Combine patterns for p10 load-cmpi fusion

This patch adds the first batch of patterns to support p10 fusion. These
will allow combine to create a single insn for a pair of instructions
that power10 can fuse and execute. These particular fusion pairs have the
requirement that only cr0 can be used when fusing a load with a compare
immediate of -1/0/1 (if signed) or 0/1 (if unsigned), so we want combine
to put that requirement in, and if it doesn't work out the splitter
can change it back into 2 insns so scheduling can move them apart.

The patterns are generated by a script genfusion.pl and live in new file
fusion.md. This script will be expanded to generate more patterns for
fusion.

This also adds option -mpower10-fusion which defaults on for power10 and
will gate all these fusion patterns. In addition I have added an
undocumented option -mpower10-fusion-ld-cmpi (which may be removed later)
that just controls the load+compare-immediate patterns. I have made
these default on for power10 but they are not disallowed for earlier
processors because it is still valid code. This allows us to test the
correctness of fusion code generation by turning it on explicitly.

gcc/ChangeLog:

	* config/rs6000/genfusion.pl: New script to generate
	define_insn_and_split patterns so combine can arrange fused
	instructions next to each other.
	* config/rs6000/fusion.md: New file, generated fused instruction
	patterns for combine.
	* config/rs6000/predicates.md (const_m1_to_1_operand): New predicate.
	(non_update_memory_operand): New predicate.
	* config/rs6000/rs6000-cpus.def: Add OPTION_MASK_P10_FUSION and
	OPTION_MASK_P10_FUSION_LD_CMPI to ISA_3_1_MASKS_SERVER and
	POWERPC_MASKS.
	* config/rs6000/rs6000-protos.h (address_is_non_pfx_d_or_x): Add
	prototype.
	* config/rs6000/rs6000.c (rs6000_option_override_internal):
	Automatically set OPTION_MASK_P10_FUSION and
	OPTION_MASK_P10_FUSION_LD_CMPI if target is power10.
	(rs600_opt_masks): Allow -mpower10-fusion
	in function attributes.
	(address_is_non_pfx_d_or_x): New function.
	* config/rs6000/rs6000.h: Add MASK_P10_FUSION.
	* config/rs6000/rs6000.md: Include fusion.md.
	* config/rs6000/rs6000.opt: Add -mpower10-fusion
	and -mpower10-fusion-ld-cmpi.
	* config/rs6000/t-rs6000: Add dependencies involving fusion.md.

