diff --git a/generated-src/linux-x86/crypto/fipsmodule/sha1-586.S b/generated-src/linux-x86/crypto/fipsmodule/sha1-586.S
index eb59f2ba9a..0e5754fe20 100644
--- a/generated-src/linux-x86/crypto/fipsmodule/sha1-586.S
+++ b/generated-src/linux-x86/crypto/fipsmodule/sha1-586.S
@@ -5,36 +5,16 @@
 
 #if !defined(OPENSSL_NO_ASM) && defined(OPENSSL_X86) && defined(__ELF__)
 .text
-.globl	sha1_block_data_order
-.hidden	sha1_block_data_order
-.type	sha1_block_data_order,@function
+.globl	sha1_block_data_order_nohw
+.hidden	sha1_block_data_order_nohw
+.type	sha1_block_data_order_nohw,@function
 .align	16
-sha1_block_data_order:
-.L_sha1_block_data_order_begin:
+sha1_block_data_order_nohw:
+.L_sha1_block_data_order_nohw_begin:
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
 	pushl	%edi
-	call	.L000pic_point
-.L000pic_point:
-	popl	%ebp
-	leal	OPENSSL_ia32cap_P-.L000pic_point(%ebp),%esi
-	leal	.LK_XX_XX-.L000pic_point(%ebp),%ebp
-	movl	(%esi),%eax
-	movl	4(%esi),%edx
-	testl	$512,%edx
-	jz	.L001x86
-	movl	8(%esi),%ecx
-	testl	$16777216,%eax
-	jz	.L001x86
-	andl	$268435456,%edx
-	andl	$1073741824,%eax
-	orl	%edx,%eax
-	cmpl	$1342177280,%eax
-	je	.Lavx_shortcut
-	jmp	.Lssse3_shortcut
-.align	16
-.L001x86:
 	movl	20(%esp),%ebp
 	movl	24(%esp),%esi
 	movl	28(%esp),%eax
@@ -43,9 +23,9 @@ sha1_block_data_order:
 	addl	%esi,%eax
 	movl	%eax,104(%esp)
 	movl	16(%ebp),%edi
-	jmp	.L002loop
+	jmp	.L000loop
 .align	16
-.L002loop:
+.L000loop:
 	movl	(%esi),%eax
 	movl	4(%esi),%ebx
 	movl	8(%esi),%ecx
@@ -1392,27 +1372,28 @@ sha1_block_data_order:
 	movl	%ebx,12(%ebp)
 	movl	%edx,%esi
 	movl	%ecx,16(%ebp)
-	jb	.L002loop
+	jb	.L000loop
 	addl	$76,%esp
 	popl	%edi
 	popl	%esi
 	popl	%ebx
 	popl	%ebp
 	ret
-.size	sha1_block_data_order,.-.L_sha1_block_data_order_begin
-.hidden	_sha1_block_data_order_ssse3
-.type	_sha1_block_data_order_ssse3,@function
+.size	sha1_block_data_order_nohw,.-.L_sha1_block_data_order_nohw_begin
+.globl	sha1_block_data_order_ssse3
+.hidden	sha1_block_data_order_ssse3
+.type	sha1_block_data_order_ssse3,@function
 .align	16
-_sha1_block_data_order_ssse3:
+sha1_block_data_order_ssse3:
+.L_sha1_block_data_order_ssse3_begin:
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
 	pushl	%edi
-	call	.L003pic_point
-.L003pic_point:
+	call	.L001pic_point
+.L001pic_point:
 	popl	%ebp
-	leal	.LK_XX_XX-.L003pic_point(%ebp),%ebp
-.Lssse3_shortcut:
+	leal	.LK_XX_XX-.L001pic_point(%ebp),%ebp
 	movdqa	(%ebp),%xmm7
 	movdqa	16(%ebp),%xmm0
 	movdqa	32(%ebp),%xmm1
@@ -1464,9 +1445,9 @@ _sha1_block_data_order_ssse3:
 	xorl	%edx,%ebp
 	pshufd	$238,%xmm0,%xmm4
 	andl	%ebp,%esi
-	jmp	.L004loop
+	jmp	.L002loop
 .align	16
-.L004loop:
+.L002loop:
 	rorl	$2,%ebx
 	xorl	%edx,%esi
 	movl	%eax,%ebp
@@ -2369,7 +2350,7 @@ _sha1_block_data_order_ssse3:
 	addl	%edx,%ecx
 	movl	196(%esp),%ebp
 	cmpl	200(%esp),%ebp
-	je	.L005done
+	je	.L003done
 	movdqa	160(%esp),%xmm7
 	movdqa	176(%esp),%xmm6
 	movdqu	(%ebp),%xmm0
@@ -2504,9 +2485,9 @@ _sha1_block_data_order_ssse3:
 	pshufd	$238,%xmm0,%xmm4
 	andl	%ebx,%esi
 	movl	%ebp,%ebx
-	jmp	.L004loop
+	jmp	.L002loop
 .align	16
-.L005done:
+.L003done:
 	addl	16(%esp),%ebx
 	xorl	%edi,%esi
 	movl	%ecx,%ebp
@@ -2619,20 +2600,21 @@ _sha1_block_data_order_ssse3:
 	popl	%ebx
 	popl	%ebp
 	ret
-.size	_sha1_block_data_order_ssse3,.-_sha1_block_data_order_ssse3
-.hidden	_sha1_block_data_order_avx
-.type	_sha1_block_data_order_avx,@function
+.size	sha1_block_data_order_ssse3,.-.L_sha1_block_data_order_ssse3_begin
+.globl	sha1_block_data_order_avx
+.hidden	sha1_block_data_order_avx
+.type	sha1_block_data_order_avx,@function
 .align	16
-_sha1_block_data_order_avx:
+sha1_block_data_order_avx:
+.L_sha1_block_data_order_avx_begin:
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
 	pushl	%edi
-	call	.L006pic_point
-.L006pic_point:
+	call	.L004pic_point
+.L004pic_point:
 	popl	%ebp
-	leal	.LK_XX_XX-.L006pic_point(%ebp),%ebp
-.Lavx_shortcut:
+	leal	.LK_XX_XX-.L004pic_point(%ebp),%ebp
 	vzeroall
 	vmovdqa	(%ebp),%xmm7
 	vmovdqa	16(%ebp),%xmm0
@@ -2681,9 +2663,9 @@ _sha1_block_data_order_avx:
 	xorl	%edx,%ebp
 	vmovdqa	%xmm6,32(%esp)
 	andl	%ebp,%esi
-	jmp	.L007loop
+	jmp	.L005loop
 .align	16
-.L007loop:
+.L005loop:
 	shrdl	$2,%ebx,%ebx
 	xorl	%edx,%esi
 	vpalignr	$8,%xmm0,%xmm1,%xmm4
@@ -3543,7 +3525,7 @@ _sha1_block_data_order_avx:
 	addl	%edx,%ecx
 	movl	196(%esp),%ebp
 	cmpl	200(%esp),%ebp
-	je	.L008done
+	je	.L006done
 	vmovdqa	160(%esp),%xmm7
 	vmovdqa	176(%esp),%xmm6
 	vmovdqu	(%ebp),%xmm0
