From: Dennis Zhang <denzha01@e124712.cambridge.arm.com>
Date: Fri, 11 Dec 2020 15:10:58 +0000 (+0000)
Subject: aarch64: intrinsics to convert BFloat16 to Float32
X-Git-Tag: releases/gcc-10.3.0~520
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=702e45ee471422dee86d32fc84f617d341d33175;p=thirdparty%2Fgcc.git

aarch64: intrinsics to convert BFloat16 to Float32

gcc/ChangeLog:

	* config/aarch64/aarch64-simd-builtins.def(vbfcvt): New entry.
	(vbfcvt_high, bfcvt): Likewise.
	* config/aarch64/aarch64-simd.md(aarch64_vbfcvt<mode>): New entry.
	(aarch64_vbfcvt_highv8bf, aarch64_bfcvtsf): Likewise.
	* config/aarch64/arm_bf16.h (vcvtah_f32_bf16): New intrinsic.
	* config/aarch64/arm_neon.h (vcvt_f32_bf16): Likewise.
	(vcvtq_low_f32_bf16, vcvtq_high_f32_bf16): Likewise.

gcc/testsuite/ChangeLog

	* gcc.target/aarch64/advsimd-intrinsics/bfcvt-compile.c
	(test_vcvt_f32_bf16, test_vcvtq_low_f32_bf16): New tests.
	(test_vcvtq_high_f32_bf16, test_vcvth_f32_bf16): Likewise.

(cherry picked from commit f7d6961126a7f06c8089d8a58bd21be43bc16806)
---

diff --git a/gcc/config/aarch64/aarch64-simd-builtins.def b/gcc/config/aarch64/aarch64-simd-builtins.def
index ba2bda26dcdd..7192f3954d31 100644
--- a/gcc/config/aarch64/aarch64-simd-builtins.def
+++ b/gcc/config/aarch64/aarch64-simd-builtins.def
@@ -728,3 +728,8 @@
   VAR1 (UNOP, bfcvtn_q, 0, v8bf)
   VAR1 (BINOP, bfcvtn2, 0, v8bf)
   VAR1 (UNOP, bfcvt, 0, bf)
+
+  /* Implemented by aarch64_{v}bfcvt{_high}<mode>.  */
+  VAR2 (UNOP, vbfcvt, 0, v4bf, v8bf)
+  VAR1 (UNOP, vbfcvt_high, 0, v8bf)
+  VAR1 (UNOP, bfcvt, 0, sf)
diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index 9f0e2bd1e6ff..2e8aa668b107 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -7238,3 +7238,31 @@
   "bfcvt\\t%h0, %s1"
   [(set_attr "type" "f_cvt")]
 )
+
+;; Use shl/shll/shll2 to convert BF scalar/vector modes to SF modes.
+(define_insn "aarch64_vbfcvt<mode>"
+  [(set (match_operand:V4SF 0 "register_operand" "=w")
+	(unspec:V4SF [(match_operand:VBF 1 "register_operand" "w")]
+		      UNSPEC_BFCVTN))]
+  "TARGET_BF16_SIMD"
+  "shll\\t%0.4s, %1.4h, #16"
+  [(set_attr "type" "neon_shift_imm_long")]
+)
+
+(define_insn "aarch64_vbfcvt_highv8bf"
+  [(set (match_operand:V4SF 0 "register_operand" "=w")
+	(unspec:V4SF [(match_operand:V8BF 1 "register_operand" "w")]
+		      UNSPEC_BFCVTN2))]
+  "TARGET_BF16_SIMD"
+  "shll2\\t%0.4s, %1.8h, #16"
+  [(set_attr "type" "neon_shift_imm_long")]
+)
+
+(define_insn "aarch64_bfcvtsf"
+  [(set (match_operand:SF 0 "register_operand" "=w")
+	(unspec:SF [(match_operand:BF 1 "register_operand" "w")]
+		    UNSPEC_BFCVT))]
+  "TARGET_BF16_FP"
+  "shl\\t%d0, %d1, #16"
+  [(set_attr "type" "neon_shift_imm")]
+)
diff --git a/gcc/config/aarch64/arm_bf16.h b/gcc/config/aarch64/arm_bf16.h
index 984875dcc014..881615498d3d 100644
--- a/gcc/config/aarch64/arm_bf16.h
+++ b/gcc/config/aarch64/arm_bf16.h
@@ -40,6 +40,13 @@ vcvth_bf16_f32 (float32_t __a)
   return __builtin_aarch64_bfcvtbf (__a);
 }
 
+__extension__ extern __inline float32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vcvtah_f32_bf16 (bfloat16_t __a)
+{
+  return __builtin_aarch64_bfcvtsf (__a);
+}
+
 #pragma GCC pop_options
 
 #endif
diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index 95bfa5ebba21..69cccd327864 100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -35680,6 +35680,27 @@ vbfmlaltq_laneq_f32 (float32x4_t __r, bfloat16x8_t __a, bfloat16x8_t __b,
   return __builtin_aarch64_bfmlalt_lane_qv4sf (__r, __a, __b, __index);
 }
 
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vcvt_f32_bf16 (bfloat16x4_t __a)
+{
+  return __builtin_aarch64_vbfcvtv4bf (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vcvtq_low_f32_bf16 (bfloat16x8_t __a)
+{
+  return __builtin_aarch64_vbfcvtv8bf (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vcvtq_high_f32_bf16 (bfloat16x8_t __a)
+{
+  return __builtin_aarch64_vbfcvt_highv8bf (__a);
+}
+
 __extension__ extern __inline bfloat16x4_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vcvt_bf16_f32 (float32x4_t __a)
diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/bfcvt-compile.c b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/bfcvt-compile.c
index bbea630b1820..47af7c494d9b 100644
--- a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/bfcvt-compile.c
+++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/bfcvt-compile.c
@@ -46,3 +46,43 @@ bfloat16_t test_bfcvt (float32_t a)
 {
   return vcvth_bf16_f32 (a);
 }
+
+/*
+**test_vcvt_f32_bf16:
+**     shll	v0.4s, v0.4h, #16
+**     ret
+*/
+float32x4_t test_vcvt_f32_bf16 (bfloat16x4_t a)
+{
+  return vcvt_f32_bf16 (a);
+}
+
+/*
+**test_vcvtq_low_f32_bf16:
+**     shll	v0.4s, v0.4h, #16
+**     ret
+*/
+float32x4_t test_vcvtq_low_f32_bf16 (bfloat16x8_t a)
+{
+  return vcvtq_low_f32_bf16 (a);
+}
+
+/*
+**test_vcvtq_high_f32_bf16:
+**     shll2	v0.4s, v0.8h, #16
+**     ret
+*/
+float32x4_t test_vcvtq_high_f32_bf16 (bfloat16x8_t a)
+{
+  return vcvtq_high_f32_bf16 (a);
+}
+
+/*
+**test_vcvtah_f32_bf16:
+**     shl	d0, d0, #16
+**     ret
+*/
+float32_t test_vcvtah_f32_bf16 (bfloat16_t a)
+{
+  return vcvtah_f32_bf16 (a);
+}