Update

2026-10-22 12:27:19 +01:00
1 parent 3530afb854
commit 6903fcff27
@@ -0,0 +1,146 @@
+// Code generated by command: go run gen_fse.go -out ../fse_decoder.s -arch amd64,arm64 -pkg=zstd. DO NOT EDIT.
+// EXPERIMENTAL arm64 output lowered from an amd64 avo program.
+
+//go:build arm64 && (!appengine && !noasm && gc && !noasm)
+
+// func buildDtable_asm(s *fseDecoder, ctx *buildDtableAsmContext) int
+TEXT ·buildDtable_asm(SB), $0-24
+	MOVD ctx+8(FP), R1
+	MOVD s+0(FP), R6
+
+	// Load values
+	MOVBU 4098(R6), R2
+	MOVD  $0, R0
+	MOVD  $1, R16
+	LSL   R2, R16, R16
+	ORR   R16, R0, R0
+	MOVD  (R1), R3
+	MOVD  16(R1), R5
+	SUB   $1, R0, R7
+	MOVD  8(R1), R1
+	MOVHU 4096(R6), R6
+
+	// End load values
+	// Init, lay down lowprob symbols
+	MOVD $0, R8
+	JMP  init_main_loop_condition
+
+init_main_loop:
+	MOVH (R1)(R8<<1), R9
+	MOVD $-1, R16
+	AND  $0xffff, R16, R16
+	AND  $0xffff, R9, R15
+	CMP  R16, R15
+	BNE  do_not_update_high_threshold
+	ADD  R7<<3, R5, R15
+	MOVB R8, 1(R15)
+	SUB  $1, R7, R7
+	MOVD $0x0000000000000001, R9
+
+do_not_update_high_threshold:
+	MOVH R9, (R3)(R8<<1)
+	ADD  $1, R8, R8
+
+init_main_loop_condition:
+	CMP R6, R8
+	BLT init_main_loop
+
+	// Spread symbols
+	// Calculate table step
+	MOVD R0, R8
+	LSR  $0x01, R8, R8
+	MOVD R0, R9
+	LSR  $0x03, R9, R9
+	ADD  R9, R8, R8
+	ADD  $3, R8, R8
+
+	// Fill add bits values
+	SUB  $1, R0, R9
+	MOVD $0, R10
+	MOVD $0, R11
+	JMP  spread_main_loop_condition
+
+spread_main_loop:
+	MOVD $0, R12
+	MOVH (R1)(R11<<1), R13
+	JMP  spread_inner_loop_condition
+
+spread_inner_loop:
+	ADD  R10<<3, R5, R15
+	MOVB R11, 1(R15)
+
+adjust_position:
+	ADD R8, R10, R10
+	AND R9, R10, R10
+	CMP R7, R10
+	BGT adjust_position
+	ADD $1, R12, R12
+
+spread_inner_loop_condition:
+	CMP R13, R12
+	BLT spread_inner_loop
+	ADD $1, R11, R11
+
+spread_main_loop_condition:
+	CMP  R6, R11
+	BLT  spread_main_loop
+	TST  R10, R10
+	BEQ  spread_check_ok
+	MOVD ctx+8(FP), R0
+	MOVD R10, 24(R0)
+	MOVD $+1, R16
+	MOVD R16, ret+16(FP)
+	RET
+
+spread_check_ok:
+	// Build Decoding table
+	MOVD $0, R6
+
+build_table_main_table:
+	ADD   R6<<3, R5, R15
+	MOVBU 1(R15), R1
+	MOVHU (R3)(R1<<1), R7
+	ADD   $1, R7, R8
+	MOVH  R8, (R3)(R1<<1)
+	MOVD  R7, R8
+	CLZ   R8, R16
+	MOVD  $63, R8
+	SUB   R16, R8, R8
+	MOVD  R2, R1
+	SUB   R8, R1, R1
+	LSL   R1, R7, R7
+	SUB   R0, R7, R7
+	ADD   R6<<3, R5, R15
+	MOVB  R1, (R15)
+	ADD   R6<<3, R5, R15
+	MOVH  R7, 2(R15)
+	CMP   R0, R7
+	BLE   build_table_check1_ok
+	MOVD  ctx+8(FP), R1
+	MOVD  R7, 24(R1)
+	MOVD  R0, 32(R1)
+	MOVD  $+2, R16
+	MOVD  R16, ret+16(FP)
+	RET
+
+build_table_check1_ok:
+	TST  $0xff, R1
+	BNE  build_table_check2_ok
+	AND  $0xffff, R6, R16
+	AND  $0xffff, R7, R15
+	CMP  R16, R15
+	BNE  build_table_check2_ok
+	MOVD ctx+8(FP), R0
+	MOVD R7, 24(R0)
+	MOVD R6, 32(R0)
+	MOVD $+3, R16
+	MOVD R16, ret+16(FP)
+	RET
+
+build_table_check2_ok:
+	ADD  $1, R6, R6
+	CMP  R0, R6
+	BLT  build_table_main_table
+	MOVD $+0, R16
+	MOVD R16, ret+16(FP)
+	RET