external/boringssl: bump revision.

This change bumps the BoringSSL revision to the current tip-of-tree.

Change-Id: I91d5bf467e16e8d86cb19a4de873985f524e5faa

4 files changed, 1730 insertions, 1744 deletions

diff --git a/win-x86_64/crypto/bn/rsaz-avx2.asm b/win-x86_64/crypto/bn/rsaz-avx2.asm
index f9188f5..45d0fd4 100644
--- a/win-x86_64/crypto/bn/rsaz-avx2.asm
+++ b/win-x86_64/crypto/bn/rsaz-avx2.asm
@@ -1,29 +1,30 @@
-OPTION	DOTNAME
-.text$	SEGMENT ALIGN(256) 'CODE'
+default	rel
+%define XMMWORD
+%define YMMWORD
+%define ZMMWORD
+section	.text code align=64
 
-PUBLIC	rsaz_avx2_eligible
 
-rsaz_avx2_eligible	PROC PUBLIC
+global	rsaz_avx2_eligible
+
+rsaz_avx2_eligible:
 	xor	eax,eax
 	DB	0F3h,0C3h		;repret
-rsaz_avx2_eligible	ENDP
 
-PUBLIC	rsaz_1024_sqr_avx2
-PUBLIC	rsaz_1024_mul_avx2
-PUBLIC	rsaz_1024_norm2red_avx2
-PUBLIC	rsaz_1024_red2norm_avx2
-PUBLIC	rsaz_1024_scatter5_avx2
-PUBLIC	rsaz_1024_gather5_avx2
 
-rsaz_1024_sqr_avx2	PROC PUBLIC
-rsaz_1024_mul_avx2::
-rsaz_1024_norm2red_avx2::
-rsaz_1024_red2norm_avx2::
-rsaz_1024_scatter5_avx2::
-rsaz_1024_gather5_avx2::
-DB	00fh,00bh
+global	rsaz_1024_sqr_avx2
+global	rsaz_1024_mul_avx2
+global	rsaz_1024_norm2red_avx2
+global	rsaz_1024_red2norm_avx2
+global	rsaz_1024_scatter5_avx2
+global	rsaz_1024_gather5_avx2
+
+rsaz_1024_sqr_avx2:
+rsaz_1024_mul_avx2:
+rsaz_1024_norm2red_avx2:
+rsaz_1024_red2norm_avx2:
+rsaz_1024_scatter5_avx2:
+rsaz_1024_gather5_avx2:
+DB	0x0f,0x0b
 	DB	0F3h,0C3h		;repret
-rsaz_1024_sqr_avx2	ENDP
 
-.text$	ENDS
-END
diff --git a/win-x86_64/crypto/bn/rsaz-x86_64.asm b/win-x86_64/crypto/bn/rsaz-x86_64.asm
index 86e828d..04d5e39 100644
--- a/win-x86_64/crypto/bn/rsaz-x86_64.asm
+++ b/win-x86_64/crypto/bn/rsaz-x86_64.asm
@@ -1,21 +1,25 @@
-OPTION	DOTNAME
-.text$	SEGMENT ALIGN(256) 'CODE'
+default	rel
+%define XMMWORD
+%define YMMWORD
+%define ZMMWORD
+section	.text code align=64
 
-EXTERN	OPENSSL_ia32cap_P:NEAR
 
-PUBLIC	rsaz_512_sqr
+EXTERN	OPENSSL_ia32cap_P
+
+global	rsaz_512_sqr
 
 ALIGN	32
-rsaz_512_sqr	PROC PUBLIC
-	mov	QWORD PTR[8+rsp],rdi	;WIN64 prologue
-	mov	QWORD PTR[16+rsp],rsi
+rsaz_512_sqr:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
 	mov	rax,rsp
-$L$SEH_begin_rsaz_512_sqr::
+$L$SEH_begin_rsaz_512_sqr:
 	mov	rdi,rcx
 	mov	rsi,rdx
 	mov	rdx,r8
 	mov	rcx,r9
-	mov	r8,QWORD PTR[40+rsp]
+	mov	r8,QWORD[40+rsp]
 
 
 	push	rbx
@@ -26,50 +30,50 @@ $L$SEH_begin_rsaz_512_sqr::
 	push	r15
 
 	sub	rsp,128+24
-$L$sqr_body::
+$L$sqr_body:
 	mov	rbp,rdx
-	mov	rdx,QWORD PTR[rsi]
-	mov	rax,QWORD PTR[8+rsi]
-	mov	QWORD PTR[128+rsp],rcx
-	jmp	$L$oop_sqr
+	mov	rdx,QWORD[rsi]
+	mov	rax,QWORD[8+rsi]
+	mov	QWORD[128+rsp],rcx
+	jmp	NEAR $L$oop_sqr
 
 ALIGN	32
-$L$oop_sqr::
-	mov	DWORD PTR[((128+8))+rsp],r8d
+$L$oop_sqr:
+	mov	DWORD[((128+8))+rsp],r8d
 
 	mov	rbx,rdx
 	mul	rdx
 	mov	r8,rax
-	mov	rax,QWORD PTR[16+rsi]
+	mov	rax,QWORD[16+rsi]
 	mov	r9,rdx
 
 	mul	rbx
 	add	r9,rax
-	mov	rax,QWORD PTR[24+rsi]
+	mov	rax,QWORD[24+rsi]
 	mov	r10,rdx
 	adc	r10,0
 
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD PTR[32+rsi]
+	mov	rax,QWORD[32+rsi]
 	mov	r11,rdx
 	adc	r11,0
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD PTR[40+rsi]
+	mov	rax,QWORD[40+rsi]
 	mov	r12,rdx
 	adc	r12,0
 
 	mul	rbx
 	add	r12,rax
-	mov	rax,QWORD PTR[48+rsi]
+	mov	rax,QWORD[48+rsi]
 	mov	r13,rdx
 	adc	r13,0
 
 	mul	rbx
 	add	r13,rax
-	mov	rax,QWORD PTR[56+rsi]
+	mov	rax,QWORD[56+rsi]
 	mov	r14,rdx
 	adc	r14,0
 
@@ -84,25 +88,25 @@ $L$oop_sqr::
 	adc	r9,r9
 
 	mul	rax
-	mov	QWORD PTR[rsp],rax
+	mov	QWORD[rsp],rax
 	add	r8,rdx
 	adc	r9,0
 
-	mov	QWORD PTR[8+rsp],r8
+	mov	QWORD[8+rsp],r8
 	shr	rcx,63
 
 
-	mov	r8,QWORD PTR[8+rsi]
-	mov	rax,QWORD PTR[16+rsi]
+	mov	r8,QWORD[8+rsi]
+	mov	rax,QWORD[16+rsi]
 	mul	r8
 	add	r10,rax
-	mov	rax,QWORD PTR[24+rsi]
+	mov	rax,QWORD[24+rsi]
 	mov	rbx,rdx
 	adc	rbx,0
 
 	mul	r8
 	add	r11,rax
-	mov	rax,QWORD PTR[32+rsi]
+	mov	rax,QWORD[32+rsi]
 	adc	rdx,0
 	add	r11,rbx
 	mov	rbx,rdx
@@ -110,7 +114,7 @@ $L$oop_sqr::
 
 	mul	r8
 	add	r12,rax
-	mov	rax,QWORD PTR[40+rsi]
+	mov	rax,QWORD[40+rsi]
 	adc	rdx,0
 	add	r12,rbx
 	mov	rbx,rdx
@@ -118,7 +122,7 @@ $L$oop_sqr::
 
 	mul	r8
 	add	r13,rax
-	mov	rax,QWORD PTR[48+rsi]
+	mov	rax,QWORD[48+rsi]
 	adc	rdx,0
 	add	r13,rbx
 	mov	rbx,rdx
@@ -126,7 +130,7 @@ $L$oop_sqr::
 
 	mul	r8
 	add	r14,rax
-	mov	rax,QWORD PTR[56+rsi]
+	mov	rax,QWORD[56+rsi]
 	adc	rdx,0
 	add	r14,rbx
 	mov	rbx,rdx
@@ -142,7 +146,7 @@ $L$oop_sqr::
 	adc	r8,0
 
 	add	rdx,rdx
-	lea	r10,QWORD PTR[r10*2+rcx]
+	lea	r10,[r10*2+rcx]
 	mov	rbx,r11
 	adc	r11,r11
 
