feat(riscv64,loong64): encode AMO atomics, vector slices and bit ops

Assisted-by: DeepSeek V4.1 Flash
2026-09-20 06:44:51 +02:00
parent 56376a0e59
commit 924e0013eb
12 changed files with 2059 additions and 37 deletions
@@ -0,0 +1,85 @@
+// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
+// SPDX-License-Identifier: BSD-3-Clause
+
+// Differential kernel for the loong64 LSX/LASX slice: every function pairs
+// with the same instructions in the go tool asm ground truth.
+
+#include "textflag.h"
+
+TEXT ·threeReg(SB), NOSPLIT, $0-0
+	VADDV   V1, V2, V3
+	VADDW   V1, V2, V3
+	VADDV   V2, V1
+	VANDV   V1, V2, V3
+	VANDV   V1, V2
+	VXORV   V1, V2, V3
+	VXORV   V1, V2
+	VSEQB   V1, V2, V3
+	VSEQV   V1, V2, V3
+	VSRAB   V1, V2, V3
+	VROTRW  V1, V2, V3
+	VPCNTV  V1, V2
+	XVADDV  X1, X2, X3
+	XVADDV  X2, X1
+	XVANDV  X1, X2, X3
+	XVXORV  X1, X2, X3
+	XVSEQB  X1, X2, X3
+	XVSEQV  X1, X2, X3
+	XVPCNTV X1, X2
+	RET
+
+TEXT ·immediates(SB), NOSPLIT, $0-0
+	VANDB  $0, V2, V3
+	VANDB  $255, V2
+	VSEQB  $3, V2, V3
+	VSEQV  $15, V2, V3
+	VSRAB  $0, V1, V2
+	VSRAB  $7, V1, V2
+	VSRAB  $6, V1
+	VROTRW $0, V1, V2
+	VROTRW $16, V1, V2
+	VROTRW $16, V1
+	XVANDB $1, X2, X2
+	RET
+
+TEXT ·conditions(SB), NOSPLIT, $0-0
+	VSETNEV     V1, FCC0
+	VSETANYEQB  V1, FCC0
+	VSETANYEQV  V2, FCC0
+	VSETALLNEV  V0, FCC0
+	XVSETNEV    X1, FCC0
+	XVSETANYEQB X1, FCC0
+	XVSETANYEQV X1, FCC0
+	XVSETALLNEV X1, FCC0
+	RET
+
+TEXT ·fpConvert(SB), NOSPLIT, $0-0
+	FFINTDV F0, F1
+	FSEL    FCC0, F3, F4, F3
+	FSEL    FCC1, F1, F2
+	RET
+
+TEXT ·memMoves(SB), NOSPLIT, $0-0
+	VMOVQ  V1, V9
+	VMOVQ  (R4), V2
+	VMOVQ  16(R4), V2
+	VMOVQ  V0, (R4)
+	VMOVQ  V0, 32(R4)
+	VMOVQ  V0,-16(R6)
+	VMOVQ  (R4)(R7), V3
+	VMOVQ  V3, (R4)(R7)
+	XVMOVQ X3, X7
+	XVMOVQ (R4), X2
+	XVMOVQ X0, (R4)
+	XVMOVQ (R4)(R7), X4
+	XVMOVQ X0, (R4)(R7)
+	RET
+
+TEXT ·elements(SB), NOSPLIT, $0-0
+	VMOVQ  R6, V0.B16
+	VMOVQ  R6, V12.W4
+	XVMOVQ R6, X0.B32
+	VMOVQ  (R4), V4.W4
+	VMOVQ  (R10), V0.W4
+	XVMOVQ (R4), X0.B32
+	RET