diff --git a/gcc/config/rs6000/fusion.md b/gcc/config/rs6000/fusion.md
new file mode 100644 (file)
index 0000000..a4d3a6a
--- /dev/null
+++ b/gcc/config/rs6000/fusion.md
@@ -0,0 +1,357 @@
+;; -*- buffer-read-only: t -*-
+;; Generated automatically by genfusion.pl
+
+;; Copyright (C) 2020 Free Software Foundation, Inc.
+;;
+;; This file is part of GCC.
+;;
+;; GCC is free software; you can redistribute it and/or modify it under
+;; the terms of the GNU General Public License as published by the Free
+;; Software Foundation; either version 3, or (at your option) any later
+;; version.
+;;
+;; GCC is distributed in the hope that it will be useful, but WITHOUT ANY
+;; WARRANTY; without even the implied warranty of MERCHANTABILITY or
+;; FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+;; for more details.
+;;
+;; You should have received a copy of the GNU General Public License
+;; along with GCC; see the file COPYING3.  If not see
+;; <http://www.gnu.org/licenses/>.
+
+;; load-cmpi fusion pattern generated by gen_ld_cmpi_p10
+;; load mode is DI result mode is clobber compare mode is CC extend is none
+(define_insn_and_split "*ld_cmpdi_cr0_DI_clobber_CC_none"
+  [(set (match_operand:CC 2 "cc_reg_operand" "=x")
+        (compare:CC (match_operand:DI 1 "non_update_memory_operand" "m")
+                 (match_operand:DI 3 "const_m1_to_1_operand" "n")))
+   (clobber (match_scratch:DI 0 "=r"))]
+  "(TARGET_P10_FUSION && TARGET_P10_FUSION_LD_CMPI)"
+  "ld%X1 %0,%1\;cmpdi 0,%0,%3"
+  "&& reload_completed
+   && (cc_reg_not_cr0_operand (operands[2], CCmode)
+       || !address_is_non_pfx_d_or_x (XEXP (operands[1],0), DImode, NON_PREFIXED_DS))"
+  [(set (match_dup 0) (match_dup 1))
+   (set (match_dup 2)
+        (compare:CC (match_dup 0)
+                   (match_dup 3)))]
+  ""
+  [(set_attr "type" "load")
+   (set_attr "cost" "8")
+   (set_attr "length" "8")])
+
+;; load-cmpi fusion pattern generated by gen_ld_cmpi_p10
+;; load mode is DI result mode is clobber compare mode is CCUNS extend is none
+(define_insn_and_split "*ld_cmpldi_cr0_DI_clobber_CCUNS_none"
+  [(set (match_operand:CCUNS 2 "cc_reg_operand" "=x")
+        (compare:CCUNS (match_operand:DI 1 "non_update_memory_operand" "m")
+                 (match_operand:DI 3 "const_0_to_1_operand" "n")))
+   (clobber (match_scratch:DI 0 "=r"))]
+  "(TARGET_P10_FUSION && TARGET_P10_FUSION_LD_CMPI)"
+  "ld%X1 %0,%1\;cmpldi 0,%0,%3"
+  "&& reload_completed
+   && (cc_reg_not_cr0_operand (operands[2], CCmode)
+       || !address_is_non_pfx_d_or_x (XEXP (operands[1],0), DImode, NON_PREFIXED_DS))"
+  [(set (match_dup 0) (match_dup 1))
+   (set (match_dup 2)
+        (compare:CCUNS (match_dup 0)
+                   (match_dup 3)))]
+  ""
+  [(set_attr "type" "load")
+   (set_attr "cost" "8")
+   (set_attr "length" "8")])
+
+;; load-cmpi fusion pattern generated by gen_ld_cmpi_p10
+;; load mode is DI result mode is DI compare mode is CC extend is none
+(define_insn_and_split "*ld_cmpdi_cr0_DI_DI_CC_none"
+  [(set (match_operand:CC 2 "cc_reg_operand" "=x")
+        (compare:CC (match_operand:DI 1 "non_update_memory_operand" "m")
+                 (match_operand:DI 3 "const_m1_to_1_operand" "n")))
+   (set (match_operand:DI 0 "gpc_reg_operand" "=r") (match_dup 1))]
+  "(TARGET_P10_FUSION && TARGET_P10_FUSION_LD_CMPI)"
+  "ld%X1 %0,%1\;cmpdi 0,%0,%3"
+  "&& reload_completed
+   && (cc_reg_not_cr0_operand (operands[2], CCmode)
+       || !address_is_non_pfx_d_or_x (XEXP (operands[1],0), DImode, NON_PREFIXED_DS))"
+  [(set (match_dup 0) (match_dup 1))
+   (set (match_dup 2)
+        (compare:CC (match_dup 0)
+                   (match_dup 3)))]
+  ""
+  [(set_attr "type" "load")
+   (set_attr "cost" "8")
+   (set_attr "length" "8")])
+
+;; load-cmpi fusion pattern generated by gen_ld_cmpi_p10
+;; load mode is DI result mode is DI compare mode is CCUNS extend is none
+(define_insn_and_split "*ld_cmpldi_cr0_DI_DI_CCUNS_none"
+  [(set (match_operand:CCUNS 2 "cc_reg_operand" "=x")
+        (compare:CCUNS (match_operand:DI 1 "non_update_memory_operand" "m")
+                 (match_operand:DI 3 "const_0_to_1_operand" "n")))
+   (set (match_operand:DI 0 "gpc_reg_operand" "=r") (match_dup 1))]
+  "(TARGET_P10_FUSION && TARGET_P10_FUSION_LD_CMPI)"
+  "ld%X1 %0,%1\;cmpldi 0,%0,%3"
+  "&& reload_completed
+   && (cc_reg_not_cr0_operand (operands[2], CCmode)
+       || !address_is_non_pfx_d_or_x (XEXP (operands[1],0), DImode, NON_PREFIXED_DS))"
+  [(set (match_dup 0) (match_dup 1))
+   (set (match_dup 2)
+        (compare:CCUNS (match_dup 0)
+                   (match_dup 3)))]
+  ""
+  [(set_attr "type" "load")
+   (set_attr "cost" "8")
+   (set_attr "length" "8")])
+
+;; load-cmpi fusion pattern generated by gen_ld_cmpi_p10
+;; load mode is SI result mode is clobber compare mode is CC extend is none
+(define_insn_and_split "*lwa_cmpdi_cr0_SI_clobber_CC_none"
+  [(set (match_operand:CC 2 "cc_reg_operand" "=x")
+        (compare:CC (match_operand:SI 1 "non_update_memory_operand" "m")
+                 (match_operand:SI 3 "const_m1_to_1_operand" "n")))
+   (clobber (match_scratch:SI 0 "=r"))]
+  "(TARGET_P10_FUSION && TARGET_P10_FUSION_LD_CMPI)"
+  "lwa%X1 %0,%1\;cmpdi 0,%0,%3"
+  "&& reload_completed
+   && (cc_reg_not_cr0_operand (operands[2], CCmode)
+       || !address_is_non_pfx_d_or_x (XEXP (operands[1],0), SImode, NON_PREFIXED_DS))"
