public inbox for gcc-cvs@sourceware.org
help / color / mirror / Atom feed
* [gcc(refs/users/wschmidt/heads/builtins10)] rs6000: Add MMA builtins
@ 2021-06-15 17:18 William Schmidt
0 siblings, 0 replies; 7+ messages in thread
From: William Schmidt @ 2021-06-15 17:18 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:c6584988cd1c20e83e6f27b95f85be684df8287c
commit c6584988cd1c20e83e6f27b95f85be684df8287c
Author: Bill Schmidt <wschmidt@linux.ibm.com>
Date: Wed Mar 24 15:50:37 2021 -0500
rs6000: Add MMA builtins
2021-03-24 Bill Schmidt <wschmidt@linux.ibm.com>
gcc/
* config/rs6000/rs6000-builtin-new.def: Add mma stanza.
Diff:
---
gcc/config/rs6000/rs6000-builtin-new.def | 404 +++++++++++++++++++++++++++++++
1 file changed, 404 insertions(+)
diff --git a/gcc/config/rs6000/rs6000-builtin-new.def b/gcc/config/rs6000/rs6000-builtin-new.def
index b0e12a0ed9b..6a36193fcc9 100644
--- a/gcc/config/rs6000/rs6000-builtin-new.def
+++ b/gcc/config/rs6000/rs6000-builtin-new.def
@@ -3332,3 +3332,407 @@
const unsigned long long __builtin_pextd (unsigned long long, unsigned long long);
PEXTD pextd {}
+
+
+[mma]
+ void __builtin_mma_assemble_acc (v512 *, vuc, vuc, vuc, vuc);
+ ASSEMBLE_ACC nothing {mma}
+
+ v512 __builtin_mma_assemble_acc_internal (vuc, vuc, vuc, vuc);
+ ASSEMBLE_ACC_INTERNAL mma_assemble_acc {mma}
+
+ void __builtin_mma_assemble_pair (v256 *, vuc, vuc);
+ ASSEMBLE_PAIR nothing {mma}
+
+ v256 __builtin_mma_assemble_pair_internal (vuc, vuc);
+ ASSEMBLE_PAIR_INTERNAL vsx_assemble_pair {mma}
+
+ void __builtin_mma_disassemble_acc (void *, v512 *);
+ DISASSEMBLE_ACC nothing {mma,quad}
+
+ vuc __builtin_mma_disassemble_acc_internal (v512, const int<2>);
+ DISASSEMBLE_ACC_INTERNAL mma_disassemble_acc {mma}
+
+ void __builtin_mma_disassemble_pair (void *, v256 *);
+ DISASSEMBLE_PAIR nothing {mma,pair}
+
+ vuc __builtin_mma_disassemble_pair_internal (v256, const int<2>);
+ DISASSEMBLE_PAIR_INTERNAL vsx_disassemble_pair {mma}
+
+ void __builtin_mma_pmxvbf16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2 nothing {mma}
+
+ v512 __builtin_mma_pmxvbf16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2_INTERNAL mma_pmxvbf16ger2 {mma}
+
+ void __builtin_mma_pmxvbf16ger2nn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2nn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NN_INTERNAL mma_pmxvbf16ger2nn {mma,quad}
+
+ void __builtin_mma_pmxvbf16ger2np (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2np_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NP_INTERNAL mma_pmxvbf16ger2np {mma,quad}
+
+ void __builtin_mma_pmxvbf16ger2pn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2pn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PN_INTERNAL mma_pmxvbf16ger2pn {mma,quad}
+
+ void __builtin_mma_pmxvbf16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PP_INTERNAL mma_pmxvbf16ger2pp {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2 nothing {mma}
+
+ v512 __builtin_mma_pmxvf16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2_INTERNAL mma_pmxvf16ger2 {mma}
+
+ void __builtin_mma_pmxvf16ger2nn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2nn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NN_INTERNAL mma_pmxvf16ger2nn {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2np (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2np_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NP_INTERNAL mma_pmxvf16ger2np {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2pn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2pn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PN_INTERNAL mma_pmxvf16ger2pn {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PP_INTERNAL mma_pmxvf16ger2pp {mma,quad}
+
+ void __builtin_mma_pmxvf32ger (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GER nothing {mma}
+
+ v512 __builtin_mma_pmxvf32ger_internal (vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GER_INTERNAL mma_pmxvf32ger {mma}
+
+ void __builtin_mma_pmxvf32gernn (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gernn_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNN_INTERNAL mma_pmxvf32gernn {mma,quad}
+
+ void __builtin_mma_pmxvf32gernp (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gernp_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNP_INTERNAL mma_pmxvf32gernp {mma,quad}
+
+ void __builtin_mma_pmxvf32gerpn (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gerpn_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPN_INTERNAL mma_pmxvf32gerpn {mma,quad}
+
+ void __builtin_mma_pmxvf32gerpp (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gerpp_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPP_INTERNAL mma_pmxvf32gerpp {mma,quad}
+
+ void __builtin_mma_pmxvf64ger (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GER nothing {mma,pair}
+
+ v512 __builtin_mma_pmxvf64ger_internal (v256, vuc, const int<4>, const int<2>);
+ PMXVF64GER_INTERNAL mma_pmxvf64ger {mma,pair}
+
+ void __builtin_mma_pmxvf64gernn (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gernn_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNN_INTERNAL mma_pmxvf64gernn {mma,pair,quad}
+
+ void __builtin_mma_pmxvf64gernp (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gernp_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNP_INTERNAL mma_pmxvf64gernp {mma,pair,quad}
+
+ void __builtin_mma_pmxvf64gerpn (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gerpn_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPN_INTERNAL mma_pmxvf64gerpn {mma,pair,quad}
+
+ void __builtin_mma_pmxvf64gerpp (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gerpp_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPP_INTERNAL mma_pmxvf64gerpp {mma,pair,quad}
+
+ void __builtin_mma_pmxvi16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2 nothing {mma}
+
+ v512 __builtin_mma_pmxvi16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2_INTERNAL mma_pmxvi16ger2 {mma}
+
+ void __builtin_mma_pmxvi16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2PP_INTERNAL mma_pmxvi16ger2pp {mma,quad}
+
+ void __builtin_mma_pmxvi16ger2s (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2S nothing {mma}
+
+ v512 __builtin_mma_pmxvi16ger2s_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2S_INTERNAL mma_pmxvi16ger2s {mma}
+
+ void __builtin_mma_pmxvi16ger2spp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2SPP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi16ger2spp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2SPP_INTERNAL mma_pmxvi16ger2spp {mma,quad}
+
+ void __builtin_mma_pmxvi4ger8 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<8>);
+ PMXVI4GER8 nothing {mma}
+
+ v512 __builtin_mma_pmxvi4ger8_internal (vuc, vuc, const int<4>, const int<4>, const int<8>);
+ PMXVI4GER8_INTERNAL mma_pmxvi4ger8 {mma}
+
+ void __builtin_mma_pmxvi4ger8pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI4GER8PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi4ger8pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI4GER8PP_INTERNAL mma_pmxvi4ger8pp {mma,quad}
+
+ void __builtin_mma_pmxvi8ger4 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4 nothing {mma}
+
+ v512 __builtin_mma_pmxvi8ger4_internal (vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4_INTERNAL mma_pmxvi8ger4 {mma}
+
+ void __builtin_mma_pmxvi8ger4pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi8ger4pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4PP_INTERNAL mma_pmxvi8ger4pp {mma,quad}
+
+ void __builtin_mma_pmxvi8ger4spp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4SPP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi8ger4spp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4SPP_INTERNAL mma_pmxvi8ger4spp {mma,quad}
+
+ void __builtin_mma_xvbf16ger2 (v512 *, vuc, vuc);
+ XVBF16GER2 nothing {mma}
+
+ v512 __builtin_mma_xvbf16ger2_internal (vuc, vuc);
+ XVBF16GER2_INTERNAL mma_xvbf16ger2 {mma}
+
+ void __builtin_mma_xvbf16ger2nn (v512 *, vuc, vuc);
+ XVBF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2nn_internal (v512, vuc, vuc);
+ XVBF16GER2NN_INTERNAL mma_xvbf16ger2nn {mma,quad}
+
+ void __builtin_mma_xvbf16ger2np (v512 *, vuc, vuc);
+ XVBF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2np_internal (v512, vuc, vuc);
+ XVBF16GER2NP_INTERNAL mma_xvbf16ger2np {mma,quad}
+
+ void __builtin_mma_xvbf16ger2pn (v512 *, vuc, vuc);
+ XVBF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2pn_internal (v512, vuc, vuc);
+ XVBF16GER2PN_INTERNAL mma_xvbf16ger2pn {mma,quad}
+
+ void __builtin_mma_xvbf16ger2pp (v512 *, vuc, vuc);
+ XVBF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2pp_internal (v512, vuc, vuc);
+ XVBF16GER2PP_INTERNAL mma_xvbf16ger2pp {mma,quad}
+
+ void __builtin_mma_xvf16ger2 (v512 *, vuc, vuc);
+ XVF16GER2 nothing {mma}
+
+ v512 __builtin_mma_xvf16ger2_internal (vuc, vuc);
+ XVF16GER2_INTERNAL mma_xvf16ger2 {mma}
+
+ void __builtin_mma_xvf16ger2nn (v512 *, vuc, vuc);
+ XVF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2nn_internal (v512, vuc, vuc);
+ XVF16GER2NN_INTERNAL mma_xvf16ger2nn {mma,quad}
+
+ void __builtin_mma_xvf16ger2np (v512 *, vuc, vuc);
+ XVF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2np_internal (v512, vuc, vuc);
+ XVF16GER2NP_INTERNAL mma_xvf16ger2np {mma,quad}
+
+ void __builtin_mma_xvf16ger2pn (v512 *, vuc, vuc);
+ XVF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2pn_internal (v512, vuc, vuc);
+ XVF16GER2PN_INTERNAL mma_xvf16ger2pn {mma,quad}
+
+ void __builtin_mma_xvf16ger2pp (v512 *, vuc, vuc);
+ XVF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2pp_internal (v512, vuc, vuc);
+ XVF16GER2PP_INTERNAL mma_xvf16ger2pp {mma,quad}
+
+ void __builtin_mma_xvf32ger (v512 *, vuc, vuc);
+ XVF32GER nothing {mma}
+
+ v512 __builtin_mma_xvf32ger_internal (vuc, vuc);
+ XVF32GER_INTERNAL mma_xvf32ger {mma}
+
+ void __builtin_mma_xvf32gernn (v512 *, vuc, vuc);
+ XVF32GERNN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gernn_internal (v512, vuc, vuc);
+ XVF32GERNN_INTERNAL mma_xvf32gernn {mma,quad}
+
+ void __builtin_mma_xvf32gernp (v512 *, vuc, vuc);
+ XVF32GERNP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gernp_internal (v512, vuc, vuc);
+ XVF32GERNP_INTERNAL mma_xvf32gernp {mma,quad}
+
+ void __builtin_mma_xvf32gerpn (v512 *, vuc, vuc);
+ XVF32GERPN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gerpn_internal (v512, vuc, vuc);
+ XVF32GERPN_INTERNAL mma_xvf32gerpn {mma,quad}
+
+ void __builtin_mma_xvf32gerpp (v512 *, vuc, vuc);
+ XVF32GERPP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gerpp_internal (v512, vuc, vuc);
+ XVF32GERPP_INTERNAL mma_xvf32gerpp {mma,quad}
+
+ void __builtin_mma_xvf64ger (v512 *, v256, vuc);
+ XVF64GER nothing {mma,pair}
+
+ v512 __builtin_mma_xvf64ger_internal (v256, vuc);
+ XVF64GER_INTERNAL mma_xvf64ger {mma,pair}
+
+ void __builtin_mma_xvf64gernn (v512 *, v256, vuc);
+ XVF64GERNN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gernn_internal (v512, v256, vuc);
+ XVF64GERNN_INTERNAL mma_xvf64gernn {mma,pair,quad}
+
+ void __builtin_mma_xvf64gernp (v512 *, v256, vuc);
+ XVF64GERNP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gernp_internal (v512, v256, vuc);
+ XVF64GERNP_INTERNAL mma_xvf64gernp {mma,pair,quad}
+
+ void __builtin_mma_xvf64gerpn (v512 *, v256, vuc);
+ XVF64GERPN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gerpn_internal (v512, v256, vuc);
+ XVF64GERPN_INTERNAL mma_xvf64gerpn {mma,pair,quad}
+
+ void __builtin_mma_xvf64gerpp (v512 *, v256, vuc);
+ XVF64GERPP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gerpp_internal (v512, v256, vuc);
+ XVF64GERPP_INTERNAL mma_xvf64gerpp {mma,pair,quad}
+
+ void __builtin_mma_xvi16ger2 (v512 *, vuc, vuc);
+ XVI16GER2 nothing {mma}
+
+ v512 __builtin_mma_xvi16ger2_internal (vuc, vuc);
+ XVI16GER2_INTERNAL mma_xvi16ger2 {mma}
+
+ void __builtin_mma_xvi16ger2pp (v512 *, vuc, vuc);
+ XVI16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi16ger2pp_internal (v512, vuc, vuc);
+ XVI16GER2PP_INTERNAL mma_xvi16ger2pp {mma,quad}
+
+ void __builtin_mma_xvi16ger2s (v512 *, vuc, vuc);
+ XVI16GER2S nothing {mma}
+
+ v512 __builtin_mma_xvi16ger2s_internal (vuc, vuc);
+ XVI16GER2S_INTERNAL mma_xvi16ger2s {mma}
+
+ void __builtin_mma_xvi16ger2spp (v512 *, vuc, vuc);
+ XVI16GER2SPP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi16ger2spp_internal (v512, vuc, vuc);
+ XVI16GER2SPP_INTERNAL mma_xvi16ger2spp {mma,quad}
+
+ void __builtin_mma_xvi4ger8 (v512 *, vuc, vuc);
+ XVI4GER8 nothing {mma}
+
+ v512 __builtin_mma_xvi4ger8_internal (vuc, vuc);
+ XVI4GER8_INTERNAL mma_xvi4ger8 {mma}
+
+ void __builtin_mma_xvi4ger8pp (v512 *, vuc, vuc);
+ XVI4GER8PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi4ger8pp_internal (v512, vuc, vuc);
+ XVI4GER8PP_INTERNAL mma_xvi4ger8pp {mma,quad}
+
+ void __builtin_mma_xvi8ger4 (v512 *, vuc, vuc);
+ XVI8GER4 nothing {mma}
+
+ v512 __builtin_mma_xvi8ger4_internal (vuc, vuc);
+ XVI8GER4_INTERNAL mma_xvi8ger4 {mma}
+
+ void __builtin_mma_xvi8ger4pp (v512 *, vuc, vuc);
+ XVI8GER4PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi8ger4pp_internal (v512, vuc, vuc);
+ XVI8GER4PP_INTERNAL mma_xvi8ger4pp {mma,quad}
+
+ void __builtin_mma_xvi8ger4spp (v512 *, vuc, vuc);
+ XVI8GER4SPP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi8ger4spp_internal (v512, vuc, vuc);
+ XVI8GER4SPP_INTERNAL mma_xvi8ger4spp {mma,quad}
+
+ void __builtin_mma_xxmfacc (v512 *);
+ XXMFACC nothing {mma,quad}
+
+ v512 __builtin_mma_xxmfacc_internal (v512);
+ XXMFACC_INTERNAL mma_xxmfacc {mma,quad}
+
+ void __builtin_mma_xxmtacc (v512 *);
+ XXMTACC nothing {mma,quad}
+
+ v512 __builtin_mma_xxmtacc_internal (v512);
+ XXMTACC_INTERNAL mma_xxmtacc {mma,quad}
+
+ void __builtin_mma_xxsetaccz (v512 *);
+ XXSETACCZ nothing {mma}
+
+ v512 __builtin_mma_xxsetaccz_internal ();
+ XXSETACCZ_INTERNAL mma_xxsetaccz {mma}
+
+ void __builtin_vsx_assemble_pair (v256 *, vuc, vuc);
+ ASSEMBLE_PAIR_V nothing {mma}
+
+ v256 __builtin_vsx_assemble_pair_internal (vuc, vuc);
+ ASSEMBLE_PAIR_V_INTERNAL vsx_assemble_pair {mma}
+
+ void __builtin_vsx_disassemble_pair (void *, v256 *);
+ DISASSEMBLE_PAIR_V nothing {mma,pair}
+
+ vuc __builtin_vsx_disassemble_pair_internal (v256, const int<2>);
+ DISASSEMBLE_PAIR_V_INTERNAL vsx_disassemble_pair {mma}
^ permalink raw reply [flat|nested] 7+ messages in thread
* [gcc(refs/users/wschmidt/heads/builtins10)] rs6000: Add MMA builtins
@ 2021-07-29 14:45 William Schmidt
0 siblings, 0 replies; 7+ messages in thread
From: William Schmidt @ 2021-07-29 14:45 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:2753411cd9d7d4b2fbe233f7eaf4414d058182b6
commit 2753411cd9d7d4b2fbe233f7eaf4414d058182b6
Author: Bill Schmidt <wschmidt@linux.ibm.com>
Date: Thu Jun 17 09:05:24 2021 -0500
rs6000: Add MMA builtins
2021-06-16 Bill Schmidt <wschmidt@linux.ibm.com>
gcc/
* config/rs6000/rs6000-builtin-new.def: Add mma stanza.
