_mma_pmxvf16ger2 (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2); +void __builtin_mma_pmxvbf16ger2 (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2); + +void __builtin_mma_pmxvi16ger2pp (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2); +void __builtin_mma_pmxvi16ger2spp (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2); +void __builtin_mma_pmxvf16ger2pp (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2); +void __builtin_mma_pmxvf16ger2pn (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2); +void __builtin_mma_pmxvf16ger2np (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2); +void __builtin_mma_pmxvf16ger2nn (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2); +void __builtin_mma_pmxvbf16ger2pp (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2); +void __builtin_mma_pmxvbf16ger2pn (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2); +void __builtin_mma_pmxvbf16ger2np (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2); +void __builtin_mma_pmxvbf16ger2nn (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2); + +void __builtin_mma_pmxvf32ger (__vector_quad *, vec_t, vec_t, uint4, uint4); +void __builtin_mma_pmxvf32gerpp (__vector_quad *, vec_t, vec_t, uint4, uint4); +void __builtin_mma_pmxvf32gerpn (__vector_quad *, vec_t, vec_t, uint4, uint4); +void __builtin_mma_pmxvf32gernp (__vector_quad *, vec_t, vec_t, uint4, uint4); +void __builtin_mma_pmxvf32gernn (__vector_quad *, vec_t, vec_t, uint4, uint4); + +void __builtin_mma_xvf64ger (__vector_quad *, __vector_pair, vec_t); +void __builtin_mma_xvf64gerpp (__vector_quad *, __vector_pair, vec_t); +void __builtin_mma_xvf64gerpn (__vector_quad *, __vector_pair, vec_t); +void __builtin_mma_xvf64gernp (__vector_quad *, __vector_pair, vec_t); +void __builtin_mma_xvf64gernn (__vector_quad *, __vector_pair, vec_t); + +void __builtin_mma_pmxvf64ger (__vector_quad *, __vector_pair, vec_t, uint4, uint2); +void __builtin_mma_pmxvf64gerpp (__vector_quad *, __vector_pair, vec_t, uint4, uint2); +void __builtin_mma_pmxvf64gerpn (__vector_quad *, __vector_pair, vec_t, uint4, uint2); +void __builtin_mma_pmxvf64gernp (__vector_quad *, __vector_pair, vec_t, uint4, uint2); +void __builtin_mma_pmxvf64gernn (__vector_quad *, __vector_pair, vec_t, uint4, uint2); + +void __builtin_mma_xxmtacc (__vector_quad *); +void __builtin_mma_xxmfacc (__vector_quad *); +void __builtin_mma_xxsetaccz (__vector_quad *); + +void __builtin_mma_assemble_acc (__vector_quad *, vec_t, vec_t, vec_t, vec_t); +void __builtin_mma_disassemble_acc (void *, __vector_quad *); + +void __builtin_mma_assemble_pair (__vector_pair *, vec_t, vec_t); +void __builtin_mma_disassemble_pair (void *, __vector_pair *); + +vec_t __builtin_vsx_xvcvspbf16 (vec_t); +vec_t __builtin_vsx_xvcvbf16sp (vec_t); +@end smallexample + @node RX Built-in Functions @subsection RX Built-in Functions GCC supports some of the RX instructions which cannot be expressed in |