+  [(set (match_dup 0) (match_dup 1))
+   (set (match_dup 2)
+        (compare:CC (match_dup 0)
+                   (match_dup 3)))]
+  ""
+  [(set_attr "type" "load")
+   (set_attr "cost" "8")
+   (set_attr "length" "8")])
+
+;; load-cmpi fusion pattern generated by gen_ld_cmpi_p10
+;; load mode is SI result mode is clobber compare mode is CCUNS extend is none
+(define_insn_and_split "*lwz_cmpldi_cr0_SI_clobber_CCUNS_none"
+  [(set (match_operand:CCUNS 2 "cc_reg_operand" "=x")
+        (compare:CCUNS (match_operand:SI 1 "non_update_memory_operand" "m")
+                 (match_operand:SI 3 "const_0_to_1_operand" "n")))
+   (clobber (match_scratch:SI 0 "=r"))]
+  "(TARGET_P10_FUSION && TARGET_P10_FUSION_LD_CMPI)"
+  "lwz%X1 %0,%1\;cmpldi 0,%0,%3"
+  "&& reload_completed
+   && (cc_reg_not_cr0_operand (operands[2], CCmode)
+       || !address_is_non_pfx_d_or_x (XEXP (operands[1],0), SImode, NON_PREFIXED_D))"
+  [(set (match_dup 0) (match_dup 1))
+   (set (match_dup 2)
+        (compare:CCUNS (match_dup 0)
+                   (match_dup 3)))]
+  ""
+  [(set_attr "type" "load")
+   (set_attr "cost" "8")
+   (set_attr "length" "8")])
+
+;; load-cmpi fusion pattern generated by gen_ld_cmpi_p10
+;; load mode is SI result mode is SI compare mode is CC extend is none
+(define_insn_and_split "*lwa_cmpdi_cr0_SI_SI_CC_none"
+  [(set (match_operand:CC 2 "cc_reg_operand" "=x")
+        (compare:CC (match_operand:SI 1 "non_update_memory_operand" "m")
+                 (match_operand:SI 3 "const_m1_to_1_operand" "n")))
+   (set (match_operand:SI 0 "gpc_reg_operand" "=r") (match_dup 1))]
+  "(TARGET_P10_FUSION && TARGET_P10_FUSION_LD_CMPI)"
+  "lwa%X1 %0,%1\;cmpdi 0,%0,%3"
+  "&& reload_completed
+   && (cc_reg_not_cr0_operand (operands[2], CCmode)
+       || !address_is_non_pfx_d_or_x (XEXP (operands[1],0), SImode, NON_PREFIXED_DS))"
+  [(set (match_dup 0) (match_dup 1))
+   (set (match_dup 2)
+        (compare:CC (match_dup 0)
+                   (match_dup 3)))]
+  ""
+  [(set_attr "type" "load")
+   (set_attr "cost" "8")
+   (set_attr "length" "8")])
+
+;; load-cmpi fusion pattern generated by gen_ld_cmpi_p10
+;; load mode is SI result mode is SI compare mode is CCUNS extend is none
+(define_insn_and_split "*lwz_cmpldi_cr0_SI_SI_CCUNS_none"
+  [(set (match_operand:CCUNS 2 "cc_reg_operand" "=x")
+        (compare:CCUNS (match_operand:SI 1 "non_update_memory_operand" "m")
+                 (match_operand:SI 3 "const_0_to_1_operand" "n")))
+   (set (match_operand:SI 0 "gpc_reg_operand" "=r") (match_dup 1))]
+  "(TARGET_P10_FUSION && TARGET_P10_FUSION_LD_CMPI)"
+  "lwz%X1 %0,%1\;cmpldi 0,%0,%3"
+  "&& reload_completed
+   && (cc_reg_not_cr0_operand (operands[2], CCmode)
+       || !address_is_non_pfx_d_or_x (XEXP (operands[1],0), SImode, NON_PREFIXED_D))"
+  [(set (match_dup 0) (match_dup 1))
+   (set (match_dup 2)
+        (compare:CCUNS (match_dup 0)
+                   (match_dup 3)))]
+  ""
+  [(set_attr "type" "load")
+   (set_attr "cost" "8")
+   (set_attr "length" "8")])
+
+;; load-cmpi fusion pattern generated by gen_ld_cmpi_p10
+;; load mode is SI result mode is EXTSI compare mode is CC extend is sign
+(define_insn_and_split "*lwa_cmpdi_cr0_SI_EXTSI_CC_sign"
+  [(set (match_operand:CC 2 "cc_reg_operand" "=x")
+        (compare:CC (match_operand:SI 1 "non_update_memory_operand" "m")
+                 (match_operand:SI 3 "const_m1_to_1_operand" "n")))
+   (set (match_operand:EXTSI 0 "gpc_reg_operand" "=r") (sign_extend:EXTSI (match_dup 1)))]
+  "(TARGET_P10_FUSION && TARGET_P10_FUSION_LD_CMPI)"
+  "lwa%X1 %0,%1\;cmpdi 0,%0,%3"
+  "&& reload_completed
+   && (cc_reg_not_cr0_operand (operands[2], CCmode)
+       || !address_is_non_pfx_d_or_x (XEXP (operands[1],0), SImode, NON_PREFIXED_DS))"
+  [(set (match_dup 0) (sign_extend:EXTSI (match_dup 1)))
+   (set (match_dup 2)
+        (compare:CC (match_dup 0)
+                   (match_dup 3)))]
+  ""
+  [(set_attr "type" "load")
+   (set_attr "cost" "8")
+   (set_attr "length" "8")])
+
+;; load-cmpi fusion pattern generated by gen_ld_cmpi_p10
+;; load mode is SI result mode is EXTSI compare mode is CCUNS extend is zero
+(define_insn_and_split "*lwz_cmpldi_cr0_SI_EXTSI_CCUNS_zero"
+  [(set (match_operand:CCUNS 2 "cc_reg_operand" "=x")
+        (compare:CCUNS (match_operand:SI 1 "non_update_memory_operand" "m")
+                 (match_operand:SI 3 "const_0_to_1_operand" "n")))
+   (set (match_operand:EXTSI 0 "gpc_reg_operand" "=r") (zero_extend:EXTSI (match_dup 1)))]
+  "(TARGET_P10_FUSION && TARGET_P10_FUSION_LD_CMPI)"
+  "lwz%X1 %0,%1\;cmpldi 0,%0,%3"
+  "&& reload_completed
+   && (cc_reg_not_cr0_operand (operands[2], CCmode)
+       || !address_is_non_pfx_d_or_x (XEXP (operands[1],0), SImode, NON_PREFIXED_D))"
+  [(set (match_dup 0) (zero_extend:EXTSI (match_dup 1)))
+   (set (match_dup 2)
+        (compare:CCUNS (match_dup 0)
+                   (match_dup 3)))]
+  ""
+  [(set_attr "type" "load")
+   (set_attr "cost" "8")
+   (set_attr "length" "8")])
+
+;; load-cmpi fusion pattern generated by gen_ld_cmpi_p10
+;; load mode is HI result mode is clobber compare mode is CC extend is sign
+(define_insn_and_split "*lha_cmpdi_cr0_HI_clobber_CC_sign"
+  [(set (match_operand:CC 2 "cc_reg_operand" "=x")
+        (compare:CC (match_operand:HI 1 "non_update_memory_operand" "m")
+                 (match_operand:HI 3 "const_m1_to_1_operand" "n")))