@@ -151,22 +155,22 @@ $L$oop_sqr::
 	adc	r10,rdx
 	adc	r11,0
 
-	mov	QWORD PTR[16+rsp],r9
-	mov	QWORD PTR[24+rsp],r10
+	mov	QWORD[16+rsp],r9
+	mov	QWORD[24+rsp],r10
 	shr	rbx,63
 
 
-	mov	r9,QWORD PTR[16+rsi]
-	mov	rax,QWORD PTR[24+rsi]
+	mov	r9,QWORD[16+rsi]
+	mov	rax,QWORD[24+rsi]
 	mul	r9
 	add	r12,rax
-	mov	rax,QWORD PTR[32+rsi]
+	mov	rax,QWORD[32+rsi]
 	mov	rcx,rdx
 	adc	rcx,0
 
 	mul	r9
 	add	r13,rax
-	mov	rax,QWORD PTR[40+rsi]
+	mov	rax,QWORD[40+rsi]
 	adc	rdx,0
 	add	r13,rcx
 	mov	rcx,rdx
@@ -174,7 +178,7 @@ $L$oop_sqr::
 
 	mul	r9
 	add	r14,rax
-	mov	rax,QWORD PTR[48+rsi]
+	mov	rax,QWORD[48+rsi]
 	adc	rdx,0
 	add	r14,rcx
 	mov	rcx,rdx
@@ -182,9 +186,9 @@ $L$oop_sqr::
 
 	mul	r9
 	mov	r10,r12
-	lea	r12,QWORD PTR[r12*2+rbx]
+	lea	r12,[r12*2+rbx]
 	add	r15,rax
-	mov	rax,QWORD PTR[56+rsi]
+	mov	rax,QWORD[56+rsi]
 	adc	rdx,0
 	add	r15,rcx
 	mov	rcx,rdx
@@ -200,29 +204,29 @@ $L$oop_sqr::
 	adc	r9,0
 
 	mov	rcx,r13
-	lea	r13,QWORD PTR[r13*2+r10]
+	lea	r13,[r13*2+r10]
 
 	mul	rax
 	add	r11,rax
 	adc	r12,rdx
 	adc	r13,0
 
-	mov	QWORD PTR[32+rsp],r11
-	mov	QWORD PTR[40+rsp],r12
+	mov	QWORD[32+rsp],r11
+	mov	QWORD[40+rsp],r12
 	shr	rcx,63
 
 
-	mov	r10,QWORD PTR[24+rsi]
-	mov	rax,QWORD PTR[32+rsi]
+	mov	r10,QWORD[24+rsi]
+	mov	rax,QWORD[32+rsi]
 	mul	r10
 	add	r14,rax
-	mov	rax,QWORD PTR[40+rsi]
+	mov	rax,QWORD[40+rsi]
 	mov	rbx,rdx
 	adc	rbx,0
 
 	mul	r10
 	add	r15,rax
-	mov	rax,QWORD PTR[48+rsi]
+	mov	rax,QWORD[48+rsi]
 	adc	rdx,0
 	add	r15,rbx
 	mov	rbx,rdx
@@ -230,9 +234,9 @@ $L$oop_sqr::
 
 	mul	r10
 	mov	r12,r14
-	lea	r14,QWORD PTR[r14*2+rcx]
+	lea	r14,[r14*2+rcx]
 	add	r8,rax
-	mov	rax,QWORD PTR[56+rsi]
+	mov	rax,QWORD[56+rsi]
 	adc	rdx,0
 	add	r8,rbx
 	mov	rbx,rdx
@@ -248,32 +252,32 @@ $L$oop_sqr::
 	adc	r10,0
 
 	mov	rbx,r15
-	lea	r15,QWORD PTR[r15*2+r12]
+	lea	r15,[r15*2+r12]
 
 	mul	rax
 	add	r13,rax
 	adc	r14,rdx
 	adc	r15,0
 
-	mov	QWORD PTR[48+rsp],r13
-	mov	QWORD PTR[56+rsp],r14
+	mov	QWORD[48+rsp],r13
+	mov	QWORD[56+rsp],r14
 	shr	rbx,63
 
 
-	mov	r11,QWORD PTR[32+rsi]
-	mov	rax,QWORD PTR[40+rsi]
+	mov	r11,QWORD[32+rsi]
+	mov	rax,QWORD[40+rsi]
 	mul	r11
 	add	r8,rax
-	mov	rax,QWORD PTR[48+rsi]
+	mov	rax,QWORD[48+rsi]
 	mov	rcx,rdx
 	adc	rcx,0
 
 	mul	r11
 	add	r9,rax
-	mov	rax,QWORD PTR[56+rsi]
+	mov	rax,QWORD[56+rsi]
 	adc	rdx,0
 	mov	r12,r8
-	lea	r8,QWORD PTR[r8*2+rbx]
+	lea	r8,[r8*2+rbx]
 	add	r9,rcx
 	mov	rcx,rdx
 	adc	rcx,0
@@ -288,23 +292,23 @@ $L$oop_sqr::
 	adc	r11,0
 
 	mov	rcx,r9
-	lea	r9,QWORD PTR[r9*2+r12]
+	lea	r9,[r9*2+r12]
 
 	mul	rax
 	add	r15,rax
 	adc	r8,rdx
 	adc	r9,0
 
-	mov	QWORD PTR[64+rsp],r15
-	mov	QWORD PTR[72+rsp],r8
+	mov	QWORD[64+rsp],r15
+	mov	QWORD[72+rsp],r8
 	shr	rcx,63
 
 
-	mov	r12,QWORD PTR[40+rsi]
-	mov	rax,QWORD PTR[48+rsi]
+	mov	r12,QWORD[40+rsi]
+	mov	rax,QWORD[48+rsi]
 	mul	r12
 	add	r10,rax
-	mov	rax,QWORD PTR[56+rsi]
+	mov	rax,QWORD[56+rsi]
 	mov	rbx,rdx
 	adc	rbx,0
 
@@ -312,7 +316,7 @@ $L$oop_sqr::
 	add	r11,rax
 	mov	rax,r12
 	mov	r15,r10
-	lea	r10,QWORD PTR[r10*2+rcx]
+	lea	r10,[r10*2+rcx]
 	adc	rdx,0
 	shr	r15,63
 	add	r11,rbx
@@ -320,19 +324,19 @@ $L$oop_sqr::
 	adc	r12,0
 
 	mov	rbx,r11
-	lea	r11,QWORD PTR[r11*2+r15]
+	lea	r11,[r11*2+r15]
 
 	mul	rax
 	add	r9,rax
 	adc	r10,rdx
 	adc	r11,0
 
-	mov	QWORD PTR[80+rsp],r9
-	mov	QWORD PTR[88+rsp],r10
+	mov	QWORD[80+rsp],r9
+	mov	QWORD[88+rsp],r10
 
