feat(asm): extend arm64 encoder with FP, conditional select, CRC32 and tests

Assisted-by: MiMo V2.5 Pro
2026-08-20 14:07:12 +02:00
parent 4221ec5741
commit 6e73f59e78
6 changed files with 768 additions and 9 deletions
@@ -0,0 +1,119 @@
+// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
+// SPDX-License-Identifier: BSD-3-Clause
+
+#include "textflag.h"
+
+// fparith exercises the FP arithmetic set.
+TEXT ·fparith(SB), NOSPLIT, $0-0
+	FADDD	F0, F1, F2
+	FSUBD	F3, F4, F5
+	FMULD	F6, F7, F8
+	FDIVD	F9, F10, F11
+	FADDS	F12, F13, F14
+	FSUBS	F15, F16, F17
+	FMULS	F18, F19, F20
+	FDIVS	F21, F22, F23
+	FSQRTD	F24, F25
+	FSQRTS	F26, F27
+	FNEGD	F28, F29
+	FNEGS	F30, F31
+	FABSD	F0, F1
+	FABSS	F2, F3
+	FNMULD	F4, F5, F6
+	FNMULS	F7, F8, F9
+	FMIND	F10, F11, F12
+	FMAXD	F13, F14, F15
+	FMINS	F16, F17, F18
+	FMAXS	F19, F20, F21
+	RET
+
+// fpfma exercises fused multiply-add.
+TEXT ·fpfma(SB), NOSPLIT, $0-0
+	FMADDD	F0, F1, F2, F3
+	FMSUBD	F4, F5, F6, F7
+	FNMADDD	F8, F9, F10, F11
+	FNMSUBD	F12, F13, F14, F15
+	FMADDS	F16, F17, F18, F19
+	FMSUBS	F20, F21, F22, F23
+	FNMADDS	F24, F25, F26, F27
+	FNMSUBS	F28, F29, F30, F0
+	RET
+
+// fpconv exercises FP↔integer conversion and cross-precision.
+// Syntax: FCVTZSD Fd, Rn (float→int: FP source first, int dest second)
+//         SCVTFD Rn, Fd (int→float: int source first, FP dest second)
+TEXT ·fpconv(SB), NOSPLIT, $0-0
+	FCVTSD	F0, F1
+	FCVTDS	F2, F3
+	FCVTZSD	F4, R0
+	FCVTZSS	F5, R1
+	FCVTZUD	F6, R2
+	FCVTZUS	F7, R3
+	SCVTFD	R4, F8
+	SCVTFS	R5, F9
+	UCVTFD	R6, F10
+	UCVTFS	R7, F11
+	SCVTFWD	R0, F12
+	SCVTFWS	R1, F13
+	UCVTFWD	R2, F14
+	UCVTFWS	R3, F15
+	FMOVS	F14, R20
+	FMOVS	R21, F15
+	FMOVD	F16, R22
+	FMOVD	R23, F17
+	RET
+
+// fpcmp exercises FP compare and conditional compare.
+// FCCMP syntax: FCCMP cond, Fn, Fm, $nzcv
+// FCSEL syntax: FCSEL cond, Fn, Fm, Fd
+TEXT ·fpcmp(SB), NOSPLIT, $0-0
+	FCMPS	F0, F1
+	FCMPD	F2, F3
+	FCMPS	$0.0, F4
+	FCMPD	$0.0, F5
+	FCCMPS	EQ, F6, F7, $0
+	FCCMPD	NE, F8, F9, $0
+	FCSELS	GE, F10, F11, F12
+	FCSELD	LT, F13, F14, F15
+	RET
+
+// frint exercises FP rounding.
+TEXT ·frint(SB), NOSPLIT, $0-0
+	FRINTND	F0, F1
+	FRINTNS	F2, F3
+	FRINTPD	F4, F5
+	FRINTPS	F6, F7
+	FRINTMD	F8, F9
+	FRINTMS	F10, F11
+	FRINTZD	F12, F13
+	FRINTZS	F14, F15
+	FRINTAD	F16, F17
+	FRINTAS	F18, F19
+	FRINTXD	F20, F21
+	FRINTXS	F22, F23
+	FRINTID	F24, F25
+	FRINTIS	F26, F27
+	FMOVD	F0, F1
+	FMOVS	F2, F3
+	RET
+
+// condsel exercises conditional select and CRC32.
+TEXT ·condsel(SB), NOSPLIT, $0-0
+	CSEL	EQ, R0, R1, R2
+	CSINC	NE, R3, R4, R5
+	CSINV	GE, R6, R7, R8
+	CSNEG	LT, R9, R10, R11
+	CSET	EQ, R12
+	CSETM	NE, R13
+	CINC	EQ, R14, R15
+	CINV	NE, R16, R17
+	CNEG	GE, R19, R20
+	CRC32B	R0, R2
+	CRC32H	R3, R5
+	CRC32W	R6, R8
+	CRC32X	R9, R11
+	CRC32CB	R12, R14
+	CRC32CH	R15, R0
+	CRC32CW	R1, R3
+	CRC32CX	R4, R6
+	RET