RISC-V: Implement instruction patterns for ZBA extension.

2021-10-25  Jim Wilson  <jimw@sifive.com>
	    Kito Cheng  <kito.cheng@sifive.com>
	    Jia-Wei Chen  <jiawei@iscas.ac.cn>

gcc/ChangeLog:

	* config/riscv/bitmanip.md (*zero_extendsidi2_bitmanip): New.
	(*shNadd): Ditto.
	(*shNadduw): Ditto.
	(*add.uw): Ditto.
	(*slliuw): Ditto.
	(riscv_rtx_costs): Ditto.
	* config/riscv/riscv.md: Include bitmanip.md
	(type): Add bitmanip bype.
	(zero_extendsidi2): Change to define_expand pattern.
	(*zero_extendsidi2_internal): New.
	(zero_extendsidi2_shifted): Disable for ZBA.

2021-10-25  Kito Cheng  <kito.cheng@sifive.com>
	    Jia-Wei Chen  <jiawei@iscas.ac.cn>

gcc/testsuite/ChangeLog:

	* gcc.target/riscv/zba-adduw.c: New.
	* gcc.target/riscv/zba-shNadd-01.c: Ditto.
	* gcc.target/riscv/zba-shNadd-02.c: Ditto.
	* gcc.target/riscv/zba-shNadd-03.c: Ditto.
	* gcc.target/riscv/zba-slliuw.c: Ditto.
	* gcc.target/riscv/zba-zextw.c: Ditto.

Co-authored-by: Kito Cheng <kito.cheng@sifive.com>
Co-authored-by: Jia-Wei Chen <jiawei@iscas.ac.cn>

gcc/config/riscv/bitmanip.md

@@ -0,0 +1,76 @@
+;; Machine description for RISC-V Bit Manipulation operations.
+;; Copyright (C) 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/>.
+
+;; ZBA extension.
+
+(define_insn "*zero_extendsidi2_bitmanip"
+  [(set (match_operand:DI 0 "register_operand" "=r,r")
+	(zero_extend:DI (match_operand:SI 1 "nonimmediate_operand" "r,m")))]
+  "TARGET_64BIT && TARGET_ZBA"
+  "@
+   zext.w\t%0,%1
+   lwu\t%0,%1"
+  [(set_attr "type" "bitmanip,load")
+   (set_attr "mode" "DI")])
+
+(define_insn "*shNadd"
+  [(set (match_operand:X 0 "register_operand" "=r")
+	(plus:X (ashift:X (match_operand:X 1 "register_operand" "r")
+			  (match_operand:QI 2 "immediate_operand" "I"))
+		(match_operand:X 3 "register_operand" "r")))]
+  "TARGET_ZBA
+   && (INTVAL (operands[2]) >= 1) && (INTVAL (operands[2]) <= 3)"
+  "sh%2add\t%0,%1,%3"
+  [(set_attr "type" "bitmanip")
+   (set_attr "mode" "<X:MODE>")])
+
+(define_insn "*shNadduw"
+  [(set (match_operand:DI 0 "register_operand" "=r")
+	(plus:DI
+	  (and:DI (ashift:DI (match_operand:DI 1 "register_operand" "r")
+			     (match_operand:QI 2 "immediate_operand" "I"))
+		 (match_operand 3 "immediate_operand" ""))
+	  (match_operand:DI 4 "register_operand" "r")))]
+  "TARGET_64BIT && TARGET_ZBA
+   && (INTVAL (operands[2]) >= 1) && (INTVAL (operands[2]) <= 3)
+   && (INTVAL (operands[3]) >> INTVAL (operands[2])) == 0xffffffff"
+  "sh%2add.uw\t%0,%1,%4"
+  [(set_attr "type" "bitmanip")
+   (set_attr "mode" "DI")])
+
+(define_insn "*add.uw"
+  [(set (match_operand:DI 0 "register_operand" "=r")
+	(plus:DI (zero_extend:DI
+		   (match_operand:SI 1 "register_operand" "r"))
+		 (match_operand:DI 2 "register_operand" "r")))]
+  "TARGET_64BIT && TARGET_ZBA"
+  "add.uw\t%0,%1,%2"
+  [(set_attr "type" "bitmanip")
+   (set_attr "mode" "DI")])
+
+(define_insn "*slliuw"
+  [(set (match_operand:DI 0 "register_operand" "=r")
+	(and:DI (ashift:DI (match_operand:DI 1 "register_operand" "r")
+			   (match_operand:QI 2 "immediate_operand" "I"))
+		(match_operand 3 "immediate_operand" "")))]
+  "TARGET_64BIT && TARGET_ZBA
+   && (INTVAL (operands[3]) >> INTVAL (operands[2])) == 0xffffffff"
+  "slli.uw\t%0,%1,%2"
+  [(set_attr "type" "bitmanip")
+   (set_attr "mode" "DI")])

gcc/config/riscv/riscv.md

@@ -170,7 +170,7 @@
 (define_attr "type"
   "unknown,branch,jump,call,load,fpload,store,fpstore,
    mtc,mfc,const,arith,logical,shift,slt,imul,idiv,move,fmove,fadd,fmul,
-   fmadd,fdiv,fcmp,fcvt,fsqrt,multi,auipc,sfb_alu,nop,ghost"
+   fmadd,fdiv,fcmp,fcvt,fsqrt,multi,auipc,sfb_alu,nop,ghost,bitmanip"
   (cond [(eq_attr "got" "load") (const_string "load")
 
 	 ;; If a doubleword move uses these expensive instructions,
@@ -1302,11 +1302,16 @@
 
 ;; Extension insns.
 