 
-	mov	r13,QWORD PTR[48+rsi]
-	mov	rax,QWORD PTR[56+rsi]
+	mov	r13,QWORD[48+rsi]
+	mov	rax,QWORD[56+rsi]
 	mul	r13
 	add	r12,rax
 	mov	rax,r13
@@ -350,78 +354,77 @@ $L$oop_sqr::
 	adc	r12,rdx
 	adc	r13,0
 
-	mov	QWORD PTR[96+rsp],r11
-	mov	QWORD PTR[104+rsp],r12
+	mov	QWORD[96+rsp],r11
+	mov	QWORD[104+rsp],r12
 
 
-	mov	rax,QWORD PTR[56+rsi]
+	mov	rax,QWORD[56+rsi]
 	mul	rax
 	add	r13,rax
 	adc	rdx,0
 
 	add	r14,rdx
 
-	mov	QWORD PTR[112+rsp],r13
-	mov	QWORD PTR[120+rsp],r14
+	mov	QWORD[112+rsp],r13
+	mov	QWORD[120+rsp],r14
 
-	mov	r8,QWORD PTR[rsp]
-	mov	r9,QWORD PTR[8+rsp]
-	mov	r10,QWORD PTR[16+rsp]
-	mov	r11,QWORD PTR[24+rsp]
-	mov	r12,QWORD PTR[32+rsp]
-	mov	r13,QWORD PTR[40+rsp]
-	mov	r14,QWORD PTR[48+rsp]
-	mov	r15,QWORD PTR[56+rsp]
+	mov	r8,QWORD[rsp]
+	mov	r9,QWORD[8+rsp]
+	mov	r10,QWORD[16+rsp]
+	mov	r11,QWORD[24+rsp]
+	mov	r12,QWORD[32+rsp]
+	mov	r13,QWORD[40+rsp]
+	mov	r14,QWORD[48+rsp]
+	mov	r15,QWORD[56+rsp]
 
 	call	__rsaz_512_reduce
 
-	add	r8,QWORD PTR[64+rsp]
-	adc	r9,QWORD PTR[72+rsp]
-	adc	r10,QWORD PTR[80+rsp]
-	adc	r11,QWORD PTR[88+rsp]
-	adc	r12,QWORD PTR[96+rsp]
-	adc	r13,QWORD PTR[104+rsp]
-	adc	r14,QWORD PTR[112+rsp]
-	adc	r15,QWORD PTR[120+rsp]
+	add	r8,QWORD[64+rsp]
+	adc	r9,QWORD[72+rsp]
+	adc	r10,QWORD[80+rsp]
+	adc	r11,QWORD[88+rsp]
+	adc	r12,QWORD[96+rsp]
+	adc	r13,QWORD[104+rsp]
+	adc	r14,QWORD[112+rsp]
+	adc	r15,QWORD[120+rsp]
 	sbb	rcx,rcx
 
 	call	__rsaz_512_subtract
 
 	mov	rdx,r8
 	mov	rax,r9
-	mov	r8d,DWORD PTR[((128+8))+rsp]
+	mov	r8d,DWORD[((128+8))+rsp]
 	mov	rsi,rdi
 
 	dec	r8d
-	jnz	$L$oop_sqr
-
-	lea	rax,QWORD PTR[((128+24+48))+rsp]
-	mov	r15,QWORD PTR[((-48))+rax]
-	mov	r14,QWORD PTR[((-40))+rax]
-	mov	r13,QWORD PTR[((-32))+rax]
-	mov	r12,QWORD PTR[((-24))+rax]
-	mov	rbp,QWORD PTR[((-16))+rax]
-	mov	rbx,QWORD PTR[((-8))+rax]
-	lea	rsp,QWORD PTR[rax]
-$L$sqr_epilogue::
-	mov	rdi,QWORD PTR[8+rsp]	;WIN64 epilogue
-	mov	rsi,QWORD PTR[16+rsp]
+	jnz	NEAR $L$oop_sqr
+
+	lea	rax,[((128+24+48))+rsp]
+	mov	r15,QWORD[((-48))+rax]
+	mov	r14,QWORD[((-40))+rax]
+	mov	r13,QWORD[((-32))+rax]
+	mov	r12,QWORD[((-24))+rax]
+	mov	rbp,QWORD[((-16))+rax]
+	mov	rbx,QWORD[((-8))+rax]
+	lea	rsp,[rax]
+$L$sqr_epilogue:
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
-$L$SEH_end_rsaz_512_sqr::
-rsaz_512_sqr	ENDP
-PUBLIC	rsaz_512_mul
+$L$SEH_end_rsaz_512_sqr:
+global	rsaz_512_mul
 
 ALIGN	32
-rsaz_512_mul	PROC PUBLIC
-	mov	QWORD PTR[8+rsp],rdi	;WIN64 prologue
-	mov	QWORD PTR[16+rsp],rsi
+rsaz_512_mul:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
 	mov	rax,rsp
-$L$SEH_begin_rsaz_512_mul::
+$L$SEH_begin_rsaz_512_mul:
 	mov	rdi,rcx
 	mov	rsi,rdx
 	mov	rdx,r8
 	mov	rcx,r9
-	mov	r8,QWORD PTR[40+rsp]
+	mov	r8,QWORD[40+rsp]
 
 
 	push	rbx
@@ -432,67 +435,66 @@ $L$SEH_begin_rsaz_512_mul::
 	push	r15
 
 	sub	rsp,128+24
-$L$mul_body::
+$L$mul_body:
 DB	102,72,15,110,199
 DB	102,72,15,110,201
-	mov	QWORD PTR[128+rsp],r8
-	mov	rbx,QWORD PTR[rdx]
+	mov	QWORD[128+rsp],r8
+	mov	rbx,QWORD[rdx]
 	mov	rbp,rdx
 	call	__rsaz_512_mul
 
 DB	102,72,15,126,199
 DB	102,72,15,126,205
 
-	mov	r8,QWORD PTR[rsp]
-	mov	r9,QWORD PTR[8+rsp]
-	mov	r10,QWORD PTR[16+rsp]
-	mov	r11,QWORD PTR[24+rsp]
-	mov	r12,QWORD PTR[32+rsp]
-	mov	r13,QWORD PTR[40+rsp]
-	mov	r14,QWORD PTR[48+rsp]
-	mov	r15,QWORD PTR[56+rsp]
+	mov	r8,QWORD[rsp]
+	mov	r9,QWORD[8+rsp]
+	mov	r10,QWORD[16+rsp]
+	mov	r11,QWORD[24+rsp]
+	mov	r12,QWORD[32+rsp]
+	mov	r13,QWORD[40+rsp]
+	mov	r14,QWORD[48+rsp]
+	mov	r15,QWORD[56+rsp]
 
 	call	__rsaz_512_reduce
-	add	r8,QWORD PTR[64+rsp]
-	adc	r9,QWORD PTR[72+rsp]
-	adc	r10,QWORD PTR[80+rsp]
-	adc	r11,QWORD PTR[88+rsp]
-	adc	r12,QWORD PTR[96+rsp]
-	adc	r13,QWORD PTR[104+rsp]
-	adc	r14,QWORD PTR[112+rsp]
-	adc	r15,QWORD PTR[120+rsp]
+	add	r8,QWORD[64+rsp]
+	adc	r9,QWORD[72+rsp]
+	adc	r10,QWORD[80+rsp]
+	adc	r11,QWORD[88+rsp]
+	adc	r12,QWORD[96+rsp]
+	adc	r13,QWORD[104+rsp]
+	adc	r14,QWORD[112+rsp]
+	adc	r15,QWORD[120+rsp]
 	sbb	rcx,rcx
 