+   (clobber (match_scratch:GPR 0 "=r"))]
+  "(TARGET_P10_FUSION && TARGET_P10_FUSION_LD_CMPI)"
+  "lha%X1 %0,%1\;cmpdi 0,%0,%3"
+  "&& reload_completed
+   && (cc_reg_not_cr0_operand (operands[2], CCmode)
+       || !address_is_non_pfx_d_or_x (XEXP (operands[1],0), HImode, NON_PREFIXED_D))"
+  [(set (match_dup 0) (sign_extend:GPR (match_dup 1)))
+   (set (match_dup 2)
+        (compare:CC (match_dup 0)
+                   (match_dup 3)))]
+  ""
+  [(set_attr "type" "load")
+   (set_attr "cost" "8")
+   (set_attr "length" "8")])
+
+;; load-cmpi fusion pattern generated by gen_ld_cmpi_p10
+;; load mode is HI result mode is clobber compare mode is CCUNS extend is zero
+(define_insn_and_split "*lhz_cmpldi_cr0_HI_clobber_CCUNS_zero"
+  [(set (match_operand:CCUNS 2 "cc_reg_operand" "=x")
+        (compare:CCUNS (match_operand:HI 1 "non_update_memory_operand" "m")
+                 (match_operand:HI 3 "const_0_to_1_operand" "n")))
+   (clobber (match_scratch:GPR 0 "=r"))]
+  "(TARGET_P10_FUSION && TARGET_P10_FUSION_LD_CMPI)"
+  "lhz%X1 %0,%1\;cmpldi 0,%0,%3"
+  "&& reload_completed
+   && (cc_reg_not_cr0_operand (operands[2], CCmode)
+       || !address_is_non_pfx_d_or_x (XEXP (operands[1],0), HImode, NON_PREFIXED_D))"
+  [(set (match_dup 0) (zero_extend:GPR (match_dup 1)))
+   (set (match_dup 2)
+        (compare:CCUNS (match_dup 0)
+                   (match_dup 3)))]
+  ""
+  [(set_attr "type" "load")
+   (set_attr "cost" "8")
+   (set_attr "length" "8")])
+
+;; load-cmpi fusion pattern generated by gen_ld_cmpi_p10
+;; load mode is HI result mode is EXTHI compare mode is CC extend is sign
+(define_insn_and_split "*lha_cmpdi_cr0_HI_EXTHI_CC_sign"
+  [(set (match_operand:CC 2 "cc_reg_operand" "=x")
+        (compare:CC (match_operand:HI 1 "non_update_memory_operand" "m")
+                 (match_operand:HI 3 "const_m1_to_1_operand" "n")))
+   (set (match_operand:EXTHI 0 "gpc_reg_operand" "=r") (sign_extend:EXTHI (match_dup 1)))]
+  "(TARGET_P10_FUSION && TARGET_P10_FUSION_LD_CMPI)"
+  "lha%X1 %0,%1\;cmpdi 0,%0,%3"
+  "&& reload_completed
+   && (cc_reg_not_cr0_operand (operands[2], CCmode)
+       || !address_is_non_pfx_d_or_x (XEXP (operands[1],0), HImode, NON_PREFIXED_D))"
+  [(set (match_dup 0) (sign_extend:EXTHI (match_dup 1)))
+   (set (match_dup 2)
+        (compare:CC (match_dup 0)
+                   (match_dup 3)))]
+  ""
+  [(set_attr "type" "load")
+   (set_attr "cost" "8")
+   (set_attr "length" "8")])
+
+;; load-cmpi fusion pattern generated by gen_ld_cmpi_p10
+;; load mode is HI result mode is EXTHI compare mode is CCUNS extend is zero
+(define_insn_and_split "*lhz_cmpldi_cr0_HI_EXTHI_CCUNS_zero"
+  [(set (match_operand:CCUNS 2 "cc_reg_operand" "=x")
+        (compare:CCUNS (match_operand:HI 1 "non_update_memory_operand" "m")
+                 (match_operand:HI 3 "const_0_to_1_operand" "n")))
+   (set (match_operand:EXTHI 0 "gpc_reg_operand" "=r") (zero_extend:EXTHI (match_dup 1)))]
+  "(TARGET_P10_FUSION && TARGET_P10_FUSION_LD_CMPI)"
+  "lhz%X1 %0,%1\;cmpldi 0,%0,%3"
+  "&& reload_completed
+   && (cc_reg_not_cr0_operand (operands[2], CCmode)
+       || !address_is_non_pfx_d_or_x (XEXP (operands[1],0), HImode, NON_PREFIXED_D))"
+  [(set (match_dup 0) (zero_extend:EXTHI (match_dup 1)))
+   (set (match_dup 2)
+        (compare:CCUNS (match_dup 0)
+                   (match_dup 3)))]
+  ""
+  [(set_attr "type" "load")
+   (set_attr "cost" "8")
+   (set_attr "length" "8")])
+
+;; load-cmpi fusion pattern generated by gen_ld_cmpi_p10
+;; load mode is QI result mode is clobber compare mode is CCUNS extend is zero
+(define_insn_and_split "*lbz_cmpldi_cr0_QI_clobber_CCUNS_zero"
+  [(set (match_operand:CCUNS 2 "cc_reg_operand" "=x")
+        (compare:CCUNS (match_operand:QI 1 "non_update_memory_operand" "m")
+                 (match_operand:QI 3 "const_0_to_1_operand" "n")))
+   (clobber (match_scratch:GPR 0 "=r"))]
+  "(TARGET_P10_FUSION && TARGET_P10_FUSION_LD_CMPI)"
+  "lbz%X1 %0,%1\;cmpldi 0,%0,%3"
+  "&& reload_completed
+   && (cc_reg_not_cr0_operand (operands[2], CCmode)
+       || !address_is_non_pfx_d_or_x (XEXP (operands[1],0), QImode, NON_PREFIXED_D))"
+  [(set (match_dup 0) (zero_extend:GPR (match_dup 1)))
+   (set (match_dup 2)
+        (compare:CCUNS (match_dup 0)
+                   (match_dup 3)))]
+  ""
+  [(set_attr "type" "load")
+   (set_attr "cost" "8")
+   (set_attr "length" "8")])
+
+;; load-cmpi fusion pattern generated by gen_ld_cmpi_p10
+;; load mode is QI result mode is GPR compare mode is CCUNS extend is zero
+(define_insn_and_split "*lbz_cmpldi_cr0_QI_GPR_CCUNS_zero"
+  [(set (match_operand:CCUNS 2 "cc_reg_operand" "=x")
+        (compare:CCUNS (match_operand:QI 1 "non_update_memory_operand" "m")
+                 (match_operand:QI 3 "const_0_to_1_operand" "n")))
+   (set (match_operand:GPR 0 "gpc_reg_operand" "=r") (zero_extend:GPR (match_dup 1)))]
+  "(TARGET_P10_FUSION && TARGET_P10_FUSION_LD_CMPI)"
+  "lbz%X1 %0,%1\;cmpldi 0,%0,%3"
+  "&& reload_completed
+   && (cc_reg_not_cr0_operand (operands[2], CCmode)
+       || !address_is_non_pfx_d_or_x (XEXP (operands[1],0), QImode, NON_PREFIXED_D))"
+  [(set (match_dup 0) (zero_extend:GPR (match_dup 1)))
+   (set (match_dup 2)
+        (compare:CCUNS (match_dup 0)
+                   (match_dup 3)))]
+  ""
+  [(set_attr "type" "load")
+   (set_attr "cost" "8")
+   (set_attr "length" "8")])
+

