diff --git a/generated-src/linux-x86/crypto/chacha/chacha-x86.S b/generated-src/linux-x86/crypto/chacha/chacha-x86.S
index a3dc02e0999..566fbb4cd61 100644
--- a/generated-src/linux-x86/crypto/chacha/chacha-x86.S
+++ b/generated-src/linux-x86/crypto/chacha/chacha-x86.S
@@ -5,29 +5,16 @@
 
 #if !defined(OPENSSL_NO_ASM) && defined(OPENSSL_X86) && defined(__ELF__)
 .text
-.globl	ChaCha20_ctr32
-.hidden	ChaCha20_ctr32
-.type	ChaCha20_ctr32,@function
+.globl	ChaCha20_ctr32_nohw
+.hidden	ChaCha20_ctr32_nohw
+.type	ChaCha20_ctr32_nohw,@function
 .align	16
-ChaCha20_ctr32:
-.L_ChaCha20_ctr32_begin:
+ChaCha20_ctr32_nohw:
+.L_ChaCha20_ctr32_nohw_begin:
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
 	pushl	%edi
-	xorl	%eax,%eax
-	cmpl	28(%esp),%eax
-	je	.L000no_data
-	call	.Lpic_point
-.Lpic_point:
-	popl	%eax
-	leal	OPENSSL_ia32cap_P-.Lpic_point(%eax),%ebp
-	testl	$16777216,(%ebp)
-	jz	.L001x86
-	testl	$512,4(%ebp)
-	jz	.L001x86
-	jmp	.Lssse3_shortcut
-.L001x86:
 	movl	32(%esp),%esi
 	movl	36(%esp),%edi
 	subl	$132,%esp
@@ -56,13 +43,13 @@ ChaCha20_ctr32:
 	movl	%ebx,116(%esp)
 	movl	%ecx,120(%esp)
 	movl	%edx,124(%esp)
-	jmp	.L002entry
+	jmp	.L000entry
 .align	16
-.L003outer_loop:
+.L001outer_loop:
 	movl	%ebx,156(%esp)
 	movl	%eax,152(%esp)
 	movl	%ecx,160(%esp)
-.L002entry:
+.L000entry:
 	movl	$1634760805,%eax
 	movl	$857760878,4(%esp)
 	movl	$2036477234,8(%esp)
@@ -90,9 +77,9 @@ ChaCha20_ctr32:
 	movl	%edi,60(%esp)
 	movl	%edx,112(%esp)
 	movl	$10,%ebx
-	jmp	.L004loop
+	jmp	.L002loop
 .align	16
-.L004loop:
+.L002loop:
 	addl	%ebp,%eax
 	movl	%ebx,128(%esp)
 	movl	%ebp,%ebx
@@ -246,14 +233,14 @@ ChaCha20_ctr32:
 	xorl	%esi,%ebp
 	roll	$7,%ebp
 	decl	%ebx
-	jnz	.L004loop
+	jnz	.L002loop
 	movl	160(%esp),%ebx
 	addl	$1634760805,%eax
 	addl	80(%esp),%ebp
 	addl	96(%esp),%ecx
 	addl	100(%esp),%esi
 	cmpl	$64,%ebx
-	jb	.L005tail
+	jb	.L003tail
 	movl	156(%esp),%ebx
 	addl	112(%esp),%edx
 	addl	120(%esp),%edi
@@ -316,9 +303,9 @@ ChaCha20_ctr32:
 	movl	%ebp,(%eax)
 	leal	64(%eax),%eax
 	subl	$64,%ecx
-	jnz	.L003outer_loop
-	jmp	.L006done
-.L005tail:
+	jnz	.L001outer_loop
+	jmp	.L004done
+.L003tail:
 	addl	112(%esp),%edx
 	addl	120(%esp),%edi
 	movl	%eax,(%esp)
@@ -362,34 +349,35 @@ ChaCha20_ctr32:
 	movl	%edi,60(%esp)
