[v2,09/11] riscv: thead: Add support for XTheadMac ISA extension
Commit Message
From: Christoph Müllner <christoph.muellner@vrull.eu>
The XTheadMac ISA extension provides multiply-accumulate/subtract
instructions:
* mula/mulaw/mulah
* muls/mulsw/mulsh
To benefit from middle-end passes, we expand the following named
patterns in riscv.md (as they are not T-Head-specific):
* maddhisi4
* msubhisi4
gcc/ChangeLog:
* config/riscv/riscv.md (maddhisi4): New expand.
(msubhisi4): New expand.
* config/riscv/thead.md (*th_mula<mode>): New pattern.
(*th_mulawsi): New pattern.
(*th_mulawsi2): New pattern.
(*th_maddhisi4): New pattern.
(*th_sextw_maddhisi4): New pattern.
(*th_muls<mode>): New pattern.
(*th_mulswsi): New pattern.
(*th_mulswsi2): New pattern.
(*th_msubhisi4): New pattern.
(*th_sextw_msubhisi4): New pattern.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/thead-mula-muls.c: New test.
Co-Developed-by: Xianmiao Qu <cooper.qu@linux.alibaba.com>
Signed-off-by: Xianmiao Qu <cooper.qu@linux.alibaba.com>
Signed-off-by: Christoph Müllner <christoph.muellner@vrull.eu>
Changed in v2:
- Add missing prefix in on INSN
---
gcc/config/riscv/riscv.md | 18 +++
gcc/config/riscv/thead.md | 121 ++++++++++++++++++
.../gcc.target/riscv/xtheadmac-mula-muls.c | 43 +++++++
3 files changed, 182 insertions(+)
create mode 100644 gcc/testsuite/gcc.target/riscv/xtheadmac-mula-muls.c
@@ -3086,6 +3086,24 @@ (define_expand "extzv<mode>"
FAIL;
})
+(define_expand "maddhisi4"
+ [(set (match_operand:SI 0 "register_operand")
+ (plus:SI
+ (mult:SI (sign_extend:SI (match_operand:HI 1 "register_operand"))
+ (sign_extend:SI (match_operand:HI 2 "register_operand")))
+ (match_operand:SI 3 "register_operand")))]
+ "TARGET_XTHEADMAC"
+)
+
+(define_expand "msubhisi4"
+ [(set (match_operand:SI 0 "register_operand")
+ (minus:SI
+ (match_operand:SI 3 "register_operand")
+ (mult:SI (sign_extend:SI (match_operand:HI 1 "register_operand"))
+ (sign_extend:SI (match_operand:HI 2 "register_operand")))))]
+ "TARGET_XTHEADMAC"
+)
+
(include "bitmanip.md")
(include "sync.md")
(include "peephole.md")
@@ -143,3 +143,124 @@ (define_insn "*th_cond_gpr_mov<GPR:mode><GPR2:mode>"
th.mveqz\t%0,%z3,%1"
[(set_attr "type" "condmove")
(set_attr "mode" "<GPR:MODE>")])
+
+;; XTheadMac
+
+(define_insn "*th_mula<mode>"
+ [(set (match_operand:X 0 "register_operand" "=r")
+ (plus:X (mult:X (match_operand:X 1 "register_operand" "r")
+ (match_operand:X 2 "register_operand" "r"))
+ (match_operand:X 3 "register_operand" "0")))]
+ "TARGET_XTHEADMAC"
+ "th.mula\\t%0,%1,%2"
+ [(set_attr "type" "imul")
+ (set_attr "mode" "<MODE>")]
+)
+
+(define_insn "*th_mulawsi"
+ [(set (match_operand:DI 0 "register_operand" "=r")
+ (sign_extend:DI
+ (plus:SI (mult:SI (match_operand:SI 1 "register_operand" "r")
+ (match_operand:SI 2 "register_operand" "r"))
+ (match_operand:SI 3 "register_operand" "0"))))]
+ "TARGET_XTHEADMAC && TARGET_64BIT"
+ "th.mulaw\\t%0,%1,%2"
+ [(set_attr "type" "imul")
+ (set_attr "mode" "SI")]
+)
+
+(define_insn "*th_mulawsi2"
+ [(set (match_operand:SI 0 "register_operand" "=r")
+ (plus:SI (mult:SI (match_operand:SI 1 "register_operand" "r")
+ (match_operand:SI 2 "register_operand" "r"))
+ (match_operand:SI 3 "register_operand" "0")))]
+ "TARGET_XTHEADMAC && TARGET_64BIT"
+ "th.mulaw\\t%0,%1,%2"
+ [(set_attr "type" "imul")
+ (set_attr "mode" "SI")]
+)
+
+(define_insn "*th_maddhisi4"
+ [(set (match_operand:SI 0 "register_operand" "=r")
+ (plus:SI
+ (mult:SI
+ (sign_extend:SI (match_operand:HI 1 "register_operand" " r"))
+ (sign_extend:SI (match_operand:HI 2 "register_operand" " r")))
+ (match_operand:SI 3 "register_operand" " 0")))]