 	call	__rsaz_512_subtract
 
-	lea	rax,QWORD PTR[((128+24+48))+rsp]
-	mov	r15,QWORD PTR[((-48))+rax]
-	mov	r14,QWORD PTR[((-40))+rax]
-	mov	r13,QWORD PTR[((-32))+rax]
-	mov	r12,QWORD PTR[((-24))+rax]
-	mov	rbp,QWORD PTR[((-16))+rax]
-	mov	rbx,QWORD PTR[((-8))+rax]
-	lea	rsp,QWORD PTR[rax]
-$L$mul_epilogue::
-	mov	rdi,QWORD PTR[8+rsp]	;WIN64 epilogue
-	mov	rsi,QWORD PTR[16+rsp]
+	lea	rax,[((128+24+48))+rsp]
+	mov	r15,QWORD[((-48))+rax]
+	mov	r14,QWORD[((-40))+rax]
+	mov	r13,QWORD[((-32))+rax]
+	mov	r12,QWORD[((-24))+rax]
+	mov	rbp,QWORD[((-16))+rax]
+	mov	rbx,QWORD[((-8))+rax]
+	lea	rsp,[rax]
+$L$mul_epilogue:
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
-$L$SEH_end_rsaz_512_mul::
-rsaz_512_mul	ENDP
-PUBLIC	rsaz_512_mul_gather4
+$L$SEH_end_rsaz_512_mul:
+global	rsaz_512_mul_gather4
 
 ALIGN	32
-rsaz_512_mul_gather4	PROC PUBLIC
-	mov	QWORD PTR[8+rsp],rdi	;WIN64 prologue
-	mov	QWORD PTR[16+rsp],rsi
+rsaz_512_mul_gather4:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
 	mov	rax,rsp
-$L$SEH_begin_rsaz_512_mul_gather4::
+$L$SEH_begin_rsaz_512_mul_gather4:
 	mov	rdi,rcx
 	mov	rsi,rdx
 	mov	rdx,r8
 	mov	rcx,r9
-	mov	r8,QWORD PTR[40+rsp]
-	mov	r9,QWORD PTR[48+rsp]
+	mov	r8,QWORD[40+rsp]
+	mov	r9,QWORD[48+rsp]
 
 
 	push	rbx
@@ -504,97 +506,97 @@ $L$SEH_begin_rsaz_512_mul_gather4::
 
 	mov	r9d,r9d
 	sub	rsp,128+24
-$L$mul_gather4_body::
-	mov	eax,DWORD PTR[64+r9*4+rdx]
+$L$mul_gather4_body:
+	mov	eax,DWORD[64+r9*4+rdx]
 DB	102,72,15,110,199
-	mov	ebx,DWORD PTR[r9*4+rdx]
+	mov	ebx,DWORD[r9*4+rdx]
 DB	102,72,15,110,201
-	mov	QWORD PTR[128+rsp],r8
+	mov	QWORD[128+rsp],r8
 
 	shl	rax,32
 	or	rbx,rax
-	mov	rax,QWORD PTR[rsi]
-	mov	rcx,QWORD PTR[8+rsi]
-	lea	rbp,QWORD PTR[128+r9*4+rdx]
+	mov	rax,QWORD[rsi]
+	mov	rcx,QWORD[8+rsi]
+	lea	rbp,[128+r9*4+rdx]
 	mul	rbx
-	mov	QWORD PTR[rsp],rax
+	mov	QWORD[rsp],rax
 	mov	rax,rcx
 	mov	r8,rdx
 
 	mul	rbx
-	movd	xmm4,DWORD PTR[rbp]
+	movd	xmm4,DWORD[rbp]
 	add	r8,rax
-	mov	rax,QWORD PTR[16+rsi]
+	mov	rax,QWORD[16+rsi]
 	mov	r9,rdx
 	adc	r9,0
 
 	mul	rbx
-	movd	xmm5,DWORD PTR[64+rbp]
+	movd	xmm5,DWORD[64+rbp]
 	add	r9,rax
-	mov	rax,QWORD PTR[24+rsi]
+	mov	rax,QWORD[24+rsi]
 	mov	r10,rdx
 	adc	r10,0
 
 	mul	rbx
 	pslldq	xmm5,4
 	add	r10,rax
-	mov	rax,QWORD PTR[32+rsi]
+	mov	rax,QWORD[32+rsi]
 	mov	r11,rdx
 	adc	r11,0
 
 	mul	rbx
 	por	xmm4,xmm5
 	add	r11,rax
-	mov	rax,QWORD PTR[40+rsi]
+	mov	rax,QWORD[40+rsi]
 	mov	r12,rdx
 	adc	r12,0
 
 	mul	rbx
 	add	r12,rax
-	mov	rax,QWORD PTR[48+rsi]
+	mov	rax,QWORD[48+rsi]
 	mov	r13,rdx
 	adc	r13,0
 
 	mul	rbx
-	lea	rbp,QWORD PTR[128+rbp]
+	lea	rbp,[128+rbp]
 	add	r13,rax
-	mov	rax,QWORD PTR[56+rsi]
+	mov	rax,QWORD[56+rsi]
 	mov	r14,rdx
 	adc	r14,0
 
 	mul	rbx
 DB	102,72,15,126,227
 	add	r14,rax
-	mov	rax,QWORD PTR[rsi]
+	mov	rax,QWORD[rsi]
 	mov	r15,rdx
 	adc	r15,0
 
-	lea	rdi,QWORD PTR[8+rsp]
+	lea	rdi,[8+rsp]
 	mov	ecx,7
-	jmp	$L$oop_mul_gather
+	jmp	NEAR $L$oop_mul_gather
 
 ALIGN	32
-$L$oop_mul_gather::
+$L$oop_mul_gather:
 	mul	rbx
 	add	r8,rax
-	mov	rax,QWORD PTR[8+rsi]
-	mov	QWORD PTR[rdi],r8
+	mov	rax,QWORD[8+rsi]
+	mov	QWORD[rdi],r8
 	mov	r8,rdx
 	adc	r8,0
 
 	mul	rbx
-	movd	xmm4,DWORD PTR[rbp]
+	movd	xmm4,DWORD[rbp]
 	add	r9,rax
-	mov	rax,QWORD PTR[16+rsi]
+	mov	rax,QWORD[16+rsi]
 	adc	rdx,0
 	add	r8,r9
 	mov	r9,rdx
 	adc	r9,0
 
 	mul	rbx
-	movd	xmm5,DWORD PTR[64+rbp]
+	movd	xmm5,DWORD[64+rbp]
 	add	r10,rax
-	mov	rax,QWORD PTR[24+rsi]
+	mov	rax,QWORD[24+rsi]
 	adc	rdx,0
 	add	r9,r10
 	mov	r10,rdx
@@ -603,7 +605,7 @@ $L$oop_mul_gather::
 	mul	rbx
 	pslldq	xmm5,4
 	add	r11,rax
-	mov	rax,QWORD PTR[32+rsi]
+	mov	rax,QWORD[32+rsi]
 	adc	rdx,0
 	add	r10,r11
 	mov	r11,rdx
@@ -612,7 +614,7 @@ $L$oop_mul_gather::
 	mul	rbx
 	por	xmm4,xmm5
 	add	r12,rax
-	mov	rax,QWORD PTR[40+rsi]
+	mov	rax,QWORD[40+rsi]
 	adc	rdx,0
 	add	r11,r12
 	mov	r12,rdx
@@ -620,7 +622,7 @@ $L$oop_mul_gather::
 
 	mul	rbx
 	add	r13,rax
-	mov	rax,QWORD PTR[48+rsi]
+	mov	rax,QWORD[48+rsi]
 	adc	rdx,0
 	add	r12,r13
 	mov	r13,rdx
@@ -628,7 +630,7 @@ $L$oop_mul_gather::
 
 	mul	rbx
 	add	r14,rax
-	mov	rax,QWORD PTR[56+rsi]
+	mov	rax,QWORD[56+rsi]
 	adc	rdx,0
 	add	r13,r14
 	mov	r14,rdx
@@ -637,80 +639,79 @@ $L$oop_mul_gather::
 	mul	rbx
 DB	102,72,15,126,227
 	add	r15,rax
-	mov	rax,QWORD PTR[rsi]
+	mov	rax,QWORD[rsi]
 	adc	rdx,0
 	add	r14,r15
 	mov	r15,rdx
 	adc	r15,0
 