 	xorl	%eax,%eax
 	xorl	%edx,%edx
-.L007tail_loop:
+.L005tail_loop:
 	movb	(%esi,%ebp,1),%al
 	movb	(%esp,%esi,1),%dl
 	leal	1(%esi),%esi
 	xorb	%dl,%al
 	movb	%al,-1(%ecx,%esi,1)
 	decl	%ebx
-	jnz	.L007tail_loop
-.L006done:
+	jnz	.L005tail_loop
+.L004done:
 	addl	$132,%esp
-.L000no_data:
 	popl	%edi
 	popl	%esi
 	popl	%ebx
 	popl	%ebp
 	ret
-.size	ChaCha20_ctr32,.-.L_ChaCha20_ctr32_begin
-.globl	ChaCha20_ssse3
-.hidden	ChaCha20_ssse3
-.type	ChaCha20_ssse3,@function
+.size	ChaCha20_ctr32_nohw,.-.L_ChaCha20_ctr32_nohw_begin
+.globl	ChaCha20_ctr32_ssse3
+.hidden	ChaCha20_ctr32_ssse3
+.type	ChaCha20_ctr32_ssse3,@function
 .align	16
-ChaCha20_ssse3:
-.L_ChaCha20_ssse3_begin:
+ChaCha20_ctr32_ssse3:
+.L_ChaCha20_ctr32_ssse3_begin:
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
 	pushl	%edi
-.Lssse3_shortcut:
+	call	.Lpic_point
+.Lpic_point:
+	popl	%eax
 	movl	20(%esp),%edi
 	movl	24(%esp),%esi
 	movl	28(%esp),%ecx
@@ -402,7 +390,7 @@ ChaCha20_ssse3:
 	leal	.Lssse3_data-.Lpic_point(%eax),%eax
 	movdqu	(%ebx),%xmm3
 	cmpl	$256,%ecx
-	jb	.L0081x
+	jb	.L0061x
 	movl	%edx,516(%esp)
 	movl	%ebx,520(%esp)
 	subl	$256,%ecx
@@ -447,9 +435,9 @@ ChaCha20_ssse3:
 	movdqa	%xmm7,-80(%ebp)
 	leal	128(%esi),%esi
 	leal	128(%edi),%edi
-	jmp	.L009outer_loop
+	jmp	.L007outer_loop
 .align	16
-.L009outer_loop:
+.L007outer_loop:
 	movdqa	-112(%ebp),%xmm1
 	movdqa	-96(%ebp),%xmm2
 	movdqa	-80(%ebp),%xmm3
@@ -484,7 +472,7 @@ ChaCha20_ssse3:
 	movl	$10,%edx
 	nop
 .align	16
-.L010loop:
+.L008loop:
 	paddd	%xmm3,%xmm0
 	movdqa	%xmm3,%xmm2
 	pxor	%xmm0,%xmm6
@@ -684,7 +672,7 @@ ChaCha20_ssse3:
 	psrld	$25,%xmm1
 	por	%xmm1,%xmm3
 	decl	%edx
-	jnz	.L010loop
+	jnz	.L008loop
 	movdqa	%xmm3,-64(%ebx)
 	movdqa	%xmm4,(%ebx)
 	movdqa	%xmm5,16(%ebx)
@@ -826,9 +814,9 @@ ChaCha20_ssse3:
 	movdqu	%xmm7,64(%edi)
 	leal	208(%edi),%edi
 	subl	$256,%ecx
-	jnc	.L009outer_loop
+	jnc	.L007outer_loop
 	addl	$256,%ecx
-	jz	.L011done
+	jz	.L009done
 	movl	520(%esp),%ebx
 	leal	-128(%esi),%esi
 	movl	516(%esp),%edx
@@ -838,7 +826,7 @@ ChaCha20_ssse3:
 	paddd	96(%eax),%xmm2
 	pand	112(%eax),%xmm3
 	por	%xmm2,%xmm3
-.L0081x:
+.L0061x:
 	movdqa	32(%eax),%xmm0
 	movdqu	(%edx),%xmm1
 	movdqu	16(%edx),%xmm2
@@ -850,9 +838,9 @@ ChaCha20_ssse3:
 	movdqa	%xmm2,32(%esp)
 	movdqa	%xmm3,48(%esp)
 	movl	$10,%edx
-	jmp	.L012loop1x
+	jmp	.L010loop1x
 .align	16
-.L013outer1x:
+.L011outer1x:
 	movdqa	80(%eax),%xmm3
 	movdqa	(%esp),%xmm0
 	movdqa	16(%esp),%xmm1
@@ -860,9 +848,9 @@ ChaCha20_ssse3:
 	paddd	48(%esp),%xmm3
 	movl	$10,%edx
 	movdqa	%xmm3,48(%esp)
-	jmp	.L012loop1x
+	jmp	.L010loop1x
 .align	16
-.L012loop1x:
+.L010loop1x:
 	paddd	%xmm1,%xmm0
 	pxor	%xmm0,%xmm3
 .byte	102,15,56,0,222
@@ -907,13 +895,13 @@ ChaCha20_ssse3:
 	pshufd	$147,%xmm1,%xmm1
 	pshufd	$57,%xmm3,%xmm3
 	decl	%edx
-	jnz	.L012loop1x
+	jnz	.L010loop1x
 	paddd	(%esp),%xmm0
 	paddd	16(%esp),%xmm1
 	paddd	32(%esp),%xmm2
 	paddd	48(%esp),%xmm3
 	cmpl	$64,%ecx
-	jb	.L014tail
+	jb	.L012tail
 	movdqu	(%esi),%xmm4
 	movdqu	16(%esi),%xmm5
 	pxor	%xmm4,%xmm0
@@ -929,9 +917,9 @@ ChaCha20_ssse3:
 	movdqu	%xmm3,48(%edi)
 	leal	64(%edi),%edi
 	subl	$64,%ecx
-	jnz	.L013outer1x
-	jmp	.L011done
-.L014tail:
+	jnz	.L011outer1x
+	jmp	.L009done
+.L012tail:
 	movdqa	%xmm0,(%esp)
 	movdqa	%xmm1,16(%esp)
 	movdqa	%xmm2,32(%esp)
@@ -939,22 +927,22 @@ ChaCha20_ssse3:
 	xorl	%eax,%eax
 	xorl	%edx,%edx
 	xorl	%ebp,%ebp
-.L015tail_loop:
+.L013tail_loop:
 	movb	(%esp,%ebp,1),%al
 	movb	(%esi,%ebp,1),%dl
 	leal	1(%ebp),%ebp
 	xorb	%dl,%al
 	movb	%al,-1(%edi,%ebp,1)
 	decl	%ecx
-	jnz	.L015tail_loop
-.L011done:
+	jnz	.L013tail_loop
+.L009done:
 	movl	512(%esp),%esp
 	popl	%edi
 	popl	%esi
 	popl	%ebx
 	popl	%ebp
 	ret
-.size	ChaCha20_ssse3,.-.L_ChaCha20_ssse3_begin
+.size	ChaCha20_ctr32_ssse3,.-.L_ChaCha20_ctr32_ssse3_begin
 .align	64
 .Lssse3_data:
 .byte	2,3,0,1,6,7,4,5,10,11,8,9,14,15,12,13
diff --git a/generated-src/mac-x86/crypto/chacha/chacha-x86.S b/generated-src/mac-x86/crypto/chacha/chacha-x86.S
index baa06acf807..48293da9185 100644
--- a/generated-src/mac-x86/crypto/chacha/chacha-x86.S
+++ b/generated-src/mac-x86/crypto/chacha/chacha-x86.S
@@ -5,28 +5,15 @@
 
 #if !defined(OPENSSL_NO_ASM) && defined(OPENSSL_X86) && defined(__APPLE__)
 .text
-.globl	_ChaCha20_ctr32
-.private_extern	_ChaCha20_ctr32
+.globl	_ChaCha20_ctr32_nohw
+.private_extern	_ChaCha20_ctr32_nohw
 .align	4
-_ChaCha20_ctr32:
-L_ChaCha20_ctr32_begin:
+_ChaCha20_ctr32_nohw:
+L_ChaCha20_ctr32_nohw_begin:
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
