From: Kyrylo Tkachov <kyrylo.tkachov@arm.com>
Date: Mon, 24 Apr 2023 10:32:15 +0000 (+0100)
Subject: aarch64: Add mulv2di3 expander for TARGET_SVE
X-Git-Tag: basepoints/gcc-15~9943
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=b98c63e9e8ceaf9e04c28d83500f98313284c7f8;p=thirdparty%2Fgcc.git

aarch64: Add mulv2di3 expander for TARGET_SVE

Motivated by a recent LLVM patch I saw, we can use SVE for 64-bit vector integer MUL (plain Advanced SIMD doesn't support it).
Since the Advanced SIMD regs are just the low 128-bit part of the SVE regs it all works transparently.
It's a reasonably straightforward implementation of the mulv2di3 optab that wires it up through the mulvnx2di3 expander and
subregs the results back to the Advanced SIMD modes.

There's more such tricks possible with other operations (and we could do 64-bit multiply-add merged operations too) but for now
this self-contained patch improves the mul case as without it for the testcases in the patch we'd have scalarised the arguments,
moved them to GP regs, performed two GP MULs and moved them back to SIMD regs.
Advertising a mulv2di3 optab from the backend should also allow for more flexibile vectorisation opportunities.

Bootstrapped and tested on aarch64-none-linux-gnu.

gcc/ChangeLog:

	* config/aarch64/aarch64-simd.md (mulv2di3): New expander.

gcc/testsuite/ChangeLog:

	* gcc.target/aarch64/sve-neon-modes_1.c: New test.
	* gcc.target/aarch64/sve-neon-modes_2.c: New test.
---

diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index e420f58633a1..9f2fce6f0331 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -458,6 +458,26 @@
   [(set_attr "type" "neon_mul_<Vetype><q>")]
 )
 
+;; Advanced SIMD does not support vector DImode MUL, but SVE does.
+;; Make use of the overlap between Z and V registers to implement the V2DI
+;; optab for TARGET_SVE.  The mulvnx2di3 expander can
+;; handle the TARGET_SVE2 case transparently.
+(define_expand "mulv2di3"
+  [(set (match_operand:V2DI 0 "register_operand")
+        (mult:V2DI (match_operand:V2DI 1 "register_operand")
+		   (match_operand:V2DI 2 "aarch64_sve_vsm_operand")))]
+  "TARGET_SVE"
+  {
+    machine_mode sve_mode = VNx2DImode;
+    rtx sve_op0 = simplify_gen_subreg (sve_mode, operands[0], V2DImode, 0);
+    rtx sve_op1 = simplify_gen_subreg (sve_mode, operands[1], V2DImode, 0);
+    rtx sve_op2 = simplify_gen_subreg (sve_mode, operands[2], V2DImode, 0);
+
+    emit_insn (gen_mulvnx2di3 (sve_op0, sve_op1, sve_op2));
+    DONE;
+  }
+)
+
 (define_insn "bswap<mode>2"
   [(set (match_operand:VDQHSD 0 "register_operand" "=w")
         (bswap:VDQHSD (match_operand:VDQHSD 1 "register_operand" "w")))]
diff --git a/gcc/testsuite/gcc.target/aarch64/sve-neon-modes_1.c b/gcc/testsuite/gcc.target/aarch64/sve-neon-modes_1.c
new file mode 100644
index 000000000000..ce4f1c70bccd
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve-neon-modes_1.c
@@ -0,0 +1,31 @@
+/* { dg-do compile } */
+/* { dg-options "-O -march=armv8.2-a+sve" } */
+/* { dg-final { check-function-bodies "**" "" "" } } */
+
+typedef long v2di  __attribute__((vector_size (16)));
+
+/*
+** foo:
+**	ptrue	p0.b, all
+**	mul	z0.d, p0/m, z0.d, z1.d
+**	ret
+*/
+
+v2di
+foo (v2di a, v2di b)
+{
+  return a * b;
+}
+
+/*
+** foo_imm:
+**	mul	z0.d, z0.d, #125
+**	ret
+*/
+
+v2di
+foo_imm (v2di a)
+{
+  return a * 125;
+}
+
diff --git a/gcc/testsuite/gcc.target/aarch64/sve-neon-modes_2.c b/gcc/testsuite/gcc.target/aarch64/sve-neon-modes_2.c
new file mode 100644
index 000000000000..02bb9f34c38f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve-neon-modes_2.c
@@ -0,0 +1,30 @@
+/* { dg-do compile } */
+/* { dg-options "-O -march=armv8.5-a+sve2" } */
+/* { dg-final { check-function-bodies "**" "" "" } } */
+
+typedef long v2di  __attribute__((vector_size (16)));
+
+/*
+** foo:
+**	mul	z0.d, z0.d, z1.d
+**	ret
+*/
+
+v2di
+foo (v2di a, v2di b)
+{
+  return a * b;
+}
+
+/*
+** foo_imm:
+**	mul	z0.d, z0.d, #125
+**	ret
+*/
+
+v2di
+foo_imm (v2di a)
+{
+  return a * 125;
+}
+