arm: ACLE intrinsics for bfloat16 dot product

This patch is part of a series adding support for Armv8.6-A features.
It adds intrinsics for brain half-precision float-point (BF16) dot
instructions with AdvSIMD support.

gcc/ChangeLog:

2020-02-25  Dennis Zhang  <dennis.zhang@arm.com>

	* config/arm/arm_neon.h (vbfdot_f32, vbfdotq_f32): New
	(vbfdot_lane_f32, vbfdotq_laneq_f32): New.
	(vbfdot_laneq_f32, vbfdotq_lane_f32): New.
	* config/arm/arm_neon_builtins.def (vbfdot): New entry.
	(vbfdot_lanev4bf, vbfdot_lanev8bf): Likewise.
	* config/arm/iterators.md (VSF2BF): New attribute.
	* config/arm/neon.md (neon_vbfdot<VCVTF:mode>): New entry.
	(neon_vbfdot_lanev4bf<VCVTF:mode>): Likewise.
	(neon_vbfdot_lanev8bf<VCVTF:mode>): Likewise.

gcc/testsuite/ChangeLog:

2020-02-25  Dennis Zhang  <dennis.zhang@arm.com>

	* gcc.target/arm/simd/bf16_dot_1.c: New test.
	* gcc.target/arm/simd/bf16_dot_2.c: New test.
	* gcc.target/arm/simd/bf16_dot_3.c: New test.

gcc/ChangeLog

+2020-02-25  Dennis Zhang  <dennis.zhang@arm.com>
+
+	* config/arm/arm_neon.h (vbfdot_f32, vbfdotq_f32): New
+	(vbfdot_lane_f32, vbfdotq_laneq_f32): New.
+	(vbfdot_laneq_f32, vbfdotq_lane_f32): New.
+	* config/arm/arm_neon_builtins.def (vbfdot): New entry.
+	(vbfdot_lanev4bf, vbfdot_lanev8bf): Likewise.
+	* config/arm/iterators.md (VSF2BF): New attribute.
+	* config/arm/neon.md (neon_vbfdot<VCVTF:mode>): New entry.
+	(neon_vbfdot_lanev4bf<VCVTF:mode>): Likewise.
+	(neon_vbfdot_lanev8bf<VCVTF:mode>): Likewise.
+
 2020-02-25  Christophe Lyon  <christophe.lyon@linaro.org>
 
 	* config/arm/arm.md (required_for_purecode): New attribute.

gcc/config/arm/arm_neon.h

@@ -18819,6 +18819,58 @@ vusmmlaq_s32 (int32x4_t __r, uint8x16_t __a, int8x16_t __b)
 
 #pragma GCC pop_options
 
+/* AdvSIMD Brain half-precision float-point (Bfloat16) intrinsics.  */
+#pragma GCC push_options
+#pragma GCC target ("arch=armv8.2-a+bf16")
+
+__extension__ extern __inline float32x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vbfdot_f32 (float32x2_t __r, bfloat16x4_t __a, bfloat16x4_t __b)
+{
+  return __builtin_neon_vbfdotv2sf (__r, __a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vbfdotq_f32 (float32x4_t __r, bfloat16x8_t __a, bfloat16x8_t __b)
+{
+  return __builtin_neon_vbfdotv4sf (__r, __a, __b);
+}
+
+__extension__ extern __inline float32x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vbfdot_lane_f32 (float32x2_t __r, bfloat16x4_t __a, bfloat16x4_t __b,
+		 const int __index)
+{
+  return __builtin_neon_vbfdot_lanev4bfv2sf (__r, __a, __b, __index);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vbfdotq_laneq_f32 (float32x4_t __r, bfloat16x8_t __a, bfloat16x8_t __b,
+		   const int __index)
+{
+  return __builtin_neon_vbfdot_lanev8bfv4sf (__r, __a, __b, __index);
+}
+
+__extension__ extern __inline float32x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vbfdot_laneq_f32 (float32x2_t __r, bfloat16x4_t __a, bfloat16x8_t __b,
+		  const int __index)
+{
+  return __builtin_neon_vbfdot_lanev8bfv2sf (__r, __a, __b, __index);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vbfdotq_lane_f32 (float32x4_t __r, bfloat16x8_t __a, bfloat16x4_t __b,
+		  const int __index)
+{
+  return __builtin_neon_vbfdot_lanev4bfv4sf (__r, __a, __b, __index);
+}
+
+#pragma GCC pop_options
+
 #ifdef __cplusplus
 }
 #endif