 	pushl	%edi
-	xorl	%eax,%eax
-	cmpl	28(%esp),%eax
-	je	L000no_data
-	call	Lpic_point
-Lpic_point:
-	popl	%eax
-	movl	L_OPENSSL_ia32cap_P$non_lazy_ptr-Lpic_point(%eax),%ebp
-	testl	$16777216,(%ebp)
-	jz	L001x86
-	testl	$512,4(%ebp)
-	jz	L001x86
-	jmp	Lssse3_shortcut
-L001x86:
 	movl	32(%esp),%esi
 	movl	36(%esp),%edi
 	subl	$132,%esp
@@ -55,13 +42,13 @@ L001x86:
 	movl	%ebx,116(%esp)
 	movl	%ecx,120(%esp)
 	movl	%edx,124(%esp)
-	jmp	L002entry
+	jmp	L000entry
 .align	4,0x90
-L003outer_loop:
+L001outer_loop:
 	movl	%ebx,156(%esp)
 	movl	%eax,152(%esp)
 	movl	%ecx,160(%esp)
-L002entry:
+L000entry:
 	movl	$1634760805,%eax
 	movl	$857760878,4(%esp)
 	movl	$2036477234,8(%esp)
@@ -89,9 +76,9 @@ L002entry:
 	movl	%edi,60(%esp)
 	movl	%edx,112(%esp)
 	movl	$10,%ebx
-	jmp	L004loop
+	jmp	L002loop
 .align	4,0x90
-L004loop:
+L002loop:
 	addl	%ebp,%eax
 	movl	%ebx,128(%esp)
 	movl	%ebp,%ebx
@@ -245,14 +232,14 @@ L004loop:
 	xorl	%esi,%ebp
 	roll	$7,%ebp
 	decl	%ebx
-	jnz	L004loop
+	jnz	L002loop
 	movl	160(%esp),%ebx
 	addl	$1634760805,%eax
 	addl	80(%esp),%ebp
 	addl	96(%esp),%ecx
 	addl	100(%esp),%esi
 	cmpl	$64,%ebx
-	jb	L005tail
+	jb	L003tail
 	movl	156(%esp),%ebx
 	addl	112(%esp),%edx
 	addl	120(%esp),%edi
@@ -315,9 +302,9 @@ L004loop:
 	movl	%ebp,(%eax)
 	leal	64(%eax),%eax
 	subl	$64,%ecx
-	jnz	L003outer_loop
-	jmp	L006done
-L005tail:
+	jnz	L001outer_loop
+	jmp	L004done
+L003tail:
 	addl	112(%esp),%edx
 	addl	120(%esp),%edi
 	movl	%eax,(%esp)
@@ -361,32 +348,33 @@ L005tail:
 	movl	%edi,60(%esp)
 	xorl	%eax,%eax
 	xorl	%edx,%edx
-L007tail_loop:
+L005tail_loop:
 	movb	(%esi,%ebp,1),%al
 	movb	(%esp,%esi,1),%dl
 	leal	1(%esi),%esi
 	xorb	%dl,%al
 	movb	%al,-1(%ecx,%esi,1)
 	decl	%ebx
-	jnz	L007tail_loop
-L006done:
+	jnz	L005tail_loop
+L004done:
 	addl	$132,%esp
-L000no_data:
 	popl	%edi
 	popl	%esi
 	popl	%ebx
 	popl	%ebp
 	ret
-.globl	_ChaCha20_ssse3
-.private_extern	_ChaCha20_ssse3
+.globl	_ChaCha20_ctr32_ssse3
+.private_extern	_ChaCha20_ctr32_ssse3
 .align	4
-_ChaCha20_ssse3:
-L_ChaCha20_ssse3_begin:
+_ChaCha20_ctr32_ssse3:
+L_ChaCha20_ctr32_ssse3_begin:
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
 	pushl	%edi
-Lssse3_shortcut:
+	call	Lpic_point
+Lpic_point:
+	popl	%eax
 	movl	20(%esp),%edi