-(define_insn_and_split "zero_extendsidi2"
+(define_expand "zero_extendsidi2"
+  [(set (match_operand:DI 0 "register_operand")
+	(zero_extend:DI (match_operand:SI 1 "nonimmediate_operand")))]
+  "TARGET_64BIT")
+
+(define_insn_and_split "*zero_extendsidi2_internal"
   [(set (match_operand:DI     0 "register_operand"     "=r,r")
 	(zero_extend:DI
 	    (match_operand:SI 1 "nonimmediate_operand" " r,m")))]
-  "TARGET_64BIT"
+  "TARGET_64BIT && !(TARGET_ZBA || TARGET_ZBB)"
   "@
    #
    lwu\t%0,%1"
@@ -2078,7 +2083,7 @@
 			   (match_operand:QI 2 "immediate_operand" "I"))
 		(match_operand 3 "immediate_operand" "")))
    (clobber (match_scratch:DI 4 "=&r"))]
-  "TARGET_64BIT
+  "TARGET_64BIT && !TARGET_ZBA
    && ((INTVAL (operands[3]) >> INTVAL (operands[2])) == 0xffffffff)"
   "#"
   "&& reload_completed"
@@ -2845,6 +2850,7 @@
   "<load>\t%3, %1\;<load>\t%0, %2\;xor\t%0, %3, %0\;li\t%3, 0"
   [(set_attr "length" "12")])
 
+(include "bitmanip.md")
 (include "sync.md")
 (include "peephole.md")
 (include "pic.md")

gcc/testsuite/gcc.target/riscv/zba-adduw.c

@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_zba_zbs -mabi=lp64 -O2" } */
+
+int foo(int n, unsigned char *arr, unsigned y){
+  int s = 0;
+  unsigned x = 0;
+  for (;x<n;x++)
+    s += arr[x+y];
+  return s;
+}
+
+/* { dg-final { scan-assembler "add.uw" } } */

gcc/testsuite/gcc.target/riscv/zba-shNadd-01.c

@@ -0,0 +1,19 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_zba -mabi=lp64 -O2" } */
+
+long test_1(long a, long b)
+{
+  return a + (b << 1);
+}
+long test_2(long a, long b)
+{
+  return a + (b << 2);
+}
+long test_3(long a, long b)
+{
+  return a + (b << 3);
+}
+
+/* { dg-final { scan-assembler-times "sh1add" 1 } } */
+/* { dg-final { scan-assembler-times "sh2add" 1 } } */
+/* { dg-final { scan-assembler-times "sh3add" 1 } } */

gcc/testsuite/gcc.target/riscv/zba-shNadd-02.c

@@ -0,0 +1,19 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv32gc_zba -mabi=ilp32 -O2" } */
+
+long test_1(long a, long b)
+{
+  return a + (b << 1);
+}
+long test_2(long a, long b)
+{
+  return a + (b << 2);
+}
+long test_3(long a, long b)
+{
+  return a + (b << 3);
+}
+
+/* { dg-final { scan-assembler-times "sh1add" 1 } } */
+/* { dg-final { scan-assembler-times "sh2add" 1 } } */
+/* { dg-final { scan-assembler-times "sh3add" 1 } } */

gcc/testsuite/gcc.target/riscv/zba-shNadd-03.c

@@ -0,0 +1,31 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_zba -mabi=lp64 -O2" } */
+
+/* RV64 only.  */
+int foos(short *x, int n){
+  return x[n];
+}
+int fooi(int *x, int n){
+  return x[n];
+}
+int fooll(long long *x, int n){
+  return x[n];
+}
+
+/* RV64 only.  */
+int ufoos(short *x, unsigned int n){
+  return x[n];
+}
+int ufooi(int *x, unsigned int n){
+  return x[n];
+}
+int ufooll(long long *x, unsigned int n){
+  return x[n];
+}
+
+/* { dg-final { scan-assembler-times "sh1add\t" 1 } } */
+/* { dg-final { scan-assembler-times "sh2add\t" 1 } } */
+/* { dg-final { scan-assembler-times "sh3add\t" 1 } } */
+/* { dg-final { scan-assembler-times "sh3add.uw" 1 } } */
+/* { dg-final { scan-assembler-times "sh3add.uw" 1 } } */
+/* { dg-final { scan-assembler-times "sh3add.uw" 1 } } */

gcc/testsuite/gcc.target/riscv/zba-slliuw.c

@@ -0,0 +1,11 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_zba -mabi=lp64 -O2" } */
+
+long
+foo (long i)
+{
+  return (long)(unsigned int)i << 10;
+}
+/* XXX: This pattern need combine improvement or intermediate instruction
+ *      from zbs.   */
+/* { dg-final { scan-assembler-not "slli.uw" } } */

gcc/testsuite/gcc.target/riscv/zba-zextw.c

@@ -0,0 +1,10 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_zba_zbs -mabi=lp64 -O2" } */
+
+long
+foo (long i)
+{
+  return (long)(unsigned int)i;
+}
+/* XXX: This pattern require combine improvement.   */
+/* { dg-final { scan-assembler-not "slli.uw" } } */