Diff:
---
gcc/config/rs6000/rs6000-builtin-new.def | 416 +++++++++++++++++++++++++++++++
1 file changed, 416 insertions(+)
diff --git a/gcc/config/rs6000/rs6000-builtin-new.def b/gcc/config/rs6000/rs6000-builtin-new.def
index 6b7a79549a4..4b65d54d913 100644
--- a/gcc/config/rs6000/rs6000-builtin-new.def
+++ b/gcc/config/rs6000/rs6000-builtin-new.def
@@ -3332,3 +3332,419 @@
const unsigned long long __builtin_pextd (unsigned long long, unsigned long long);
PEXTD pextd {}
+
+
+[mma]
+ void __builtin_mma_assemble_acc (v512 *, vuc, vuc, vuc, vuc);
+ ASSEMBLE_ACC nothing {mma}
+
+ v512 __builtin_mma_assemble_acc_internal (vuc, vuc, vuc, vuc);
+ ASSEMBLE_ACC_INTERNAL mma_assemble_acc {mma}
+
+ void __builtin_mma_assemble_pair (v256 *, vuc, vuc);
+ ASSEMBLE_PAIR nothing {mma}
+
+ v256 __builtin_mma_assemble_pair_internal (vuc, vuc);
+ ASSEMBLE_PAIR_INTERNAL vsx_assemble_pair {mma}
+
+ void __builtin_mma_build_acc (v512 *, vuc, vuc, vuc, vuc);
+ BUILD_ACC nothing {mma}
+
+ v512 __builtin_mma_build_acc_internal (vuc, vuc, vuc, vuc);
+ BUILD_ACC_INTERNAL mma_assemble_acc {mma}
+
+ void __builtin_mma_disassemble_acc (void *, v512 *);
+ DISASSEMBLE_ACC nothing {mma,quad}
+
+ vuc __builtin_mma_disassemble_acc_internal (v512, const int<2>);
+ DISASSEMBLE_ACC_INTERNAL mma_disassemble_acc {mma}
+
+ void __builtin_mma_disassemble_pair (void *, v256 *);
+ DISASSEMBLE_PAIR nothing {mma,pair}
+
+ vuc __builtin_mma_disassemble_pair_internal (v256, const int<2>);
+ DISASSEMBLE_PAIR_INTERNAL vsx_disassemble_pair {mma}
+
+ void __builtin_mma_pmxvbf16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2 nothing {mma}
+
+ v512 __builtin_mma_pmxvbf16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2_INTERNAL mma_pmxvbf16ger2 {mma}
+
+ void __builtin_mma_pmxvbf16ger2nn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2nn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NN_INTERNAL mma_pmxvbf16ger2nn {mma,quad}
+
+ void __builtin_mma_pmxvbf16ger2np (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2np_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NP_INTERNAL mma_pmxvbf16ger2np {mma,quad}
+
+ void __builtin_mma_pmxvbf16ger2pn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2pn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PN_INTERNAL mma_pmxvbf16ger2pn {mma,quad}
+
+ void __builtin_mma_pmxvbf16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PP_INTERNAL mma_pmxvbf16ger2pp {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2 nothing {mma}
+
+ v512 __builtin_mma_pmxvf16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2_INTERNAL mma_pmxvf16ger2 {mma}
+
+ void __builtin_mma_pmxvf16ger2nn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2nn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NN_INTERNAL mma_pmxvf16ger2nn {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2np (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2np_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NP_INTERNAL mma_pmxvf16ger2np {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2pn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2pn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PN_INTERNAL mma_pmxvf16ger2pn {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PP_INTERNAL mma_pmxvf16ger2pp {mma,quad}
+
+ void __builtin_mma_pmxvf32ger (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GER nothing {mma}
+
+ v512 __builtin_mma_pmxvf32ger_internal (vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GER_INTERNAL mma_pmxvf32ger {mma}
+
+ void __builtin_mma_pmxvf32gernn (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gernn_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNN_INTERNAL mma_pmxvf32gernn {mma,quad}
+
+ void __builtin_mma_pmxvf32gernp (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gernp_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNP_INTERNAL mma_pmxvf32gernp {mma,quad}
+
+ void __builtin_mma_pmxvf32gerpn (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gerpn_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPN_INTERNAL mma_pmxvf32gerpn {mma,quad}
+
+ void __builtin_mma_pmxvf32gerpp (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gerpp_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPP_INTERNAL mma_pmxvf32gerpp {mma,quad}
+
+ void __builtin_mma_pmxvf64ger (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GER nothing {mma,pair}
+
+ v512 __builtin_mma_pmxvf64ger_internal (v256, vuc, const int<4>, const int<2>);
+ PMXVF64GER_INTERNAL mma_pmxvf64ger {mma,pair}
+
+ void __builtin_mma_pmxvf64gernn (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gernn_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNN_INTERNAL mma_pmxvf64gernn {mma,pair,quad}
+
+ void __builtin_mma_pmxvf64gernp (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gernp_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNP_INTERNAL mma_pmxvf64gernp {mma,pair,quad}
+
+ void __builtin_mma_pmxvf64gerpn (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gerpn_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPN_INTERNAL mma_pmxvf64gerpn {mma,pair,quad}
+
+ void __builtin_mma_pmxvf64gerpp (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gerpp_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPP_INTERNAL mma_pmxvf64gerpp {mma,pair,quad}
+
+ void __builtin_mma_pmxvi16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2 nothing {mma}
+
+ v512 __builtin_mma_pmxvi16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2_INTERNAL mma_pmxvi16ger2 {mma}
+
+ void __builtin_mma_pmxvi16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2PP_INTERNAL mma_pmxvi16ger2pp {mma,quad}
+
+ void __builtin_mma_pmxvi16ger2s (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2S nothing {mma}
+
+ v512 __builtin_mma_pmxvi16ger2s_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2S_INTERNAL mma_pmxvi16ger2s {mma}
+
+ void __builtin_mma_pmxvi16ger2spp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2SPP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi16ger2spp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2SPP_INTERNAL mma_pmxvi16ger2spp {mma,quad}
+
+ void __builtin_mma_pmxvi4ger8 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<8>);
+ PMXVI4GER8 nothing {mma}
+
+ v512 __builtin_mma_pmxvi4ger8_internal (vuc, vuc, const int<4>, const int<4>, const int<8>);
+ PMXVI4GER8_INTERNAL mma_pmxvi4ger8 {mma}
+
+ void __builtin_mma_pmxvi4ger8pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI4GER8PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi4ger8pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI4GER8PP_INTERNAL mma_pmxvi4ger8pp {mma,quad}
+
+ void __builtin_mma_pmxvi8ger4 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4 nothing {mma}
+
+ v512 __builtin_mma_pmxvi8ger4_internal (vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4_INTERNAL mma_pmxvi8ger4 {mma}
+
+ void __builtin_mma_pmxvi8ger4pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi8ger4pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4PP_INTERNAL mma_pmxvi8ger4pp {mma,quad}
+
+ void __builtin_mma_pmxvi8ger4spp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4SPP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi8ger4spp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4SPP_INTERNAL mma_pmxvi8ger4spp {mma,quad}
+
+ void __builtin_mma_xvbf16ger2 (v512 *, vuc, vuc);
+ XVBF16GER2 nothing {mma}
+
+ v512 __builtin_mma_xvbf16ger2_internal (vuc, vuc);
+ XVBF16GER2_INTERNAL mma_xvbf16ger2 {mma}
+
+ void __builtin_mma_xvbf16ger2nn (v512 *, vuc, vuc);
+ XVBF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2nn_internal (v512, vuc, vuc);
+ XVBF16GER2NN_INTERNAL mma_xvbf16ger2nn {mma,quad}
+
+ void __builtin_mma_xvbf16ger2np (v512 *, vuc, vuc);
+ XVBF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2np_internal (v512, vuc, vuc);
+ XVBF16GER2NP_INTERNAL mma_xvbf16ger2np {mma,quad}
+
+ void __builtin_mma_xvbf16ger2pn (v512 *, vuc, vuc);
+ XVBF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2pn_internal (v512, vuc, vuc);
+ XVBF16GER2PN_INTERNAL mma_xvbf16ger2pn {mma,quad}
+
+ void __builtin_mma_xvbf16ger2pp (v512 *, vuc, vuc);
+ XVBF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2pp_internal (v512, vuc, vuc);
+ XVBF16GER2PP_INTERNAL mma_xvbf16ger2pp {mma,quad}
+
+ void __builtin_mma_xvf16ger2 (v512 *, vuc, vuc);
+ XVF16GER2 nothing {mma}
+
+ v512 __builtin_mma_xvf16ger2_internal (vuc, vuc);
+ XVF16GER2_INTERNAL mma_xvf16ger2 {mma}
+
+ void __builtin_mma_xvf16ger2nn (v512 *, vuc, vuc);
+ XVF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2nn_internal (v512, vuc, vuc);
+ XVF16GER2NN_INTERNAL mma_xvf16ger2nn {mma,quad}
+
+ void __builtin_mma_xvf16ger2np (v512 *, vuc, vuc);
+ XVF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2np_internal (v512, vuc, vuc);
+ XVF16GER2NP_INTERNAL mma_xvf16ger2np {mma,quad}
+
+ void __builtin_mma_xvf16ger2pn (v512 *, vuc, vuc);
+ XVF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2pn_internal (v512, vuc, vuc);
+ XVF16GER2PN_INTERNAL mma_xvf16ger2pn {mma,quad}
+
+ void __builtin_mma_xvf16ger2pp (v512 *, vuc, vuc);
+ XVF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2pp_internal (v512, vuc, vuc);
+ XVF16GER2PP_INTERNAL mma_xvf16ger2pp {mma,quad}
+
+ void __builtin_mma_xvf32ger (v512 *, vuc, vuc);
+ XVF32GER nothing {mma}
+
+ v512 __builtin_mma_xvf32ger_internal (vuc, vuc);
+ XVF32GER_INTERNAL mma_xvf32ger {mma}
+
+ void __builtin_mma_xvf32gernn (v512 *, vuc, vuc);
+ XVF32GERNN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gernn_internal (v512, vuc, vuc);
+ XVF32GERNN_INTERNAL mma_xvf32gernn {mma,quad}
+
+ void __builtin_mma_xvf32gernp (v512 *, vuc, vuc);
+ XVF32GERNP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gernp_internal (v512, vuc, vuc);
+ XVF32GERNP_INTERNAL mma_xvf32gernp {mma,quad}
+
+ void __builtin_mma_xvf32gerpn (v512 *, vuc, vuc);
+ XVF32GERPN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gerpn_internal (v512, vuc, vuc);
+ XVF32GERPN_INTERNAL mma_xvf32gerpn {mma,quad}
+
+ void __builtin_mma_xvf32gerpp (v512 *, vuc, vuc);
+ XVF32GERPP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gerpp_internal (v512, vuc, vuc);
+ XVF32GERPP_INTERNAL mma_xvf32gerpp {mma,quad}
+
+ void __builtin_mma_xvf64ger (v512 *, v256, vuc);
+ XVF64GER nothing {mma,pair}
+
+ v512 __builtin_mma_xvf64ger_internal (v256, vuc);
+ XVF64GER_INTERNAL mma_xvf64ger {mma,pair}
+
+ void __builtin_mma_xvf64gernn (v512 *, v256, vuc);
+ XVF64GERNN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gernn_internal (v512, v256, vuc);
+ XVF64GERNN_INTERNAL mma_xvf64gernn {mma,pair,quad}
+
+ void __builtin_mma_xvf64gernp (v512 *, v256, vuc);
+ XVF64GERNP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gernp_internal (v512, v256, vuc);
+ XVF64GERNP_INTERNAL mma_xvf64gernp {mma,pair,quad}
+
+ void __builtin_mma_xvf64gerpn (v512 *, v256, vuc);
+ XVF64GERPN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gerpn_internal (v512, v256, vuc);
+ XVF64GERPN_INTERNAL mma_xvf64gerpn {mma,pair,quad}
+
+ void __builtin_mma_xvf64gerpp (v512 *, v256, vuc);
+ XVF64GERPP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gerpp_internal (v512, v256, vuc);
+ XVF64GERPP_INTERNAL mma_xvf64gerpp {mma,pair,quad}
+
+ void __builtin_mma_xvi16ger2 (v512 *, vuc, vuc);
+ XVI16GER2 nothing {mma}
+
+ v512 __builtin_mma_xvi16ger2_internal (vuc, vuc);
+ XVI16GER2_INTERNAL mma_xvi16ger2 {mma}
+
+ void __builtin_mma_xvi16ger2pp (v512 *, vuc, vuc);
+ XVI16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi16ger2pp_internal (v512, vuc, vuc);