 	movl	24(%esp),%esi
 	movl	28(%esp),%ecx
@@ -399,7 +387,7 @@ Lssse3_shortcut:
 	leal	Lssse3_data-Lpic_point(%eax),%eax
 	movdqu	(%ebx),%xmm3
 	cmpl	$256,%ecx
-	jb	L0081x
+	jb	L0061x
 	movl	%edx,516(%esp)
 	movl	%ebx,520(%esp)
 	subl	$256,%ecx
@@ -444,9 +432,9 @@ Lssse3_shortcut:
 	movdqa	%xmm7,-80(%ebp)
 	leal	128(%esi),%esi
 	leal	128(%edi),%edi
-	jmp	L009outer_loop
+	jmp	L007outer_loop
 .align	4,0x90
-L009outer_loop:
+L007outer_loop:
 	movdqa	-112(%ebp),%xmm1
 	movdqa	-96(%ebp),%xmm2
 	movdqa	-80(%ebp),%xmm3
@@ -481,7 +469,7 @@ L009outer_loop:
 	movl	$10,%edx
 	nop
 .align	4,0x90
-L010loop:
+L008loop:
 	paddd	%xmm3,%xmm0
 	movdqa	%xmm3,%xmm2
 	pxor	%xmm0,%xmm6
@@ -681,7 +669,7 @@ L010loop:
 	psrld	$25,%xmm1
 	por	%xmm1,%xmm3
 	decl	%edx
-	jnz	L010loop
+	jnz	L008loop
 	movdqa	%xmm3,-64(%ebx)
 	movdqa	%xmm4,(%ebx)
 	movdqa	%xmm5,16(%ebx)
@@ -823,9 +811,9 @@ L010loop:
 	movdqu	%xmm7,64(%edi)
 	leal	208(%edi),%edi
 	subl	$256,%ecx
-	jnc	L009outer_loop
+	jnc	L007outer_loop
 	addl	$256,%ecx
-	jz	L011done
+	jz	L009done
 	movl	520(%esp),%ebx
 	leal	-128(%esi),%esi
 	movl	516(%esp),%edx
@@ -835,7 +823,7 @@ L010loop:
 	paddd	96(%eax),%xmm2
 	pand	112(%eax),%xmm3
 	por	%xmm2,%xmm3
-L0081x:
+L0061x:
 	movdqa	32(%eax),%xmm0
 	movdqu	(%edx),%xmm1
 	movdqu	16(%edx),%xmm2
@@ -847,9 +835,9 @@ L0081x:
 	movdqa	%xmm2,32(%esp)
 	movdqa	%xmm3,48(%esp)
 	movl	$10,%edx
-	jmp	L012loop1x
+	jmp	L010loop1x
 .align	4,0x90
-L013outer1x:
+L011outer1x:
 	movdqa	80(%eax),%xmm3
 	movdqa	(%esp),%xmm0
 	movdqa	16(%esp),%xmm1
@@ -857,9 +845,9 @@ L013outer1x:
 	paddd	48(%esp),%xmm3
 	movl	$10,%edx
 	movdqa	%xmm3,48(%esp)
-	jmp	L012loop1x
+	jmp	L010loop1x
 .align	4,0x90
-L012loop1x:
+L010loop1x:
 	paddd	%xmm1,%xmm0
 	pxor	%xmm0,%xmm3
 .byte	102,15,56,0,222
@@ -904,13 +892,13 @@ L012loop1x:
 	pshufd	$147,%xmm1,%xmm1
 	pshufd	$57,%xmm3,%xmm3
 	decl	%edx
-	jnz	L012loop1x
+	jnz	L010loop1x
 	paddd	(%esp),%xmm0
 	paddd	16(%esp),%xmm1
 	paddd	32(%esp),%xmm2
 	paddd	48(%esp),%xmm3
 	cmpl	$64,%ecx
-	jb	L014tail
+	jb	L012tail
 	movdqu	(%esi),%xmm4
 	movdqu	16(%esi),%xmm5
 	pxor	%xmm4,%xmm0
@@ -926,9 +914,9 @@ L012loop1x:
 	movdqu	%xmm3,48(%edi)
 	leal	64(%edi),%edi
 	subl	$64,%ecx
-	jnz	L013outer1x
-	jmp	L011done
-L014tail:
+	jnz	L011outer1x
+	jmp	L009done