-	lea	rbp,QWORD PTR[128+rbp]
-	lea	rdi,QWORD PTR[8+rdi]
+	lea	rbp,[128+rbp]
+	lea	rdi,[8+rdi]
 
 	dec	ecx
-	jnz	$L$oop_mul_gather
+	jnz	NEAR $L$oop_mul_gather
 
-	mov	QWORD PTR[rdi],r8
-	mov	QWORD PTR[8+rdi],r9
-	mov	QWORD PTR[16+rdi],r10
-	mov	QWORD PTR[24+rdi],r11
-	mov	QWORD PTR[32+rdi],r12
-	mov	QWORD PTR[40+rdi],r13
-	mov	QWORD PTR[48+rdi],r14
-	mov	QWORD PTR[56+rdi],r15
+	mov	QWORD[rdi],r8
+	mov	QWORD[8+rdi],r9
+	mov	QWORD[16+rdi],r10
+	mov	QWORD[24+rdi],r11
+	mov	QWORD[32+rdi],r12
+	mov	QWORD[40+rdi],r13
+	mov	QWORD[48+rdi],r14
+	mov	QWORD[56+rdi],r15
 
 DB	102,72,15,126,199
 DB	102,72,15,126,205
 
-	mov	r8,QWORD PTR[rsp]
-	mov	r9,QWORD PTR[8+rsp]
-	mov	r10,QWORD PTR[16+rsp]
-	mov	r11,QWORD PTR[24+rsp]
-	mov	r12,QWORD PTR[32+rsp]
-	mov	r13,QWORD PTR[40+rsp]
-	mov	r14,QWORD PTR[48+rsp]
-	mov	r15,QWORD PTR[56+rsp]
+	mov	r8,QWORD[rsp]
+	mov	r9,QWORD[8+rsp]
+	mov	r10,QWORD[16+rsp]
+	mov	r11,QWORD[24+rsp]
+	mov	r12,QWORD[32+rsp]
+	mov	r13,QWORD[40+rsp]
+	mov	r14,QWORD[48+rsp]
+	mov	r15,QWORD[56+rsp]
 
 	call	__rsaz_512_reduce
-	add	r8,QWORD PTR[64+rsp]
-	adc	r9,QWORD PTR[72+rsp]
-	adc	r10,QWORD PTR[80+rsp]
-	adc	r11,QWORD PTR[88+rsp]
-	adc	r12,QWORD PTR[96+rsp]
-	adc	r13,QWORD PTR[104+rsp]
-	adc	r14,QWORD PTR[112+rsp]
-	adc	r15,QWORD PTR[120+rsp]
+	add	r8,QWORD[64+rsp]
+	adc	r9,QWORD[72+rsp]
+	adc	r10,QWORD[80+rsp]
+	adc	r11,QWORD[88+rsp]
+	adc	r12,QWORD[96+rsp]
+	adc	r13,QWORD[104+rsp]
+	adc	r14,QWORD[112+rsp]
+	adc	r15,QWORD[120+rsp]
 	sbb	rcx,rcx
 
 	call	__rsaz_512_subtract
 
-	lea	rax,QWORD PTR[((128+24+48))+rsp]
-	mov	r15,QWORD PTR[((-48))+rax]
-	mov	r14,QWORD PTR[((-40))+rax]
-	mov	r13,QWORD PTR[((-32))+rax]
-	mov	r12,QWORD PTR[((-24))+rax]
-	mov	rbp,QWORD PTR[((-16))+rax]
-	mov	rbx,QWORD PTR[((-8))+rax]
-	lea	rsp,QWORD PTR[rax]
-$L$mul_gather4_epilogue::
-	mov	rdi,QWORD PTR[8+rsp]	;WIN64 epilogue
-	mov	rsi,QWORD PTR[16+rsp]
+	lea	rax,[((128+24+48))+rsp]
+	mov	r15,QWORD[((-48))+rax]
+	mov	r14,QWORD[((-40))+rax]
+	mov	r13,QWORD[((-32))+rax]
+	mov	r12,QWORD[((-24))+rax]
+	mov	rbp,QWORD[((-16))+rax]
+	mov	rbx,QWORD[((-8))+rax]
+	lea	rsp,[rax]
+$L$mul_gather4_epilogue:
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
-$L$SEH_end_rsaz_512_mul_gather4::
-rsaz_512_mul_gather4	ENDP
-PUBLIC	rsaz_512_mul_scatter4
+$L$SEH_end_rsaz_512_mul_gather4:
+global	rsaz_512_mul_scatter4
 
 ALIGN	32
-rsaz_512_mul_scatter4	PROC PUBLIC
-	mov	QWORD PTR[8+rsp],rdi	;WIN64 prologue
-	mov	QWORD PTR[16+rsp],rsi
+rsaz_512_mul_scatter4:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
 	mov	rax,rsp
-$L$SEH_begin_rsaz_512_mul_scatter4::
+$L$SEH_begin_rsaz_512_mul_scatter4:
 	mov	rdi,rcx
 	mov	rsi,rdx
 	mov	rdx,r8
 	mov	rcx,r9
-	mov	r8,QWORD PTR[40+rsp]
-	mov	r9,QWORD PTR[48+rsp]
+	mov	r8,QWORD[40+rsp]
+	mov	r9,QWORD[48+rsp]
 
 
 	push	rbx
@@ -722,90 +723,89 @@ $L$SEH_begin_rsaz_512_mul_scatter4::
 
 	mov	r9d,r9d
 	sub	rsp,128+24
-$L$mul_scatter4_body::
-	lea	r8,QWORD PTR[r9*4+r8]
+$L$mul_scatter4_body:
+	lea	r8,[r9*4+r8]
 DB	102,72,15,110,199
 DB	102,72,15,110,202
 DB	102,73,15,110,208
-	mov	QWORD PTR[128+rsp],rcx
+	mov	QWORD[128+rsp],rcx
 
 	mov	rbp,rdi
-	mov	rbx,QWORD PTR[rdi]
+	mov	rbx,QWORD[rdi]
 	call	__rsaz_512_mul
 
 DB	102,72,15,126,199
 DB	102,72,15,126,205
 
-	mov	r8,QWORD PTR[rsp]
-	mov	r9,QWORD PTR[8+rsp]
-	mov	r10,QWORD PTR[16+rsp]
-	mov	r11,QWORD PTR[24+rsp]
-	mov	r12,QWORD PTR[32+rsp]
-	mov	r13,QWORD PTR[40+rsp]
-	mov	r14,QWORD PTR[48+rsp]
-	mov	r15,QWORD PTR[56+rsp]
+	mov	r8,QWORD[rsp]
+	mov	r9,QWORD[8+rsp]
+	mov	r10,QWORD[16+rsp]
+	mov	r11,QWORD[24+rsp]
+	mov	r12,QWORD[32+rsp]
+	mov	r13,QWORD[40+rsp]
+	mov	r14,QWORD[48+rsp]
+	mov	r15,QWORD[56+rsp]
 