@@ -3674,9 +3656,9 @@ _sha1_block_data_order_avx:
 	movl	%esi,%ebp
 	andl	%ebx,%esi
 	movl	%ebp,%ebx
-	jmp	.L007loop
+	jmp	.L005loop
 .align	16
-.L008done:
+.L006done:
 	addl	16(%esp),%ebx
 	xorl	%edi,%esi
 	movl	%ecx,%ebp
@@ -3790,7 +3772,7 @@ _sha1_block_data_order_avx:
 	popl	%ebx
 	popl	%ebp
 	ret
-.size	_sha1_block_data_order_avx,.-_sha1_block_data_order_avx
+.size	sha1_block_data_order_avx,.-.L_sha1_block_data_order_avx_begin
 .align	64
 .LK_XX_XX:
 .long	1518500249,1518500249,1518500249,1518500249
diff --git a/generated-src/linux-x86/crypto/fipsmodule/sha256-586.S b/generated-src/linux-x86/crypto/fipsmodule/sha256-586.S
index ee41b78cbf..41b3759d36 100644
--- a/generated-src/linux-x86/crypto/fipsmodule/sha256-586.S
+++ b/generated-src/linux-x86/crypto/fipsmodule/sha256-586.S
@@ -5,12 +5,12 @@
 
 #if !defined(OPENSSL_NO_ASM) && defined(OPENSSL_X86) && defined(__ELF__)
 .text
-.globl	sha256_block_data_order
-.hidden	sha256_block_data_order
-.type	sha256_block_data_order,@function
+.globl	sha256_block_data_order_nohw
+.hidden	sha256_block_data_order_nohw
+.type	sha256_block_data_order_nohw,@function
 .align	16
-sha256_block_data_order:
-.L_sha256_block_data_order_begin:
+sha256_block_data_order_nohw:
+.L_sha256_block_data_order_nohw_begin:
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -22,7 +22,7 @@ sha256_block_data_order:
 	call	.L000pic_point
 .L000pic_point:
 	popl	%ebp
-	leal	.L001K256-.L000pic_point(%ebp),%ebp
+	leal	.LK256-.L000pic_point(%ebp),%ebp
 	subl	$16,%esp
 	andl	$-64,%esp
 	shll	$6,%eax
@@ -31,29 +31,13 @@ sha256_block_data_order:
 	movl	%edi,4(%esp)
 	movl	%eax,8(%esp)
 	movl	%ebx,12(%esp)
-	leal	OPENSSL_ia32cap_P-.L001K256(%ebp),%edx
-	movl	(%edx),%ecx
-	movl	4(%edx),%ebx
-	testl	$1048576,%ecx
-	jnz	.L002loop
-	movl	8(%edx),%edx
-	testl	$16777216,%ecx
-	jz	.L003no_xmm
-	andl	$1073741824,%ecx
-	andl	$268435968,%ebx
-	orl	%ebx,%ecx
-	andl	$1342177280,%ecx
-	cmpl	$1342177280,%ecx
-	je	.L004AVX
-	testl	$512,%ebx
-	jnz	.L005SSSE3
-.L003no_xmm:
+.L001no_xmm:
 	subl	%edi,%eax
 	cmpl	$256,%eax
-	jae	.L006unrolled
-	jmp	.L002loop
+	jae	.L002unrolled
+	jmp	.L003loop
 .align	16
-.L002loop:
+.L003loop:
 	movl	(%edi),%eax
 	movl	4(%edi),%ebx
 	movl	8(%edi),%ecx
@@ -122,7 +106,7 @@ sha256_block_data_order:
 	movl	%ecx,28(%esp)
 	movl	%edi,32(%esp)
 .align	16
-.L00700_15:
+.L00400_15:
 	movl	%edx,%ecx
 	movl	24(%esp),%esi
 	rorl	$14,%ecx
@@ -160,11 +144,11 @@ sha256_block_data_order:
 	addl	$4,%ebp
 	addl	%ebx,%eax
 	cmpl	$3248222580,%esi
-	jne	.L00700_15
+	jne	.L00400_15
 	movl	156(%esp),%ecx
-	jmp	.L00816_63
+	jmp	.L00516_63
 .align	16
-.L00816_63:
+.L00516_63:
 	movl	%ecx,%ebx
 	movl	104(%esp),%esi
 	rorl	$11,%ecx
@@ -219,7 +203,7 @@ sha256_block_data_order:
 	addl	$4,%ebp
 	addl	%ebx,%eax
 	cmpl	$3329325298,%esi
-	jne	.L00816_63
+	jne	.L00516_63
 	movl	356(%esp),%esi
 	movl	8(%esp),%ebx
 	movl	16(%esp),%ecx
@@ -246,7 +230,7 @@ sha256_block_data_order:
 	leal	356(%esp),%esp
 	subl	$256,%ebp
 	cmpl	8(%esp),%edi
-	jb	.L002loop
+	jb	.L003loop
 	movl	12(%esp),%esp
 	popl	%edi
 	popl	%esi
@@ -254,7 +238,7 @@ sha256_block_data_order:
 	popl	%ebp
 	ret
 .align	64
-.L001K256:
+.LK256:
 .long	1116352408,1899447441,3049323471,3921009573,961987163,1508970993,2453635748,2870763221,3624381080,310598401,607225278,1426881987,1925078388,2162078206,2614888103,3248222580,3835390401,4022224774,264347078,604807628,770255983,1249150122,1555081692,1996064986,2554220882,2821834349,2952996808,3210313671,3336571891,3584528711,113926993,338241895,666307205,773529912,1294757372,1396182291,1695183700,1986661051,2177026350,2456956037,2730485921,2820302411,3259730800,3345764771,3516065817,3600352804,4094571909,275423344,430227734,506948616,659060556,883997877,958139571,1322822218,1537002063,1747873779,1955562222,2024104815,2227730452,2361852424,2428436474,2756734187,3204031479,3329325298
 .long	66051,67438087,134810123,202182159
 .byte	83,72,65,50,53,54,32,98,108,111,99,107,32,116,114,97
@@ -263,7 +247,7 @@ sha256_block_data_order:
 .byte	112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103
 .byte	62,0
 .align	16
-.L006unrolled:
+.L002unrolled:
 	leal	-96(%esp),%esp
 	movl	(%esi),%eax
 	movl	4(%esi),%ebp
@@ -280,9 +264,9 @@ sha256_block_data_order:
 	movl	%ebx,20(%esp)
 	movl	%ecx,24(%esp)
 	movl	%esi,28(%esp)
-	jmp	.L009grand_loop
+	jmp	.L006grand_loop
 .align	16
-.L009grand_loop:
+.L006grand_loop:
 	movl	(%edi),%ebx
 	movl	4(%edi),%ecx
 	bswap	%ebx
@@ -3162,15 +3146,40 @@ sha256_block_data_order:
 	movl	%ebx,24(%esp)