+ XVI16GER2PP_INTERNAL mma_xvi16ger2pp {mma,quad}
+
+ void __builtin_mma_xvi16ger2s (v512 *, vuc, vuc);
+ XVI16GER2S nothing {mma}
+
+ v512 __builtin_mma_xvi16ger2s_internal (vuc, vuc);
+ XVI16GER2S_INTERNAL mma_xvi16ger2s {mma}
+
+ void __builtin_mma_xvi16ger2spp (v512 *, vuc, vuc);
+ XVI16GER2SPP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi16ger2spp_internal (v512, vuc, vuc);
+ XVI16GER2SPP_INTERNAL mma_xvi16ger2spp {mma,quad}
+
+ void __builtin_mma_xvi4ger8 (v512 *, vuc, vuc);
+ XVI4GER8 nothing {mma}
+
+ v512 __builtin_mma_xvi4ger8_internal (vuc, vuc);
+ XVI4GER8_INTERNAL mma_xvi4ger8 {mma}
+
+ void __builtin_mma_xvi4ger8pp (v512 *, vuc, vuc);
+ XVI4GER8PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi4ger8pp_internal (v512, vuc, vuc);
+ XVI4GER8PP_INTERNAL mma_xvi4ger8pp {mma,quad}
+
+ void __builtin_mma_xvi8ger4 (v512 *, vuc, vuc);
+ XVI8GER4 nothing {mma}
+
+ v512 __builtin_mma_xvi8ger4_internal (vuc, vuc);
+ XVI8GER4_INTERNAL mma_xvi8ger4 {mma}
+
+ void __builtin_mma_xvi8ger4pp (v512 *, vuc, vuc);
+ XVI8GER4PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi8ger4pp_internal (v512, vuc, vuc);
+ XVI8GER4PP_INTERNAL mma_xvi8ger4pp {mma,quad}
+
+ void __builtin_mma_xvi8ger4spp (v512 *, vuc, vuc);
+ XVI8GER4SPP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi8ger4spp_internal (v512, vuc, vuc);
+ XVI8GER4SPP_INTERNAL mma_xvi8ger4spp {mma,quad}
+
+ void __builtin_mma_xxmfacc (v512 *);
+ XXMFACC nothing {mma,quad}
+
+ v512 __builtin_mma_xxmfacc_internal (v512);
+ XXMFACC_INTERNAL mma_xxmfacc {mma,quad}
+
+ void __builtin_mma_xxmtacc (v512 *);
+ XXMTACC nothing {mma,quad}
+
+ v512 __builtin_mma_xxmtacc_internal (v512);
+ XXMTACC_INTERNAL mma_xxmtacc {mma,quad}
+
+ void __builtin_mma_xxsetaccz (v512 *);
+ XXSETACCZ nothing {mma}
+
+ v512 __builtin_mma_xxsetaccz_internal ();
+ XXSETACCZ_INTERNAL mma_xxsetaccz {mma}
+
+ void __builtin_vsx_assemble_pair (v256 *, vuc, vuc);
+ ASSEMBLE_PAIR_V nothing {mma}
+
+ v256 __builtin_vsx_assemble_pair_internal (vuc, vuc);
+ ASSEMBLE_PAIR_V_INTERNAL vsx_assemble_pair {mma}
+
+ void __builtin_vsx_build_pair (v256 *, vuc, vuc);
+ BUILD_PAIR nothing {mma}
+
+ v256 __builtin_vsx_build_pair_internal (vuc, vuc);
+ BUILD_PAIR_INTERNAL vsx_assemble_pair {mma}
+
+ void __builtin_vsx_disassemble_pair (void *, v256 *);
+ DISASSEMBLE_PAIR_V nothing {mma,pair}
+
+ vuc __builtin_vsx_disassemble_pair_internal (v256, const int<2>);
+ DISASSEMBLE_PAIR_V_INTERNAL vsx_disassemble_pair {mma}
^ permalink raw reply [flat|nested] 7+ messages in thread
* [gcc(refs/users/wschmidt/heads/builtins10)] rs6000: Add MMA builtins
@ 2021-06-25 16:17 William Schmidt
0 siblings, 0 replies; 7+ messages in thread
From: William Schmidt @ 2021-06-25 16:17 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:77ad89361fed0f355a3e3fbe63493fcb5756ed8e
commit 77ad89361fed0f355a3e3fbe63493fcb5756ed8e
Author: Bill Schmidt <wschmidt@linux.ibm.com>
Date: Thu Jun 17 09:05:24 2021 -0500
rs6000: Add MMA builtins
2021-06-16 Bill Schmidt <wschmidt@linux.ibm.com>
gcc/
* config/rs6000/rs6000-builtin-new.def: Add mma stanza.
Diff:
---
gcc/config/rs6000/rs6000-builtin-new.def | 416 +++++++++++++++++++++++++++++++
1 file changed, 416 insertions(+)
diff --git a/gcc/config/rs6000/rs6000-builtin-new.def b/gcc/config/rs6000/rs6000-builtin-new.def
index b0e12a0ed9b..f3e1c8bbd82 100644
--- a/gcc/config/rs6000/rs6000-builtin-new.def
+++ b/gcc/config/rs6000/rs6000-builtin-new.def
@@ -3332,3 +3332,419 @@
const unsigned long long __builtin_pextd (unsigned long long, unsigned long long);
PEXTD pextd {}
+
+
+[mma]
+ void __builtin_mma_assemble_acc (v512 *, vuc, vuc, vuc, vuc);
+ ASSEMBLE_ACC nothing {mma}
+
+ v512 __builtin_mma_assemble_acc_internal (vuc, vuc, vuc, vuc);
+ ASSEMBLE_ACC_INTERNAL mma_assemble_acc {mma}
+
+ void __builtin_mma_assemble_pair (v256 *, vuc, vuc);
+ ASSEMBLE_PAIR nothing {mma}
+
+ v256 __builtin_mma_assemble_pair_internal (vuc, vuc);
+ ASSEMBLE_PAIR_INTERNAL vsx_assemble_pair {mma}
+
+ void __builtin_mma_build_acc (v512 *, vuc, vuc, vuc, vuc);
+ BUILD_ACC nothing {mma}
+
+ v512 __builtin_mma_build_acc_internal (vuc, vuc, vuc, vuc);
+ BUILD_ACC_INTERNAL mma_assemble_acc {mma}
+
+ void __builtin_mma_disassemble_acc (void *, v512 *);
+ DISASSEMBLE_ACC nothing {mma,quad}
+
+ vuc __builtin_mma_disassemble_acc_internal (v512, const int<2>);
+ DISASSEMBLE_ACC_INTERNAL mma_disassemble_acc {mma}
+
+ void __builtin_mma_disassemble_pair (void *, v256 *);
+ DISASSEMBLE_PAIR nothing {mma,pair}
+
+ vuc __builtin_mma_disassemble_pair_internal (v256, const int<2>);
+ DISASSEMBLE_PAIR_INTERNAL vsx_disassemble_pair {mma}
+
+ void __builtin_mma_pmxvbf16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2 nothing {mma}
+
+ v512 __builtin_mma_pmxvbf16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2_INTERNAL mma_pmxvbf16ger2 {mma}
+
+ void __builtin_mma_pmxvbf16ger2nn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2nn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NN_INTERNAL mma_pmxvbf16ger2nn {mma,quad}
+
+ void __builtin_mma_pmxvbf16ger2np (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2np_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NP_INTERNAL mma_pmxvbf16ger2np {mma,quad}
+
+ void __builtin_mma_pmxvbf16ger2pn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2pn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PN_INTERNAL mma_pmxvbf16ger2pn {mma,quad}
+
+ void __builtin_mma_pmxvbf16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PP_INTERNAL mma_pmxvbf16ger2pp {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2 nothing {mma}
+
+ v512 __builtin_mma_pmxvf16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2_INTERNAL mma_pmxvf16ger2 {mma}
+
+ void __builtin_mma_pmxvf16ger2nn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2nn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NN_INTERNAL mma_pmxvf16ger2nn {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2np (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2np_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NP_INTERNAL mma_pmxvf16ger2np {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2pn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2pn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PN_INTERNAL mma_pmxvf16ger2pn {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PP_INTERNAL mma_pmxvf16ger2pp {mma,quad}
+
+ void __builtin_mma_pmxvf32ger (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GER nothing {mma}
+
+ v512 __builtin_mma_pmxvf32ger_internal (vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GER_INTERNAL mma_pmxvf32ger {mma}
+
+ void __builtin_mma_pmxvf32gernn (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gernn_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNN_INTERNAL mma_pmxvf32gernn {mma,quad}
+
+ void __builtin_mma_pmxvf32gernp (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gernp_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNP_INTERNAL mma_pmxvf32gernp {mma,quad}
+
+ void __builtin_mma_pmxvf32gerpn (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gerpn_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPN_INTERNAL mma_pmxvf32gerpn {mma,quad}
+
+ void __builtin_mma_pmxvf32gerpp (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gerpp_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPP_INTERNAL mma_pmxvf32gerpp {mma,quad}
+
+ void __builtin_mma_pmxvf64ger (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GER nothing {mma,pair}
+
+ v512 __builtin_mma_pmxvf64ger_internal (v256, vuc, const int<4>, const int<2>);
+ PMXVF64GER_INTERNAL mma_pmxvf64ger {mma,pair}
+
+ void __builtin_mma_pmxvf64gernn (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gernn_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNN_INTERNAL mma_pmxvf64gernn {mma,pair,quad}
+
+ void __builtin_mma_pmxvf64gernp (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gernp_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNP_INTERNAL mma_pmxvf64gernp {mma,pair,quad}
+
+ void __builtin_mma_pmxvf64gerpn (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gerpn_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPN_INTERNAL mma_pmxvf64gerpn {mma,pair,quad}
+
+ void __builtin_mma_pmxvf64gerpp (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gerpp_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPP_INTERNAL mma_pmxvf64gerpp {mma,pair,quad}
+
+ void __builtin_mma_pmxvi16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2 nothing {mma}
+
+ v512 __builtin_mma_pmxvi16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2_INTERNAL mma_pmxvi16ger2 {mma}
+
+ void __builtin_mma_pmxvi16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2PP_INTERNAL mma_pmxvi16ger2pp {mma,quad}
+
+ void __builtin_mma_pmxvi16ger2s (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2S nothing {mma}
+
+ v512 __builtin_mma_pmxvi16ger2s_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2S_INTERNAL mma_pmxvi16ger2s {mma}
+
+ void __builtin_mma_pmxvi16ger2spp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2SPP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi16ger2spp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2SPP_INTERNAL mma_pmxvi16ger2spp {mma,quad}
+
+ void __builtin_mma_pmxvi4ger8 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<8>);
+ PMXVI4GER8 nothing {mma}
+
+ v512 __builtin_mma_pmxvi4ger8_internal (vuc, vuc, const int<4>, const int<4>, const int<8>);
+ PMXVI4GER8_INTERNAL mma_pmxvi4ger8 {mma}
+
+ void __builtin_mma_pmxvi4ger8pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI4GER8PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi4ger8pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI4GER8PP_INTERNAL mma_pmxvi4ger8pp {mma,quad}
+
+ void __builtin_mma_pmxvi8ger4 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4 nothing {mma}
+
+ v512 __builtin_mma_pmxvi8ger4_internal (vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4_INTERNAL mma_pmxvi8ger4 {mma}
+
+ void __builtin_mma_pmxvi8ger4pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi8ger4pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4PP_INTERNAL mma_pmxvi8ger4pp {mma,quad}
+
+ void __builtin_mma_pmxvi8ger4spp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4SPP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi8ger4spp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4SPP_INTERNAL mma_pmxvi8ger4spp {mma,quad}
+
+ void __builtin_mma_xvbf16ger2 (v512 *, vuc, vuc);
+ XVBF16GER2 nothing {mma}
+
+ v512 __builtin_mma_xvbf16ger2_internal (vuc, vuc);
+ XVBF16GER2_INTERNAL mma_xvbf16ger2 {mma}
+
+ void __builtin_mma_xvbf16ger2nn (v512 *, vuc, vuc);
+ XVBF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2nn_internal (v512, vuc, vuc);
+ XVBF16GER2NN_INTERNAL mma_xvbf16ger2nn {mma,quad}
+
+ void __builtin_mma_xvbf16ger2np (v512 *, vuc, vuc);
+ XVBF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2np_internal (v512, vuc, vuc);
+ XVBF16GER2NP_INTERNAL mma_xvbf16ger2np {mma,quad}
+
+ void __builtin_mma_xvbf16ger2pn (v512 *, vuc, vuc);
+ XVBF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2pn_internal (v512, vuc, vuc);
+ XVBF16GER2PN_INTERNAL mma_xvbf16ger2pn {mma,quad}
+
+ void __builtin_mma_xvbf16ger2pp (v512 *, vuc, vuc);
+ XVBF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2pp_internal (v512, vuc, vuc);
+ XVBF16GER2PP_INTERNAL mma_xvbf16ger2pp {mma,quad}
+
+ void __builtin_mma_xvf16ger2 (v512 *, vuc, vuc);
+ XVF16GER2 nothing {mma}
+
+ v512 __builtin_mma_xvf16ger2_internal (vuc, vuc);
+ XVF16GER2_INTERNAL mma_xvf16ger2 {mma}
+