 	call	__rsaz_512_reduce
-	add	r8,QWORD PTR[64+rsp]
-	adc	r9,QWORD PTR[72+rsp]
-	adc	r10,QWORD PTR[80+rsp]
-	adc	r11,QWORD PTR[88+rsp]
-	adc	r12,QWORD PTR[96+rsp]
-	adc	r13,QWORD PTR[104+rsp]
-	adc	r14,QWORD PTR[112+rsp]
-	adc	r15,QWORD PTR[120+rsp]
+	add	r8,QWORD[64+rsp]
+	adc	r9,QWORD[72+rsp]
+	adc	r10,QWORD[80+rsp]
+	adc	r11,QWORD[88+rsp]
+	adc	r12,QWORD[96+rsp]
+	adc	r13,QWORD[104+rsp]
+	adc	r14,QWORD[112+rsp]
+	adc	r15,QWORD[120+rsp]
 DB	102,72,15,126,214
 	sbb	rcx,rcx
 
 	call	__rsaz_512_subtract
 
-	mov	DWORD PTR[rsi],r8d
+	mov	DWORD[rsi],r8d
 	shr	r8,32
-	mov	DWORD PTR[128+rsi],r9d
+	mov	DWORD[128+rsi],r9d
 	shr	r9,32
-	mov	DWORD PTR[256+rsi],r10d
+	mov	DWORD[256+rsi],r10d
 	shr	r10,32
-	mov	DWORD PTR[384+rsi],r11d
+	mov	DWORD[384+rsi],r11d
 	shr	r11,32
-	mov	DWORD PTR[512+rsi],r12d
+	mov	DWORD[512+rsi],r12d
 	shr	r12,32
-	mov	DWORD PTR[640+rsi],r13d
+	mov	DWORD[640+rsi],r13d
 	shr	r13,32
-	mov	DWORD PTR[768+rsi],r14d
+	mov	DWORD[768+rsi],r14d
 	shr	r14,32
-	mov	DWORD PTR[896+rsi],r15d
+	mov	DWORD[896+rsi],r15d
 	shr	r15,32
-	mov	DWORD PTR[64+rsi],r8d
-	mov	DWORD PTR[192+rsi],r9d
-	mov	DWORD PTR[320+rsi],r10d
-	mov	DWORD PTR[448+rsi],r11d
-	mov	DWORD PTR[576+rsi],r12d
-	mov	DWORD PTR[704+rsi],r13d
-	mov	DWORD PTR[832+rsi],r14d
-	mov	DWORD PTR[960+rsi],r15d
-
-	lea	rax,QWORD PTR[((128+24+48))+rsp]
-	mov	r15,QWORD PTR[((-48))+rax]
-	mov	r14,QWORD PTR[((-40))+rax]
-	mov	r13,QWORD PTR[((-32))+rax]
-	mov	r12,QWORD PTR[((-24))+rax]
-	mov	rbp,QWORD PTR[((-16))+rax]
-	mov	rbx,QWORD PTR[((-8))+rax]
-	lea	rsp,QWORD PTR[rax]
-$L$mul_scatter4_epilogue::
-	mov	rdi,QWORD PTR[8+rsp]	;WIN64 epilogue
-	mov	rsi,QWORD PTR[16+rsp]
+	mov	DWORD[64+rsi],r8d
+	mov	DWORD[192+rsi],r9d
+	mov	DWORD[320+rsi],r10d
+	mov	DWORD[448+rsi],r11d
+	mov	DWORD[576+rsi],r12d
+	mov	DWORD[704+rsi],r13d
+	mov	DWORD[832+rsi],r14d
+	mov	DWORD[960+rsi],r15d
+
+	lea	rax,[((128+24+48))+rsp]
+	mov	r15,QWORD[((-48))+rax]
+	mov	r14,QWORD[((-40))+rax]
+	mov	r13,QWORD[((-32))+rax]
+	mov	r12,QWORD[((-24))+rax]
+	mov	rbp,QWORD[((-16))+rax]
+	mov	rbx,QWORD[((-8))+rax]
+	lea	rsp,[rax]
+$L$mul_scatter4_epilogue:
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
-$L$SEH_end_rsaz_512_mul_scatter4::
-rsaz_512_mul_scatter4	ENDP
-PUBLIC	rsaz_512_mul_by_one
+$L$SEH_end_rsaz_512_mul_scatter4:
+global	rsaz_512_mul_by_one
 
 ALIGN	32
-rsaz_512_mul_by_one	PROC PUBLIC
-	mov	QWORD PTR[8+rsp],rdi	;WIN64 prologue
-	mov	QWORD PTR[16+rsp],rsi
+rsaz_512_mul_by_one:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
 	mov	rax,rsp
-$L$SEH_begin_rsaz_512_mul_by_one::
+$L$SEH_begin_rsaz_512_mul_by_one:
 	mov	rdi,rcx
 	mov	rsi,rdx
 	mov	rdx,r8
@@ -820,71 +820,70 @@ $L$SEH_begin_rsaz_512_mul_by_one::
 	push	r15
 
 	sub	rsp,128+24
-$L$mul_by_one_body::
+$L$mul_by_one_body:
 	mov	rbp,rdx
-	mov	QWORD PTR[128+rsp],rcx
+	mov	QWORD[128+rsp],rcx
 
-	mov	r8,QWORD PTR[rsi]
+	mov	r8,QWORD[rsi]
 	pxor	xmm0,xmm0
-	mov	r9,QWORD PTR[8+rsi]
-	mov	r10,QWORD PTR[16+rsi]
-	mov	r11,QWORD PTR[24+rsi]
-	mov	r12,QWORD PTR[32+rsi]
-	mov	r13,QWORD PTR[40+rsi]
-	mov	r14,QWORD PTR[48+rsi]
-	mov	r15,QWORD PTR[56+rsi]
-
-	movdqa	XMMWORD PTR[rsp],xmm0
-	movdqa	XMMWORD PTR[16+rsp],xmm0
-	movdqa	XMMWORD PTR[32+rsp],xmm0
-	movdqa	XMMWORD PTR[48+rsp],xmm0
-	movdqa	XMMWORD PTR[64+rsp],xmm0
-	movdqa	XMMWORD PTR[80+rsp],xmm0
-	movdqa	XMMWORD PTR[96+rsp],xmm0
+	mov	r9,QWORD[8+rsi]
+	mov	r10,QWORD[16+rsi]
+	mov	r11,QWORD[24+rsi]
+	mov	r12,QWORD[32+rsi]
+	mov	r13,QWORD[40+rsi]
+	mov	r14,QWORD[48+rsi]
+	mov	r15,QWORD[56+rsi]
+
+	movdqa	XMMWORD[rsp],xmm0
+	movdqa	XMMWORD[16+rsp],xmm0
+	movdqa	XMMWORD[32+rsp],xmm0
+	movdqa	XMMWORD[48+rsp],xmm0
+	movdqa	XMMWORD[64+rsp],xmm0
+	movdqa	XMMWORD[80+rsp],xmm0
+	movdqa	XMMWORD[96+rsp],xmm0
 	call	__rsaz_512_reduce
-	mov	QWORD PTR[rdi],r8
-	mov	QWORD PTR[8+rdi],r9
-	mov	QWORD PTR[16+rdi],r10
-	mov	QWORD PTR[24+rdi],r11
-	mov	QWORD PTR[32+rdi],r12
-	mov	QWORD PTR[40+rdi],r13
-	mov	QWORD PTR[48+rdi],r14
-	mov	QWORD PTR[56+rdi],r15
-
-	lea	rax,QWORD PTR[((128+24+48))+rsp]
-	mov	r15,QWORD PTR[((-48))+rax]
-	mov	r14,QWORD PTR[((-40))+rax]
-	mov	r13,QWORD PTR[((-32))+rax]
-	mov	r12,QWORD PTR[((-24))+rax]
-	mov	rbp,QWORD PTR[((-16))+rax]
-	mov	rbx,QWORD PTR[((-8))+rax]
-	lea	rsp,QWORD PTR[rax]
-$L$mul_by_one_epilogue::
-	mov	rdi,QWORD PTR[8+rsp]	;WIN64 epilogue
-	mov	rsi,QWORD PTR[16+rsp]
+	mov	QWORD[rdi],r8
+	mov	QWORD[8+rdi],r9
+	mov	QWORD[16+rdi],r10
+	mov	QWORD[24+rdi],r11
+	mov	QWORD[32+rdi],r12
+	mov	QWORD[40+rdi],r13
+	mov	QWORD[48+rdi],r14
+	mov	QWORD[56+rdi],r15
+
+	lea	rax,[((128+24+48))+rsp]
+	mov	r15,QWORD[((-48))+rax]
+	mov	r14,QWORD[((-40))+rax]
+	mov	r13,QWORD[((-32))+rax]
+	mov	r12,QWORD[((-24))+rax]
+	mov	rbp,QWORD[((-16))+rax]
+	mov	rbx,QWORD[((-8))+rax]
+	lea	rsp,[rax]
+$L$mul_by_one_epilogue:
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
-$L$SEH_end_rsaz_512_mul_by_one::
-rsaz_512_mul_by_one	ENDP
+$L$SEH_end_rsaz_512_mul_by_one:
 
