From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 1005) id 190663858414; Sat, 5 Nov 2022 02:58:18 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 190663858414 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org; s=default; t=1667617098; bh=vjFxV/ihHN43E/NUqKsTy9Cbtb6SIVdv5ubu5y1YuJg=; h=From:To:Subject:Date:From; b=WlUOlWmlNaUZnluJsmDbL2LcP3MqYNJgsoj0JoUItyb6oncYM4fk/yLxgTNZshz/J znMHH9GOFAWpjJjQyKLPfx46802woYaR+3raz7UVWdad5KCbDeApqTwgpbg7QJ793W 1HHkr1EmA1aI2J/Ms2+dEO5AgEtL3kQnMfkqs9rM= Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit From: Michael Meissner To: gcc-cvs@gcc.gnu.org Subject: [gcc(refs/users/meissner/heads/dmf003)] Make MMA insns support dmr registers. X-Act-Checkin: gcc X-Git-Author: Michael Meissner X-Git-Refname: refs/users/meissner/heads/dmf003 X-Git-Oldrev: bb7c78fd2648604a3adcaaaf4ca5564482ac1696 X-Git-Newrev: fbb3f89e02ee33d188e4c5080901f34de5b2499e Message-Id: <20221105025818.190663858414@sourceware.org> Date: Sat, 5 Nov 2022 02:58:18 +0000 (GMT) List-Id: https://gcc.gnu.org/g:fbb3f89e02ee33d188e4c5080901f34de5b2499e commit fbb3f89e02ee33d188e4c5080901f34de5b2499e Author: Michael Meissner Date: Fri Nov 4 22:57:54 2022 -0400 Make MMA insns support dmr registers. 2022-11-04 Michael Meissner gcc/ * config/rs6000/mma.md (mma_): New define_expand to handle mma_ for dense math and non dense math. (mma_ insn): Restrict to non dense math. (mma_xxsetaccz): Convert to define_expand to handle non dense math and dense math. (mma_xxsetaccz_p10): Rename from mma_xxsetaccz and restrict usage to non dense math. (mma_xxsetaccz_dm): Dense math version of mma_xxsetaccz. (mma_): Add support for dense math. (mma_): Likewise. (mma_): Likewise. (mma_): Likewise. (mma_): Likewise. (mma_): Likewise. (mma_): Likewise. (mma_): Likewise. (mma_): Likewise. (mma_): Likewise. (mma_): Likewise. (mma_): Likewise. (mma_): Likewise. (mma_): Likewise. * config/rs6000/rs6000.cc (print_operand): Make %A handle only DMRs if dense math and only FPRs if not dense math. (rs6000_split_multireg_move): Do not generate accumulator prime or de-prime instructions if dense math. gcc/testsuite/ * gcc.target/powerpc/dm-double-test.c: New test. * lib/target-supports.exp (check_effective_target_ppc_dmr_ok): New target test. Diff: --- gcc/config/rs6000/mma.md | 247 ++++++++++++++-------- gcc/config/rs6000/rs6000-c.cc | 3 + gcc/config/rs6000/rs6000.cc | 35 +-- gcc/testsuite/gcc.target/powerpc/dm-double-test.c | 194 +++++++++++++++++ gcc/testsuite/lib/target-supports.exp | 19 ++ 5 files changed, 389 insertions(+), 109 deletions(-) diff --git a/gcc/config/rs6000/mma.md b/gcc/config/rs6000/mma.md index fe2e9c9e63e..835f34e8e00 100644 --- a/gcc/config/rs6000/mma.md +++ b/gcc/config/rs6000/mma.md @@ -545,190 +545,249 @@ "dmxxextfdmr256 %0,%1,2" [(set_attr "type" "mma")]) -(define_insn "mma_" +;; MMA instructions that do not use their accumulators as an input, still must +;; not allow their vector operands to overlap the registers used by the +;; accumulator. We enforce this by marking the output as early clobber. If we +;; have dense math, we don't need the whole prime/de-prime action, so just make +;; thse instructions be NOPs. + +(define_expand "mma_" + [(set (match_operand:XO 0 "register_operand") + (unspec:XO [(match_operand:XO 1 "register_operand")] + MMA_ACC))] + "TARGET_MMA" +{ + if (TARGET_DENSE_MATH) + { + if (!rtx_equal_p (operands[0], operands[1])) + emit_move_insn (operands[0], operands[1]); + DONE; + } + + /* Generate the prime/de-prime code. */ +}) + +(define_insn "*mma_" [(set (match_operand:XO 0 "fpr_reg_operand" "=&d") (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0")] MMA_ACC))] - "TARGET_MMA" + "TARGET_MMA && !TARGET_DENSE_MATH" " %A0" [(set_attr "type" "mma")]) ;; We can't have integer constants in XOmode so we wrap this in an -;; UNSPEC_VOLATILE. +;; UNSPEC_VOLATILE for the non-dense math case. For dense math, we don't need +;; to disable optimization and we can do a normal UNSPEC. -(define_insn "mma_xxsetaccz" - [(set (match_operand:XO 0 "fpr_reg_operand" "=d") +(define_expand "mma_xxsetaccz" + [(set (match_operand:XO 0 "register_operand") (unspec_volatile:XO [(const_int 0)] UNSPECV_MMA_XXSETACCZ))] "TARGET_MMA" +{ + if (TARGET_DENSE_MATH) + { + emit_insn (gen_mma_xxsetaccz_dm (operands[0])); + DONE; + } +}) + +(define_insn "*mma_xxsetaccz_p10" + [(set (match_operand:XO 0 "fpr_reg_operand" "=d") + (unspec_volatile:XO [(const_int 0)] + UNSPECV_MMA_XXSETACCZ))] + "TARGET_MMA && !TARGET_DENSE_MATH" "xxsetaccz %A0" [(set_attr "type" "mma")]) + +(define_insn "mma_xxsetaccz_dm" + [(set (match_operand:XO 0 "dmr_operand" "=wD") + (unspec:XO [(const_int 0)] + UNSPECV_MMA_XXSETACCZ))] + "TARGET_DENSE_MATH" + "dmsetaccz %0" + [(set_attr "type" "mma")]) + (define_insn "mma_" - [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d") - (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa") - (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")] + [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d") + (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa") + (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")] MMA_VV))] "TARGET_MMA" " %A0,%x1,%x2" - [(set_attr "type" "mma")]) + [(set_attr "type" "mma") + (set_attr "isa" "dm,not_dm,not_dm")]) (define_insn "mma_" - [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d") - (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0") - (match_operand:V16QI 2 "vsx_register_operand" "v,?wa") - (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")] + [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d") + (unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0") + (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa") + (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")] MMA_AVV))] "TARGET_MMA" " %A0,%x2,%x3" - [(set_attr "type" "mma")]) + [(set_attr "type" "mma") + (set_attr "isa" "dm,not_dm,not_dm")]) (define_insn "mma_" - [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d") - (unspec:XO [(match_operand:OO 1 "vsx_register_operand" "v,?wa") - (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")] + [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d") + (unspec:XO [(match_operand:OO 1 "vsx_register_operand" "wa,v,?wa") + (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")] MMA_PV))] "TARGET_MMA" " %A0,%x1,%x2" - [(set_attr "type" "mma")]) + [(set_attr "type" "mma") + (set_attr "isa" "dm,not_dm,not_dm")]) (define_insn "mma_" - [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d") - (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0") - (match_operand:OO 2 "vsx_register_operand" "v,?wa") - (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")] + [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d") + (unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0") + (match_operand:OO 2 "vsx_register_operand" "wa,v,?wa") + (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")] MMA_APV))] "TARGET_MMA" " %A0,%x2,%x3" - [(set_attr "type" "mma")]) + [(set_attr "type" "mma") + (set_attr "isa" "dm,not_dm,not_dm")]) (define_insn "mma_" - [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d") - (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa") - (match_operand:V16QI 2 "vsx_register_operand" "v,?wa") - (match_operand:SI 3 "const_0_to_15_operand" "n,n") - (match_operand:SI 4 "const_0_to_15_operand" "n,n") - (match_operand:SI 5 "u8bit_cint_operand" "n,n")] + [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d") + (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa") + (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa") + (match_operand:SI 3 "const_0_to_15_operand" "n,n,n") + (match_operand:SI 4 "const_0_to_15_operand" "n,n,n") + (match_operand:SI 5 "u8bit_cint_operand" "n,n,n")] MMA_VVI4I4I8))] "TARGET_MMA" " %A0,%x1,%x2,%3,%4,%5" [(set_attr "type" "mma") - (set_attr "prefixed" "yes")]) + (set_attr "prefixed" "yes") + (set_attr "isa" "dm,not_dm,not_dm")]) (define_insn "mma_" - [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d") - (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0") - (match_operand:V16QI 2 "vsx_register_operand" "v,?wa") - (match_operand:V16QI 3 "vsx_register_operand" "v,?wa") - (match_operand:SI 4 "const_0_to_15_operand" "n,n") - (match_operand:SI 5 "const_0_to_15_operand" "n,n") - (match_operand:SI 6 "u8bit_cint_operand" "n,n")] + [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d") + (unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0") + (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa") + (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa") + (match_operand:SI 4 "const_0_to_15_operand" "n,n,n") + (match_operand:SI 5 "const_0_to_15_operand" "n,n,n") + (match_operand:SI 6 "u8bit_cint_operand" "n,n,n")] MMA_AVVI4I4I8))] "TARGET_MMA" " %A0,%x2,%x3,%4,%5,%6" [(set_attr "type" "mma") - (set_attr "prefixed" "yes")]) + (set_attr "prefixed" "yes") + (set_attr "isa" "dm,not_dm,not_dm")]) (define_insn "mma_" - [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d") - (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa") - (match_operand:V16QI 2 "vsx_register_operand" "v,?wa") - (match_operand:SI 3 "const_0_to_15_operand" "n,n") - (match_operand:SI 4 "const_0_to_15_operand" "n,n") - (match_operand:SI 5 "const_0_to_3_operand" "n,n")] + [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d") + (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa") + (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa") + (match_operand:SI 3 "const_0_to_15_operand" "n,n,n") + (match_operand:SI 4 "const_0_to_15_operand" "n,n,n") + (match_operand:SI 5 "const_0_to_3_operand" "n,n,n")] MMA_VVI4I4I2))] "TARGET_MMA" " %A0,%x1,%x2,%3,%4,%5" [(set_attr "type" "mma") - (set_attr "prefixed" "yes")]) + (set_attr "prefixed" "yes") + (set_attr "isa" "dm,not_dm,not_dm")]) (define_insn "mma_" - [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d") - (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0") - (match_operand:V16QI 2 "vsx_register_operand" "v,?wa") - (match_operand:V16QI 3 "vsx_register_operand" "v,?wa") - (match_operand:SI 4 "const_0_to_15_operand" "n,n") - (match_operand:SI 5 "const_0_to_15_operand" "n,n") - (match_operand:SI 6 "const_0_to_3_operand" "n,n")] + [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d") + (unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0") + (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa") + (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa") + (match_operand:SI 4 "const_0_to_15_operand" "n,n,n") + (match_operand:SI 5 "const_0_to_15_operand" "n,n,n") + (match_operand:SI 6 "const_0_to_3_operand" "n,n,n")] MMA_AVVI4I4I2))] "TARGET_MMA" " %A0,%x2,%x3,%4,%5,%6" [(set_attr "type" "mma") - (set_attr "prefixed" "yes")]) + (set_attr "prefixed" "yes") + (set_attr "isa" "dm,not_dm,not_dm")]) (define_insn "mma_" - [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d") - (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa") - (match_operand:V16QI 2 "vsx_register_operand" "v,?wa") - (match_operand:SI 3 "const_0_to_15_operand" "n,n") - (match_operand:SI 4 "const_0_to_15_operand" "n,n")] + [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d") + (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa") + (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa") + (match_operand:SI 3 "const_0_to_15_operand" "n,n,n") + (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")] MMA_VVI4I4))] "TARGET_MMA" " %A0,%x1,%x2,%3,%4" [(set_attr "type" "mma") - (set_attr "prefixed" "yes")]) + (set_attr "prefixed" "yes") + (set_attr "isa" "dm,not_dm,not_dm")]) (define_insn "mma_" - [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d") - (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0") - (match_operand:V16QI 2 "vsx_register_operand" "v,?wa") - (match_operand:V16QI 3 "vsx_register_operand" "v,?wa") - (match_operand:SI 4 "const_0_to_15_operand" "n,n") - (match_operand:SI 5 "const_0_to_15_operand" "n,n")] + [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d") + (unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0") + (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa") + (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa") + (match_operand:SI 4 "const_0_to_15_operand" "n,n,n") + (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")] MMA_AVVI4I4))] "TARGET_MMA" " %A0,%x2,%x3,%4,%5" [(set_attr "type" "mma") - (set_attr "prefixed" "yes")]) + (set_attr "prefixed" "yes") + (set_attr "isa" "dm,not_dm,not_dm")]) (define_insn "mma_" - [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d") - (unspec:XO [(match_operand:OO 1 "vsx_register_operand" "v,?wa") - (match_operand:V16QI 2 "vsx_register_operand" "v,?wa") - (match_operand:SI 3 "const_0_to_15_operand" "n,n") - (match_operand:SI 4 "const_0_to_3_operand" "n,n")] + [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d") + (unspec:XO [(match_operand:OO 1 "vsx_register_operand" "wa,v,?wa") + (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa") + (match_operand:SI 3 "const_0_to_15_operand" "n,n,n") + (match_operand:SI 4 "const_0_to_3_operand" "n,n,n")] MMA_PVI4I2))] "TARGET_MMA" " %A0,%x1,%x2,%3,%4" [(set_attr "type" "mma") - (set_attr "prefixed" "yes")]) + (set_attr "prefixed" "yes") + (set_attr "isa" "dm,not_dm,not_dm")]) (define_insn "mma_" - [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d") - (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0") - (match_operand:OO 2 "vsx_register_operand" "v,?wa") - (match_operand:V16QI 3 "vsx_register_operand" "v,?wa") - (match_operand:SI 4 "const_0_to_15_operand" "n,n") - (match_operand:SI 5 "const_0_to_3_operand" "n,n")] + [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d") + (unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0") + (match_operand:OO 2 "vsx_register_operand" "wa,v,?wa") + (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa") + (match_operand:SI 4 "const_0_to_15_operand" "n,n,n") + (match_operand:SI 5 "const_0_to_3_operand" "n,n,n")] MMA_APVI4I2))] "TARGET_MMA" " %A0,%x2,%x3,%4,%5" [(set_attr "type" "mma") - (set_attr "prefixed" "yes")]) + (set_attr "prefixed" "yes") + (set_attr "isa" "dm,not_dm,not_dm")]) (define_insn "mma_" - [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d") - (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa") - (match_operand:V16QI 2 "vsx_register_operand" "v,?wa") - (match_operand:SI 3 "const_0_to_15_operand" "n,n") - (match_operand:SI 4 "const_0_to_15_operand" "n,n") - (match_operand:SI 5 "const_0_to_15_operand" "n,n")] + [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d") + (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa") + (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa") + (match_operand:SI 3 "const_0_to_15_operand" "n,n,n") + (match_operand:SI 4 "const_0_to_15_operand" "n,n,n") + (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")] MMA_VVI4I4I4))] "TARGET_MMA" " %A0,%x1,%x2,%3,%4,%5" [(set_attr "type" "mma") - (set_attr "prefixed" "yes")]) + (set_attr "prefixed" "yes") + (set_attr "isa" "dm,not_dm,not_dm")]) (define_insn "mma_" - [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d") - (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0") - (match_operand:V16QI 2 "vsx_register_operand" "v,?wa") - (match_operand:V16QI 3 "vsx_register_operand" "v,?wa") - (match_operand:SI 4 "const_0_to_15_operand" "n,n") - (match_operand:SI 5 "const_0_to_15_operand" "n,n") - (match_operand:SI 6 "const_0_to_15_operand" "n,n")] + [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d") + (unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0") + (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa") + (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa") + (match_operand:SI 4 "const_0_to_15_operand" "n,n,n") + (match_operand:SI 5 "const_0_to_15_operand" "n,n,n") + (match_operand:SI 6 "const_0_to_15_operand" "n,n,n")] MMA_AVVI4I4I4))] "TARGET_MMA" " %A0,%x2,%x3,%4,%5,%6" [(set_attr "type" "mma") - (set_attr "prefixed" "yes")]) + (set_attr "prefixed" "yes") + (set_attr "isa" "dm,not_dm,not_dm")]) diff --git a/gcc/config/rs6000/rs6000-c.cc b/gcc/config/rs6000/rs6000-c.cc index 3b781639be1..296aa3b1630 100644 --- a/gcc/config/rs6000/rs6000-c.cc +++ b/gcc/config/rs6000/rs6000-c.cc @@ -600,6 +600,9 @@ rs6000_target_modify_macros (bool define_p, HOST_WIDE_INT flags) /* Tell the user if we support the MMA instructions. */ if ((flags & OPTION_MASK_MMA) != 0) rs6000_define_or_undefine_macro (define_p, "__MMA__"); + /* Tell the user if we support the dense math instructions. */ + if ((flags & OPTION_MASK_DENSE_MATH) != 0) + rs6000_define_or_undefine_macro (define_p, "__PPC_DMR__"); /* Whether pc-relative code is being generated. */ if ((flags & OPTION_MASK_PCREL) != 0) rs6000_define_or_undefine_macro (define_p, "__PCREL__"); diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc index 03f43f70a62..caa908e7e2c 100644 --- a/gcc/config/rs6000/rs6000.cc +++ b/gcc/config/rs6000/rs6000.cc @@ -13909,8 +13909,13 @@ print_operand (FILE *file, rtx x, int code) overlapping with the FPR registers. */ if (!REG_P (x)) output_operand_lossage ("invalid %%A value"); - else if (TARGET_DENSE_MATH && DMR_REGNO_P (REGNO (x))) - fprintf (file, "%d", REGNO (x) - FIRST_DMR_REGNO); + else if (TARGET_DENSE_MATH) + { + if (DMR_REGNO_P (REGNO (x))) + fprintf (file, "%d", REGNO (x) - FIRST_DMR_REGNO); + else + output_operand_lossage ("%%A operand is not a DMR"); + } else if (!FP_REGNO_P (REGNO (x)) || (REGNO (x) % 4) != 0) output_operand_lossage ("invalid %%A value"); else @@ -27298,7 +27303,7 @@ rs6000_split_multireg_move (rtx dst, rtx src) /* If we are reading an accumulator register, we have to deprime it before we can access it. */ - if (TARGET_MMA + if (TARGET_MMA && !TARGET_DENSE_MATH && GET_MODE (src) == XOmode && FP_REGNO_P (REGNO (src))) emit_insn (gen_mma_xxmfacc (src, src)); @@ -27330,9 +27335,9 @@ rs6000_split_multireg_move (rtx dst, rtx src) emit_insn (gen_rtx_SET (dst2, src2)); } - /* If we are writing an accumulator register, we have to - prime it after we've written it. */ - if (TARGET_MMA + /* If we are writing an accumulator register that overlaps with the + FPR registers, we have to prime it after we've written it. */ + if (TARGET_MMA && !TARGET_DENSE_MATH && GET_MODE (dst) == XOmode && FP_REGNO_P (REGNO (dst))) emit_insn (gen_mma_xxmtacc (dst, dst)); @@ -27401,9 +27406,9 @@ rs6000_split_multireg_move (rtx dst, rtx src) emit_insn (gen_rtx_SET (dst_i, op)); } - /* We are writing an accumulator register, so we have to - prime it after we've