+ void __builtin_mma_xvf16ger2nn (v512 *, vuc, vuc);
+ XVF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2nn_internal (v512, vuc, vuc);
+ XVF16GER2NN_INTERNAL mma_xvf16ger2nn {mma,quad}
+
+ void __builtin_mma_xvf16ger2np (v512 *, vuc, vuc);
+ XVF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2np_internal (v512, vuc, vuc);
+ XVF16GER2NP_INTERNAL mma_xvf16ger2np {mma,quad}
+
+ void __builtin_mma_xvf16ger2pn (v512 *, vuc, vuc);
+ XVF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2pn_internal (v512, vuc, vuc);
+ XVF16GER2PN_INTERNAL mma_xvf16ger2pn {mma,quad}
+
+ void __builtin_mma_xvf16ger2pp (v512 *, vuc, vuc);
+ XVF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2pp_internal (v512, vuc, vuc);
+ XVF16GER2PP_INTERNAL mma_xvf16ger2pp {mma,quad}
+
+ void __builtin_mma_xvf32ger (v512 *, vuc, vuc);
+ XVF32GER nothing {mma}
+
+ v512 __builtin_mma_xvf32ger_internal (vuc, vuc);
+ XVF32GER_INTERNAL mma_xvf32ger {mma}
+
+ void __builtin_mma_xvf32gernn (v512 *, vuc, vuc);
+ XVF32GERNN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gernn_internal (v512, vuc, vuc);
+ XVF32GERNN_INTERNAL mma_xvf32gernn {mma,quad}
+
+ void __builtin_mma_xvf32gernp (v512 *, vuc, vuc);
+ XVF32GERNP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gernp_internal (v512, vuc, vuc);
+ XVF32GERNP_INTERNAL mma_xvf32gernp {mma,quad}
+
+ void __builtin_mma_xvf32gerpn (v512 *, vuc, vuc);
+ XVF32GERPN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gerpn_internal (v512, vuc, vuc);
+ XVF32GERPN_INTERNAL mma_xvf32gerpn {mma,quad}
+
+ void __builtin_mma_xvf32gerpp (v512 *, vuc, vuc);
+ XVF32GERPP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gerpp_internal (v512, vuc, vuc);
+ XVF32GERPP_INTERNAL mma_xvf32gerpp {mma,quad}
+
+ void __builtin_mma_xvf64ger (v512 *, v256, vuc);
+ XVF64GER nothing {mma,pair}
+
+ v512 __builtin_mma_xvf64ger_internal (v256, vuc);
+ XVF64GER_INTERNAL mma_xvf64ger {mma,pair}
+
+ void __builtin_mma_xvf64gernn (v512 *, v256, vuc);
+ XVF64GERNN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gernn_internal (v512, v256, vuc);
+ XVF64GERNN_INTERNAL mma_xvf64gernn {mma,pair,quad}
+
+ void __builtin_mma_xvf64gernp (v512 *, v256, vuc);
+ XVF64GERNP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gernp_internal (v512, v256, vuc);
+ XVF64GERNP_INTERNAL mma_xvf64gernp {mma,pair,quad}
+
+ void __builtin_mma_xvf64gerpn (v512 *, v256, vuc);
+ XVF64GERPN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gerpn_internal (v512, v256, vuc);
+ XVF64GERPN_INTERNAL mma_xvf64gerpn {mma,pair,quad}
+
+ void __builtin_mma_xvf64gerpp (v512 *, v256, vuc);
+ XVF64GERPP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gerpp_internal (v512, v256, vuc);
+ XVF64GERPP_INTERNAL mma_xvf64gerpp {mma,pair,quad}
+
+ void __builtin_mma_xvi16ger2 (v512 *, vuc, vuc);
+ XVI16GER2 nothing {mma}
+
+ v512 __builtin_mma_xvi16ger2_internal (vuc, vuc);
+ XVI16GER2_INTERNAL mma_xvi16ger2 {mma}
+
+ void __builtin_mma_xvi16ger2pp (v512 *, vuc, vuc);
+ XVI16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi16ger2pp_internal (v512, vuc, vuc);
+ XVI16GER2PP_INTERNAL mma_xvi16ger2pp {mma,quad}
+
+ void __builtin_mma_xvi16ger2s (v512 *, vuc, vuc);
+ XVI16GER2S nothing {mma}
+
+ v512 __builtin_mma_xvi16ger2s_internal (vuc, vuc);
+ XVI16GER2S_INTERNAL mma_xvi16ger2s {mma}
+
+ void __builtin_mma_xvi16ger2spp (v512 *, vuc, vuc);
+ XVI16GER2SPP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi16ger2spp_internal (v512, vuc, vuc);
+ XVI16GER2SPP_INTERNAL mma_xvi16ger2spp {mma,quad}
+
+ void __builtin_mma_xvi4ger8 (v512 *, vuc, vuc);
+ XVI4GER8 nothing {mma}
+
+ v512 __builtin_mma_xvi4ger8_internal (vuc, vuc);
+ XVI4GER8_INTERNAL mma_xvi4ger8 {mma}
+
+ void __builtin_mma_xvi4ger8pp (v512 *, vuc, vuc);
+ XVI4GER8PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi4ger8pp_internal (v512, vuc, vuc);
+ XVI4GER8PP_INTERNAL mma_xvi4ger8pp {mma,quad}
+
+ void __builtin_mma_xvi8ger4 (v512 *, vuc, vuc);
+ XVI8GER4 nothing {mma}
+
+ v512 __builtin_mma_xvi8ger4_internal (vuc, vuc);
+ XVI8GER4_INTERNAL mma_xvi8ger4 {mma}
+
+ void __builtin_mma_xvi8ger4pp (v512 *, vuc, vuc);
+ XVI8GER4PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi8ger4pp_internal (v512, vuc, vuc);
+ XVI8GER4PP_INTERNAL mma_xvi8ger4pp {mma,quad}
+
+ void __builtin_mma_xvi8ger4spp (v512 *, vuc, vuc);
+ XVI8GER4SPP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi8ger4spp_internal (v512, vuc, vuc);
+ XVI8GER4SPP_INTERNAL mma_xvi8ger4spp {mma,quad}
+
+ void __builtin_mma_xxmfacc (v512 *);
+ XXMFACC nothing {mma,quad}
+
+ v512 __builtin_mma_xxmfacc_internal (v512);
+ XXMFACC_INTERNAL mma_xxmfacc {mma,quad}
+
+ void __builtin_mma_xxmtacc (v512 *);
+ XXMTACC nothing {mma,quad}
+
+ v512 __builtin_mma_xxmtacc_internal (v512);
+ XXMTACC_INTERNAL mma_xxmtacc {mma,quad}
+
+ void __builtin_mma_xxsetaccz (v512 *);
+ XXSETACCZ nothing {mma}
+
+ v512 __builtin_mma_xxsetaccz_internal ();
+ XXSETACCZ_INTERNAL mma_xxsetaccz {mma}
+
+ void __builtin_vsx_assemble_pair (v256 *, vuc, vuc);
+ ASSEMBLE_PAIR_V nothing {mma}
+
+ v256 __builtin_vsx_assemble_pair_internal (vuc, vuc);
+ ASSEMBLE_PAIR_V_INTERNAL vsx_assemble_pair {mma}
+
+ void __builtin_vsx_build_pair (v256 *, vuc, vuc);
+ BUILD_PAIR nothing {mma}
+
+ v256 __builtin_vsx_build_pair_internal (vuc, vuc);
+ BUILD_PAIR_INTERNAL vsx_assemble_pair {mma}
+
+ void __builtin_vsx_disassemble_pair (void *, v256 *);
+ DISASSEMBLE_PAIR_V nothing {mma,pair}
+
+ vuc __builtin_vsx_disassemble_pair_internal (v256, const int<2>);
+ DISASSEMBLE_PAIR_V_INTERNAL vsx_disassemble_pair {mma}
^ permalink raw reply [flat|nested] 7+ messages in thread
* [gcc(refs/users/wschmidt/heads/builtins10)] rs6000: Add MMA builtins
@ 2021-04-26 20:50 William Schmidt
0 siblings, 0 replies; 7+ messages in thread
From: William Schmidt @ 2021-04-26 20:50 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:c0d6bbaf99ad160d97bbce8863050952f8cc4cd3
commit c0d6bbaf99ad160d97bbce8863050952f8cc4cd3
Author: Bill Schmidt <wschmidt@linux.ibm.com>
Date: Wed Mar 24 15:50:37 2021 -0500
rs6000: Add MMA builtins
2021-03-24 Bill Schmidt <wschmidt@linux.ibm.com>
gcc/
* config/rs6000/rs6000-builtin-new.def: Add mma stanza.
Diff:
---
gcc/config/rs6000/rs6000-builtin-new.def | 404 +++++++++++++++++++++++++++++++
1 file changed, 404 insertions(+)
diff --git a/gcc/config/rs6000/rs6000-builtin-new.def b/gcc/config/rs6000/rs6000-builtin-new.def
index dcb455ed6dd..71fe0431da6 100644
--- a/gcc/config/rs6000/rs6000-builtin-new.def
+++ b/gcc/config/rs6000/rs6000-builtin-new.def
@@ -3221,3 +3221,407 @@
const unsigned long long __builtin_pextd (unsigned long long, unsigned long long);
PEXTD pextd {}
+
+
+[mma]
+ void __builtin_mma_assemble_acc (v512 *, vuc, vuc, vuc, vuc);
+ ASSEMBLE_ACC nothing {mma}
+
+ v512 __builtin_mma_assemble_acc_internal (vuc, vuc, vuc, vuc);
+ ASSEMBLE_ACC_INTERNAL mma_assemble_acc {mma}
+
+ void __builtin_mma_assemble_pair (v256 *, vuc, vuc);
+ ASSEMBLE_PAIR nothing {mma}
+
+ v256 __builtin_mma_assemble_pair_internal (vuc, vuc);
+ ASSEMBLE_PAIR_INTERNAL vsx_assemble_pair {mma}
+
+ void __builtin_mma_disassemble_acc (void *, v512 *);
+ DISASSEMBLE_ACC nothing {mma,quad}
+
+ vuc __builtin_mma_disassemble_acc_internal (v512, const int<2>);
+ DISASSEMBLE_ACC_INTERNAL mma_disassemble_acc {mma}
+
+ void __builtin_mma_disassemble_pair (void *, v256 *);
+ DISASSEMBLE_PAIR nothing {mma,pair}
+
+ vuc __builtin_mma_disassemble_pair_internal (v256, const int<2>);
+ DISASSEMBLE_PAIR_INTERNAL vsx_disassemble_pair {mma}
+
+ void __builtin_mma_pmxvbf16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2 nothing {mma}
+
+ v512 __builtin_mma_pmxvbf16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2_INTERNAL mma_pmxvbf16ger2 {mma}
+
+ void __builtin_mma_pmxvbf16ger2nn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2nn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NN_INTERNAL mma_pmxvbf16ger2nn {mma,quad}
+
+ void __builtin_mma_pmxvbf16ger2np (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2np_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NP_INTERNAL mma_pmxvbf16ger2np {mma,quad}
+
+ void __builtin_mma_pmxvbf16ger2pn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2pn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PN_INTERNAL mma_pmxvbf16ger2pn {mma,quad}
+
+ void __builtin_mma_pmxvbf16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PP_INTERNAL mma_pmxvbf16ger2pp {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2 nothing {mma}
+
+ v512 __builtin_mma_pmxvf16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2_INTERNAL mma_pmxvf16ger2 {mma}
+
+ void __builtin_mma_pmxvf16ger2nn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2nn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NN_INTERNAL mma_pmxvf16ger2nn {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2np (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2np_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NP_INTERNAL mma_pmxvf16ger2np {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2pn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2pn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PN_INTERNAL mma_pmxvf16ger2pn {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PP_INTERNAL mma_pmxvf16ger2pp {mma,quad}
+
+ void __builtin_mma_pmxvf32ger (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GER nothing {mma}
+
+ v512 __builtin_mma_pmxvf32ger_internal (vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GER_INTERNAL mma_pmxvf32ger {mma}
+
+ void __builtin_mma_pmxvf32gernn (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gernn_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNN_INTERNAL mma_pmxvf32gernn {mma,quad}
+
+ void __builtin_mma_pmxvf32gernp (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gernp_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNP_INTERNAL mma_pmxvf32gernp {mma,quad}
+
+ void __builtin_mma_pmxvf32gerpn (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gerpn_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPN_INTERNAL mma_pmxvf32gerpn {mma,quad}
+
+ void __builtin_mma_pmxvf32gerpp (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gerpp_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPP_INTERNAL mma_pmxvf32gerpp {mma,quad}
+
+ void __builtin_mma_pmxvf64ger (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GER nothing {mma,pair}
+
+ v512 __builtin_mma_pmxvf64ger_internal (v256, vuc, const int<4>, const int<2>);
+ PMXVF64GER_INTERNAL mma_pmxvf64ger {mma,pair}
+
+ void __builtin_mma_pmxvf64gernn (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gernn_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNN_INTERNAL mma_pmxvf64gernn {mma,pair,quad}
+
+ void __builtin_mma_pmxvf64gernp (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gernp_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNP_INTERNAL mma_pmxvf64gernp {mma,pair,quad}
+
+ void __builtin_mma_pmxvf64gerpn (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gerpn_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPN_INTERNAL mma_pmxvf64gerpn {mma,pair,quad}
+
+ void __builtin_mma_pmxvf64gerpp (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gerpp_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPP_INTERNAL mma_pmxvf64gerpp {mma,pair,quad}
+
+ void __builtin_mma_pmxvi16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2 nothing {mma}
+
+ v512 __builtin_mma_pmxvi16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2_INTERNAL mma_pmxvi16ger2 {mma}
+
+ void __builtin_mma_pmxvi16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2PP_INTERNAL mma_pmxvi16ger2pp {mma,quad}