 ALIGN	32
-__rsaz_512_reduce	PROC PRIVATE
+__rsaz_512_reduce:
 	mov	rbx,r8
-	imul	rbx,QWORD PTR[((128+8))+rsp]
-	mov	rax,QWORD PTR[rbp]
+	imul	rbx,QWORD[((128+8))+rsp]
+	mov	rax,QWORD[rbp]
 	mov	ecx,8
-	jmp	$L$reduction_loop
+	jmp	NEAR $L$reduction_loop
 
 ALIGN	32
-$L$reduction_loop::
+$L$reduction_loop:
 	mul	rbx
-	mov	rax,QWORD PTR[8+rbp]
+	mov	rax,QWORD[8+rbp]
 	neg	r8
 	mov	r8,rdx
 	adc	r8,0
 
 	mul	rbx
 	add	r9,rax
-	mov	rax,QWORD PTR[16+rbp]
+	mov	rax,QWORD[16+rbp]
 	adc	rdx,0
 	add	r8,r9
 	mov	r9,rdx
@@ -892,7 +891,7 @@ $L$reduction_loop::
 
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD PTR[24+rbp]
+	mov	rax,QWORD[24+rbp]
 	adc	rdx,0
 	add	r9,r10
 	mov	r10,rdx
@@ -900,10 +899,10 @@ $L$reduction_loop::
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD PTR[32+rbp]
+	mov	rax,QWORD[32+rbp]
 	adc	rdx,0
 	add	r10,r11
-	mov	rsi,QWORD PTR[((128+8))+rsp]
+	mov	rsi,QWORD[((128+8))+rsp]
 
 
 	adc	rdx,0
@@ -911,7 +910,7 @@ $L$reduction_loop::
 
 	mul	rbx
 	add	r12,rax
-	mov	rax,QWORD PTR[40+rbp]
+	mov	rax,QWORD[40+rbp]
 	adc	rdx,0
 	imul	rsi,r8
 	add	r11,r12
@@ -920,7 +919,7 @@ $L$reduction_loop::
 
 	mul	rbx
 	add	r13,rax
-	mov	rax,QWORD PTR[48+rbp]
+	mov	rax,QWORD[48+rbp]
 	adc	rdx,0
 	add	r12,r13
 	mov	r13,rdx
@@ -928,7 +927,7 @@ $L$reduction_loop::
 
 	mul	rbx
 	add	r14,rax
-	mov	rax,QWORD PTR[56+rbp]
+	mov	rax,QWORD[56+rbp]
 	adc	rdx,0
 	add	r13,r14
 	mov	r14,rdx
@@ -937,146 +936,146 @@ $L$reduction_loop::
 	mul	rbx
 	mov	rbx,rsi
 	add	r15,rax
-	mov	rax,QWORD PTR[rbp]
+	mov	rax,QWORD[rbp]
 	adc	rdx,0
 	add	r14,r15
 	mov	r15,rdx
 	adc	r15,0
 
 	dec	ecx
-	jne	$L$reduction_loop
+	jne	NEAR $L$reduction_loop
 
 	DB	0F3h,0C3h		;repret
-__rsaz_512_reduce	ENDP
+
 
 ALIGN	32
-__rsaz_512_subtract	PROC PRIVATE
-	mov	QWORD PTR[rdi],r8
-	mov	QWORD PTR[8+rdi],r9
-	mov	QWORD PTR[16+rdi],r10
-	mov	QWORD PTR[24+rdi],r11
-	mov	QWORD PTR[32+rdi],r12
-	mov	QWORD PTR[40+rdi],r13
-	mov	QWORD PTR[48+rdi],r14
-	mov	QWORD PTR[56+rdi],r15
-
-	mov	r8,QWORD PTR[rbp]
-	mov	r9,QWORD PTR[8+rbp]
+__rsaz_512_subtract:
+	mov	QWORD[rdi],r8
+	mov	QWORD[8+rdi],r9
+	mov	QWORD[16+rdi],r10
+	mov	QWORD[24+rdi],r11
+	mov	QWORD[32+rdi],r12
+	mov	QWORD[40+rdi],r13
+	mov	QWORD[48+rdi],r14
+	mov	QWORD[56+rdi],r15
+
+	mov	r8,QWORD[rbp]
+	mov	r9,QWORD[8+rbp]
 	neg	r8
 	not	r9
 	and	r8,rcx
-	mov	r10,QWORD PTR[16+rbp]
+	mov	r10,QWORD[16+rbp]
 	and	r9,rcx
 	not	r10
-	mov	r11,QWORD PTR[24+rbp]
+	mov	r11,QWORD[24+rbp]
 	and	r10,rcx
 	not	r11
-	mov	r12,QWORD PTR[32+rbp]
+	mov	r12,QWORD[32+rbp]
 	and	r11,rcx
 	not	r12
-	mov	r13,QWORD PTR[40+rbp]
+	mov	r13,QWORD[40+rbp]
 	and	r12,rcx
 	not	r13
-	mov	r14,QWORD PTR[48+rbp]
+	mov	r14,QWORD[48+rbp]
 	and	r13,rcx
 	not	r14
-	mov	r15,QWORD PTR[56+rbp]
+	mov	r15,QWORD[56+rbp]
 	and	r14,rcx
 	not	r15
 	and	r15,rcx
 