 	movl	%ecx,28(%esp)
 	cmpl	104(%esp),%edi
-	jb	.L009grand_loop
+	jb	.L006grand_loop
 	movl	108(%esp),%esp
 	popl	%edi
 	popl	%esi
 	popl	%ebx
 	popl	%ebp
 	ret
-.align	32
-.L005SSSE3:
+.size	sha256_block_data_order_nohw,.-.L_sha256_block_data_order_nohw_begin
+.globl	sha256_block_data_order_ssse3
+.hidden	sha256_block_data_order_ssse3
+.type	sha256_block_data_order_ssse3,@function
+.align	16
+sha256_block_data_order_ssse3:
+.L_sha256_block_data_order_ssse3_begin:
+	pushl	%ebp
+	pushl	%ebx
+	pushl	%esi
+	pushl	%edi
+	movl	20(%esp),%esi
+	movl	24(%esp),%edi
+	movl	28(%esp),%eax
+	movl	%esp,%ebx
+	call	.L007pic_point
+.L007pic_point:
+	popl	%ebp
+	leal	.LK256-.L007pic_point(%ebp),%ebp
+	subl	$16,%esp
+	andl	$-64,%esp
+	shll	$6,%eax
+	addl	%edi,%eax
+	movl	%esi,(%esp)
+	movl	%edi,4(%esp)
+	movl	%eax,8(%esp)
+	movl	%ebx,12(%esp)
 	leal	-96(%esp),%esp
 	movl	(%esi),%eax
 	movl	4(%esi),%ebx
@@ -3189,9 +3198,9 @@ sha256_block_data_order:
 	movl	%ecx,24(%esp)
 	movl	%esi,28(%esp)
 	movdqa	256(%ebp),%xmm7
-	jmp	.L010grand_ssse3
+	jmp	.L008grand_ssse3
 .align	16
-.L010grand_ssse3:
+.L008grand_ssse3:
 	movdqu	(%edi),%xmm0
 	movdqu	16(%edi),%xmm1
 	movdqu	32(%edi),%xmm2
@@ -3214,9 +3223,9 @@ sha256_block_data_order:
 	paddd	%xmm3,%xmm7
 	movdqa	%xmm6,64(%esp)
 	movdqa	%xmm7,80(%esp)
-	jmp	.L011ssse3_00_47
+	jmp	.L009ssse3_00_47
 .align	16
-.L011ssse3_00_47:
+.L009ssse3_00_47:
 	addl	$64,%ebp
 	movl	%edx,%ecx
 	movdqa	%xmm1,%xmm4
@@ -3859,7 +3868,7 @@ sha256_block_data_order:
 	addl	%ecx,%eax
 	movdqa	%xmm6,80(%esp)
 	cmpl	$66051,64(%ebp)
-	jne	.L011ssse3_00_47
+	jne	.L009ssse3_00_47
 	movl	%edx,%ecx
 	rorl	$14,%edx
 	movl	20(%esp),%esi
@@ -4373,15 +4382,40 @@ sha256_block_data_order:
 	movdqa	64(%ebp),%xmm7
 	subl	$192,%ebp
 	cmpl	104(%esp),%edi
-	jb	.L010grand_ssse3
+	jb	.L008grand_ssse3
 	movl	108(%esp),%esp
 	popl	%edi
 	popl	%esi
 	popl	%ebx
 	popl	%ebp
 	ret
-.align	32
-.L004AVX:
+.size	sha256_block_data_order_ssse3,.-.L_sha256_block_data_order_ssse3_begin
+.globl	sha256_block_data_order_avx
+.hidden	sha256_block_data_order_avx
+.type	sha256_block_data_order_avx,@function
+.align	16
+sha256_block_data_order_avx:
+.L_sha256_block_data_order_avx_begin:
+	pushl	%ebp
+	pushl	%ebx
+	pushl	%esi
+	pushl	%edi
+	movl	20(%esp),%esi
+	movl	24(%esp),%edi
+	movl	28(%esp),%eax
+	movl	%esp,%ebx
+	call	.L010pic_point
+.L010pic_point:
+	popl	%ebp
+	leal	.LK256-.L010pic_point(%ebp),%ebp
+	subl	$16,%esp
+	andl	$-64,%esp
+	shll	$6,%eax
+	addl	%edi,%eax
+	movl	%esi,(%esp)
+	movl	%edi,4(%esp)
+	movl	%eax,8(%esp)
+	movl	%ebx,12(%esp)
 	leal	-96(%esp),%esp
 	vzeroall
 	movl	(%esi),%eax
@@ -4401,9 +4435,9 @@ sha256_block_data_order:
 	movl	%ecx,24(%esp)
 	movl	%esi,28(%esp)
 	vmovdqa	256(%ebp),%xmm7
-	jmp	.L012grand_avx
+	jmp	.L011grand_avx
 .align	32
-.L012grand_avx:
+.L011grand_avx:
 	vmovdqu	(%edi),%xmm0
 	vmovdqu	16(%edi),%xmm1
 	vmovdqu	32(%edi),%xmm2
@@ -4422,9 +4456,9 @@ sha256_block_data_order:
 	vmovdqa	%xmm5,48(%esp)
 	vmovdqa	%xmm6,64(%esp)
 	vmovdqa	%xmm7,80(%esp)
-	jmp	.L013avx_00_47
+	jmp	.L012avx_00_47
 .align	16
-.L013avx_00_47:
+.L012avx_00_47:
 	addl	$64,%ebp
 	vpalignr	$4,%xmm0,%xmm1,%xmm4
 	movl	%edx,%ecx
@@ -5039,7 +5073,7 @@ sha256_block_data_order:
 	addl	%ecx,%eax
 	vmovdqa	%xmm6,80(%esp)
 	cmpl	$66051,64(%ebp)
-	jne	.L013avx_00_47
+	jne	.L012avx_00_47
 	movl	%edx,%ecx
 	shrdl	$14,%edx,%edx
 	movl	20(%esp),%esi
@@ -5553,7 +5587,7 @@ sha256_block_data_order:
 	vmovdqa	64(%ebp),%xmm7
 	subl	$192,%ebp
 	cmpl	104(%esp),%edi
-	jb	.L012grand_avx
+	jb	.L011grand_avx
 	movl	108(%esp),%esp
 	vzeroall
 	popl	%edi
@@ -5561,5 +5595,5 @@ sha256_block_data_order:
 	popl	%ebx
 	popl	%ebp
 	ret
-.size	sha256_block_data_order,.-.L_sha256_block_data_order_begin
+.size	sha256_block_data_order_avx,.-.L_sha256_block_data_order_avx_begin
 #endif  // !defined(OPENSSL_NO_ASM) && defined(OPENSSL_X86) && defined(__ELF__)
diff --git a/generated-src/mac-x86/crypto/fipsmodule/sha1-586.S b/generated-src/mac-x86/crypto/fipsmodule/sha1-586.S
index 76ee6bc5a3..f0ab02be58 100644
--- a/generated-src/mac-x86/crypto/fipsmodule/sha1-586.S
+++ b/generated-src/mac-x86/crypto/fipsmodule/sha1-586.S
@@ -5,35 +5,15 @@
 
 #if !defined(OPENSSL_NO_ASM) && defined(OPENSSL_X86) && defined(__APPLE__)
 .text
-.globl	_sha1_block_data_order
-.private_extern	_sha1_block_data_order
+.globl	_sha1_block_data_order_nohw
+.private_extern	_sha1_block_data_order_nohw
 .align	4
-_sha1_block_data_order:
-L_sha1_block_data_order_begin:
+_sha1_block_data_order_nohw:
+L_sha1_block_data_order_nohw_begin:
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
 	pushl	%edi
-	call	L000pic_point
-L000pic_point:
-	popl	%ebp
-	movl	L_OPENSSL_ia32cap_P$non_lazy_ptr-L000pic_point(%ebp),%esi
-	leal	LK_XX_XX-L000pic_point(%ebp),%ebp
-	movl	(%esi),%eax
-	movl	4(%esi),%edx
-	testl	$512,%edx
-	jz	L001x86
-	movl	8(%esi),%ecx
-	testl	$16777216,%eax
-	jz	L001x86
-	andl	$268435456,%edx
-	andl	$1073741824,%eax
-	orl	%edx,%eax
-	cmpl	$1342177280,%eax
-	je	Lavx_shortcut
-	jmp	Lssse3_shortcut
-.align	4,0x90
-L001x86:
 	movl	20(%esp),%ebp
 	movl	24(%esp),%esi
 	movl	28(%esp),%eax
@@ -42,9 +22,9 @@ L001x86:
 	addl	%esi,%eax
 	movl	%eax,104(%esp)
 	movl	16(%ebp),%edi
-	jmp	L002loop
+	jmp	L000loop
 .align	4,0x90
-L002loop:
+L000loop:
 	movl	(%esi),%eax
 	movl	4(%esi),%ebx
 	movl	8(%esi),%ecx
@@ -1391,25 +1371,26 @@ L002loop:
 	movl	%ebx,12(%ebp)
 	movl	%edx,%esi
 	movl	%ecx,16(%ebp)
-	jb	L002loop
+	jb	L000loop
 	addl	$76,%esp
 	popl	%edi
 	popl	%esi
 	popl	%ebx
 	popl	%ebp
 	ret
-.private_extern	__sha1_block_data_order_ssse3
+.globl	_sha1_block_data_order_ssse3
+.private_extern	_sha1_block_data_order_ssse3
 .align	4
-__sha1_block_data_order_ssse3:
+_sha1_block_data_order_ssse3:
+L_sha1_block_data_order_ssse3_begin:
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
 	pushl	%edi
-	call	L003pic_point
-L003pic_point:
+	call	L001pic_point
+L001pic_point:
 	popl	%ebp
-	leal	LK_XX_XX-L003pic_point(%ebp),%ebp
-Lssse3_shortcut:
+	leal	LK_XX_XX-L001pic_point(%ebp),%ebp
 	movdqa	(%ebp),%xmm7
 	movdqa	16(%ebp),%xmm0
 	movdqa	32(%ebp),%xmm1
@@ -1461,9 +1442,9 @@ Lssse3_shortcut:
 	xorl	%edx,%ebp
 	pshufd	$238,%xmm0,%xmm4
 	andl	%ebp,%esi
-	jmp	L004loop
+	jmp	L002loop
 .align	4,0x90
-L004loop:
+L002loop:
 	rorl	$2,%ebx
 	xorl	%edx,%esi
 	movl	%eax,%ebp
@@ -2366,7 +2347,7 @@ L004loop:
 	addl	%edx,%ecx
 	movl	196(%esp),%ebp
 	cmpl	200(%esp),%ebp
-	je	L005done
+	je	L003done
 	movdqa	160(%esp),%xmm7
 	movdqa	176(%esp),%xmm6
 	movdqu	(%ebp),%xmm0
@@ -2501,9 +2482,9 @@ L004loop:
 	pshufd	$238,%xmm0,%xmm4
 	andl	%ebx,%esi
 	movl	%ebp,%ebx
-	jmp	L004loop
+	jmp	L002loop
 .align	4,0x90
-L005done:
+L003done:
 	addl	16(%esp),%ebx
 	xorl	%edi,%esi
 	movl	%ecx,%ebp
@@ -2616,18 +2597,19 @@ L005done:
 	popl	%ebx
 	popl	%ebp
 	ret
-.private_extern	__sha1_block_data_order_avx
+.globl	_sha1_block_data_order_avx
+.private_extern	_sha1_block_data_order_avx
 .align	4
-__sha1_block_data_order_avx:
+_sha1_block_data_order_avx:
+L_sha1_block_data_order_avx_begin:
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
 	pushl	%edi
-	call	L006pic_point
-L006pic_point:
+	call	L004pic_point
+L004pic_point:
 	popl	%ebp
-	leal	LK_XX_XX-L006pic_point(%ebp),%ebp
-Lavx_shortcut:
+	leal	LK_XX_XX-L004pic_point(%ebp),%ebp
 	vzeroall
 	vmovdqa	(%ebp),%xmm7
 	vmovdqa	16(%ebp),%xmm0
@@ -2676,9 +2658,9 @@ Lavx_shortcut:
 	xorl	%edx,%ebp
 	vmovdqa	%xmm6,32(%esp)
 	andl	%ebp,%esi
-	jmp	L007loop
+	jmp	L005loop
 .align	4,0x90
-L007loop:
+L005loop:
 	shrdl	$2,%ebx,%ebx
 	xorl	%edx,%esi
 	vpalignr	$8,%xmm0,%xmm1,%xmm4
@@ -3538,7 +3520,7 @@ L007loop:
 	addl	%edx,%ecx
 	movl	196(%esp),%ebp
 	cmpl	200(%esp),%ebp
-	je	L008done
+	je	L006done
 	vmovdqa	160(%esp),%xmm7
 	vmovdqa	176(%esp),%xmm6
 	vmovdqu	(%ebp),%xmm0
@@ -3669,9 +3651,9 @@ L007loop:
 	movl	%esi,%ebp
 	andl	%ebx,%esi
 	movl	%ebp,%ebx
-	jmp	L007loop
+	jmp	L005loop
 .align	4,0x90
-L008done:
+L006done:
 	addl	16(%esp),%ebx
 	xorl	%edi,%esi
 	movl	%ecx,%ebp
@@ -3797,8 +3779,4 @@ LK_XX_XX:
 .byte	102,111,114,109,32,102,111,114,32,120,56,54,44,32,67,82
 .byte	89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112
 .byte	114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
-.section __IMPORT,__pointers,non_lazy_symbol_pointers
-L_OPENSSL_ia32cap_P$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/mac-x86/crypto/fipsmodule/sha256-586.S b/generated-src/mac-x86/crypto/fipsmodule/sha256-586.S
index d43510a491..8e74e68620 100644
--- a/generated-src/mac-x86/crypto/fipsmodule/sha256-586.S
+++ b/generated-src/mac-x86/crypto/fipsmodule/sha256-586.S
@@ -5,11 +5,11 @@
 
 #if !defined(OPENSSL_NO_ASM) && defined(OPENSSL_X86) && defined(__APPLE__)
 .text
-.globl	_sha256_block_data_order
-.private_extern	_sha256_block_data_order
+.globl	_sha256_block_data_order_nohw
+.private_extern	_sha256_block_data_order_nohw
 .align	4
-_sha256_block_data_order:
-L_sha256_block_data_order_begin:
+_sha256_block_data_order_nohw:
+L_sha256_block_data_order_nohw_begin:
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -21,7 +21,7 @@ L_sha256_block_data_order_begin:
 	call	L000pic_point
 L000pic_point:
 	popl	%ebp
-	leal	L001K256-L000pic_point(%ebp),%ebp
+	leal	LK256-L000pic_point(%ebp),%ebp
 	subl	$16,%esp
 	andl	$-64,%esp
 	shll	$6,%eax
@@ -30,29 +30,13 @@ L000pic_point:
 	movl	%edi,4(%esp)
 	movl	%eax,8(%esp)
 	movl	%ebx,12(%esp)
-	movl	L_OPENSSL_ia32cap_P$non_lazy_ptr-L001K256(%ebp),%edx
-	movl	(%edx),%ecx
-	movl	4(%edx),%ebx
-	testl	$1048576,%ecx
-	jnz	L002loop
-	movl	8(%edx),%edx
-	testl	$16777216,%ecx
-	jz	L003no_xmm
-	andl	$1073741824,%ecx
-	andl	$268435968,%ebx
-	orl	%ebx,%ecx
-	andl	$1342177280,%ecx
-	cmpl	$1342177280,%ecx
-	je	L004AVX
-	testl	$512,%ebx
-	jnz	L005SSSE3
-L003no_xmm:
+L001no_xmm:
 	subl	%edi,%eax
 	cmpl	$256,%eax
-	jae	L006unrolled
-	jmp	L002loop
+	jae	L002unrolled
+	jmp	L003loop
 .align	4,0x90
-L002loop:
+L003loop:
 	movl	(%edi),%eax
 	movl	4(%edi),%ebx
 	movl	8(%edi),%ecx
@@ -121,7 +105,7 @@ L002loop:
 	movl	%ecx,28(%esp)
 	movl	%edi,32(%esp)
 .align	4,0x90
-L00700_15:
+L00400_15:
 	movl	%edx,%ecx
 	movl	24(%esp),%esi
 	rorl	$14,%ecx
@@ -159,11 +143,11 @@ L00700_15:
 	addl	$4,%ebp
 	addl	%ebx,%eax
 	cmpl	$3248222580,%esi
-	jne	L00700_15
+	jne	L00400_15
 	movl	156(%esp),%ecx
-	jmp	L00816_63
+	jmp	L00516_63
 .align	4,0x90
-L00816_63:
+L00516_63:
 	movl	%ecx,%ebx
 	movl	104(%esp),%esi
 	rorl	$11,%ecx
@@ -218,7 +202,7 @@ L00816_63:
 	addl	$4,%ebp
 	addl	%ebx,%eax
 	cmpl	$3329325298,%esi
-	jne	L00816_63
+	jne	L00516_63
 	movl	356(%esp),%esi
 	movl	8(%esp),%ebx
 	movl	16(%esp),%ecx
@@ -245,7 +229,7 @@ L00816_63:
 	leal	356(%esp),%esp
 	subl	$256,%ebp
 	cmpl	8(%esp),%edi
-	jb	L002loop
+	jb	L003loop
 	movl	12(%esp),%esp
 	popl	%edi
 	popl	%esi
@@ -253,7 +237,7 @@ L00816_63:
 	popl	%ebp
 	ret
 .align	6,0x90
-L001K256:
+LK256:
 .long	1116352408,1899447441,3049323471,3921009573,961987163,1508970993,2453635748,2870763221,3624381080,310598401,607225278,1426881987,1925078388,2162078206,2614888103,3248222580,3835390401,4022224774,264347078,604807628,770255983,1249150122,1555081692,1996064986,2554220882,2821834349,2952996808,3210313671,3336571891,3584528711,113926993,338241895,666307205,773529912,1294757372,1396182291,1695183700,1986661051,2177026350,2456956037,2730485921,2820302411,3259730800,3345764771,3516065817,3600352804,4094571909,275423344,430227734,506948616,659060556,883997877,958139571,1322822218,1537002063,1747873779,1955562222,2024104815,2227730452,2361852424,2428436474,2756734187,3204031479,3329325298
 .long	66051,67438087,134810123,202182159
 .byte	83,72,65,50,53,54,32,98,108,111,99,107,32,116,114,97
@@ -262,7 +246,7 @@ L001K256:
 .byte	112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103
 .byte	62,0
 .align	4,0x90
-L006unrolled:
+L002unrolled:
 	leal	-96(%esp),%esp
 	movl	(%esi),%eax
 	movl	4(%esi),%ebp
@@ -279,9 +263,9 @@ L006unrolled:
 	movl	%ebx,20(%esp)
 	movl	%ecx,24(%esp)
 	movl	%esi,28(%esp)
-	jmp	L009grand_loop
+	jmp	L006grand_loop
 .align	4,0x90
-L009grand_loop:
+L006grand_loop:
 	movl	(%edi),%ebx
 	movl	4(%edi),%ecx
 	bswap	%ebx
@@ -3161,15 +3145,38 @@ L009grand_loop:
 	movl	%ebx,24(%esp)
 	movl	%ecx,28(%esp)
 	cmpl	104(%esp),%edi
-	jb	L009grand_loop
+	jb	L006grand_loop
 	movl	108(%esp),%esp
 	popl	%edi
 	popl	%esi
 	popl	%ebx
 	popl	%ebp
 	ret
-.align	5,0x90
-L005SSSE3:
+.globl	_sha256_block_data_order_ssse3
+.private_extern	_sha256_block_data_order_ssse3
+.align	4
+_sha256_block_data_order_ssse3:
+L_sha256_block_data_order_ssse3_begin:
+	pushl	%ebp
+	pushl	%ebx
+	pushl	%esi
+	pushl	%edi
+	movl	20(%esp),%esi
+	movl	24(%esp),%edi
+	movl	28(%esp),%eax
+	movl	%esp,%ebx
+	call	L007pic_point
+L007pic_point:
+	popl	%ebp
+	leal	LK256-L007pic_point(%ebp),%ebp
+	subl	$16,%esp
+	andl	$-64,%esp
+	shll	$6,%eax
+	addl	%edi,%eax
+	movl	%esi,(%esp)
+	movl	%edi,4(%esp)
+	movl	%eax,8(%esp)
+	movl	%ebx,12(%esp)
 	leal	-96(%esp),%esp
 	movl	(%esi),%eax
 	movl	4(%esi),%ebx
@@ -3188,9 +3195,9 @@ L005SSSE3:
 	movl	%ecx,24(%esp)
 	movl	%esi,28(%esp)
 	movdqa	256(%ebp),%xmm7
-	jmp	L010grand_ssse3
+	jmp	L008grand_ssse3
 .align	4,0x90
-L010grand_ssse3:
+L008grand_ssse3:
 	movdqu	(%edi),%xmm0
 	movdqu	16(%edi),%xmm1
 	movdqu	32(%edi),%xmm2
@@ -3213,9 +3220,9 @@ L010grand_ssse3:
 	paddd	%xmm3,%xmm7
 	movdqa	%xmm6,64(%esp)
 	movdqa	%xmm7,80(%esp)
-	jmp	L011ssse3_00_47
+	jmp	L009ssse3_00_47
 .align	4,0x90
-L011ssse3_00_47:
+L009ssse3_00_47:
 	addl	$64,%ebp
 	movl	%edx,%ecx
 	movdqa	%xmm1,%xmm4
@@ -3858,7 +3865,7 @@ L011ssse3_00_47:
 	addl	%ecx,%eax
 	movdqa	%xmm6,80(%esp)
