From fcedfddf00b3f994e4f4e40332ac7fc192c63244 Mon Sep 17 00:00:00 2001
From: polwex <polwex@sortug.com>
Date: Sun, 5 Oct 2025 21:56:51 +0700
Subject: claude is gud

---
 vere/ext/gmp/gen/x86_64-macos/mpn/rsblsh_n.s | 269 +++++++++++++++++++++++++++
 1 file changed, 269 insertions(+)
 create mode 100644 vere/ext/gmp/gen/x86_64-macos/mpn/rsblsh_n.s

(limited to 'vere/ext/gmp/gen/x86_64-macos/mpn/rsblsh_n.s')

diff --git a/vere/ext/gmp/gen/x86_64-macos/mpn/rsblsh_n.s b/vere/ext/gmp/gen/x86_64-macos/mpn/rsblsh_n.s
new file mode 100644
index 0000000..329c600
--- /dev/null
+++ b/vere/ext/gmp/gen/x86_64-macos/mpn/rsblsh_n.s
@@ -0,0 +1,269 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  
+  
+
+
+
+
+
+
+
+
+	.text
+	.align	5, 0x90
+	.globl	___gmpn_rsblsh_n
+	
+	
+___gmpn_rsblsh_n:
+
+	
+
+
+	mov	(%rdx), %r10
+
+	mov	%ecx, %eax
+	shr	$3, %rcx
+	xor	%r9d, %r9d
+	sub	%r8, %r9
+	and	$7, %eax
+
+	lea	Ltab(%rip), %r11
+
+	movslq	(%r11,%rax,4), %rax
+	add	%r11, %rax
+	jmp	*%rax
+
+
+L0:	lea	32(%rsi), %rsi
+	lea	32(%rdx), %rdx
+	lea	32(%rdi), %rdi
+	xor	%r11d, %r11d
+	jmp	Le0
+
+L7:	mov	%r10, %r11
+	lea	24(%rsi), %rsi
+	lea	24(%rdx), %rdx
+	lea	24(%rdi), %rdi
+	xor	%r10d, %r10d
+	jmp	Le7
+
+L6:	lea	16(%rsi), %rsi
+	lea	16(%rdx), %rdx
+	lea	16(%rdi), %rdi
+	xor	%r11d, %r11d
+	jmp	Le6
+
+L5:	mov	%r10, %r11
+	lea	8(%rsi), %rsi
+	lea	8(%rdx), %rdx
+	lea	8(%rdi), %rdi
+	xor	%r10d, %r10d
+	jmp	Le5
+
+Lend:	sbb	24(%rsi), %rax
+	mov	%rax, -40(%rdi)
+	.byte	0xc4,194,179,0xf7,195
+	sbb	%rcx, %rax
+	
+	ret
+
+	.align	5, 0x90
+Ltop:	jrcxz	Lend
+	mov	-32(%rdx), %r10
+	sbb	24(%rsi), %rax
+	lea	64(%rsi), %rsi
+	.byte	0xc4,66,179,0xf7,219
+	mov	%rax, -40(%rdi)
+Le0:	dec	%rcx
+	.byte	0xc4,194,185,0xf7,194
+	lea	(%r11,%rax), %rax
+	mov	-24(%rdx), %r11
+	sbb	-32(%rsi), %rax
+	.byte	0xc4,66,179,0xf7,210
+	mov	%rax, -32(%rdi)
+Le7:	.byte	0xc4,194,185,0xf7,195
+	lea	(%r10,%rax), %rax
+	mov	-16(%rdx), %r10
+	sbb	-24(%rsi), %rax
+	.byte	0xc4,66,179,0xf7,219
+	mov	%rax, -24(%rdi)
+Le6:	.byte	0xc4,194,185,0xf7,194
+	lea	(%r11,%rax), %rax
+	mov	-8(%rdx), %r11
+	sbb	-16(%rsi), %rax
+	.byte	0xc4,66,179,0xf7,210
+	mov	%rax, -16(%rdi)
+Le5:	.byte	0xc4,194,185,0xf7,195
+	lea	(%r10,%rax), %rax
+	mov	(%rdx), %r10
+	sbb	-8(%rsi), %rax
+	.byte	0xc4,66,179,0xf7,219
+	mov	%rax, -8(%rdi)
+Le4:	.byte	0xc4,194,185,0xf7,194
+	lea	(%r11,%rax), %rax
+	mov	8(%rdx), %r11
+	sbb	(%rsi), %rax
+	.byte	0xc4,66,179,0xf7,210
+	mov	%rax, (%rdi)
+Le3:	.byte	0xc4,194,185,0xf7,195
+	lea	(%r10,%rax), %rax
+	mov	16(%rdx), %r10
+	sbb	8(%rsi), %rax
+	.byte	0xc4,66,179,0xf7,219
+	mov	%rax, 8(%rdi)
+Le2:	.byte	0xc4,194,185,0xf7,194
+	lea	(%r11,%rax), %rax
+	mov	24(%rdx), %r11
+	sbb	16(%rsi), %rax
+	lea	64(%rdx), %rdx
+	.byte	0xc4,66,179,0xf7,210
+	mov	%rax, 16(%rdi)
+	lea	64(%rdi), %rdi
+Le1:	.byte	0xc4,194,185,0xf7,195
+	lea	(%r10,%rax), %rax
+	jmp	Ltop
+
+L4:	xor	%r11d, %r11d
+	jmp	Le4
+
+L3:	mov	%r10, %r11
+	lea	-8(%rsi), %rsi
+	lea	-8(%rdx), %rdx
+	lea	-8(%rdi), %rdi
+	xor	%r10d, %r10d
+	jmp	Le3
+
+L2:	lea	-16(%rsi), %rsi
+	lea	-16(%rdx), %rdx
+	lea	-16(%rdi), %rdi
+	xor	%r11d, %r11d
+	jmp	Le2
+
+L1:	mov	%r10, %r11
+	lea	-24(%rsi), %rsi
+	lea	40(%rdx), %rdx
+	lea	40(%rdi), %rdi
+	xor	%r10d, %r10d
+	jmp	Le1
+	
+	.text
+	.align	3, 0x90
+Ltab:	.set	L0_tmp, L0-Ltab
+	.long	L0_tmp
+
+	.set	L1_tmp, L1-Ltab
+	.long	L1_tmp
+
+	.set	L2_tmp, L2-Ltab
+	.long	L2_tmp
+
+	.set	L3_tmp, L3-Ltab
+	.long	L3_tmp
+
+	.set	L4_tmp, L4-Ltab
+	.long	L4_tmp
+
+	.set	L5_tmp, L5-Ltab
+	.long	L5_tmp
+
+	.set	L6_tmp, L6-Ltab
+	.long	L6_tmp
+
+	.set	L7_tmp, L7-Ltab
+	.long	L7_tmp
+
+
-- 
cgit v1.2.3