diff --git a/gcc/config/rs6000/genfusion.pl b/gcc/config/rs6000/genfusion.pl
new file mode 100755 (executable)
index 0000000..2b53c10
--- /dev/null
+++ b/gcc/config/rs6000/genfusion.pl
@@ -0,0 +1,148 @@
+#!/usr/bin/perl
+# Generate fusion.md
+#
+# Copyright (C) 2020,2021 Free Software Foundation, Inc.
+#
+# This file is part of GCC.
+#
+# GCC is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3, or (at your option)
+# any later version.
+#
+# GCC is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with GCC; see the file COPYING3.  If not see
+# <http://www.gnu.org/licenses/>.
+
+use warnings;
+use strict;
+
+print <<'EOF';
+;; Generated automatically by genfusion.pl
+
+;; Copyright (C) 2020,2021 Free Software Foundation, Inc.
+;;
+;; This file is part of GCC.
+;;
+;; GCC is free software; you can redistribute it and/or modify it under
+;; the terms of the GNU General Public License as published by the Free
+;; Software Foundation; either version 3, or (at your option) any later
+;; version.
+;;
+;; GCC is distributed in the hope that it will be useful, but WITHOUT ANY
+;; WARRANTY; without even the implied warranty of MERCHANTABILITY or
+;; FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+;; for more details.
+;;
+;; You should have received a copy of the GNU General Public License
+;; along with GCC; see the file COPYING3.  If not see
+;; <http://www.gnu.org/licenses/>.
+
+EOF
+
+sub mode_to_ldst_char
+{
+    my ($mode) = @_;
+    my %x = (DI => 'd', SI => 'w', HI => 'h', QI => 'b');
+    return $x{$mode} if exists $x{$mode};
+    return '?';
+}
+
+sub gen_ld_cmpi_p10
+{
+    my ($lmode, $ldst, $clobbermode, $result, $cmpl, $echr, $constpred,
+       $ccmode, $np, $extend, $resultmode);
+  LMODE: foreach $lmode ('DI','SI','HI','QI') {
+      $ldst = mode_to_ldst_char($lmode);
+      $clobbermode = $lmode;
+      # For clobber, we need a SI/DI reg in case we
+      # split because we have to sign/zero extend.
+      if ($lmode eq 'HI' || $lmode eq 'QI') { $clobbermode = "GPR"; }
+    RESULT: foreach $result ('clobber', $lmode,  "EXT".$lmode) {
+       # EXTDI does not exist, and we cannot directly produce HI/QI results.
+       next RESULT if $result eq "EXTDI" || $result eq "HI" || $result eq "QI";
+       # Don't allow EXTQI because that would allow HI result which we can't do.
+       $result = "GPR" if $result eq "EXTQI";
+      CCMODE: foreach $ccmode ('CC','CCUNS') {
+         $np = "NON_PREFIXED_D";
+         if ( $ccmode eq 'CC' ) {
+             next CCMODE if $lmode eq 'QI';
+             if ( $lmode eq 'DI' || $lmode eq 'SI' ) {
+                 # ld and lwa are both DS-FORM.
+                 $np = "NON_PREFIXED_DS";
+             }
+             $cmpl = "";
+             $echr = "a";
+             $constpred = "const_m1_to_1_operand";
+         } else {
+             if ( $lmode eq 'DI' ) {
+                 # ld is DS-form, but lwz is not.
+                 $np = "NON_PREFIXED_DS";
+             }
+             $cmpl = "l";
+             $echr = "z";
+             $constpred = "const_0_to_1_operand";
+         }
+         if ($lmode eq 'DI') { $echr = ""; }
+         if ($result =~ m/^EXT/ || $result eq 'GPR' || $clobbermode eq 'GPR') {
+             # We always need extension if result > lmode.
+             if ( $ccmode eq 'CC' ) {
+                 $extend = "sign";
+             } else {
+                 $extend = "zero";
+             }
+         } else {
+             # Result of SI/DI does not need sign extension.
+             $extend = "none";
+         }
+         print ";; load-cmpi fusion pattern generated by gen_ld_cmpi_p10\n";
+         print ";; load mode is $lmode result mode is $result compare mode is $ccmode extend is $extend\n";
+
+         print "(define_insn_and_split \"*l${ldst}${echr}_cmp${cmpl}di_cr0_${lmode}_${result}_${ccmode}_${extend}\"\n";
+         print "  [(set (match_operand:${ccmode} 2 \"cc_reg_operand\" \"=x\")\n";
+         print "        (compare:${ccmode} (match_operand:${lmode} 1 \"non_update_memory_operand\" \"m\")\n";
+         if ($ccmode eq 'CCUNS') { print "   "; }
+         print "                    (match_operand:${lmode} 3 \"${constpred}\" \"n\")))\n";
+         if ($result eq 'clobber') {
+             print "   (clobber (match_scratch:${clobbermode} 0 \"=r\"))]\n";
+         } elsif ($result eq $lmode) {
+             print "   (set (match_operand:${result} 0 \"gpc_reg_operand\" \"=r\") (match_dup 1))]\n";
+         } else {
+             print "   (set (match_operand:${result} 0 \"gpc_reg_operand\" \"=r\") (${extend}_extend:${result} (match_dup 1)))]\n";
+         }
+         print "  \"(TARGET_P10_FUSION && TARGET_P10_FUSION_LD_CMPI)\"\n";
+         print "  \"l${ldst}${echr}%X1 %0,%1\\;cmp${cmpl}di %2,%0,%3\"\n";
+         print "  \"&& reload_completed\n";
+         print "   && (cc_reg_not_cr0_operand (operands[2], CCmode)\n";
+         print "       || !address_is_non_pfx_d_or_x (XEXP (operands[1], 0),\n";
+         print "                                      ${lmode}mode, ${np}))\"\n";
+
+         if ($extend eq "none") {
+             print "  [(set (match_dup 0) (match_dup 1))\n";
+         } else {
+             $resultmode = $result;
+             if ( $result eq 'clobber' ) { $resultmode = $clobbermode }
+             print "  [(set (match_dup 0) (${extend}_extend:${resultmode} (match_dup 1)))\n";
+         }
+         print "   (set (match_dup 2)\n";
+         print "        (compare:${ccmode} (match_dup 0) (match_dup 3)))]\n";
+         print "  \"\"\n";
+         print "  [(set_attr \"type\" \"load\")\n";
+         print "   (set_attr \"cost\" \"8\")\n";
+         print "   (set_attr \"length\" \"8\")])\n";
+         print "\n";
+      }
+    }
+  }
+}
+
+
+gen_ld_cmpi_p10();
+
+exit(0);
+

