From: Michael Meissner Date: Tue, 19 Mar 2024 05:01:25 +0000 (-0400) Subject: PowerPC: Switch to dense math names for all MMA operations. X-Git-Url: https://gcc.gnu.org/git/?a=commitdiff_plain;h=f4c6cc290f3742ddafeedd15712ebbf6c57e922e;hp=64bb9c0b57b3fa6ba03793dedf2fb83ef8cba837;p=gcc.git PowerPC: Switch to dense math names for all MMA operations. This patch changes the assembler instruction names for MMA instructions from the original name used in power10 to the new name when used with the dense math system. I.e. xvf64gerpp becomes dmxvf64gerpp. The assembler will emit the same bits for either spelling. For the non-prefixed MMA instructions, we add a 'dm' prefix in front of the instruction. However, the prefixed instructions have a 'pm' prefix, and we add the 'dm' prefix afterwards. To prevent having two sets of parallel int attributes, we remove the "pm" prefix from the instruction string in the attributes, and add it later, both in the insn name and in the output template. 2024-03-19 Michael Meissner gcc/ * config/rs6000/mma.md (vvi4i4i8): Change the instruction to not have a "pm" prefix. (avvi4i4i8): Likewise. (vvi4i4i2): Likewise. (avvi4i4i2): Likewise. (vvi4i4): Likewise. (avvi4i4): Likewise. (pvi4i2): Likewise. (apvi4i2): Likewise. (vvi4i4i4): Likewise. (avvi4i4i4): Likewise. (mma_xxsetaccz): Add support for running on DMF systems, generating the dense math instruction and using the dense math accumulators. (mma_): Likewise. (mma_): Likewise. (mma_): Likewise. (mma_): Likewise. (mma_pm): Add support for running on DMF systems, generating the dense math instruction and using the dense math accumulators. Rename the insn with a 'pm' prefix and add either 'pm' or 'pmdm' prefixes based on whether we have the original MMA specification or if we have dense math support. (mma_pm): Likewise. (mma_pm): Likewise. (mma_pm): Likewise. (mma_pm): Likewise. (mma_pm): Likewise. (mma_pm): Likewise. (mma_pm): Likewise. --- diff --git a/gcc/config/rs6000/mma.md b/gcc/config/rs6000/mma.md index 2ce613b46cca..f3870eac51ae 100644 --- a/gcc/config/rs6000/mma.md +++ b/gcc/config/rs6000/mma.md @@ -224,44 +224,47 @@ (UNSPEC_MMA_XVF64GERNP "xvf64gernp") (UNSPEC_MMA_XVF64GERNN "xvf64gernn")]) -(define_int_attr vvi4i4i8 [(UNSPEC_MMA_PMXVI4GER8 "pmxvi4ger8")]) +;; The "pm" prefix is not in these expansions, so that we can generate +;; pmdmxvi4ger8 on systems with dense math registers and xvi4ger8 on systems +;; without dense math registers. +(define_int_attr vvi4i4i8 [(UNSPEC_MMA_PMXVI4GER8 "xvi4ger8")]) -(define_int_attr avvi4i4i8 [(UNSPEC_MMA_PMXVI4GER8PP "pmxvi4ger8pp")]) +(define_int_attr avvi4i4i8 [(UNSPEC_MMA_PMXVI4GER8PP "xvi4ger8pp")]) -(define_int_attr vvi4i4i2 [(UNSPEC_MMA_PMXVI16GER2 "pmxvi16ger2") - (UNSPEC_MMA_PMXVI16GER2S "pmxvi16ger2s") - (UNSPEC_MMA_PMXVF16GER2 "pmxvf16ger2") - (UNSPEC_MMA_PMXVBF16GER2 "pmxvbf16ger2")]) +(define_int_attr vvi4i4i2 [(UNSPEC_MMA_PMXVI16GER2 "xvi16ger2") + (UNSPEC_MMA_PMXVI16GER2S "xvi16ger2s") + (UNSPEC_MMA_PMXVF16GER2 "xvf16ger2") + (UNSPEC_MMA_PMXVBF16GER2 "xvbf16ger2")]) -(define_int_attr avvi4i4i2 [(UNSPEC_MMA_PMXVI16GER2PP "pmxvi16ger2pp") - (UNSPEC_MMA_PMXVI16GER2SPP "pmxvi16ger2spp") - (UNSPEC_MMA_PMXVF16GER2PP "pmxvf16ger2pp") - (UNSPEC_MMA_PMXVF16GER2PN "pmxvf16ger2pn") - (UNSPEC_MMA_PMXVF16GER2NP "pmxvf16ger2np") - (UNSPEC_MMA_PMXVF16GER2NN "pmxvf16ger2nn") - (UNSPEC_MMA_PMXVBF16GER2PP "pmxvbf16ger2pp") - (UNSPEC_MMA_PMXVBF16GER2PN "pmxvbf16ger2pn") - (UNSPEC_MMA_PMXVBF16GER2NP "pmxvbf16ger2np") - (UNSPEC_MMA_PMXVBF16GER2NN "pmxvbf16ger2nn")]) +(define_int_attr avvi4i4i2 [(UNSPEC_MMA_PMXVI16GER2PP "xvi16ger2pp") + (UNSPEC_MMA_PMXVI16GER2SPP "xvi16ger2spp") + (UNSPEC_MMA_PMXVF16GER2PP "xvf16ger2pp") + (UNSPEC_MMA_PMXVF16GER2PN "xvf16ger2pn") + (UNSPEC_MMA_PMXVF16GER2NP "xvf16ger2np") + (UNSPEC_MMA_PMXVF16GER2NN "xvf16ger2nn") + (UNSPEC_MMA_PMXVBF16GER2PP "xvbf16ger2pp") + (UNSPEC_MMA_PMXVBF16GER2PN "xvbf16ger2pn") + (UNSPEC_MMA_PMXVBF16GER2NP "xvbf16ger2np") + (UNSPEC_MMA_PMXVBF16GER2NN "xvbf16ger2nn")]) -(define_int_attr vvi4i4 [(UNSPEC_MMA_PMXVF32GER "pmxvf32ger")]) +(define_int_attr vvi4i4 [(UNSPEC_MMA_PMXVF32GER "xvf32ger")]) -(define_int_attr avvi4i4 [(UNSPEC_MMA_PMXVF32GERPP "pmxvf32gerpp") - (UNSPEC_MMA_PMXVF32GERPN "pmxvf32gerpn") - (UNSPEC_MMA_PMXVF32GERNP "pmxvf32gernp") - (UNSPEC_MMA_PMXVF32GERNN "pmxvf32gernn")]) +(define_int_attr avvi4i4 [(UNSPEC_MMA_PMXVF32GERPP "xvf32gerpp") + (UNSPEC_MMA_PMXVF32GERPN "xvf32gerpn") + (UNSPEC_MMA_PMXVF32GERNP "xvf32gernp") + (UNSPEC_MMA_PMXVF32GERNN "xvf32gernn")]) -(define_int_attr pvi4i2 [(UNSPEC_MMA_PMXVF64GER "pmxvf64ger")]) +(define_int_attr pvi4i2 [(UNSPEC_MMA_PMXVF64GER "xvf64ger")]) -(define_int_attr apvi4i2 [(UNSPEC_MMA_PMXVF64GERPP "pmxvf64gerpp") - (UNSPEC_MMA_PMXVF64GERPN "pmxvf64gerpn") - (UNSPEC_MMA_PMXVF64GERNP "pmxvf64gernp") - (UNSPEC_MMA_PMXVF64GERNN "pmxvf64gernn")]) +(define_int_attr apvi4i2 [(UNSPEC_MMA_PMXVF64GERPP "xvf64gerpp") + (UNSPEC_MMA_PMXVF64GERPN "xvf64gerpn") + (UNSPEC_MMA_PMXVF64GERNP "xvf64gernp") + (UNSPEC_MMA_PMXVF64GERNN "xvf64gernn")]) -(define_int_attr vvi4i4i4 [(UNSPEC_MMA_PMXVI8GER4 "pmxvi8ger4")]) +(define_int_attr vvi4i4i4 [(UNSPEC_MMA_PMXVI8GER4 "xvi8ger4")]) -(define_int_attr avvi4i4i4 [(UNSPEC_MMA_PMXVI8GER4PP "pmxvi8ger4pp") - (UNSPEC_MMA_PMXVI8GER4SPP "pmxvi8ger4spp")]) +(define_int_attr avvi4i4i4 [(UNSPEC_MMA_PMXVI8GER4PP "xvi8ger4pp") + (UNSPEC_MMA_PMXVI8GER4SPP "xvi8ger4spp")]) ;; Vector pair support. OOmode can only live in VSRs. @@ -546,7 +549,9 @@ (unspec_volatile:XO [(const_int 0)] UNSPECV_MMA_XXSETACCZ))] "TARGET_MMA" - "xxsetaccz %A0" +{ + return TARGET_DENSE_MATH ? "dmsetdmrz %A0" : "xxsetaccz %A0"; +} [(set_attr "type" "mma")]) (define_insn "mma_" @@ -555,7 +560,9 @@ (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")] MMA_VV))] "TARGET_MMA" - " %A0,%x1,%x2" +{ + return TARGET_DENSE_MATH ? "dm %A0,%x1,%x2" : " %A0,%x1,%x2"; +} [(set_attr "type" "mma")]) (define_insn "mma_" @@ -565,7 +572,9 @@ (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")] MMA_AVV))] "TARGET_MMA" - " %A0,%x2,%x3" +{ + return TARGET_DENSE_MATH ? "dm %A0,%x2,%x3" : " %A0,%x2,%x3"; +} [(set_attr "type" "mma")]) (define_insn "mma_" @@ -574,7 +583,9 @@ (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")] MMA_PV))] "TARGET_MMA" - " %A0,%x1,%x2" +{ + return TARGET_DENSE_MATH ? "dm %A0,%x1,%x2" : " %A0,%x1,%x2"; +} [(set_attr "type" "mma")]) (define_insn "mma_" @@ -584,10 +595,12 @@ (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")] MMA_APV))] "TARGET_MMA" - " %A0,%x2,%x3" +{ + return TARGET_DENSE_MATH ? "dm %A0,%x2,%x3" : " %A0,%x2,%x3"; +} [(set_attr "type" "mma")]) -(define_insn "mma_" +(define_insn "mma_pm" [(set (match_operand:XO 0 "accumulator_operand" "=&wD,&wD") (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa") (match_operand:V16QI 2 "vsx_register_operand" "v,?wa") @@ -596,11 +609,15 @@ (match_operand:SI 5 "u8bit_cint_operand" "n,n")] MMA_VVI4I4I8))] "TARGET_MMA" - " %A0,%x1,%x2,%3,%4,%5" +{ + return (TARGET_DENSE_MATH + ? "pmdm %A0,%x1,%x2,%3,%4,%5" + : "pm %A0,%x1,%x2,%3,%4,%5"); +} [(set_attr "type" "mma") (set_attr "prefixed" "yes")]) -(define_insn "mma_" +(define_insn "mma_pm" [(set (match_operand:XO 0 "accumulator_operand" "=&wD,&wD") (unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0") (match_operand:V16QI 2 "vsx_register_operand" "v,?wa") @@ -610,11 +627,15 @@ (match_operand:SI 6 "u8bit_cint_operand" "n,n")] MMA_AVVI4I4I8))] "TARGET_MMA" - " %A0,%x2,%x3,%4,%5,%6" +{ + return (TARGET_DENSE_MATH + ? "pmdm %A0,%x2,%x3,%4,%5,%6" + : "pm %A0,%x2,%x3,%4,%5,%6"); +} [(set_attr "type" "mma") (set_attr "prefixed" "yes")]) -(define_insn "mma_" +(define_insn "mma_pm" [(set (match_operand:XO 0 "accumulator_operand" "=&wD,&wD") (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa") (match_operand:V16QI 2 "vsx_register_operand" "v,?wa") @@ -623,11 +644,15 @@ (match_operand:SI 5 "const_0_to_3_operand" "n,n")] MMA_VVI4I4I2))] "TARGET_MMA" - " %A0,%x1,%x2,%3,%4,%5" +{ + return (TARGET_DENSE_MATH + ? "pmdm %A0,%x1,%x2,%3,%4,%5" + : "pm %A0,%x1,%x2,%3,%4,%5"); +} [(set_attr "type" "mma") (set_attr "prefixed" "yes")]) -(define_insn "mma_" +(define_insn "mma_pm" [(set (match_operand:XO 0 "accumulator_operand" "=&wD,&wD") (unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0") (match_operand:V16QI 2 "vsx_register_operand" "v,?wa") @@ -637,11 +662,15 @@ (match_operand:SI 6 "const_0_to_3_operand" "n,n")] MMA_AVVI4I4I2))] "TARGET_MMA" - " %A0,%x2,%x3,%4,%5,%6" +{ + return (TARGET_DENSE_MATH + ? "pmdm %A0,%x2,%x3,%4,%5,%6" + : "pm %A0,%x2,%x3,%4,%5,%6"); +} [(set_attr "type" "mma") (set_attr "prefixed" "yes")]) -(define_insn "mma_" +(define_insn "mma_pm" [(set (match_operand:XO 