+L012tail:
 	movdqa	%xmm0,(%esp)
 	movdqa	%xmm1,16(%esp)
 	movdqa	%xmm2,32(%esp)
@@ -936,15 +924,15 @@ L014tail:
 	xorl	%eax,%eax
 	xorl	%edx,%edx
 	xorl	%ebp,%ebp
-L015tail_loop:
+L013tail_loop:
 	movb	(%esp,%ebp,1),%al
 	movb	(%esi,%ebp,1),%dl
 	leal	1(%ebp),%ebp
 	xorb	%dl,%al
 	movb	%al,-1(%edi,%ebp,1)
 	decl	%ecx
-	jnz	L015tail_loop
-L011done:
+	jnz	L013tail_loop
+L009done:
 	movl	512(%esp),%esp
 	popl	%edi
 	popl	%esi
@@ -966,8 +954,4 @@ Lssse3_data:
 .byte	44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32
 .byte	60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111
 .byte	114,103,62,0
-.section __IMPORT,__pointers,non_lazy_symbol_pointers
-L_OPENSSL_ia32cap_P$non_lazy_ptr:
-.indirect_symbol	_OPENSSL_ia32cap_P
-.long	0
 #endif  // !defined(OPENSSL_NO_ASM) && defined(OPENSSL_X86) && defined(__APPLE__)
diff --git a/generated-src/win-x86/crypto/chacha/chacha-x86.asm b/generated-src/win-x86/crypto/chacha/chacha-x86.asm
index e99ad2915ea..880348ca49d 100644
--- a/generated-src/win-x86/crypto/chacha/chacha-x86.asm
+++ b/generated-src/win-x86/crypto/chacha/chacha-x86.asm
@@ -11,27 +11,14 @@ section	.text	code align=64
 %else
 section	.text	code
 %endif
-global	_ChaCha20_ctr32
+global	_ChaCha20_ctr32_nohw
 align	16
-_ChaCha20_ctr32:
-L$_ChaCha20_ctr32_begin:
+_ChaCha20_ctr32_nohw:
+L$_ChaCha20_ctr32_nohw_begin:
 	push	ebp
 	push	ebx
 	push	esi
 	push	edi
-	xor	eax,eax
-	cmp	eax,DWORD [28+esp]
-	je	NEAR L$000no_data
-	call	L$pic_point
-L$pic_point:
-	pop	eax
-	lea	ebp,[_OPENSSL_ia32cap_P]
-	test	DWORD [ebp],16777216
-	jz	NEAR L$001x86
-	test	DWORD [4+ebp],512
-	jz	NEAR L$001x86
-	jmp	NEAR L$ssse3_shortcut
-L$001x86:
 	mov	esi,DWORD [32+esp]
 	mov	edi,DWORD [36+esp]
 	sub	esp,132
@@ -60,13 +47,13 @@ L$001x86:
 	mov	DWORD [116+esp],ebx
 	mov	DWORD [120+esp],ecx
 	mov	DWORD [124+esp],edx
-	jmp	NEAR L$002entry
+	jmp	NEAR L$000entry
 align	16
-L$003outer_loop:
+L$001outer_loop:
 	mov	DWORD [156+esp],ebx
 	mov	DWORD [152+esp],eax
 	mov	DWORD [160+esp],ecx
-L$002entry:
+L$000entry:
 	mov	eax,1634760805
 	mov	DWORD [4+esp],857760878
 	mov	DWORD [8+esp],2036477234
@@ -94,9 +81,9 @@ L$002entry:
 	mov	DWORD [60+esp],edi
 	mov	DWORD [112+esp],edx
 	mov	ebx,10
-	jmp	NEAR L$004loop
+	jmp	NEAR L$002loop
 align	16