+
+ void __builtin_mma_pmxvi16ger2s (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2S nothing {mma}
+
+ v512 __builtin_mma_pmxvi16ger2s_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2S_INTERNAL mma_pmxvi16ger2s {mma}
+
+ void __builtin_mma_pmxvi16ger2spp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2SPP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi16ger2spp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2SPP_INTERNAL mma_pmxvi16ger2spp {mma,quad}
+
+ void __builtin_mma_pmxvi4ger8 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<8>);
+ PMXVI4GER8 nothing {mma}
+
+ v512 __builtin_mma_pmxvi4ger8_internal (vuc, vuc, const int<4>, const int<4>, const int<8>);
+ PMXVI4GER8_INTERNAL mma_pmxvi4ger8 {mma}
+
+ void __builtin_mma_pmxvi4ger8pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI4GER8PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi4ger8pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI4GER8PP_INTERNAL mma_pmxvi4ger8pp {mma,quad}
+
+ void __builtin_mma_pmxvi8ger4 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4 nothing {mma}
+
+ v512 __builtin_mma_pmxvi8ger4_internal (vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4_INTERNAL mma_pmxvi8ger4 {mma}
+
+ void __builtin_mma_pmxvi8ger4pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi8ger4pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4PP_INTERNAL mma_pmxvi8ger4pp {mma,quad}
+
+ void __builtin_mma_pmxvi8ger4spp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4SPP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi8ger4spp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4SPP_INTERNAL mma_pmxvi8ger4spp {mma,quad}
+
+ void __builtin_mma_xvbf16ger2 (v512 *, vuc, vuc);
+ XVBF16GER2 nothing {mma}
+
+ v512 __builtin_mma_xvbf16ger2_internal (vuc, vuc);
+ XVBF16GER2_INTERNAL mma_xvbf16ger2 {mma}
+
+ void __builtin_mma_xvbf16ger2nn (v512 *, vuc, vuc);
+ XVBF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2nn_internal (v512, vuc, vuc);
+ XVBF16GER2NN_INTERNAL mma_xvbf16ger2nn {mma,quad}
+
+ void __builtin_mma_xvbf16ger2np (v512 *, vuc, vuc);
+ XVBF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2np_internal (v512, vuc, vuc);
+ XVBF16GER2NP_INTERNAL mma_xvbf16ger2np {mma,quad}
+
+ void __builtin_mma_xvbf16ger2pn (v512 *, vuc, vuc);
+ XVBF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2pn_internal (v512, vuc, vuc);
+ XVBF16GER2PN_INTERNAL mma_xvbf16ger2pn {mma,quad}
+
+ void __builtin_mma_xvbf16ger2pp (v512 *, vuc, vuc);
+ XVBF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2pp_internal (v512, vuc, vuc);
+ XVBF16GER2PP_INTERNAL mma_xvbf16ger2pp {mma,quad}
+
+ void __builtin_mma_xvf16ger2 (v512 *, vuc, vuc);
+ XVF16GER2 nothing {mma}
+
+ v512 __builtin_mma_xvf16ger2_internal (vuc, vuc);
+ XVF16GER2_INTERNAL mma_xvf16ger2 {mma}
+
+ void __builtin_mma_xvf16ger2nn (v512 *, vuc, vuc);
+ XVF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2nn_internal (v512, vuc, vuc);
+ XVF16GER2NN_INTERNAL mma_xvf16ger2nn {mma,quad}
+
+ void __builtin_mma_xvf16ger2np (v512 *, vuc, vuc);
+ XVF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2np_internal (v512, vuc, vuc);
+ XVF16GER2NP_INTERNAL mma_xvf16ger2np {mma,quad}
+
+ void __builtin_mma_xvf16ger2pn (v512 *, vuc, vuc);
+ XVF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2pn_internal (v512, vuc, vuc);
+ XVF16GER2PN_INTERNAL mma_xvf16ger2pn {mma,quad}
+
+ void __builtin_mma_xvf16ger2pp (v512 *, vuc, vuc);
+ XVF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2pp_internal (v512, vuc, vuc);
+ XVF16GER2PP_INTERNAL mma_xvf16ger2pp {mma,quad}
+
+ void __builtin_mma_xvf32ger (v512 *, vuc, vuc);
+ XVF32GER nothing {mma}
+
+ v512 __builtin_mma_xvf32ger_internal (vuc, vuc);
+ XVF32GER_INTERNAL mma_xvf32ger {mma}
+
+ void __builtin_mma_xvf32gernn (v512 *, vuc, vuc);
+ XVF32GERNN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gernn_internal (v512, vuc, vuc);
+ XVF32GERNN_INTERNAL mma_xvf32gernn {mma,quad}
+
+ void __builtin_mma_xvf32gernp (v512 *, vuc, vuc);
+ XVF32GERNP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gernp_internal (v512, vuc, vuc);
+ XVF32GERNP_INTERNAL mma_xvf32gernp {mma,quad}
+
+ void __builtin_mma_xvf32gerpn (v512 *, vuc, vuc);
+ XVF32GERPN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gerpn_internal (v512, vuc, vuc);
+ XVF32GERPN_INTERNAL mma_xvf32gerpn {mma,quad}
+
+ void __builtin_mma_xvf32gerpp (v512 *, vuc, vuc);
+ XVF32GERPP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gerpp_internal (v512, vuc, vuc);
+ XVF32GERPP_INTERNAL mma_xvf32gerpp {mma,quad}
+
+ void __builtin_mma_xvf64ger (v512 *, v256, vuc);
+ XVF64GER nothing {mma,pair}
+
+ v512 __builtin_mma_xvf64ger_internal (v256, vuc);
+ XVF64GER_INTERNAL mma_xvf64ger {mma,pair}
+
+ void __builtin_mma_xvf64gernn (v512 *, v256, vuc);
+ XVF64GERNN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gernn_internal (v512, v256, vuc);
+ XVF64GERNN_INTERNAL mma_xvf64gernn {mma,pair,quad}
+
+ void __builtin_mma_xvf64gernp (v512 *, v256, vuc);
+ XVF64GERNP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gernp_internal (v512, v256, vuc);
+ XVF64GERNP_INTERNAL mma_xvf64gernp {mma,pair,quad}
+
+ void __builtin_mma_xvf64gerpn (v512 *, v256, vuc);
+ XVF64GERPN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gerpn_internal (v512, v256, vuc);
+ XVF64GERPN_INTERNAL mma_xvf64gerpn {mma,pair,quad}
+
+ void __builtin_mma_xvf64gerpp (v512 *, v256, vuc);
+ XVF64GERPP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gerpp_internal (v512, v256, vuc);
+ XVF64GERPP_INTERNAL mma_xvf64gerpp {mma,pair,quad}
+
+ void __builtin_mma_xvi16ger2 (v512 *, vuc, vuc);
+ XVI16GER2 nothing {mma}
+
+ v512 __builtin_mma_xvi16ger2_internal (vuc, vuc);
+ XVI16GER2_INTERNAL mma_xvi16ger2 {mma}
+
+ void __builtin_mma_xvi16ger2pp (v512 *, vuc, vuc);
+ XVI16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi16ger2pp_internal (v512, vuc, vuc);
+ XVI16GER2PP_INTERNAL mma_xvi16ger2pp {mma,quad}
+
+ void __builtin_mma_xvi16ger2s (v512 *, vuc, vuc);
+ XVI16GER2S nothing {mma}
+
+ v512 __builtin_mma_xvi16ger2s_internal (vuc, vuc);
+ XVI16GER2S_INTERNAL mma_xvi16ger2s {mma}
+
+ void __builtin_mma_xvi16ger2spp (v512 *, vuc, vuc);
+ XVI16GER2SPP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi16ger2spp_internal (v512, vuc, vuc);
+ XVI16GER2SPP_INTERNAL mma_xvi16ger2spp {mma,quad}
+
+ void __builtin_mma_xvi4ger8 (v512 *, vuc, vuc);
+ XVI4GER8 nothing {mma}
+
+ v512 __builtin_mma_xvi4ger8_internal (vuc, vuc);
+ XVI4GER8_INTERNAL mma_xvi4ger8 {mma}
+
+ void __builtin_mma_xvi4ger8pp (v512 *, vuc, vuc);
+ XVI4GER8PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi4ger8pp_internal (v512, vuc, vuc);
+ XVI4GER8PP_INTERNAL mma_xvi4ger8pp {mma,quad}
+
+ void __builtin_mma_xvi8ger4 (v512 *, vuc, vuc);
+ XVI8GER4 nothing {mma}
+
+ v512 __builtin_mma_xvi8ger4_internal (vuc, vuc);
+ XVI8GER4_INTERNAL mma_xvi8ger4 {mma}
+
+ void __builtin_mma_xvi8ger4pp (v512 *, vuc, vuc);
+ XVI8GER4PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi8ger4pp_internal (v512, vuc, vuc);
+ XVI8GER4PP_INTERNAL mma_xvi8ger4pp {mma,quad}
+
+ void __builtin_mma_xvi8ger4spp (v512 *, vuc, vuc);
+ XVI8GER4SPP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi8ger4spp_internal (v512, vuc, vuc);
+ XVI8GER4SPP_INTERNAL mma_xvi8ger4spp {mma,quad}
+
+ void __builtin_mma_xxmfacc (v512 *);
+ XXMFACC nothing {mma,quad}
+
+ v512 __builtin_mma_xxmfacc_internal (v512);
+ XXMFACC_INTERNAL mma_xxmfacc {mma,quad}
+
+ void __builtin_mma_xxmtacc (v512 *);
+ XXMTACC nothing {mma,quad}
+
+ v512 __builtin_mma_xxmtacc_internal (v512);
+ XXMTACC_INTERNAL mma_xxmtacc {mma,quad}
+
+ void __builtin_mma_xxsetaccz (v512 *);
+ XXSETACCZ nothing {mma}
+
+ v512 __builtin_mma_xxsetaccz_internal ();
+ XXSETACCZ_INTERNAL mma_xxsetaccz {mma}
+
+ void __builtin_vsx_assemble_pair (v256 *, vuc, vuc);
+ ASSEMBLE_PAIR_V nothing {mma}
+
+ v256 __builtin_vsx_assemble_pair_internal (vuc, vuc);
+ ASSEMBLE_PAIR_V_INTERNAL vsx_assemble_pair {mma}
+
+ void __builtin_vsx_disassemble_pair (void *, v256 *);
+ DISASSEMBLE_PAIR_V nothing {mma,pair}
+
+ vuc __builtin_vsx_disassemble_pair_internal (v256, const int<2>);
+ DISASSEMBLE_PAIR_V_INTERNAL vsx_disassemble_pair {mma}
^ permalink raw reply [flat|nested] 7+ messages in thread
* [gcc(refs/users/wschmidt/heads/builtins10)] rs6000: Add MMA builtins
@ 2021-04-02 22:11 William Schmidt
0 siblings, 0 replies; 7+ messages in thread
From: William Schmidt @ 2021-04-02 22:11 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:f8c2cd70bc8d6038e20d436c52c7b4ff15347340
commit f8c2cd70bc8d6038e20d436c52c7b4ff15347340
Author: Bill Schmidt <wschmidt@linux.ibm.com>
Date: Wed Mar 24 15:50:37 2021 -0500
rs6000: Add MMA builtins
2021-03-24 Bill Schmidt <wschmidt@linux.ibm.com>
gcc/
* config/rs6000/rs6000-builtin-new.def: Add mma stanza.
Diff:
---
gcc/config/rs6000/rs6000-builtin-new.def | 404 +++++++++++++++++++++++++++++++
1 file changed, 404 insertions(+)
diff --git a/gcc/config/rs6000/rs6000-builtin-new.def b/gcc/config/rs6000/rs6000-builtin-new.def
index dcb455ed6dd..71fe0431da6 100644
--- a/gcc/config/rs6000/rs6000-builtin-new.def
+++ b/gcc/config/rs6000/rs6000-builtin-new.def
@@ -3221,3 +3221,407 @@
const unsigned long long __builtin_pextd (unsigned long long, unsigned long long);
PEXTD pextd {}
+
+
+[mma]
+ void __builtin_mma_assemble_acc (v512 *, vuc, vuc, vuc, vuc);
+ ASSEMBLE_ACC nothing {mma}
+
+ v512 __builtin_mma_assemble_acc_internal (vuc, vuc, vuc, vuc);
+ ASSEMBLE_ACC_INTERNAL mma_assemble_acc {mma}
+
+ void __builtin_mma_assemble_pair (v256 *, vuc, vuc);
+ ASSEMBLE_PAIR nothing {mma}
+
+ v256 __builtin_mma_assemble_pair_internal (vuc, vuc);
+ ASSEMBLE_PAIR_INTERNAL vsx_assemble_pair {mma}
+
+ void __builtin_mma_disassemble_acc (void *, v512 *);
+ DISASSEMBLE_ACC nothing {mma,quad}
+
+ vuc __builtin_mma_disassemble_acc_internal (v512, const int<2>);
+ DISASSEMBLE_ACC_INTERNAL mma_disassemble_acc {mma}
+
+ void __builtin_mma_disassemble_pair (void *, v256 *);
+ DISASSEMBLE_PAIR nothing {mma,pair}
+
+ vuc __builtin_mma_disassemble_pair_internal (v256, const int<2>);
+ DISASSEMBLE_PAIR_INTERNAL vsx_disassemble_pair {mma}
+
+ void __builtin_mma_pmxvbf16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2 nothing {mma}
+
+ v512 __builtin_mma_pmxvbf16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2_INTERNAL mma_pmxvbf16ger2 {mma}
+
+ void __builtin_mma_pmxvbf16ger2nn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2nn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NN_INTERNAL mma_pmxvbf16ger2nn {mma,quad}
+
+ void __builtin_mma_pmxvbf16ger2np (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2np_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NP_INTERNAL mma_pmxvbf16ger2np {mma,quad}
+
+ void __builtin_mma_pmxvbf16ger2pn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2pn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PN_INTERNAL mma_pmxvbf16ger2pn {mma,quad}
+
+ void __builtin_mma_pmxvbf16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PP_INTERNAL mma_pmxvbf16ger2pp {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2 nothing {mma}
+
+ v512 __builtin_mma_pmxvf16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2_INTERNAL mma_pmxvf16ger2 {mma}
+