 	cmpl	$66051,64(%ebp)
-	jne	L011ssse3_00_47
+	jne	L009ssse3_00_47
 	movl	%edx,%ecx
 	rorl	$14,%edx
 	movl	20(%esp),%esi
@@ -4372,15 +4379,38 @@ L011ssse3_00_47:
 	movdqa	64(%ebp),%xmm7
 	subl	$192,%ebp
 	cmpl	104(%esp),%edi
-	jb	L010grand_ssse3
+	jb	L008grand_ssse3
 	movl	108(%esp),%esp
 	popl	%edi
 	popl	%esi
 	popl	%ebx
 	popl	%ebp
 	ret
-.align	5,0x90
-L004AVX:
+.globl	_sha256_block_data_order_avx
+.private_extern	_sha256_block_data_order_avx
+.align	4
+_sha256_block_data_order_avx:
+L_sha256_block_data_order_avx_begin:
+	pushl	%ebp
+	pushl	%ebx
+	pushl	%esi
+	pushl	%edi
+	movl	20(%esp),%esi
+	movl	24(%esp),%edi
+	movl	28(%esp),%eax
+	movl	%esp,%ebx
+	call	L010pic_point
+L010pic_point:
+	popl	%ebp
+	leal	LK256-L010pic_point(%ebp),%ebp
+	subl	$16,%esp
+	andl	$-64,%esp
+	shll	$6,%eax
+	addl	%edi,%eax
+	movl	%esi,(%esp)
+	movl	%edi,4(%esp)
+	movl	%eax,8(%esp)
+	movl	%ebx,12(%esp)
 	leal	-96(%esp),%esp
 	vzeroall
 	movl	(%esi),%eax
@@ -4400,9 +4430,9 @@ L004AVX:
 	movl	%ecx,24(%esp)
 	movl	%esi,28(%esp)
 	vmovdqa	256(%ebp),%xmm7
-	jmp	L012grand_avx
+	jmp	L011grand_avx
 .align	5,0x90
-L012grand_avx:
+L011grand_avx:
 	vmovdqu	(%edi),%xmm0
 	vmovdqu	16(%edi),%xmm1
 	vmovdqu	32(%edi),%xmm2
@@ -4421,9 +4451,9 @@ L012grand_avx:
 	vmovdqa	%xmm5,48(%esp)
 	vmovdqa	%xmm6,64(%esp)
 	vmovdqa	%xmm7,80(%esp)
-	jmp	L013avx_00_47
+	jmp	L012avx_00_47
 .align	4,0x90
-L013avx_00_47:
+L012avx_00_47:
 	addl	$64,%ebp
 	vpalignr	$4,%xmm0,%xmm1,%xmm4
 	movl	%edx,%ecx
@@ -5038,7 +5068,7 @@ L013avx_00_47:
 	addl	%ecx,%eax
 	vmovdqa	%xmm6,80(%esp)
 	cmpl	$66051,64(%ebp)
-	jne	L013avx_00_47
+	jne	L012avx_00_47
 	movl	%edx,%ecx
 	shrdl	$14,%edx,%edx
 	movl	20(%esp),%esi
@@ -5552,7 +5582,7 @@ L013avx_00_47:
 	vmovdqa	64(%ebp),%xmm7
 	subl	$192,%ebp
 	cmpl	104(%esp),%edi
-	jb	L012grand_avx
+	jb	L011grand_avx
 	movl	108(%esp),%esp
 	vzeroall
 	popl	%edi
@@ -5560,8 +5590,4 @@ L013avx_00_47:
 	popl	%ebx
 	popl	%ebp
 	ret
-.section __IMPORT,__pointers,non_lazy_symbol_pointers
-L_OPENSSL_ia32cap_P$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/fipsmodule/sha1-586.asm b/generated-src/win-x86/crypto/fipsmodule/sha1-586.asm
index ae30b3d13d..8cff61f50f 100644
--- a/generated-src/win-x86/crypto/fipsmodule/sha1-586.asm
+++ b/generated-src/win-x86/crypto/fipsmodule/sha1-586.asm
@@ -11,35 +11,14 @@ section	.text	code align=64
 %else
 section	.text	code
 %endif
-;extern	_OPENSSL_ia32cap_P
-global	_sha1_block_data_order
+global	_sha1_block_data_order_nohw
 align	16
-_sha1_block_data_order:
-L$_sha1_block_data_order_begin:
+_sha1_block_data_order_nohw:
+L$_sha1_block_data_order_nohw_begin:
 	push	ebp
 	push	ebx
 	push	esi
 	push	edi
-	call	L$000pic_point
-L$000pic_point:
-	pop	ebp
-	lea	esi,[_OPENSSL_ia32cap_P]
-	lea	ebp,[(L$K_XX_XX-L$000pic_point)+ebp]
-	mov	eax,DWORD [esi]
-	mov	edx,DWORD [4+esi]
-	test	edx,512
-	jz	NEAR L$001x86
-	mov	ecx,DWORD [8+esi]
-	test	eax,16777216
-	jz	NEAR L$001x86
-	and	edx,268435456
-	and	eax,1073741824
-	or	eax,edx
-	cmp	eax,1342177280
-	je	NEAR L$avx_shortcut
-	jmp	NEAR L$ssse3_shortcut
-align	16
-L$001x86:
 	mov	ebp,DWORD [20+esp]
 	mov	esi,DWORD [24+esp]
 	mov	eax,DWORD [28+esp]
@@ -48,9 +27,9 @@ L$001x86:
 	add	eax,esi
 	mov	DWORD [104+esp],eax
 	mov	edi,DWORD [16+ebp]
-	jmp	NEAR L$002loop
+	jmp	NEAR L$000loop
 align	16
-L$002loop:
+L$000loop:
 	mov	eax,DWORD [esi]
 	mov	ebx,DWORD [4+esi]
 	mov	ecx,DWORD [8+esi]
@@ -1397,24 +1376,25 @@ L$002loop:
 	mov	DWORD [12+ebp],ebx
 	mov	esi,edx
 	mov	DWORD [16+ebp],ecx
-	jb	NEAR L$002loop
+	jb	NEAR L$000loop
 	add	esp,76
 	pop	edi
 	pop	esi
 	pop	ebx
 	pop	ebp
 	ret
+global	_sha1_block_data_order_ssse3
 align	16
-__sha1_block_data_order_ssse3:
+_sha1_block_data_order_ssse3:
+L$_sha1_block_data_order_ssse3_begin:
 	push	ebp
 	push	ebx
 	push	esi
 	push	edi
-	call	L$003pic_point
-L$003pic_point:
+	call	L$001pic_point
+L$001pic_point:
 	pop	ebp
-	lea	ebp,[(L$K_XX_XX-L$003pic_point)+ebp]
-L$ssse3_shortcut:
+	lea	ebp,[(L$K_XX_XX-L$001pic_point)+ebp]
 	movdqa	xmm7,[ebp]
 	movdqa	xmm0,[16+ebp]
 	movdqa	xmm1,[32+ebp]
@@ -1466,9 +1446,9 @@ db	102,15,56,0,222
 	xor	ebp,edx
 	pshufd	xmm4,xmm0,238
 	and	esi,ebp
-	jmp	NEAR L$004loop
+	jmp	NEAR L$002loop
 align	16
-L$004loop:
+L$002loop:
 	ror	ebx,2
 	xor	esi,edx
 	mov	ebp,eax
@@ -2371,7 +2351,7 @@ L$004loop:
 	add	ecx,edx
 	mov	ebp,DWORD [196+esp]
 	cmp	ebp,DWORD [200+esp]
-	je	NEAR L$005done
+	je	NEAR L$003done
 	movdqa	xmm7,[160+esp]
 	movdqa	xmm6,[176+esp]
 	movdqu	xmm0,[ebp]
@@ -2506,9 +2486,9 @@ db	102,15,56,0,222
 	pshufd	xmm4,xmm0,238