-L$004loop:
+L$002loop:
 	add	eax,ebp
 	mov	DWORD [128+esp],ebx
 	mov	ebx,ebp
@@ -250,14 +237,14 @@ L$004loop:
 	xor	ebp,esi
 	rol	ebp,7
 	dec	ebx
-	jnz	NEAR L$004loop
+	jnz	NEAR L$002loop
 	mov	ebx,DWORD [160+esp]
 	add	eax,1634760805
 	add	ebp,DWORD [80+esp]
 	add	ecx,DWORD [96+esp]
 	add	esi,DWORD [100+esp]
 	cmp	ebx,64
-	jb	NEAR L$005tail
+	jb	NEAR L$003tail
 	mov	ebx,DWORD [156+esp]
 	add	edx,DWORD [112+esp]
 	add	edi,DWORD [120+esp]
@@ -320,9 +307,9 @@ L$004loop:
 	mov	DWORD [eax],ebp
 	lea	eax,[64+eax]
 	sub	ecx,64
-	jnz	NEAR L$003outer_loop
-	jmp	NEAR L$006done
-L$005tail:
+	jnz	NEAR L$001outer_loop
+	jmp	NEAR L$004done
+L$003tail:
 	add	edx,DWORD [112+esp]
 	add	edi,DWORD [120+esp]
 	mov	DWORD [esp],eax
@@ -366,31 +353,32 @@ L$005tail:
 	mov	DWORD [60+esp],edi
 	xor	eax,eax
 	xor	edx,edx
-L$007tail_loop:
+L$005tail_loop:
 	mov	al,BYTE [ebp*1+esi]
 	mov	dl,BYTE [esi*1+esp]
 	lea	esi,[1+esi]
 	xor	al,dl
 	mov	BYTE [esi*1+ecx-1],al
 	dec	ebx
-	jnz	NEAR L$007tail_loop
-L$006done:
+	jnz	NEAR L$005tail_loop
+L$004done:
 	add	esp,132
-L$000no_data:
 	pop	edi
 	pop	esi
 	pop	ebx
 	pop	ebp
 	ret
-global	_ChaCha20_ssse3
+global	_ChaCha20_ctr32_ssse3
 align	16
-_ChaCha20_ssse3:
-L$_ChaCha20_ssse3_begin:
+_ChaCha20_ctr32_ssse3:
+L$_ChaCha20_ctr32_ssse3_begin:
 	push	ebp
 	push	ebx
 	push	esi
 	push	edi
-L$ssse3_shortcut:
+	call	L$pic_point
+L$pic_point:
+	pop	eax
 	mov	edi,DWORD [20+esp]
 	mov	esi,DWORD [24+esp]
 	mov	ecx,DWORD [28+esp]
@@ -403,7 +391,7 @@ L$ssse3_shortcut:
 	lea	eax,[(L$ssse3_data-L$pic_point)+eax]
 	movdqu	xmm3,[ebx]
 	cmp	ecx,256
-	jb	NEAR L$0081x
+	jb	NEAR L$0061x
 	mov	DWORD [516+esp],edx
 	mov	DWORD [520+esp],ebx
 	sub	ecx,256
@@ -448,9 +436,9 @@ L$ssse3_shortcut:
 	movdqa	[ebp-80],xmm7
 	lea	esi,[128+esi]
 	lea	edi,[128+edi]
-	jmp	NEAR L$009outer_loop
+	jmp	NEAR L$007outer_loop
 align	16
-L$009outer_loop:
+L$007outer_loop:
 	movdqa	xmm1,[ebp-112]
 	movdqa	xmm2,[ebp-96]
 	movdqa	xmm3,[ebp-80]
@@ -485,7 +473,7 @@ L$009outer_loop:
 	mov	edx,10
 	nop
 align	16
-L$010loop:
+L$008loop:
 	paddd	xmm0,xmm3
 	movdqa	xmm2,xmm3
 	pxor	xmm6,xmm0
@@ -685,7 +673,7 @@ L$010loop:
 	psrld	xmm1,25
 	por	xmm3,xmm1
 	dec	edx
-	jnz	NEAR L$010loop
+	jnz	NEAR L$008loop
 	movdqa	[ebx-64],xmm3
 	movdqa	[ebx],xmm4