gcc/config/arm/arm_neon_builtins.def

@@ -381,3 +381,7 @@ VAR2 (MAC_LANE_PAIR, vcmlaq_lane270, v4sf, v8hf)
 VAR1 (TERNOP, smmla, v16qi)
 VAR1 (UTERNOP, ummla, v16qi)
 VAR1 (USTERNOP, usmmla, v16qi)
+
+VAR2 (TERNOP, vbfdot, v2sf, v4sf)
+VAR2 (MAC_LANE_PAIR, vbfdot_lanev4bf, v2sf, v4sf)
+VAR2 (MAC_LANE_PAIR, vbfdot_lanev8bf, v2sf, v4sf)

gcc/config/arm/iterators.md

@@ -835,6 +835,8 @@
 (define_mode_attr VSI2QI [(V2SI "V8QI") (V4SI "V16QI")])
 (define_mode_attr vsi2qi [(V2SI "v8qi") (V4SI "v16qi")])
 
+(define_mode_attr VSF2BF [(V2SF "V4BF") (V4SF "V8BF")])
+
 ;;----------------------------------------------------------------------------
 ;; Code attributes
 ;;----------------------------------------------------------------------------

gcc/config/arm/neon.md

@@ -6596,3 +6596,51 @@ if (BYTES_BIG_ENDIAN)
   "v<sup>mmla.<mmla_sfx>\t%q0, %q2, %q3"
   [(set_attr "type" "neon_mla_s_q")]
 )
+
+(define_insn "neon_vbfdot<VCVTF:mode>"
+  [(set (match_operand:VCVTF 0 "register_operand" "=w")
+	(plus:VCVTF (match_operand:VCVTF 1 "register_operand" "0")
+		    (unspec:VCVTF [
+			    (match_operand:<VSF2BF> 2 "register_operand" "w")
+			    (match_operand:<VSF2BF> 3 "register_operand" "w")]
+		     UNSPEC_DOT_S)))]
+  "TARGET_BF16_SIMD"
+  "vdot.bf16\\t%<V_reg>0, %<V_reg>2, %<V_reg>3"
+  [(set_attr "type" "neon_dot<q>")]
+)
+
+(define_insn "neon_vbfdot_lanev4bf<VCVTF:mode>"
+  [(set (match_operand:VCVTF 0 "register_operand" "=w")
+	(plus:VCVTF (match_operand:VCVTF 1 "register_operand" "0")
+		    (unspec:VCVTF [
+			    (match_operand:<VSF2BF> 2 "register_operand" "w")
+			    (match_operand:V4BF 3 "register_operand" "x")
+			    (match_operand:SI 4 "immediate_operand" "i")]
+		     UNSPEC_DOT_S)))]
+  "TARGET_BF16_SIMD"
+  "vdot.bf16\\t%<V_reg>0, %<V_reg>2, %P3[%c4]"
+  [(set_attr "type" "neon_dot<q>")]
+)
+
+(define_insn "neon_vbfdot_lanev8bf<VCVTF:mode>"
+  [(set (match_operand:VCVTF 0 "register_operand" "=w")
+	(plus:VCVTF (match_operand:VCVTF 1 "register_operand" "0")
+		    (unspec:VCVTF [
+			    (match_operand:<VSF2BF> 2 "register_operand" "w")
+			    (match_operand:V8BF 3 "register_operand" "x")
+			    (match_operand:SI 4 "immediate_operand" "i")]
+		     UNSPEC_DOT_S)))]
+  "TARGET_BF16_SIMD"
+  {
+    int lane = INTVAL (operands[4]);
+    int half = GET_MODE_NUNITS (GET_MODE (operands[3])) / 4;
+    if (lane < half)
+      return "vdot.bf16\\t%<V_reg>0, %<V_reg>2, %e3[%c4]";
+    else
+      {
+	operands[4] = GEN_INT (lane - half);
+	return "vdot.bf16\\t%<V_reg>0, %<V_reg>2, %f3[%c4]";
+      }
+  }
+  [(set_attr "type" "neon_dot<q>")]
+)

gcc/testsuite/ChangeLog

+2020-02-25  Dennis Zhang  <dennis.zhang@arm.com>
+
+	* gcc.target/arm/simd/bf16_dot_1.c: New test.
+	* gcc.target/arm/simd/bf16_dot_2.c: New test.
+	* gcc.target/arm/simd/bf16_dot_3.c: New test.
+
 2020-02-25  Jakub Jelinek  <jakub@redhat.com>
 