diff --git a/gcc/config/rs6000/predicates.md b/gcc/config/rs6000/predicates.md
index 5d1952e..76328ec 100644 (file)
--- a/gcc/config/rs6000/predicates.md
+++ b/gcc/config/rs6000/predicates.md
@@ -297,6 +297,11 @@
   (and (match_code "const_int")
        (match_test "IN_RANGE (INTVAL (op), 0, 1)")))
 
+;; Match op = -1, op = 0, or op = 1.
+(define_predicate "const_m1_to_1_operand"
+  (and (match_code "const_int")
+       (match_test "IN_RANGE (INTVAL (op), -1, 1)")))
+
 ;; Match op = 0..3.
 (define_predicate "const_0_to_3_operand"
   (and (match_code "const_int")
@@ -847,6 +852,15 @@
                    || GET_CODE (XEXP (op, 0)) == PRE_DEC
                    || GET_CODE (XEXP (op, 0)) == PRE_MODIFY))"))
 
+;; Anything that matches memory_operand but does not update the address.
+(define_predicate "non_update_memory_operand"
+  (match_code "mem")
+{
+  if (update_address_mem (op, mode))
+    return 0;
+  return memory_operand (op, mode);
+})
+
 ;; Return 1 if the operand is a MEM with an indexed-form address.
 (define_special_predicate "indexed_address_mem"
   (match_test "(MEM_P (op)