 	and	esi,ebx
 	mov	ebx,ebp
-	jmp	NEAR L$004loop
+	jmp	NEAR L$002loop
 align	16
-L$005done:
+L$003done:
 	add	ebx,DWORD [16+esp]
 	xor	esi,edi
 	mov	ebp,ecx
@@ -2621,17 +2601,18 @@ L$005done:
 	pop	ebx
 	pop	ebp
 	ret
+global	_sha1_block_data_order_avx
 align	16
-__sha1_block_data_order_avx:
+_sha1_block_data_order_avx:
+L$_sha1_block_data_order_avx_begin:
 	push	ebp
 	push	ebx
 	push	esi
 	push	edi
-	call	L$006pic_point
-L$006pic_point:
+	call	L$004pic_point
+L$004pic_point:
 	pop	ebp
-	lea	ebp,[(L$K_XX_XX-L$006pic_point)+ebp]
-L$avx_shortcut:
+	lea	ebp,[(L$K_XX_XX-L$004pic_point)+ebp]
 	vzeroall
 	vmovdqa	xmm7,[ebp]
 	vmovdqa	xmm0,[16+ebp]
@@ -2680,9 +2661,9 @@ L$avx_shortcut:
 	xor	ebp,edx
 	vmovdqa	[32+esp],xmm6
 	and	esi,ebp
-	jmp	NEAR L$007loop
+	jmp	NEAR L$005loop
 align	16
-L$007loop:
+L$005loop:
 	shrd	ebx,ebx,2
 	xor	esi,edx
 	vpalignr	xmm4,xmm1,xmm0,8
@@ -3542,7 +3523,7 @@ L$007loop:
 	add	ecx,edx
 	mov	ebp,DWORD [196+esp]
 	cmp	ebp,DWORD [200+esp]
-	je	NEAR L$008done
+	je	NEAR L$006done
 	vmovdqa	xmm7,[160+esp]
 	vmovdqa	xmm6,[176+esp]
 	vmovdqu	xmm0,[ebp]
@@ -3673,9 +3654,9 @@ L$007loop:
 	mov	ebp,esi
 	and	esi,ebx
 	mov	ebx,ebp
-	jmp	NEAR L$007loop
+	jmp	NEAR L$005loop
 align	16
-L$008done:
+L$006done:
 	add	ebx,DWORD [16+esp]
 	xor	esi,edi
 	mov	ebp,ecx
@@ -3801,8 +3782,6 @@ db	83,72,65,49,32,98,108,111,99,107,32,116,114,97,110,115
 db	102,111,114,109,32,102,111,114,32,120,56,54,44,32,67,82
 db	89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112
 db	114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
-segment	.bss
-common	_OPENSSL_ia32cap_P 16
 %else
 ; Work around https://bugzilla.nasm.us/show_bug.cgi?id=3392738
 ret
diff --git a/generated-src/win-x86/crypto/fipsmodule/sha256-586.asm b/generated-src/win-x86/crypto/fipsmodule/sha256-586.asm
index 434195bad4..61b3a6b199 100644
--- a/generated-src/win-x86/crypto/fipsmodule/sha256-586.asm
+++ b/generated-src/win-x86/crypto/fipsmodule/sha256-586.asm
@@ -11,11 +11,10 @@ section	.text	code align=64
 %else
 section	.text	code
 %endif
-;extern	_OPENSSL_ia32cap_P
-global	_sha256_block_data_order
+global	_sha256_block_data_order_nohw
 align	16
-_sha256_block_data_order:
-L$_sha256_block_data_order_begin:
+_sha256_block_data_order_nohw:
+L$_sha256_block_data_order_nohw_begin:
 	push	ebp
 	push	ebx
 	push	esi
@@ -27,7 +26,7 @@ L$_sha256_block_data_order_begin:
 	call	L$000pic_point
 L$000pic_point:
 	pop	ebp
-	lea	ebp,[(L$001K256-L$000pic_point)+ebp]
+	lea	ebp,[(L$K256-L$000pic_point)+ebp]
 	sub	esp,16
 	and	esp,-64
 	shl	eax,6
@@ -36,29 +35,13 @@ L$000pic_point:
 	mov	DWORD [4+esp],edi
 	mov	DWORD [8+esp],eax
 	mov	DWORD [12+esp],ebx
-	lea	edx,[_OPENSSL_ia32cap_P]
-	mov	ecx,DWORD [edx]
-	mov	ebx,DWORD [4+edx]
-	test	ecx,1048576
-	jnz	NEAR L$002loop
-	mov	edx,DWORD [8+edx]
-	test	ecx,16777216
-	jz	NEAR L$003no_xmm
-	and	ecx,1073741824
-	and	ebx,268435968
-	or	ecx,ebx
-	and	ecx,1342177280
-	cmp	ecx,1342177280
-	je	NEAR L$004AVX
-	test	ebx,512
-	jnz	NEAR L$005SSSE3
-L$003no_xmm:
+L$001no_xmm:
 	sub	eax,edi
 	cmp	eax,256
-	jae	NEAR L$006unrolled
-	jmp	NEAR L$002loop
+	jae	NEAR L$002unrolled
+	jmp	NEAR L$003loop
 align	16
-L$002loop:
+L$003loop:
 	mov	eax,DWORD [edi]
 	mov	ebx,DWORD [4+edi]
 	mov	ecx,DWORD [8+edi]
@@ -127,7 +110,7 @@ L$002loop:
 	mov	DWORD [28+esp],ecx
 	mov	DWORD [32+esp],edi
 align	16
-L$00700_15:
+L$00400_15:
 	mov	ecx,edx
 	mov	esi,DWORD [24+esp]
 	ror	ecx,14
@@ -165,11 +148,11 @@ L$00700_15:
 	add	ebp,4
 	add	eax,ebx
 	cmp	esi,3248222580
-	jne	NEAR L$00700_15
+	jne	NEAR L$00400_15
 	mov	ecx,DWORD [156+esp]
-	jmp	NEAR L$00816_63
+	jmp	NEAR L$00516_63
 align	16
-L$00816_63:
+L$00516_63:
 	mov	ebx,ecx
 	mov	esi,DWORD [104+esp]
 	ror	ecx,11
@@ -224,7 +207,7 @@ L$00816_63:
 	add	ebp,4
 	add	eax,ebx
 	cmp	esi,3329325298
-	jne	NEAR L$00816_63
+	jne	NEAR L$00516_63
 	mov	esi,DWORD [356+esp]
 	mov	ebx,DWORD [8+esp]
 	mov	ecx,DWORD [16+esp]
@@ -251,7 +234,7 @@ L$00816_63:
 	lea	esp,[356+esp]
 	sub	ebp,256
 	cmp	edi,DWORD [8+esp]
-	jb	NEAR L$002loop
+	jb	NEAR L$003loop
 	mov	esp,DWORD [12+esp]
 	pop	edi
 	pop	esi
@@ -259,7 +242,7 @@ L$00816_63:
 	pop	ebp
 	ret
 align	64
-L$001K256:
+L$K256:
 dd	1116352408,1899447441,3049323471,3921009573,961987163,1508970993,2453635748,2870763221,3624381080,310598401,607225278,1426881987,1925078388,2162078206,2614888103,3248222580,3835390401,4022224774,264347078,604807628,770255983,1249150122,1555081692,1996064986,2554220882,2821834349,2952996808,3210313671,3336571891,3584528711,113926993,338241895,666307205,773529912,1294757372,1396182291,1695183700,1986661051,2177026350,2456956037,2730485921,2820302411,3259730800,3345764771,3516065817,3600352804,4094571909,275423344,430227734,506948616,659060556,883997877,958139571,1322822218,1537002063,1747873779,1955562222,2024104815,2227730452,2361852424,2428436474,2756734187,3204031479,3329325298
 dd	66051,67438087,134810123,202182159
 db	83,72,65,50,53,54,32,98,108,111,99,107,32,116,114,97
@@ -268,7 +251,7 @@ db	67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97
 db	112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103
 db	62,0
 align	16
-L$006unrolled:
+L$002unrolled:
 	lea	esp,[esp-96]
 	mov	eax,DWORD [esi]
 	mov	ebp,DWORD [4+esi]
@@ -285,9 +268,9 @@ L$006unrolled:
 	mov	DWORD [20+esp],ebx
 	mov	DWORD [24+esp],ecx
 	mov	DWORD [28+esp],esi
-	jmp	NEAR L$009grand_loop
+	jmp	NEAR L$006grand_loop
 align	16
-L$009grand_loop:
+L$006grand_loop:
 	mov	ebx,DWORD [edi]
 	mov	ecx,DWORD [4+edi]
 	bswap	ebx
@@ -3167,15 +3150,37 @@ L$009grand_loop:
 	mov	DWORD [24+esp],ebx
 	mov	DWORD [28+esp],ecx
 	cmp	edi,DWORD [104+esp]
-	jb	NEAR L$009grand_loop
+	jb	NEAR L$006grand_loop
 	mov	esp,DWORD [108+esp]
 	pop	edi
 	pop	esi
 	pop	ebx
 	pop	ebp
 	ret
-align	32
-L$005SSSE3:
+global	_sha256_block_data_order_ssse3
+align	16
+_sha256_block_data_order_ssse3:
+L$_sha256_block_data_order_ssse3_begin:
+	push	ebp
+	push	ebx
+	push	esi
+	push	edi
+	mov	esi,DWORD [20+esp]
+	mov	edi,DWORD [24+esp]
+	mov	eax,DWORD [28+esp]
+	mov	ebx,esp
+	call	L$007pic_point
+L$007pic_point:
+	pop	ebp
+	lea	ebp,[(L$K256-L$007pic_point)+ebp]
+	sub	esp,16
+	and	esp,-64
+	shl	eax,6
+	add	eax,edi
+	mov	DWORD [esp],esi
+	mov	DWORD [4+esp],edi
+	mov	DWORD [8+esp],eax
+	mov	DWORD [12+esp],ebx
 	lea	esp,[esp-96]
 	mov	eax,DWORD [esi]
 	mov	ebx,DWORD [4+esi]
@@ -3194,9 +3199,9 @@ L$005SSSE3:
 	mov	DWORD [24+esp],ecx
 	mov	DWORD [28+esp],esi
 	movdqa	xmm7,[256+ebp]
-	jmp	NEAR L$010grand_ssse3
+	jmp	NEAR L$008grand_ssse3
 align	16
-L$010grand_ssse3:
+L$008grand_ssse3:
 	movdqu	xmm0,[edi]
 	movdqu	xmm1,[16+edi]
 	movdqu	xmm2,[32+edi]
@@ -3219,9 +3224,9 @@ db	102,15,56,0,223
 	paddd	xmm7,xmm3
 	movdqa	[64+esp],xmm6
 	movdqa	[80+esp],xmm7
-	jmp	NEAR L$011ssse3_00_47
+	jmp	NEAR L$009ssse3_00_47
 align	16
-L$011ssse3_00_47:
+L$009ssse3_00_47:
 	add	ebp,64
 	mov	ecx,edx
 	movdqa	xmm4,xmm1
@@ -3864,7 +3869,7 @@ db	102,15,58,15,249,4
 	add	eax,ecx
 	movdqa	[80+esp],xmm6
 	cmp	DWORD [64+ebp],66051
-	jne	NEAR L$011ssse3_00_47
+	jne	NEAR L$009ssse3_00_47
 	mov	ecx,edx
 	ror	edx,14
 	mov	esi,DWORD [20+esp]
@@ -4378,15 +4383,37 @@ db	102,15,58,15,249,4
 	movdqa	xmm7,[64+ebp]
 	sub	ebp,192
 	cmp	edi,DWORD [104+esp]
-	jb	NEAR L$010grand_ssse3
+	jb	NEAR L$008grand_ssse3
 	mov	esp,DWORD [108+esp]
 	pop	edi
 	pop	esi
 	pop	ebx
 	pop	ebp
 	ret
-align	32
-L$004AVX:
+global	_sha256_block_data_order_avx
+align	16
+_sha256_block_data_order_avx:
+L$_sha256_block_data_order_avx_begin:
+	push	ebp
+	push	ebx
+	push	esi
+	push	edi
+	mov	esi,DWORD [20+esp]
+	mov	edi,DWORD [24+esp]
+	mov	eax,DWORD [28+esp]
+	mov	ebx,esp
+	call	L$010pic_point
+L$010pic_point:
+	pop	ebp
+	lea	ebp,[(L$K256-L$010pic_point)+ebp]
+	sub	esp,16
+	and	esp,-64
+	shl	eax,6
+	add	eax,edi
+	mov	DWORD [esp],esi
+	mov	DWORD [4+esp],edi
+	mov	DWORD [8+esp],eax
+	mov	DWORD [12+esp],ebx
 	lea	esp,[esp-96]
 	vzeroall
 	mov	eax,DWORD [esi]
@@ -4406,9 +4433,9 @@ L$004AVX:
 	mov	DWORD [24+esp],ecx
 	mov	DWORD [28+esp],esi
 	vmovdqa	xmm7,[256+ebp]
-	jmp	NEAR L$012grand_avx
+	jmp	NEAR L$011grand_avx
 align	32
-L$012grand_avx:
+L$011grand_avx:
 	vmovdqu	xmm0,[edi]
 	vmovdqu	xmm1,[16+edi]
 	vmovdqu	xmm2,[32+edi]
@@ -4427,9 +4454,9 @@ L$012grand_avx:
 	vmovdqa	[48+esp],xmm5
 	vmovdqa	[64+esp],xmm6
 	vmovdqa	[80+esp],xmm7
-	jmp	NEAR L$013avx_00_47
+	jmp	NEAR L$012avx_00_47
 align	16
-L$013avx_00_47:
+L$012avx_00_47:
 	add	ebp,64
 	vpalignr	xmm4,xmm1,xmm0,4
 	mov	ecx,edx
@@ -5044,7 +5071,7 @@ L$013avx_00_47:
 	add	eax,ecx
 	vmovdqa	[80+esp],xmm6
 	cmp	DWORD [64+ebp],66051
-	jne	NEAR L$013avx_00_47
+	jne	NEAR L$012avx_00_47
 	mov	ecx,edx
 	shrd	edx,edx,14
 	mov	esi,DWORD [20+esp]
@@ -5558,7 +5585,7 @@ L$013avx_00_47:
 	vmovdqa	xmm7,[64+ebp]
 	sub	ebp,192
 	cmp	edi,DWORD [104+esp]
-	jb	NEAR L$012grand_avx
+	jb	NEAR L$011grand_avx
 	mov	esp,DWORD [108+esp]
 	vzeroall
 	pop	edi
@@ -5566,8 +5593,6 @@ L$013avx_00_47:
 	pop	ebx
 	pop	ebp
 	ret
-segment	.bss
-common	_OPENSSL_ia32cap_P 16
 %else
 ; Work around https://bugzilla.nasm.us/show_bug.cgi?id=3392738
 ret