+ "TARGET_XTHEADMAC"
+ "th.mulah\\t%0,%1,%2"
+ [(set_attr "type" "imul")
+ (set_attr "mode" "SI")]
+)
+
+(define_insn "*th_sextw_maddhisi4"
+ [(set (match_operand:DI 0 "register_operand" "=r")
+ (sign_extend:DI
+ (plus:SI
+ (mult:SI
+ (sign_extend:SI (match_operand:HI 1 "register_operand" " r"))
+ (sign_extend:SI (match_operand:HI 2 "register_operand" " r")))
+ (match_operand:SI 3 "register_operand" " 0"))))]
+ "TARGET_XTHEADMAC && TARGET_64BIT"
+ "th.mulah\\t%0,%1,%2"
+ [(set_attr "type" "imul")
+ (set_attr "mode" "SI")]
+)
+
+(define_insn "*th_muls<mode>"
+ [(set (match_operand:X 0 "register_operand" "=r")
+ (minus:X (match_operand:X 3 "register_operand" "0")
+ (mult:X (match_operand:X 1 "register_operand" "r")
+ (match_operand:X 2 "register_operand" "r"))))]
+ "TARGET_XTHEADMAC"
+ "th.muls\\t%0,%1,%2"
+ [(set_attr "type" "imul")
+ (set_attr "mode" "<MODE>")]
+)
+
+(define_insn "*th_mulswsi"
+ [(set (match_operand:DI 0 "register_operand" "=r")
+ (sign_extend:DI
+ (minus:SI (match_operand:SI 3 "register_operand" "0")
+ (mult:SI (match_operand:SI 1 "register_operand" "r")
+ (match_operand:SI 2 "register_operand" "r")))))]
+ "TARGET_XTHEADMAC && TARGET_64BIT"
+ "th.mulsw\\t%0,%1,%2"
+ [(set_attr "type" "imul")
+ (set_attr "mode" "SI")]
+)
+
+(define_insn "*th_mulswsi2"
+ [(set (match_operand:SI 0 "register_operand" "=r")
+ (minus:SI (match_operand:SI 3 "register_operand" "0")
+ (mult:SI (match_operand:SI 1 "register_operand" "r")
+ (match_operand:SI 2 "register_operand" "r"))))]
+ "TARGET_XTHEADMAC && TARGET_64BIT"
+ "th.mulsw\\t%0,%1,%2"
+ [(set_attr "type" "imul")
+ (set_attr "mode" "SI")]
+)
+
+(define_insn "*th_msubhisi4"
+ [(set (match_operand:SI 0 "register_operand" "=r")
+ (minus:SI (match_operand:SI 3 "register_operand" " 0")
+ (mult:SI (sign_extend:SI (match_operand:HI 1 "register_operand" " r"))
+ (sign_extend:SI (match_operand:HI 2 "register_operand" " r")))))]
+ "TARGET_XTHEADMAC"
+ "th.mulsh\\t%0,%1,%2"
+ [(set_attr "type" "imul")
+ (set_attr "mode" "SI")]
+)
+
+(define_insn "*th_sextw_msubhisi4"
+ [(set (match_operand:DI 0 "register_operand" "=r")
+ (sign_extend:DI
+ (minus:SI (match_operand:SI 3 "register_operand" " 0")
+ (mult:SI
+ (sign_extend:SI (match_operand:HI 1 "register_operand" " r"))
+ (sign_extend:SI (match_operand:HI 2 "register_operand" " r"))))))]
+ "TARGET_XTHEADMAC && TARGET_64BIT"
+ "th.mulsh\\t%0,%1,%2"
+ [(set_attr "type" "imul")
+ (set_attr "mode" "SI")]
+)
new file mode 100644
@@ -0,0 +1,43 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv32gc_xtheadmac" { target { rv32 } } } */
+/* { dg-options "-march=rv64gc_xtheadmac" { target { rv64 } } } */
+/* { dg-skip-if "" { *-*-* } { "-O0" "-O1" "-Og" } } */
+
+long f_mula(long a, long b, long c)
+{
+ return a + b * c;
+}
+
+long f_muls(long a, long b, long c)
+{
+ return a - b * c;
+}
+
+#if __riscv_xlen == 64
+int f_mulaw(int a, int b, int c)
+{
+ return a + b * c;
+}
+
+int f_mulsw(int a, int b, int c)
+{
+ return a - b * c;
+}
+#endif
+
+long f_mulah(int a, unsigned short b, unsigned short c)
+{
+ return a + (int)(short)b * (int)(short)c;
+}
+
+long f_mulsh(int a, unsigned short b, unsigned short c)
+{
+ return a - (int)(short)b * (int)(short)c;
+}
+
+/* { dg-final { scan-assembler-times "th.mula\t" 1 } } */
+/* { dg-final { scan-assembler-times "th.muls\t" 1 } } */
+/* { dg-final { scan-assembler-times "th.mulaw\t" 1 { target { rv64 } } } } */
+/* { dg-final { scan-assembler-times "th.mulsw\t" 1 { target { rv64 } } } } */
+/* { dg-final { scan-assembler-times "th.mulah\t" 1 } } */
+/* { dg-final { scan-assembler-times "th.mulsh\t" 1 } } */