diff --git a/gcc/config/rs6000/rs6000-cpus.def b/gcc/config/rs6000/rs6000-cpus.def
index fa5c75b..fc9376d 100644 (file)
--- a/gcc/config/rs6000/rs6000-cpus.def
+++ b/gcc/config/rs6000/rs6000-cpus.def
@@ -81,7 +81,9 @@
 
 #define ISA_3_1_MASKS_SERVER   (ISA_3_0_MASKS_SERVER                   \
                                 | OPTION_MASK_POWER10                  \
-                                | OTHER_POWER10_MASKS)
+                                | OTHER_POWER10_MASKS                  \
+                                | OPTION_MASK_P10_FUSION               \
+                                | OPTION_MASK_P10_FUSION_LD_CMPI)
 
 /* Flags that need to be turned off if -mno-power9-vector.  */
 #define OTHER_P9_VECTOR_MASKS  (OPTION_MASK_FLOAT128_HW                \
@@ -128,6 +130,8 @@
                                 | OPTION_MASK_FLOAT128_KEYWORD         \
                                 | OPTION_MASK_FPRND                    \
                                 | OPTION_MASK_POWER10                  \
+                                | OPTION_MASK_P10_FUSION               \
+                                | OPTION_MASK_P10_FUSION_LD_CMPI       \
                                 | OPTION_MASK_HTM                      \
                                 | OPTION_MASK_ISEL                     \
                                 | OPTION_MASK_MFCRF                    \

diff --git a/gcc/config/rs6000/rs6000-protos.h b/gcc/config/rs6000/rs6000-protos.h
index 9a46a41..6157097 100644 (file)
--- a/gcc/config/rs6000/rs6000-protos.h
+++ b/gcc/config/rs6000/rs6000-protos.h
@@ -192,6 +192,8 @@ enum non_prefixed_form {
 
 extern enum insn_form address_to_insn_form (rtx, machine_mode,
                                            enum non_prefixed_form);
+extern bool address_is_non_pfx_d_or_x (rtx addr, machine_mode mode,
+                                      enum non_prefixed_form non_prefix_format);
 extern bool prefixed_load_p (rtx_insn *);
 extern bool prefixed_store_p (rtx_insn *);
 extern bool prefixed_paddi_p (rtx_insn *);

diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index f5565a1..e46d45f 100644 (file)
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -4430,6 +4430,13 @@ rs6000_option_override_internal (bool global_init_p)
   if (TARGET_POWER10 && (rs6000_isa_flags_explicit & OPTION_MASK_MMA) == 0)
     rs6000_isa_flags |= OPTION_MASK_MMA;
 
+  if (TARGET_POWER10 && (rs6000_isa_flags_explicit & OPTION_MASK_P10_FUSION) == 0)
+    rs6000_isa_flags |= OPTION_MASK_P10_FUSION;
+
+  if (TARGET_POWER10 &&
+      (rs6000_isa_flags_explicit & OPTION_MASK_P10_FUSION_LD_CMPI) == 0)
+    rs6000_isa_flags |= OPTION_MASK_P10_FUSION_LD_CMPI;
+
   /* Turn off vector pair/mma options on non-power10 systems.  */
   else if (!TARGET_POWER10 && TARGET_MMA)
     {
@@ -23787,6 +23794,7 @@ static struct rs6000_opt_mask const rs6000_opt_masks[] =
   { "power9-minmax",           OPTION_MASK_P9_MINMAX,          false, true  },
   { "power9-misc",             OPTION_MASK_P9_MISC,            false, true  },
   { "power9-vector",           OPTION_MASK_P9_VECTOR,          false, true  },
+  { "power10-fusion",          OPTION_MASK_P10_FUSION,         false, true  },
   { "powerpc-gfxopt",          OPTION_MASK_PPC_GFXOPT,         false, true  },
   { "powerpc-gpopt",           OPTION_MASK_PPC_GPOPT,          false, true  },
   { "prefixed",                        OPTION_MASK_PREFIXED,           false, true  },
@@ -25878,6 +25886,50 @@ address_to_insn_form (rtx addr,
   return INSN_FORM_BAD;
 }
 