 	PR rtl-optimization/93908

gcc/testsuite/gcc.target/arm/simd/bf16_dot_1.c

+/* { dg-do assemble } */
+/* { dg-require-effective-target arm_v8_2a_bf16_neon_ok } */
+/* { dg-options "-save-temps -O2" } */
+/* { dg-add-options arm_v8_2a_bf16_neon } */
+
+#include "arm_neon.h"
+
+/* BF16 DOT without lane.  */
+float32x2_t
+test_vbfdot_f32 (float32x2_t r, bfloat16x4_t a, bfloat16x4_t b)
+{
+  /* vdot.bf16 d, d, d */
+  return vbfdot_f32 (r, a, b);
+}
+
+float32x4_t
+test_vbfdotq_f32 (float32x4_t r, bfloat16x8_t a, bfloat16x8_t b)
+{
+  /* vdot.bf16 q, q, q */
+  return vbfdotq_f32 (r, a, b);
+}
+
+/* 64-bit BF16 DOT with lane.  */
+float32x2_t
+test_vbfdot_lane_f32_0 (float32x2_t r, bfloat16x4_t a, bfloat16x4_t b)
+{
+  /* vdot.bf16 d, d, d[0] */
+  return vbfdot_lane_f32 (r, a, b, 0);
+}
+
+float32x2_t
+test_vbfdot_lane_f32_1 (float32x2_t r, bfloat16x4_t a, bfloat16x4_t b)
+{
+  /* vdot.bf16 d, d, d[1] */
+  return vbfdot_lane_f32 (r, a, b, 1);
+}
+
+float32x2_t
+test_vbfdot_laneq_f32_0 (float32x2_t r, bfloat16x4_t a, bfloat16x8_t b)
+{
+  /* vdot.bf16 d, d, d[0] */
+  return vbfdot_laneq_f32 (r, a, b, 0);
+}
+
+float32x2_t
+test_vbfdot_laneq_f32_1 (float32x2_t r, bfloat16x4_t a, bfloat16x8_t b)
+{
+  /* vdot.bf16 d, d, d[1] */
+  return vbfdot_laneq_f32 (r, a, b, 1);
+}
+
+float32x2_t
+test_vbfdot_laneq_f32_2 (float32x2_t r, bfloat16x4_t a, bfloat16x8_t b)
+{
+  /* vdot.bf16 d, d, d[0] */
+  return vbfdot_laneq_f32 (r, a, b, 2);
+}
+
+float32x2_t
+test_vbfdot_laneq_f32_3 (float32x2_t r, bfloat16x4_t a, bfloat16x8_t b)
+{
+  /* vdot.bf16 d, d, d[1] */
+  return vbfdot_laneq_f32 (r, a, b, 3);
+}
+
+/* 128-bit BF16 DOT with lane.  */
+float32x4_t
+test_vbfdotq_lane_f32_0 (float32x4_t r, bfloat16x8_t a, bfloat16x4_t b)
+{
+  /* vdot.bf16 q, q, d[0] */
+  return vbfdotq_lane_f32 (r, a, b, 0);
+}
+
+float32x4_t
+test_vbfdotq_lane_f32_1 (float32x4_t r, bfloat16x8_t a, bfloat16x4_t b)
+{
+  /* vdot.bf16 q, q, d[1] */
+  return vbfdotq_lane_f32 (r, a, b, 1);
+}
+
+float32x4_t
+test_vbfdotq_laneq_f32_0 (float32x4_t r, bfloat16x8_t a, bfloat16x8_t b)
+{
+  /* vdot.bf16 q, q, d[0] */
+  return vbfdotq_laneq_f32 (r, a, b, 0);
+}
+
+float32x4_t
+test_vbfdotq_laneq_f32_3 (float32x4_t r, bfloat16x8_t a, bfloat16x8_t b)
+{
+  /* vdot.bf16 q, q, d[1] */
+  return vbfdotq_laneq_f32 (r, a, b, 3);
+}
+
+/* { dg-final { scan-assembler-times {\tvdot.bf16\td[0-9]+, d[0-9]+, d[0-9]+\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvdot.bf16\tq[0-9]+, q[0-9]+, q[0-9]+\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvdot.bf16\td[0-9]+, d[0-9]+, d[0-9]+\[0\]\n} 3 } } */
+/* { dg-final { scan-assembler-times {\tvdot.bf16\td[0-9]+, d[0-9]+, d[0-9]+\[1\]\n} 3 } } */
+/* { dg-final { scan-assembler-times {\tvdot.bf16\tq[0-9]+, q[0-9]+, d[0-9]+\[0\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvdot.bf16\tq[0-9]+, q[0-9]+, d[0-9]+\[1\]\n} 2 } } */