+ void __builtin_mma_pmxvf16ger2nn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2nn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NN_INTERNAL mma_pmxvf16ger2nn {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2np (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2np_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NP_INTERNAL mma_pmxvf16ger2np {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2pn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2pn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PN_INTERNAL mma_pmxvf16ger2pn {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PP_INTERNAL mma_pmxvf16ger2pp {mma,quad}
+
+ void __builtin_mma_pmxvf32ger (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GER nothing {mma}
+
+ v512 __builtin_mma_pmxvf32ger_internal (vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GER_INTERNAL mma_pmxvf32ger {mma}
+
+ void __builtin_mma_pmxvf32gernn (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gernn_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNN_INTERNAL mma_pmxvf32gernn {mma,quad}
+
+ void __builtin_mma_pmxvf32gernp (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gernp_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNP_INTERNAL mma_pmxvf32gernp {mma,quad}
+
+ void __builtin_mma_pmxvf32gerpn (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gerpn_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPN_INTERNAL mma_pmxvf32gerpn {mma,quad}
+
+ void __builtin_mma_pmxvf32gerpp (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gerpp_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPP_INTERNAL mma_pmxvf32gerpp {mma,quad}
+
+ void __builtin_mma_pmxvf64ger (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GER nothing {mma,pair}
+
+ v512 __builtin_mma_pmxvf64ger_internal (v256, vuc, const int<4>, const int<2>);
+ PMXVF64GER_INTERNAL mma_pmxvf64ger {mma,pair}
+
+ void __builtin_mma_pmxvf64gernn (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gernn_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNN_INTERNAL mma_pmxvf64gernn {mma,pair,quad}
+
+ void __builtin_mma_pmxvf64gernp (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gernp_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNP_INTERNAL mma_pmxvf64gernp {mma,pair,quad}
+
+ void __builtin_mma_pmxvf64gerpn (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gerpn_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPN_INTERNAL mma_pmxvf64gerpn {mma,pair,quad}
+
+ void __builtin_mma_pmxvf64gerpp (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gerpp_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPP_INTERNAL mma_pmxvf64gerpp {mma,pair,quad}
+
+ void __builtin_mma_pmxvi16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2 nothing {mma}
+
+ v512 __builtin_mma_pmxvi16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2_INTERNAL mma_pmxvi16ger2 {mma}
+
+ void __builtin_mma_pmxvi16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2PP_INTERNAL mma_pmxvi16ger2pp {mma,quad}
+
+ void __builtin_mma_pmxvi16ger2s (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2S nothing {mma}
+
+ v512 __builtin_mma_pmxvi16ger2s_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2S_INTERNAL mma_pmxvi16ger2s {mma}
+
+ void __builtin_mma_pmxvi16ger2spp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2SPP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi16ger2spp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2SPP_INTERNAL mma_pmxvi16ger2spp {mma,quad}
+
+ void __builtin_mma_pmxvi4ger8 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<8>);
+ PMXVI4GER8 nothing {mma}
+
+ v512 __builtin_mma_pmxvi4ger8_internal (vuc, vuc, const int<4>, const int<4>, const int<8>);
+ PMXVI4GER8_INTERNAL mma_pmxvi4ger8 {mma}
+
+ void __builtin_mma_pmxvi4ger8pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI4GER8PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi4ger8pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI4GER8PP_INTERNAL mma_pmxvi4ger8pp {mma,quad}
+
+ void __builtin_mma_pmxvi8ger4 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4 nothing {mma}
+
+ v512 __builtin_mma_pmxvi8ger4_internal (vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4_INTERNAL mma_pmxvi8ger4 {mma}
+
+ void __builtin_mma_pmxvi8ger4pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi8ger4pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4PP_INTERNAL mma_pmxvi8ger4pp {mma,quad}
+
+ void __builtin_mma_pmxvi8ger4spp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4SPP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi8ger4spp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4SPP_INTERNAL mma_pmxvi8ger4spp {mma,quad}
+
+ void __builtin_mma_xvbf16ger2 (v512 *, vuc, vuc);
+ XVBF16GER2 nothing {mma}
+
+ v512 __builtin_mma_xvbf16ger2_internal (vuc, vuc);
+ XVBF16GER2_INTERNAL mma_xvbf16ger2 {mma}
+
+ void __builtin_mma_xvbf16ger2nn (v512 *, vuc, vuc);
+ XVBF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2nn_internal (v512, vuc, vuc);
+ XVBF16GER2NN_INTERNAL mma_xvbf16ger2nn {mma,quad}
+
+ void __builtin_mma_xvbf16ger2np (v512 *, vuc, vuc);
+ XVBF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2np_internal (v512, vuc, vuc);
+ XVBF16GER2NP_INTERNAL mma_xvbf16ger2np {mma,quad}
+
+ void __builtin_mma_xvbf16ger2pn (v512 *, vuc, vuc);
+ XVBF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2pn_internal (v512, vuc, vuc);
+ XVBF16GER2PN_INTERNAL mma_xvbf16ger2pn {mma,quad}
+
+ void __builtin_mma_xvbf16ger2pp (v512 *, vuc, vuc);
+ XVBF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2pp_internal (v512, vuc, vuc);
+ XVBF16GER2PP_INTERNAL mma_xvbf16ger2pp {mma,quad}
+
+ void __builtin_mma_xvf16ger2 (v512 *, vuc, vuc);
+ XVF16GER2 nothing {mma}
+
+ v512 __builtin_mma_xvf16ger2_internal (vuc, vuc);
+ XVF16GER2_INTERNAL mma_xvf16ger2 {mma}
+
+ void __builtin_mma_xvf16ger2nn (v512 *, vuc, vuc);
+ XVF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2nn_internal (v512, vuc, vuc);
+ XVF16GER2NN_INTERNAL mma_xvf16ger2nn {mma,quad}
+
+ void __builtin_mma_xvf16ger2np (v512 *, vuc, vuc);
+ XVF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2np_internal (v512, vuc, vuc);
+ XVF16GER2NP_INTERNAL mma_xvf16ger2np {mma,quad}
+
+ void __builtin_mma_xvf16ger2pn (v512 *, vuc, vuc);
+ XVF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2pn_internal (v512, vuc, vuc);
+ XVF16GER2PN_INTERNAL mma_xvf16ger2pn {mma,quad}
+
+ void __builtin_mma_xvf16ger2pp (v512 *, vuc, vuc);
+ XVF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2pp_internal (v512, vuc, vuc);
+ XVF16GER2PP_INTERNAL mma_xvf16ger2pp {mma,quad}
+
+ void __builtin_mma_xvf32ger (v512 *, vuc, vuc);
+ XVF32GER nothing {mma}
+
+ v512 __builtin_mma_xvf32ger_internal (vuc, vuc);
+ XVF32GER_INTERNAL mma_xvf32ger {mma}
+
+ void __builtin_mma_xvf32gernn (v512 *, vuc, vuc);
+ XVF32GERNN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gernn_internal (v512, vuc, vuc);
+ XVF32GERNN_INTERNAL mma_xvf32gernn {mma,quad}
+
+ void __builtin_mma_xvf32gernp (v512 *, vuc, vuc);
+ XVF32GERNP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gernp_internal (v512, vuc, vuc);
+ XVF32GERNP_INTERNAL mma_xvf32gernp {mma,quad}
+
+ void __builtin_mma_xvf32gerpn (v512 *, vuc, vuc);
+ XVF32GERPN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gerpn_internal (v512, vuc, vuc);
+ XVF32GERPN_INTERNAL mma_xvf32gerpn {mma,quad}
+
+ void __builtin_mma_xvf32gerpp (v512 *, vuc, vuc);
+ XVF32GERPP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gerpp_internal (v512, vuc, vuc);
+ XVF32GERPP_INTERNAL mma_xvf32gerpp {mma,quad}
+
+ void __builtin_mma_xvf64ger (v512 *, v256, vuc);
+ XVF64GER nothing {mma,pair}
+
+ v512 __builtin_mma_xvf64ger_internal (v256, vuc);
+ XVF64GER_INTERNAL mma_xvf64ger {mma,pair}
+
+ void __builtin_mma_xvf64gernn (v512 *, v256, vuc);
+ XVF64GERNN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gernn_internal (v512, v256, vuc);
+ XVF64GERNN_INTERNAL mma_xvf64gernn {mma,pair,quad}
+
+ void __builtin_mma_xvf64gernp (v512 *, v256, vuc);
+ XVF64GERNP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gernp_internal (v512, v256, vuc);
+ XVF64GERNP_INTERNAL mma_xvf64gernp {mma,pair,quad}
+
+ void __builtin_mma_xvf64gerpn (v512 *, v256, vuc);
+ XVF64GERPN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gerpn_internal (v512, v256, vuc);
+ XVF64GERPN_INTERNAL mma_xvf64gerpn {mma,pair,quad}
+
+ void __builtin_mma_xvf64gerpp (v512 *, v256, vuc);
+ XVF64GERPP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gerpp_internal (v512, v256, vuc);
+ XVF64GERPP_INTERNAL mma_xvf64gerpp {mma,pair,quad}
+
+ void __builtin_mma_xvi16ger2 (v512 *, vuc, vuc);
+ XVI16GER2 nothing {mma}
+
+ v512 __builtin_mma_xvi16ger2_internal (vuc, vuc);
+ XVI16GER2_INTERNAL mma_xvi16ger2 {mma}
+
+ void __builtin_mma_xvi16ger2pp (v512 *, vuc, vuc);
+ XVI16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi16ger2pp_internal (v512, vuc, vuc);
+ XVI16GER2PP_INTERNAL mma_xvi16ger2pp {mma,quad}
+
+ void __builtin_mma_xvi16ger2s (v512 *, vuc, vuc);
+ XVI16GER2S nothing {mma}
+
+ v512 __builtin_mma_xvi16ger2s_internal (vuc, vuc);
+ XVI16GER2S_INTERNAL mma_xvi16ger2s {mma}
+
+ void __builtin_mma_xvi16ger2spp (v512 *, vuc, vuc);
+ XVI16GER2SPP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi16ger2spp_internal (v512, vuc, vuc);
+ XVI16GER2SPP_INTERNAL mma_xvi16ger2spp {mma,quad}
+
+ void __builtin_mma_xvi4ger8 (v512 *, vuc, vuc);
+ XVI4GER8 nothing {mma}
+
+ v512 __builtin_mma_xvi4ger8_internal (vuc, vuc);
+ XVI4GER8_INTERNAL mma_xvi4ger8 {mma}
+
+ void __builtin_mma_xvi4ger8pp (v512 *, vuc, vuc);
+ XVI4GER8PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi4ger8pp_internal (v512, vuc, vuc);
+ XVI4GER8PP_INTERNAL mma_xvi4ger8pp {mma,quad}
+
+ void __builtin_mma_xvi8ger4 (v512 *, vuc, vuc);
+ XVI8GER4 nothing {mma}
+
+ v512 __builtin_mma_xvi8ger4_internal (vuc, vuc);
+ XVI8GER4_INTERNAL mma_xvi8ger4 {mma}
+
+ void __builtin_mma_xvi8ger4pp (v512 *, vuc, vuc);
+ XVI8GER4PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi8ger4pp_internal (v512, vuc, vuc);
+ XVI8GER4PP_INTERNAL mma_xvi8ger4pp {mma,quad}
+
+ void __builtin_mma_xvi8ger4spp (v512 *, vuc, vuc);
+ XVI8GER4SPP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi8ger4spp_internal (v512, vuc, vuc);
+ XVI8GER4SPP_INTERNAL mma_xvi8ger4spp {mma,quad}
+
+ void __builtin_mma_xxmfacc (v512 *);
+ XXMFACC nothing {mma,quad}
+
+ v512 __builtin_mma_xxmfacc_internal (v512);
+ XXMFACC_INTERNAL mma_xxmfacc {mma,quad}
+
+ void __builtin_mma_xxmtacc (v512 *);
+ XXMTACC nothing {mma,quad}
+
+ v512 __builtin_mma_xxmtacc_internal (v512);
+ XXMTACC_INTERNAL mma_xxmtacc {mma,quad}
+
+ void __builtin_mma_xxsetaccz (v512 *);
+ XXSETACCZ nothing {mma}
+
+ v512 __builtin_mma_xxsetaccz_internal ();
+ XXSETACCZ_INTERNAL mma_xxsetaccz {mma}
+
+ void __builtin_vsx_assemble_pair (v256 *, vuc, vuc);
+ ASSEMBLE_PAIR_V nothing {mma}
+
+ v256 __builtin_vsx_assemble_pair_internal (vuc, vuc);
+ ASSEMBLE_PAIR_V_INTERNAL vsx_assemble_pair {mma}
+
+ void __builtin_vsx_disassemble_pair (void *, v256 *);
+ DISASSEMBLE_PAIR_V nothing {mma,pair}
+
+ vuc __builtin_vsx_disassemble_pair_internal (v256, const int<2>);
+ DISASSEMBLE_PAIR_V_INTERNAL vsx_disassemble_pair {mma}
^ permalink raw reply [flat|nested] 7+ messages in thread
* [gcc(refs/users/wschmidt/heads/builtins10)] rs6000: Add MMA builtins
@ 2021-04-01 19:49 William Schmidt
0 siblings, 0 replies; 7+ messages in thread
From: William Schmidt @ 2021-04-01 19:49 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:eb8dcbe9bed2fef572fc0a9b1e1e99f754ce09ee
commit eb8dcbe9bed2fef572fc0a9b1e1e99f754ce09ee
Author: Bill Schmidt <wschmidt@linux.ibm.com>
Date: Wed Mar 24 15:50:37 2021 -0500
rs6000: Add MMA builtins
2021-03-24 Bill Schmidt <wschmidt@linux.ibm.com>
gcc/
* config/rs6000/rs6000-builtin-new.def: Add mma stanza.