+/* Given address rtx ADDR for a load of MODE, is this legitimate for a
+   non-prefixed D-form or X-form instruction?  NON_PREFIXED_FORMAT is
+   given NON_PREFIXED_D or NON_PREFIXED_DS to indicate whether we want
+   a D-form or DS-form instruction.  X-form and base_reg are always
+   allowed.  */
+bool
+address_is_non_pfx_d_or_x (rtx addr, machine_mode mode,
+                          enum non_prefixed_form non_prefixed_format)
+{
+  enum insn_form result_form;
+
+  result_form = address_to_insn_form (addr, mode, non_prefixed_format);
+
+  switch (non_prefixed_format)
+    {
+    case NON_PREFIXED_D:
+      switch (result_form)
+       {
+       case INSN_FORM_X:
+       case INSN_FORM_D:
+       case INSN_FORM_DS:
+       case INSN_FORM_BASE_REG:
+         return true;
+       default:
+         return false;
+       }
+      break;
+    case NON_PREFIXED_DS:
+      switch (result_form)
+       {
+       case INSN_FORM_X:
+       case INSN_FORM_DS:
+       case INSN_FORM_BASE_REG:
+         return true;
+       default:
+         return false;
+       }
+      break;
+    default:
+      break;
+    }
+  return false;
+}
+
 /* Helper function to see if we're potentially looking at lfs/stfs.
    - PARALLEL containing a SET and a CLOBBER
    - stfs:

diff --git a/gcc/config/rs6000/rs6000.h b/gcc/config/rs6000/rs6000.h
index b05dd82..233a92b 100644 (file)
--- a/gcc/config/rs6000/rs6000.h
+++ b/gcc/config/rs6000/rs6000.h
@@ -539,6 +539,7 @@ extern int rs6000_vector_align[];
 #define MASK_UPDATE                    OPTION_MASK_UPDATE
 #define MASK_VSX                       OPTION_MASK_VSX
 #define MASK_POWER10                   OPTION_MASK_POWER10
+#define MASK_P10_FUSION                        OPTION_MASK_P10_FUSION
 
 #ifndef IN_LIBGCC2
 #define MASK_POWERPC64                 OPTION_MASK_POWERPC64

diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
index 9764253..a131552 100644 (file)
--- a/gcc/config/rs6000/rs6000.md
+++ b/gcc/config/rs6000/rs6000.md
@@ -14927,3 +14927,4 @@
 (include "dfp.md")
 (include "crypto.md")
 (include "htm.md")
+(include "fusion.md")

diff --git a/gcc/config/rs6000/rs6000.opt b/gcc/config/rs6000/rs6000.opt
index d128e52..6240f77 100644 (file)
--- a/gcc/config/rs6000/rs6000.opt
+++ b/gcc/config/rs6000/rs6000.opt
@@ -479,6 +479,14 @@ mpower8-vector
 Target Mask(P8_VECTOR) Var(rs6000_isa_flags)
 Use vector and scalar instructions added in ISA 2.07.
 
+mpower10-fusion
+Target Mask(P10_FUSION) Var(rs6000_isa_flags)
+Fuse certain integer operations together for better performance on power10.
+
+mpower10-fusion-ld-cmpi
+Target Undocumented Mask(P10_FUSION_LD_CMPI) Var(rs6000_isa_flags)
+Fuse certain integer operations together for better performance on power10.
+
 mcrypto
 Target Mask(CRYPTO) Var(rs6000_isa_flags)
 Use ISA 2.07 Category:Vector.AES and Category:Vector.SHA2 instructions.

diff --git a/gcc/config/rs6000/t-rs6000 b/gcc/config/rs6000/t-rs6000
index af96b21..e3a58bf 100644 (file)
--- a/gcc/config/rs6000/t-rs6000
+++ b/gcc/config/rs6000/t-rs6000
@@ -47,6 +47,9 @@ rs6000-call.o: $(srcdir)/config/rs6000/rs6000-call.c
        $(COMPILE) $<
        $(POSTCOMPILE)
 
+$(srcdir)/config/rs6000/fusion.md: $(srcdir)/config/rs6000/genfusion.pl
+       $(srcdir)/config/rs6000/genfusion.pl > $(srcdir)/config/rs6000/fusion.md
+
 $(srcdir)/config/rs6000/rs6000-tables.opt: $(srcdir)/config/rs6000/genopt.sh \
   $(srcdir)/config/rs6000/rs6000-cpus.def
        $(SHELL) $(srcdir)/config/rs6000/genopt.sh $(srcdir)/config/rs6000 > \
@@ -86,4 +89,5 @@ MD_INCLUDES = $(srcdir)/config/rs6000/rs64.md \
        $(srcdir)/config/rs6000/mma.md \
        $(srcdir)/config/rs6000/crypto.md \
        $(srcdir)/config/rs6000/htm.md \
-       $(srcdir)/config/rs6000/dfp.md
+       $(srcdir)/config/rs6000/dfp.md \
+       $(srcdir)/config/rs6000/fusion.md