 	movdqa	[16+ebx],xmm5
@@ -827,9 +815,9 @@ L$010loop:
 	movdqu	[64+edi],xmm7
 	lea	edi,[208+edi]
 	sub	ecx,256
-	jnc	NEAR L$009outer_loop
+	jnc	NEAR L$007outer_loop
 	add	ecx,256
-	jz	NEAR L$011done
+	jz	NEAR L$009done
 	mov	ebx,DWORD [520+esp]
 	lea	esi,[esi-128]
 	mov	edx,DWORD [516+esp]
@@ -839,7 +827,7 @@ L$010loop:
 	paddd	xmm2,[96+eax]
 	pand	xmm3,[112+eax]
 	por	xmm3,xmm2
-L$0081x:
+L$0061x:
 	movdqa	xmm0,[32+eax]
 	movdqu	xmm1,[edx]
 	movdqu	xmm2,[16+edx]
@@ -851,9 +839,9 @@ L$0081x:
 	movdqa	[32+esp],xmm2
 	movdqa	[48+esp],xmm3
 	mov	edx,10
-	jmp	NEAR L$012loop1x
+	jmp	NEAR L$010loop1x
 align	16
-L$013outer1x:
+L$011outer1x:
 	movdqa	xmm3,[80+eax]
 	movdqa	xmm0,[esp]
 	movdqa	xmm1,[16+esp]
@@ -861,9 +849,9 @@ L$013outer1x:
 	paddd	xmm3,[48+esp]
 	mov	edx,10
 	movdqa	[48+esp],xmm3
-	jmp	NEAR L$012loop1x
+	jmp	NEAR L$010loop1x
 align	16
-L$012loop1x:
+L$010loop1x:
 	paddd	xmm0,xmm1
 	pxor	xmm3,xmm0
 db	102,15,56,0,222
@@ -908,13 +896,13 @@ db	102,15,56,0,223
 	pshufd	xmm1,xmm1,147
 	pshufd	xmm3,xmm3,57
 	dec	edx
-	jnz	NEAR L$012loop1x
+	jnz	NEAR L$010loop1x
 	paddd	xmm0,[esp]
 	paddd	xmm1,[16+esp]
 	paddd	xmm2,[32+esp]
 	paddd	xmm3,[48+esp]
 	cmp	ecx,64
-	jb	NEAR L$014tail
+	jb	NEAR L$012tail
 	movdqu	xmm4,[esi]
 	movdqu	xmm5,[16+esi]
 	pxor	xmm0,xmm4
@@ -930,9 +918,9 @@ db	102,15,56,0,223
 	movdqu	[48+edi],xmm3
 	lea	edi,[64+edi]
 	sub	ecx,64
-	jnz	NEAR L$013outer1x
-	jmp	NEAR L$011done
-L$014tail:
+	jnz	NEAR L$011outer1x
+	jmp	NEAR L$009done
+L$012tail:
 	movdqa	[esp],xmm0
 	movdqa	[16+esp],xmm1
 	movdqa	[32+esp],xmm2
@@ -940,15 +928,15 @@ L$014tail:
 	xor	eax,eax
 	xor	edx,edx
 	xor	ebp,ebp
-L$015tail_loop:
+L$013tail_loop:
 	mov	al,BYTE [ebp*1+esp]
 	mov	dl,BYTE [ebp*1+esi]
 	lea	ebp,[1+ebp]
 	xor	al,dl
 	mov	BYTE [ebp*1+edi-1],al
 	dec	ecx
-	jnz	NEAR L$015tail_loop
-L$011done:
+	jnz	NEAR L$013tail_loop
+L$009done:
 	mov	esp,DWORD [512+esp]
 	pop	edi
 	pop	esi
@@ -970,8 +958,6 @@ db	67,104,97,67,104,97,50,48,32,102,111,114,32,120,56,54
 db	44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32
 db	60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111
 db	114,103,62,0
-segment	.bss
-common	_OPENSSL_ia32cap_P 16
 %else
 ; Work around https://bugzilla.nasm.us/show_bug.cgi?id=3392738
 ret