gcc/testsuite/gcc.target/arm/simd/bf16_dot_2.c

+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_2a_bf16_neon_ok } */
+/* { dg-add-options arm_v8_2a_bf16_neon } */
+
+#include "arm_neon.h"
+
+float32x2_t
+test_vbfdot_lane_f32_a (float32x2_t r, bfloat16x4_t a, bfloat16x4_t b)
+{
+  /* { dg-error "lane -1 out of range 0 - 1" "" {target *-*-*} 0 } */
+  return vbfdot_lane_f32 (r, a, b, -1);
+}
+
+float32x2_t
+test_vbfdot_lane_f32_b (float32x2_t r, bfloat16x4_t a, bfloat16x4_t b)
+{
+  /* { dg-error "lane 2 out of range 0 - 1" "" {target *-*-*} 0 } */
+  return vbfdot_lane_f32 (r, a, b, 2);
+}
+
+float32x2_t
+test_vbfdot_laneq_f32_a (float32x2_t r, bfloat16x4_t a, bfloat16x8_t b)
+{
+  /* { dg-error "lane -1 out of range 0 - 3" "" { target *-*-* } 0 } */
+  return vbfdot_laneq_f32 (r, a, b, -1);
+}
+
+float32x2_t
+test_vbfdot_laneq_f32_b (float32x2_t r, bfloat16x4_t a, bfloat16x8_t b)
+{
+  /* { dg-error "lane 4 out of range 0 - 3" "" { target *-*-* } 0 } */
+  return vbfdot_laneq_f32 (r, a, b, 4);
+}

gcc/testsuite/gcc.target/arm/simd/bf16_dot_3.c

+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_2a_bf16_neon_ok } */
+/* { dg-add-options arm_v8_2a_bf16_neon } */
+
+#include "arm_neon.h"
+
+float32x4_t
+test_vbfdotq_lane_f32_a (float32x4_t r, bfloat16x8_t a, bfloat16x4_t b)
+{
+  /* { dg-error "lane -1 out of range 0 - 1" "" {target *-*-*} 0 } */
+  return vbfdotq_lane_f32 (r, a, b, -1);
+}
+
+float32x4_t
+test_vbfdotq_lane_f32_b (float32x4_t r, bfloat16x8_t a, bfloat16x4_t b)
+{
+  /* { dg-error "lane 2 out of range 0 - 1" "" {target *-*-*} 0 } */
+  return vbfdotq_lane_f32 (r, a, b, 2);
+}
+
+float32x4_t
+test_vbfdotq_laneq_f32_a (float32x4_t r, bfloat16x8_t a, bfloat16x8_t b)
+{
+  /* { dg-error "lane -1 out of range 0 - 3" "" { target *-*-* } 0 } */
+  return vbfdotq_laneq_f32 (r, a, b, -1);
+}
+
+float32x4_t
+test_vbfdotq_laneq_f32_b (float32x4_t r, bfloat16x8_t a, bfloat16x8_t b)
+{
+  /* { dg-error "lane 4 out of range 0 - 3" "" { target *-*-* } 0 } */
+  return vbfdotq_laneq_f32 (r, a, b, 4);
+}