Diff:
---
gcc/config/rs6000/rs6000-builtin-new.def | 404 +++++++++++++++++++++++++++++++
1 file changed, 404 insertions(+)
diff --git a/gcc/config/rs6000/rs6000-builtin-new.def b/gcc/config/rs6000/rs6000-builtin-new.def
index 4e235c8c56f..b4df31d82a0 100644
--- a/gcc/config/rs6000/rs6000-builtin-new.def
+++ b/gcc/config/rs6000/rs6000-builtin-new.def
@@ -3223,3 +3223,407 @@
const unsigned long long __builtin_pextd (unsigned long long, unsigned long long);
PEXTD pextd {}
+
+
+[mma]
+ void __builtin_mma_assemble_acc (v512 *, vuc, vuc, vuc, vuc);
+ ASSEMBLE_ACC nothing {mma}
+
+ v512 __builtin_mma_assemble_acc_internal (vuc, vuc, vuc, vuc);
+ ASSEMBLE_ACC_INTERNAL mma_assemble_acc {mma}
+
+ void __builtin_mma_assemble_pair (v256 *, vuc, vuc);
+ ASSEMBLE_PAIR nothing {mma}
+
+ v256 __builtin_mma_assemble_pair_internal (vuc, vuc);
+ ASSEMBLE_PAIR_INTERNAL vsx_assemble_pair {mma}
+
+ void __builtin_mma_disassemble_acc (void *, v512 *);
+ DISASSEMBLE_ACC nothing {mma,quad}
+
+ vuc __builtin_mma_disassemble_acc_internal (v512, const int<2>);
+ DISASSEMBLE_ACC_INTERNAL mma_disassemble_acc {mma}
+
+ void __builtin_mma_disassemble_pair (void *, v256 *);
+ DISASSEMBLE_PAIR nothing {mma,pair}
+
+ vuc __builtin_mma_disassemble_pair_internal (v256, const int<2>);
+ DISASSEMBLE_PAIR_INTERNAL vsx_disassemble_pair {mma}
+
+ void __builtin_mma_pmxvbf16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2 nothing {mma}
+
+ v512 __builtin_mma_pmxvbf16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2_INTERNAL mma_pmxvbf16ger2 {mma}
+
+ void __builtin_mma_pmxvbf16ger2nn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2nn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NN_INTERNAL mma_pmxvbf16ger2nn {mma,quad}
+
+ void __builtin_mma_pmxvbf16ger2np (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2np_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NP_INTERNAL mma_pmxvbf16ger2np {mma,quad}
+
+ void __builtin_mma_pmxvbf16ger2pn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2pn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PN_INTERNAL mma_pmxvbf16ger2pn {mma,quad}
+
+ void __builtin_mma_pmxvbf16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PP_INTERNAL mma_pmxvbf16ger2pp {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2 nothing {mma}
+
+ v512 __builtin_mma_pmxvf16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2_INTERNAL mma_pmxvf16ger2 {mma}
+
+ void __builtin_mma_pmxvf16ger2nn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2nn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NN_INTERNAL mma_pmxvf16ger2nn {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2np (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2np_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NP_INTERNAL mma_pmxvf16ger2np {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2pn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2pn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PN_INTERNAL mma_pmxvf16ger2pn {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PP_INTERNAL mma_pmxvf16ger2pp {mma,quad}
+
+ void __builtin_mma_pmxvf32ger (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GER nothing {mma}
+
+ v512 __builtin_mma_pmxvf32ger_internal (vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GER_INTERNAL mma_pmxvf32ger {mma}
+
+ void __builtin_mma_pmxvf32gernn (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gernn_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNN_INTERNAL mma_pmxvf32gernn {mma,quad}
+
+ void __builtin_mma_pmxvf32gernp (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gernp_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNP_INTERNAL mma_pmxvf32gernp {mma,quad}
+
+ void __builtin_mma_pmxvf32gerpn (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gerpn_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPN_INTERNAL mma_pmxvf32gerpn {mma,quad}
+
+ void __builtin_mma_pmxvf32gerpp (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gerpp_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPP_INTERNAL mma_pmxvf32gerpp {mma,quad}
+
+ void __builtin_mma_pmxvf64ger (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GER nothing {mma,pair}
+
+ v512 __builtin_mma_pmxvf64ger_internal (v256, vuc, const int<4>, const int<2>);
+ PMXVF64GER_INTERNAL mma_pmxvf64ger {mma,pair}
+
+ void __builtin_mma_pmxvf64gernn (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gernn_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNN_INTERNAL mma_pmxvf64gernn {mma,pair,quad}
+
+ void __builtin_mma_pmxvf64gernp (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gernp_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNP_INTERNAL mma_pmxvf64gernp {mma,pair,quad}
+
+ void __builtin_mma_pmxvf64gerpn (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gerpn_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPN_INTERNAL mma_pmxvf64gerpn {mma,pair,quad}
+
+ void __builtin_mma_pmxvf64gerpp (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gerpp_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPP_INTERNAL mma_pmxvf64gerpp {mma,pair,quad}
+
+ void __builtin_mma_pmxvi16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2 nothing {mma}
+
+ v512 __builtin_mma_pmxvi16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2_INTERNAL mma_pmxvi16ger2 {mma}
+
+ void __builtin_mma_pmxvi16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2PP_INTERNAL mma_pmxvi16ger2pp {mma,quad}
+
+ void __builtin_mma_pmxvi16ger2s (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2S nothing {mma}
+
+ v512 __builtin_mma_pmxvi16ger2s_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2S_INTERNAL mma_pmxvi16ger2s {mma}
+
+ void __builtin_mma_pmxvi16ger2spp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2SPP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi16ger2spp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2SPP_INTERNAL mma_pmxvi16ger2spp {mma,quad}
+
+ void __builtin_mma_pmxvi4ger8 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<8>);
+ PMXVI4GER8 nothing {mma}
+
+ v512 __builtin_mma_pmxvi4ger8_internal (vuc, vuc, const int<4>, const int<4>, const int<8>);
+ PMXVI4GER8_INTERNAL mma_pmxvi4ger8 {mma}
+
+ void __builtin_mma_pmxvi4ger8pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI4GER8PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi4ger8pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI4GER8PP_INTERNAL mma_pmxvi4ger8pp {mma,quad}
+
+ void __builtin_mma_pmxvi8ger4 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4 nothing {mma}
+
+ v512 __builtin_mma_pmxvi8ger4_internal (vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4_INTERNAL mma_pmxvi8ger4 {mma}
+
+ void __builtin_mma_pmxvi8ger4pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi8ger4pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4PP_INTERNAL mma_pmxvi8ger4pp {mma,quad}
+
+ void __builtin_mma_pmxvi8ger4spp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4SPP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi8ger4spp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4SPP_INTERNAL mma_pmxvi8ger4spp {mma,quad}
+
+ void __builtin_mma_xvbf16ger2 (v512 *, vuc, vuc);
+ XVBF16GER2 nothing {mma}
+
+ v512 __builtin_mma_xvbf16ger2_internal (vuc, vuc);
+ XVBF16GER2_INTERNAL mma_xvbf16ger2 {mma}
+
+ void __builtin_mma_xvbf16ger2nn (v512 *, vuc, vuc);
+ XVBF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2nn_internal (v512, vuc, vuc);
+ XVBF16GER2NN_INTERNAL mma_xvbf16ger2nn {mma,quad}
+
+ void __builtin_mma_xvbf16ger2np (v512 *, vuc, vuc);
+ XVBF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2np_internal (v512, vuc, vuc);
+ XVBF16GER2NP_INTERNAL mma_xvbf16ger2np {mma,quad}
+
+ void __builtin_mma_xvbf16ger2pn (v512 *, vuc, vuc);
+ XVBF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2pn_internal (v512, vuc, vuc);
+ XVBF16GER2PN_INTERNAL mma_xvbf16ger2pn {mma,quad}
+
+ void __builtin_mma_xvbf16ger2pp (v512 *, vuc, vuc);
+ XVBF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2pp_internal (v512, vuc, vuc);
+ XVBF16GER2PP_INTERNAL mma_xvbf16ger2pp {mma,quad}
+
+ void __builtin_mma_xvf16ger2 (v512 *, vuc, vuc);
+ XVF16GER2 nothing {mma}
+
+ v512 __builtin_mma_xvf16ger2_internal (vuc, vuc);
+ XVF16GER2_INTERNAL mma_xvf16ger2 {mma}
+
+ void __builtin_mma_xvf16ger2nn (v512 *, vuc, vuc);
+ XVF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2nn_internal (v512, vuc, vuc);
+ XVF16GER2NN_INTERNAL mma_xvf16ger2nn {mma,quad}
+
+ void __builtin_mma_xvf16ger2np (v512 *, vuc, vuc);
+ XVF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2np_internal (v512, vuc, vuc);
+ XVF16GER2NP_INTERNAL mma_xvf16ger2np {mma,quad}
+
+ void __builtin_mma_xvf16ger2pn (v512 *, vuc, vuc);
+ XVF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2pn_internal (v512, vuc, vuc);
+ XVF16GER2PN_INTERNAL mma_xvf16ger2pn {mma,quad}
+
+ void __builtin_mma_xvf16ger2pp (v512 *, vuc, vuc);
+ XVF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2pp_internal (v512, vuc, vuc);
+ XVF16GER2PP_INTERNAL mma_xvf16ger2pp {mma,quad}
+
+ void __builtin_mma_xvf32ger (v512 *, vuc, vuc);
+ XVF32GER nothing {mma}
+
+ v512 __builtin_mma_xvf32ger_internal (vuc, vuc);
+ XVF32GER_INTERNAL mma_xvf32ger {mma}
+
+ void __builtin_mma_xvf32gernn (v512 *, vuc, vuc);
+ XVF32GERNN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gernn_internal (v512, vuc, vuc);
+ XVF32GERNN_INTERNAL mma_xvf32gernn {mma,quad}
+
+ void __builtin_mma_xvf32gernp (v512 *, vuc, vuc);
+ XVF32GERNP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gernp_internal (v512, vuc, vuc);
+ XVF32GERNP_INTERNAL mma_xvf32gernp {mma,quad}
+
+ void __builtin_mma_xvf32gerpn (v512 *, vuc, vuc);
+ XVF32GERPN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gerpn_internal (v512, vuc, vuc);
+ XVF32GERPN_INTERNAL mma_xvf32gerpn {mma,quad}
+
+ void __builtin_mma_xvf32gerpp (v512 *, vuc, vuc);
+ XVF32GERPP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gerpp_internal (v512, vuc, vuc);
+ XVF32GERPP_INTERNAL mma_xvf32gerpp {mma,quad}
+
+ void __builtin_mma_xvf64ger (v512 *, v256, vuc);
+ XVF64GER nothing {mma,pair}
+
+ v512 __builtin_mma_xvf64ger_internal (v256, vuc);
+ XVF64GER_INTERNAL mma_xvf64ger {mma,pair}
+
+ void __builtin_mma_xvf64gernn (v512 *, v256, vuc);
+ XVF64GERNN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gernn_internal (v512, v256, vuc);
+ XVF64GERNN_INTERNAL mma_xvf64gernn {mma,pair,quad}
+
+ void __builtin_mma_xvf64gernp (v512 *, v256, vuc);
+ XVF64GERNP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gernp_internal (v512, v256, vuc);
+ XVF64GERNP_INTERNAL mma_xvf64gernp {mma,pair,quad}
+
+ void __builtin_mma_xvf64gerpn (v512 *, v256, vuc);
+ XVF64GERPN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gerpn_internal (v512, v256, vuc);
+ XVF64GERPN_INTERNAL mma_xvf64gerpn {mma,pair,quad}
+
+ void __builtin_mma_xvf64gerpp (v512 *, v256, vuc);
+ XVF64GERPP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gerpp_internal (v512, v256, vuc);
+ XVF64GERPP_INTERNAL mma_xvf64gerpp {mma,pair,quad}
+
+ void __builtin_mma_xvi16ger2 (v512 *, vuc, vuc);
+ XVI16GER2 nothing {mma}
+
+ v512 __builtin_mma_xvi16ger2_internal (vuc, vuc);
+ XVI16GER2_INTERNAL mma_xvi16ger2 {mma}
+
+ void __builtin_mma_xvi16ger2pp (v512 *, vuc, vuc);
+ XVI16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi16ger2pp_internal (v512, vuc, vuc);
+ XVI16GER2PP_INTERNAL mma_xvi16ger2pp {mma,quad}
+
+ void __builtin_mma_xvi16ger2s (v512 *, vuc, vuc);
+ XVI16GER2S nothing {mma}
+
+ v512 __builtin_mma_xvi16ger2s_internal (vuc, vuc);
+ XVI16GER2S_INTERNAL mma_xvi16ger2s {mma}
+
+ void __builtin_mma_xvi16ger2spp (v512 *, vuc, vuc);
+ XVI16GER2SPP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi16ger2spp_internal (v512, vuc, vuc);
+ XVI16GER2SPP_INTERNAL mma_xvi16ger2spp {mma,quad}
+
+ void __builtin_mma_xvi4ger8 (v512 *, vuc, vuc);
+ XVI4GER8 nothing {mma}
+
+ v512 __builtin_mma_xvi4ger8_internal (vuc, vuc);
+ XVI4GER8_INTERNAL mma_xvi4ger8 {mma}
+
+ void __builtin_mma_xvi4ger8pp (v512 *, vuc, vuc);
+ XVI4GER8PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi4ger8pp_internal (v512, vuc, vuc);
+ XVI4GER8PP_INTERNAL mma_xvi4ger8pp {mma,quad}
+
+ void __builtin_mma_xvi8ger4 (v512 *, vuc, vuc);
+ XVI8GER4 nothing {mma}
+
+ v512 __builtin_mma_xvi8ger4_internal (vuc, vuc);
+ XVI8GER4_INTERNAL mma_xvi8ger4 {mma}
+
+ void __builtin_mma_xvi8ger4pp (v512 *, vuc, vuc);
+ XVI8GER4PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi8ger4pp_internal (v512, vuc, vuc);
+ XVI8GER4PP_INTERNAL mma_xvi8ger4pp {mma,quad}
+
+ void __builtin_mma_xvi8ger4spp (v512 *, vuc, vuc);
+ XVI8GER4SPP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi8ger4spp_internal (v512, vuc, vuc);
+ XVI8GER4SPP_INTERNAL mma_xvi8ger4spp {mma,quad}
+
+ void __builtin_mma_xxmfacc (v512 *);
+ XXMFACC nothing {mma,quad}
+
+ v512 __builtin_mma_xxmfacc_internal (v512);
+ XXMFACC_INTERNAL mma_xxmfacc {mma,quad}
+
+ void __builtin_mma_xxmtacc (v512 *);
+ XXMTACC nothing {mma,quad}
+
+ v512 __builtin_mma_xxmtacc_internal (v512);
+ XXMTACC_INTERNAL mma_xxmtacc {mma,quad}
+
+ void __builtin_mma_xxsetaccz (v512 *);
+ XXSETACCZ nothing {mma}
+
+ v512 __builtin_mma_xxsetaccz_internal ();
+ XXSETACCZ_INTERNAL mma_xxsetaccz {mma}
+
+ void __builtin_vsx_assemble_pair (v256 *, vuc, vuc);
+ ASSEMBLE_PAIR_V nothing {mma}
+
+ v256 __builtin_vsx_assemble_pair_internal (vuc, vuc);
+ ASSEMBLE_PAIR_V_INTERNAL vsx_assemble_pair {mma}
+
+ void __builtin_vsx_disassemble_pair (void *, v256 *);
+ DISASSEMBLE_PAIR_V nothing {mma,pair}
+
+ vuc __builtin_vsx_disassemble_pair_internal (v256, const int<2>);
+ DISASSEMBLE_PAIR_V_INTERNAL vsx_disassemble_pair {mma}
^ permalink raw reply [flat|nested] 7+ messages in thread
* [gcc(refs/users/wschmidt/heads/builtins10)] rs6000: Add MMA builtins
@ 2021-03-25 15:47 William Schmidt
0 siblings, 0 replies; 7+ messages in thread
From: William Schmidt @ 2021-03-25 15:47 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:0501458528248a467aa1a50e30c40446ef79565b
commit 0501458528248a467aa1a50e30c40446ef79565b
Author: Bill Schmidt <wschmidt@linux.ibm.com>
Date: Wed Mar 24 15:50:37 2021 -0500
rs6000: Add MMA builtins
2021-03-24 Bill Schmidt <wschmidt@linux.ibm.com>
gcc/
* config/rs6000/rs6000-builtin-new.def: Add mma stanza.