0 "accumulator_operand" "=&wD,&wD") (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa") (match_operand:V16QI 2 "vsx_register_operand" "v,?wa") @@ -649,11 +678,15 @@ (match_operand:SI 4 "const_0_to_15_operand" "n,n")] MMA_VVI4I4))] "TARGET_MMA" - " %A0,%x1,%x2,%3,%4" +{ + return (TARGET_DENSE_MATH + ? "pmdm %A0,%x1,%x2,%3,%4" + : "pm %A0,%x1,%x2,%3,%4"); +} [(set_attr "type" "mma") (set_attr "prefixed" "yes")]) -(define_insn "mma_" +(define_insn "mma_pm" [(set (match_operand:XO 0 "accumulator_operand" "=&wD,&wD") (unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0") (match_operand:V16QI 2 "vsx_register_operand" "v,?wa") @@ -662,11 +695,15 @@ (match_operand:SI 5 "const_0_to_15_operand" "n,n")] MMA_AVVI4I4))] "TARGET_MMA" - " %A0,%x2,%x3,%4,%5" +{ + return (TARGET_DENSE_MATH + ? "pmdm %A0,%x2,%x3,%4,%5" + : "pm %A0,%x2,%x3,%4,%5"); +} [(set_attr "type" "mma") (set_attr "prefixed" "yes")]) -(define_insn "mma_" +(define_insn "mma_pm" [(set (match_operand:XO 0 "accumulator_operand" "=&wD,&wD") (unspec:XO [(match_operand:OO 1 "vsx_register_operand" "v,?wa") (match_operand:V16QI 2 "vsx_register_operand" "v,?wa") @@ -674,11 +711,15 @@ (match_operand:SI 4 "const_0_to_3_operand" "n,n")] MMA_PVI4I2))] "TARGET_MMA" - " %A0,%x1,%x2,%3,%4" +{ + return (TARGET_DENSE_MATH + ? "pmdm %A0,%x1,%x2,%3,%4" + : "pm %A0,%x1,%x2,%3,%4"); +} [(set_attr "type" "mma") (set_attr "prefixed" "yes")]) -(define_insn "mma_" +(define_insn "mma_pm" [(set (match_operand:XO 0 "accumulator_operand" "=&wD,&wD") (unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0") (match_operand:OO 2 "vsx_register_operand" "v,?wa") @@ -687,11 +728,15 @@ (match_operand:SI 5 "const_0_to_3_operand" "n,n")] MMA_APVI4I2))] "TARGET_MMA" - " %A0,%x2,%x3,%4,%5" +{ + return (TARGET_DENSE_MATH + ? "pmdm %A0,%x2,%x3,%4,%5" + : "pm %A0,%x2,%x3,%4,%5"); +} [(set_attr "type" "mma") (set_attr "prefixed" "yes")]) -(define_insn "mma_" +(define_insn "mma_pm" [(set (match_operand:XO 0 "accumulator_operand" "=&wD,&wD") (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa") (match_operand:V16QI 2 "vsx_register_operand" "v,?wa") @@ -700,11 +745,15 @@ (match_operand:SI 5 "const_0_to_15_operand" "n,n")] MMA_VVI4I4I4))] "TARGET_MMA" - " %A0,%x1,%x2,%3,%4,%5" +{ + return (TARGET_DENSE_MATH + ? "pmdm %A0,%x1,%x2,%3,%4,%5" + : "pm %A0,%x1,%x2,%3,%4,%5"); +} [(set_attr "type" "mma") (set_attr "prefixed" "yes")]) -(define_insn "mma_" +(define_insn "mma_pm" [(set (match_operand:XO 0 "accumulator_operand" "=&wD,&wD") (unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0") (match_operand:V16QI 2 "vsx_register_operand" "v,?wa") @@ -714,6 +763,10 @@ (match_operand:SI 6 "const_0_to_15_operand" "n,n")] MMA_AVVI4I4I4))] "TARGET_MMA" - " %A0,%x2,%x3,%4,%5,%6" +{ + return (TARGET_DENSE_MATH + ? "pmdm %A0,%x2,%x3,%4,%5,%6" + : "pm %A0,%x2,%x3,%4,%5,%6"); +} [(set_attr "type" "mma") (set_attr "prefixed" "yes")])