written it. */ - if (GET_MODE (src) == XOmode) + /* On systems without dense math where accumulators overlap with the + vector registers, we have to prime it after we've written it. */ + if (GET_MODE (src) == XOmode && !TARGET_DENSE_MATH) emit_insn (gen_mma_xxmtacc (dst, dst)); return; @@ -27414,9 +27419,9 @@ rs6000_split_multireg_move (rtx dst, rtx src) if (REG_P (src) && REG_P (dst) && (REGNO (src) < REGNO (dst))) { - /* If we are reading an accumulator register, we have to - deprime it before we can access it. */ - if (TARGET_MMA + /* If we are reading an accumulator register and we don't have dense + math, we have to deprime it before we can access it. */ + if (TARGET_MMA && !TARGET_DENSE_MATH && GET_MODE (src) == XOmode && FP_REGNO_P (REGNO (src))) emit_insn (gen_mma_xxmfacc (src, src)); @@ -27444,7 +27449,7 @@ rs6000_split_multireg_move (rtx dst, rtx src) /* If we are writing an accumulator register, we have to prime it after we've written it. */ - if (TARGET_MMA + if (TARGET_MMA && !TARGET_DENSE_MATH && GET_MODE (dst) == XOmode && FP_REGNO_P (REGNO (dst))) emit_insn (gen_mma_xxmtacc (dst, dst)); } @@ -27581,7 +27586,7 @@ rs6000_split_multireg_move (rtx dst, rtx src) /* If we are reading an accumulator register, we have to deprime it before we can access it. */ - if (TARGET_MMA && REG_P (src) + if (TARGET_MMA && !TARGET_DENSE_MATH && REG_P (src) && GET_MODE (src) == XOmode && FP_REGNO_P (REGNO (src))) emit_insn (gen_mma_xxmfacc (src, src)); @@ -27613,7 +27618,7 @@ rs6000_split_multireg_move (rtx dst, rtx src) /* If we are writing an accumulator register, we have to prime it after we've written it. */ - if (TARGET_MMA && REG_P (dst) + if (TARGET_MMA && !TARGET_DENSE_MATH && REG_P (dst) && GET_MODE (dst) == XOmode && FP_REGNO_P (REGNO (dst))) emit_insn (gen_mma_xxmtacc (dst, dst)); diff --git a/gcc/testsuite/gcc.target/powerpc/dm-double-test.c b/gcc/testsuite/gcc.target/powerpc/dm-double-test.c new file mode 100644 index 00000000000..51733d6f641 --- /dev/null +++ b/gcc/testsuite/gcc.target/powerpc/dm-double-test.c @@ -0,0 +1,194 @@ +/* Test derived from mma-double-1.c, modified for dense math. */ +/* { dg-do compile } */ +/* { dg-require-effective-target powerpc_dense_math_ok } */ +/* { dg-options "-mdejagnu-cpu=future -O2" } */ + +#include +#include +#include + +typedef unsigned char vec_t __attribute__ ((vector_size (16))); +typedef double v4sf_t __attribute__ ((vector_size (16))); +#define SAVE_ACC(ACC, ldc, J) \ + __builtin_mma_disassemble_acc (result, ACC); \ + rowC = (v4sf_t *) &CO[0*ldc+J]; \ + rowC[0] += result[0]; \ + rowC = (v4sf_t *) &CO[1*ldc+J]; \ + rowC[0] += result[1]; \ + rowC = (v4sf_t *) &CO[2*ldc+J]; \ + rowC[0] += result[2]; \ + rowC = (v4sf_t *) &CO[3*ldc+J]; \ + rowC[0] += result[3]; + +void +DM (int m, int n, int k, double *A, double *B, double *C) +{ + __vector_quad acc0, acc1, acc2, acc3, acc4, acc5, acc6, acc7; + v4sf_t result[4]; + v4sf_t *rowC; + for (int l = 0; l < n; l += 4) + { + double *CO; + double *AO; + AO = A; + CO = C; + C += m * 4; + for (int j = 0; j < m; j += 16) + { + double *BO = B; + __builtin_mma_xxsetaccz (&acc0); + __builtin_mma_xxsetaccz (&acc1); + __builtin_mma_xxsetaccz (&acc2); + __builtin_mma_xxsetaccz (&acc3); + __builtin_mma_xxsetaccz (&acc4); + __builtin_mma_xxsetaccz (&acc5); + __builtin_mma_xxsetaccz (&acc6); + __builtin_mma_xxsetaccz (&acc7); + unsigned long i; + + for (i = 0; i < k; i++) + { + vec_t *rowA = (vec_t *) & AO[i * 16]; + __vector_pair rowB; + vec_t *rb = (vec_t *) & BO[i * 4]; + __builtin_mma_assemble_pair (&rowB, rb[1], rb[0]); + __builtin_mma_xvf64gerpp (&acc0, rowB, rowA[0]); + __builtin_mma_xvf64gerpp (&acc1, rowB, rowA[1]); + __builtin_mma_xvf64gerpp (&acc2, rowB, rowA[2]); + __builtin_mma_xvf64gerpp (&acc3, rowB, rowA[3]); + __builtin_mma_xvf64gerpp (&acc4, rowB, rowA[4]); + __builtin_mma_xvf64gerpp (&acc5, rowB, rowA[5]); + __builtin_mma_xvf64gerpp (&acc6, rowB, rowA[6]); + __builtin_mma_xvf64gerpp (&acc7, rowB, rowA[7]); + } + SAVE_ACC (&acc0, m, 0); + SAVE_ACC (&acc2, m, 4); + SAVE_ACC (&acc1, m, 2); + SAVE_ACC (&acc3, m, 6); + SAVE_ACC (&acc4, m, 8); + SAVE_ACC (&acc6, m, 12); + SAVE_ACC (&acc5, m, 10); + SAVE_ACC (&acc7, m, 14); + AO += k * 16; + BO += k * 4; + CO += 16; + } + B += k * 4; + } +} + +void +init (double *matrix, int row, int column) +{ + for (int j = 0; j < column; j++) + { + for (int i = 0; i < row; i++) + { + matrix[j * row + i] = (i * 16 + 2 + j) / 0.123; + } + } +} + +void +init0 (double *matrix, double *matrix1, int row, int column) +{ + for (int j = 0; j < column; j++) + for (int i = 0; i < row; i++) + matrix[j * row + i] = matrix1[j * row + i] = 0; +} + + +void +print (const char *name, const double *matrix, int row, int column) +{ + printf ("Matrix %s has %d rows and %d columns:\n", name, row, column); + for (int i = 0; i < row; i++) + { + for (int j = 0; j < column; j++) + { + printf ("%f ", matrix[j * row + i]); + } + printf ("\n"); + } + printf ("\n"); +} + +int +main (int argc, char *argv[]) +{ + int rowsA, colsB, common; + int i, j, k; + int ret = 0; + + for (int t = 16; t <= 128; t += 16) + { + for (int t1 = 4; t1 <= 16; t1 += 4) + { + rowsA = t; + colsB = t1; + common = 1; + /* printf ("Running test for rows = %d,cols = %d\n", t, t1); */ + double A[rowsA * common]; + double B[common * colsB]; + double C[rowsA * colsB]; + double D[rowsA * colsB]; + + + init (A, rowsA, common); + init (B, common, colsB); + init0 (C, D, rowsA, colsB); + DM (rowsA, colsB, common, A, B, C); + + for (i = 0; i < colsB; i++) + { + for (j = 0; j < rowsA; j++) + { + D[i * rowsA + j] = 0; + for (k = 0; k < common; k++) + { + D[i * rowsA + j] += + A[k * rowsA + j] * B[k + common * i]; + } + } + } + for (i = 0; i < colsB; i++) + { + for (j = 0; j < rowsA; j++) + { + for (k = 0; k < common; k++) + { + if (D[i * rowsA + j] != C[i * rowsA + j]) + { + printf ("Error %d,%d,%d\n",i,j,k); + ret++; + } + } + } + } + if (ret) + { + print ("A", A, rowsA, common); + print ("B", B, common, colsB); + print ("C", C, rowsA, colsB); + print ("D", D, rowsA, colsB); + } + } + } + +#ifdef VERBOSE + if (ret) + printf ("DM double test fail: %d errors\n",ret); + else + printf ("DM double test success: 0 DM errors\n"); +#else + if (ret) + abort(); +#endif + + return ret; +} + +/* { dg-final { scan-assembler-times {\mdmsetaccz\M} 8 } } */ +/* { dg-final { scan-assembler-times {\mdmxvf64gerpp\M} 8 } } */ +/* { dg-final { scan-assembler-times {\mdmxxextfdmr512\M} 11 } } */ + diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp index 0e45a2baed5..6826d150e65 100644 --- a/gcc/testsuite/lib/target-supports.exp +++ b/gcc/testsuite/lib/target-supports.exp @@ -6534,6 +6534,25 @@ proc check_effective_target_power10_ok { } { } } +# Return 1 if this is a PowerPC target supporting -mcpu=future or -mdense-math +# which enables the dense math operations. +proc check_effective_target_powerpc_dense_math_ok { } { + return [check_no_compiler_messages_nocache powerpc_dense_math_ok assembly { + __vector_quad vq; + void test (void) + { + #ifndef __PPC_DMR__ + #error "target does not have dense math support." + #else + /* Make sure we have dense math support. */ + __vector_quad dmr; + __asm__ ("dmsetaccz %A0" : "=wD" (dmr)); + vq = dmr; + #endif + } + } "-mcpu=future"] +} + # Return 1 if this is a PowerPC target supporting -mfloat128 via either # software emulation on power7/power8 systems or hardware support on power9.