Diff:
---
gcc/config/rs6000/rs6000-builtin-new.def | 404 +++++++++++++++++++++++++++++++
1 file changed, 404 insertions(+)
diff --git a/gcc/config/rs6000/rs6000-builtin-new.def b/gcc/config/rs6000/rs6000-builtin-new.def
index 451a49d167c..ccdfbd3ccd5 100644
--- a/gcc/config/rs6000/rs6000-builtin-new.def
+++ b/gcc/config/rs6000/rs6000-builtin-new.def
@@ -3238,3 +3238,407 @@
const unsigned long long __builtin_pextd (unsigned long long, unsigned long long);
PEXTD pextd {}
+
+
+[mma]
+ void __builtin_mma_assemble_acc (v512 *, vuc, vuc, vuc, vuc);
+ ASSEMBLE_ACC nothing {mma}
+
+ v512 __builtin_mma_assemble_acc_internal (vuc, vuc, vuc, vuc);
+ ASSEMBLE_ACC_INTERNAL mma_assemble_acc {mma}
+
+ void __builtin_mma_assemble_pair (v256 *, vuc, vuc);
+ ASSEMBLE_PAIR nothing {mma}
+
+ v256 __builtin_mma_assemble_pair_internal (vuc, vuc);
+ ASSEMBLE_PAIR_INTERNAL vsx_assemble_pair {mma}
+
+ void __builtin_mma_disassemble_acc (void *, v512 *);
+ DISASSEMBLE_ACC nothing {mma,quad}
+
+ vuc __builtin_mma_disassemble_acc_internal (v512, const int<2>);
+ DISASSEMBLE_ACC_INTERNAL mma_disassemble_acc {mma}
+
+ void __builtin_mma_disassemble_pair (void *, v256 *);
+ DISASSEMBLE_PAIR nothing {mma,pair}
+
+ vuc __builtin_mma_disassemble_pair_internal (v256, const int<2>);
+ DISASSEMBLE_PAIR_INTERNAL vsx_disassemble_pair {mma}
+
+ void __builtin_mma_pmxvbf16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2 nothing {mma}
+
+ v512 __builtin_mma_pmxvbf16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2_INTERNAL mma_pmxvbf16ger2 {mma}
+
+ void __builtin_mma_pmxvbf16ger2nn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2nn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NN_INTERNAL mma_pmxvbf16ger2nn {mma,quad}
+
+ void __builtin_mma_pmxvbf16ger2np (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2np_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2NP_INTERNAL mma_pmxvbf16ger2np {mma,quad}
+
+ void __builtin_mma_pmxvbf16ger2pn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2pn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PN_INTERNAL mma_pmxvbf16ger2pn {mma,quad}
+
+ void __builtin_mma_pmxvbf16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvbf16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVBF16GER2PP_INTERNAL mma_pmxvbf16ger2pp {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2 nothing {mma}
+
+ v512 __builtin_mma_pmxvf16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2_INTERNAL mma_pmxvf16ger2 {mma}
+
+ void __builtin_mma_pmxvf16ger2nn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2nn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NN_INTERNAL mma_pmxvf16ger2nn {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2np (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2np_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2NP_INTERNAL mma_pmxvf16ger2np {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2pn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2pn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PN_INTERNAL mma_pmxvf16ger2pn {mma,quad}
+
+ void __builtin_mma_pmxvf16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVF16GER2PP_INTERNAL mma_pmxvf16ger2pp {mma,quad}
+
+ void __builtin_mma_pmxvf32ger (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GER nothing {mma}
+
+ v512 __builtin_mma_pmxvf32ger_internal (vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GER_INTERNAL mma_pmxvf32ger {mma}
+
+ void __builtin_mma_pmxvf32gernn (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gernn_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNN_INTERNAL mma_pmxvf32gernn {mma,quad}
+
+ void __builtin_mma_pmxvf32gernp (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gernp_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERNP_INTERNAL mma_pmxvf32gernp {mma,quad}
+
+ void __builtin_mma_pmxvf32gerpn (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPN nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gerpn_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPN_INTERNAL mma_pmxvf32gerpn {mma,quad}
+
+ void __builtin_mma_pmxvf32gerpp (v512 *, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvf32gerpp_internal (v512, vuc, vuc, const int<4>, const int<4>);
+ PMXVF32GERPP_INTERNAL mma_pmxvf32gerpp {mma,quad}
+
+ void __builtin_mma_pmxvf64ger (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GER nothing {mma,pair}
+
+ v512 __builtin_mma_pmxvf64ger_internal (v256, vuc, const int<4>, const int<2>);
+ PMXVF64GER_INTERNAL mma_pmxvf64ger {mma,pair}
+
+ void __builtin_mma_pmxvf64gernn (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gernn_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNN_INTERNAL mma_pmxvf64gernn {mma,pair,quad}
+
+ void __builtin_mma_pmxvf64gernp (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gernp_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERNP_INTERNAL mma_pmxvf64gernp {mma,pair,quad}
+
+ void __builtin_mma_pmxvf64gerpn (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gerpn_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPN_INTERNAL mma_pmxvf64gerpn {mma,pair,quad}
+
+ void __builtin_mma_pmxvf64gerpp (v512 *, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_pmxvf64gerpp_internal (v512, v256, vuc, const int<4>, const int<2>);
+ PMXVF64GERPP_INTERNAL mma_pmxvf64gerpp {mma,pair,quad}
+
+ void __builtin_mma_pmxvi16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2 nothing {mma}
+
+ v512 __builtin_mma_pmxvi16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2_INTERNAL mma_pmxvi16ger2 {mma}
+
+ void __builtin_mma_pmxvi16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2PP_INTERNAL mma_pmxvi16ger2pp {mma,quad}
+
+ void __builtin_mma_pmxvi16ger2s (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2S nothing {mma}
+
+ v512 __builtin_mma_pmxvi16ger2s_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2S_INTERNAL mma_pmxvi16ger2s {mma}
+
+ void __builtin_mma_pmxvi16ger2spp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2SPP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi16ger2spp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
+ PMXVI16GER2SPP_INTERNAL mma_pmxvi16ger2spp {mma,quad}
+
+ void __builtin_mma_pmxvi4ger8 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<8>);
+ PMXVI4GER8 nothing {mma}
+
+ v512 __builtin_mma_pmxvi4ger8_internal (vuc, vuc, const int<4>, const int<4>, const int<8>);
+ PMXVI4GER8_INTERNAL mma_pmxvi4ger8 {mma}
+
+ void __builtin_mma_pmxvi4ger8pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI4GER8PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi4ger8pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI4GER8PP_INTERNAL mma_pmxvi4ger8pp {mma,quad}
+
+ void __builtin_mma_pmxvi8ger4 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4 nothing {mma}
+
+ v512 __builtin_mma_pmxvi8ger4_internal (vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4_INTERNAL mma_pmxvi8ger4 {mma}
+
+ void __builtin_mma_pmxvi8ger4pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4PP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi8ger4pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4PP_INTERNAL mma_pmxvi8ger4pp {mma,quad}
+
+ void __builtin_mma_pmxvi8ger4spp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4SPP nothing {mma,quad}
+
+ v512 __builtin_mma_pmxvi8ger4spp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>);
+ PMXVI8GER4SPP_INTERNAL mma_pmxvi8ger4spp {mma,quad}
+
+ void __builtin_mma_xvbf16ger2 (v512 *, vuc, vuc);
+ XVBF16GER2 nothing {mma}
+
+ v512 __builtin_mma_xvbf16ger2_internal (vuc, vuc);
+ XVBF16GER2_INTERNAL mma_xvbf16ger2 {mma}
+
+ void __builtin_mma_xvbf16ger2nn (v512 *, vuc, vuc);
+ XVBF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2nn_internal (v512, vuc, vuc);
+ XVBF16GER2NN_INTERNAL mma_xvbf16ger2nn {mma,quad}
+
+ void __builtin_mma_xvbf16ger2np (v512 *, vuc, vuc);
+ XVBF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2np_internal (v512, vuc, vuc);
+ XVBF16GER2NP_INTERNAL mma_xvbf16ger2np {mma,quad}
+
+ void __builtin_mma_xvbf16ger2pn (v512 *, vuc, vuc);
+ XVBF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2pn_internal (v512, vuc, vuc);
+ XVBF16GER2PN_INTERNAL mma_xvbf16ger2pn {mma,quad}
+
+ void __builtin_mma_xvbf16ger2pp (v512 *, vuc, vuc);
+ XVBF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvbf16ger2pp_internal (v512, vuc, vuc);
+ XVBF16GER2PP_INTERNAL mma_xvbf16ger2pp {mma,quad}
+
+ void __builtin_mma_xvf16ger2 (v512 *, vuc, vuc);
+ XVF16GER2 nothing {mma}
+
+ v512 __builtin_mma_xvf16ger2_internal (vuc, vuc);
+ XVF16GER2_INTERNAL mma_xvf16ger2 {mma}
+
+ void __builtin_mma_xvf16ger2nn (v512 *, vuc, vuc);
+ XVF16GER2NN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2nn_internal (v512, vuc, vuc);
+ XVF16GER2NN_INTERNAL mma_xvf16ger2nn {mma,quad}
+
+ void __builtin_mma_xvf16ger2np (v512 *, vuc, vuc);
+ XVF16GER2NP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2np_internal (v512, vuc, vuc);
+ XVF16GER2NP_INTERNAL mma_xvf16ger2np {mma,quad}
+
+ void __builtin_mma_xvf16ger2pn (v512 *, vuc, vuc);
+ XVF16GER2PN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2pn_internal (v512, vuc, vuc);
+ XVF16GER2PN_INTERNAL mma_xvf16ger2pn {mma,quad}
+
+ void __builtin_mma_xvf16ger2pp (v512 *, vuc, vuc);
+ XVF16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf16ger2pp_internal (v512, vuc, vuc);
+ XVF16GER2PP_INTERNAL mma_xvf16ger2pp {mma,quad}
+
+ void __builtin_mma_xvf32ger (v512 *, vuc, vuc);
+ XVF32GER nothing {mma}
+
+ v512 __builtin_mma_xvf32ger_internal (vuc, vuc);
+ XVF32GER_INTERNAL mma_xvf32ger {mma}
+
+ void __builtin_mma_xvf32gernn (v512 *, vuc, vuc);
+ XVF32GERNN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gernn_internal (v512, vuc, vuc);
+ XVF32GERNN_INTERNAL mma_xvf32gernn {mma,quad}
+
+ void __builtin_mma_xvf32gernp (v512 *, vuc, vuc);
+ XVF32GERNP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gernp_internal (v512, vuc, vuc);
+ XVF32GERNP_INTERNAL mma_xvf32gernp {mma,quad}
+
+ void __builtin_mma_xvf32gerpn (v512 *, vuc, vuc);
+ XVF32GERPN nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gerpn_internal (v512, vuc, vuc);
+ XVF32GERPN_INTERNAL mma_xvf32gerpn {mma,quad}
+
+ void __builtin_mma_xvf32gerpp (v512 *, vuc, vuc);
+ XVF32GERPP nothing {mma,quad}
+
+ v512 __builtin_mma_xvf32gerpp_internal (v512, vuc, vuc);
+ XVF32GERPP_INTERNAL mma_xvf32gerpp {mma,quad}
+
+ void __builtin_mma_xvf64ger (v512 *, v256, vuc);
+ XVF64GER nothing {mma,pair}
+
+ v512 __builtin_mma_xvf64ger_internal (v256, vuc);
+ XVF64GER_INTERNAL mma_xvf64ger {mma,pair}
+
+ void __builtin_mma_xvf64gernn (v512 *, v256, vuc);
+ XVF64GERNN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gernn_internal (v512, v256, vuc);
+ XVF64GERNN_INTERNAL mma_xvf64gernn {mma,pair,quad}
+
+ void __builtin_mma_xvf64gernp (v512 *, v256, vuc);
+ XVF64GERNP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gernp_internal (v512, v256, vuc);
+ XVF64GERNP_INTERNAL mma_xvf64gernp {mma,pair,quad}
+
+ void __builtin_mma_xvf64gerpn (v512 *, v256, vuc);
+ XVF64GERPN nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gerpn_internal (v512, v256, vuc);
+ XVF64GERPN_INTERNAL mma_xvf64gerpn {mma,pair,quad}
+
+ void __builtin_mma_xvf64gerpp (v512 *, v256, vuc);
+ XVF64GERPP nothing {mma,pair,quad}
+
+ v512 __builtin_mma_xvf64gerpp_internal (v512, v256, vuc);
+ XVF64GERPP_INTERNAL mma_xvf64gerpp {mma,pair,quad}
+
+ void __builtin_mma_xvi16ger2 (v512 *, vuc, vuc);
+ XVI16GER2 nothing {mma}
+
+ v512 __builtin_mma_xvi16ger2_internal (vuc, vuc);
+ XVI16GER2_INTERNAL mma_xvi16ger2 {mma}
+
+ void __builtin_mma_xvi16ger2pp (v512 *, vuc, vuc);
+ XVI16GER2PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi16ger2pp_internal (v512, vuc, vuc);
+ XVI16GER2PP_INTERNAL mma_xvi16ger2pp {mma,quad}
+
+ void __builtin_mma_xvi16ger2s (v512 *, vuc, vuc);
+ XVI16GER2S nothing {mma}
+
+ v512 __builtin_mma_xvi16ger2s_internal (vuc, vuc);
+ XVI16GER2S_INTERNAL mma_xvi16ger2s {mma}
+
+ void __builtin_mma_xvi16ger2spp (v512 *, vuc, vuc);
+ XVI16GER2SPP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi16ger2spp_internal (v512, vuc, vuc);
+ XVI16GER2SPP_INTERNAL mma_xvi16ger2spp {mma,quad}
+
+ void __builtin_mma_xvi4ger8 (v512 *, vuc, vuc);
+ XVI4GER8 nothing {mma}
+
+ v512 __builtin_mma_xvi4ger8_internal (vuc, vuc);
+ XVI4GER8_INTERNAL mma_xvi4ger8 {mma}
+
+ void __builtin_mma_xvi4ger8pp (v512 *, vuc, vuc);
+ XVI4GER8PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi4ger8pp_internal (v512, vuc, vuc);
+ XVI4GER8PP_INTERNAL mma_xvi4ger8pp {mma,quad}
+
+ void __builtin_mma_xvi8ger4 (v512 *, vuc, vuc);
+ XVI8GER4 nothing {mma}
+
+ v512 __builtin_mma_xvi8ger4_internal (vuc, vuc);
+ XVI8GER4_INTERNAL mma_xvi8ger4 {mma}
+
+ void __builtin_mma_xvi8ger4pp (v512 *, vuc, vuc);
+ XVI8GER4PP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi8ger4pp_internal (v512, vuc, vuc);
+ XVI8GER4PP_INTERNAL mma_xvi8ger4pp {mma,quad}
+
+ void __builtin_mma_xvi8ger4spp (v512 *, vuc, vuc);
+ XVI8GER4SPP nothing {mma,quad}
+
+ v512 __builtin_mma_xvi8ger4spp_internal (v512, vuc, vuc);
+ XVI8GER4SPP_INTERNAL mma_xvi8ger4spp {mma,quad}
+
+ void __builtin_mma_xxmfacc (v512 *);
+ XXMFACC nothing {mma,quad}
+
+ v512 __builtin_mma_xxmfacc_internal (v512);
+ XXMFACC_INTERNAL mma_xxmfacc {mma,quad}
+
+ void __builtin_mma_xxmtacc (v512 *);
+ XXMTACC nothing {mma,quad}
+
+ v512 __builtin_mma_xxmtacc_internal (v512);
+ XXMTACC_INTERNAL mma_xxmtacc {mma,quad}
+
+ void __builtin_mma_xxsetaccz (v512 *);
+ XXSETACCZ nothing {mma}
+
+ v512 __builtin_mma_xxsetaccz_internal ();
+ XXSETACCZ_INTERNAL mma_xxsetaccz {mma}
+
+ void __builtin_vsx_assemble_pair (v256 *, vuc, vuc);
+ ASSEMBLE_PAIR_V nothing {mma}
+
+ v256 __builtin_vsx_assemble_pair_internal (vuc, vuc);
+ ASSEMBLE_PAIR_V_INTERNAL vsx_assemble_pair {mma}
+
+ void __builtin_vsx_disassemble_pair (void *, v256 *);
+ DISASSEMBLE_PAIR_V nothing {mma,pair}
+
+ vuc __builtin_vsx_disassemble_pair_internal (v256, const int<2>);
+ DISASSEMBLE_PAIR_V_INTERNAL vsx_disassemble_pair {mma}
^ permalink raw reply [flat|nested] 7+ messages in thread
end of thread, other threads:[~2021-07-29 14:45 UTC | newest]
Thread overview: 7+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-06-15 17:18 [gcc(refs/users/wschmidt/heads/builtins10)] rs6000: Add MMA builtins William Schmidt
-- strict thread matches above, loose matches on Subject: below --
2021-07-29 14:45 William Schmidt
2021-06-25 16:17 William Schmidt
2021-04-26 20:50 William Schmidt
2021-04-02 22:11 William Schmidt
2021-04-01 19:49 William Schmidt
2021-03-25 15:47 William Schmidt
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).