-	add	r8,QWORD PTR[rdi]
-	adc	r9,QWORD PTR[8+rdi]
-	adc	r10,QWORD PTR[16+rdi]
-	adc	r11,QWORD PTR[24+rdi]
-	adc	r12,QWORD PTR[32+rdi]
-	adc	r13,QWORD PTR[40+rdi]
-	adc	r14,QWORD PTR[48+rdi]
-	adc	r15,QWORD PTR[56+rdi]
-
-	mov	QWORD PTR[rdi],r8
-	mov	QWORD PTR[8+rdi],r9
-	mov	QWORD PTR[16+rdi],r10
-	mov	QWORD PTR[24+rdi],r11
-	mov	QWORD PTR[32+rdi],r12
-	mov	QWORD PTR[40+rdi],r13
-	mov	QWORD PTR[48+rdi],r14
-	mov	QWORD PTR[56+rdi],r15
+	add	r8,QWORD[rdi]
+	adc	r9,QWORD[8+rdi]
+	adc	r10,QWORD[16+rdi]
+	adc	r11,QWORD[24+rdi]
+	adc	r12,QWORD[32+rdi]
+	adc	r13,QWORD[40+rdi]
+	adc	r14,QWORD[48+rdi]
+	adc	r15,QWORD[56+rdi]
+
+	mov	QWORD[rdi],r8
+	mov	QWORD[8+rdi],r9
+	mov	QWORD[16+rdi],r10
+	mov	QWORD[24+rdi],r11
+	mov	QWORD[32+rdi],r12
+	mov	QWORD[40+rdi],r13
+	mov	QWORD[48+rdi],r14
+	mov	QWORD[56+rdi],r15
 
 	DB	0F3h,0C3h		;repret
-__rsaz_512_subtract	ENDP
+
 
 ALIGN	32
-__rsaz_512_mul	PROC PRIVATE
-	lea	rdi,QWORD PTR[8+rsp]
+__rsaz_512_mul:
+	lea	rdi,[8+rsp]
 
-	mov	rax,QWORD PTR[rsi]
+	mov	rax,QWORD[rsi]
 	mul	rbx
-	mov	QWORD PTR[rdi],rax
-	mov	rax,QWORD PTR[8+rsi]
+	mov	QWORD[rdi],rax
+	mov	rax,QWORD[8+rsi]
 	mov	r8,rdx
 
 	mul	rbx
 	add	r8,rax
-	mov	rax,QWORD PTR[16+rsi]
+	mov	rax,QWORD[16+rsi]
 	mov	r9,rdx
 	adc	r9,0
 
 	mul	rbx
 	add	r9,rax
-	mov	rax,QWORD PTR[24+rsi]
+	mov	rax,QWORD[24+rsi]
 	mov	r10,rdx
 	adc	r10,0
 
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD PTR[32+rsi]
+	mov	rax,QWORD[32+rsi]
 	mov	r11,rdx
 	adc	r11,0
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD PTR[40+rsi]
+	mov	rax,QWORD[40+rsi]
 	mov	r12,rdx
 	adc	r12,0
 
 	mul	rbx
 	add	r12,rax
-	mov	rax,QWORD PTR[48+rsi]
+	mov	rax,QWORD[48+rsi]
 	mov	r13,rdx
 	adc	r13,0
 
 	mul	rbx
 	add	r13,rax
-	mov	rax,QWORD PTR[56+rsi]
+	mov	rax,QWORD[56+rsi]
 	mov	r14,rdx
 	adc	r14,0
 
 	mul	rbx
 	add	r14,rax
-	mov	rax,QWORD PTR[rsi]
+	mov	rax,QWORD[rsi]
 	mov	r15,rdx
 	adc	r15,0
 
-	lea	rbp,QWORD PTR[8+rbp]
-	lea	rdi,QWORD PTR[8+rdi]
+	lea	rbp,[8+rbp]
+	lea	rdi,[8+rdi]
 
 	mov	ecx,7
-	jmp	$L$oop_mul
+	jmp	NEAR $L$oop_mul
 
 ALIGN	32
-$L$oop_mul::
-	mov	rbx,QWORD PTR[rbp]
+$L$oop_mul:
+	mov	rbx,QWORD[rbp]
 	mul	rbx
 	add	r8,rax
-	mov	rax,QWORD PTR[8+rsi]
-	mov	QWORD PTR[rdi],r8
+	mov	rax,QWORD[8+rsi]
+	mov	QWORD[rdi],r8
 	mov	r8,rdx
 	adc	r8,0
 
 	mul	rbx
 	add	r9,rax
-	mov	rax,QWORD PTR[16+rsi]
+	mov	rax,QWORD[16+rsi]
 	adc	rdx,0
 	add	r8,r9
 	mov	r9,rdx
@@ -1084,7 +1083,7 @@ $L$oop_mul::
 
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD PTR[24+rsi]
+	mov	rax,QWORD[24+rsi]
 	adc	rdx,0
 	add	r9,r10
 	mov	r10,rdx
@@ -1092,7 +1091,7 @@ $L$oop_mul::
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD PTR[32+rsi]
+	mov	rax,QWORD[32+rsi]
 	adc	rdx,0
 	add	r10,r11
 	mov	r11,rdx
@@ -1100,7 +1099,7 @@ $L$oop_mul::
 
 	mul	rbx
 	add	r12,rax
-	mov	rax,QWORD PTR[40+rsi]
+	mov	rax,QWORD[40+rsi]
 	adc	rdx,0
 	add	r11,r12
 	mov	r12,rdx
@@ -1108,7 +1107,7 @@ $L$oop_mul::
 
 	mul	rbx
 	add	r13,rax
-	mov	rax,QWORD PTR[48+rsi]
+	mov	rax,QWORD[48+rsi]
 	adc	rdx,0
 	add	r12,r13
 	mov	r13,rdx
@@ -1116,81 +1115,81 @@ $L$oop_mul::
 
 	mul	rbx
 	add	r14,rax
-	mov	rax,QWORD PTR[56+rsi]
+	mov	rax,QWORD[56+rsi]
 	adc	rdx,0
 	add	r13,r14
 	mov	r14,rdx
-	lea	rbp,QWORD PTR[8+rbp]
+	lea	rbp,[8+rbp]
 	adc	r14,0
 
 	mul	rbx
 	add	r15,rax
-	mov	rax,QWORD PTR[rsi]
+	mov	rax,QWORD[rsi]
 	adc	rdx,0
 	add	r14,r15
 	mov	r15,rdx
 	adc	r15,0
 
-	lea	rdi,QWORD PTR[8+rdi]
+	lea	rdi,[8+rdi]
 
 	dec	ecx
-	jnz	$L$oop_mul
+	jnz	NEAR $L$oop_mul
 
-	mov	QWORD PTR[rdi],r8
-	mov	QWORD PTR[8+rdi],r9
-	mov	QWORD PTR[16+rdi],r10
-	mov	QWORD PTR[24+rdi],r11
-	mov	QWORD PTR[32+rdi],r12
-	mov	QWORD PTR[40+rdi],r13
-	mov	QWORD PTR[48+rdi],r14
-	mov	QWORD PTR[56+rdi],r15
+	mov	QWORD[rdi],r8
+	mov	QWORD[8+rdi],r9
+	mov	QWORD[16+rdi],r10
+	mov	QWORD[24+rdi],r11
+	mov	QWORD[32+rdi],r12
+	mov	QWORD[40+rdi],r13
+	mov	QWORD[48+rdi],r14
+	mov	QWORD[56+rdi],r15
 
 	DB	0F3h,0C3h		;repret
-__rsaz_512_mul	ENDP
-PUBLIC	rsaz_512_scatter4
+
+global	rsaz_512_scatter4
 
 ALIGN	16
-rsaz_512_scatter4	PROC PUBLIC
-	lea	rcx,QWORD PTR[r8*4+rcx]
+rsaz_512_scatter4:
+	lea	rcx,[r8*4+rcx]
 	mov	r9d,8
-	jmp	$L$oop_scatter
+	jmp	NEAR $L$oop_scatter
 ALIGN	16
-$L$oop_scatter::
-	mov	rax,QWORD PTR[rdx]
-	lea	rdx,QWORD PTR[8+rdx]
-	mov	DWORD PTR[rcx],eax
+$L$oop_scatter:
+	mov	rax,QWORD[rdx]
+	lea	rdx,[8+rdx]
+	mov	DWORD[rcx],eax
 	shr	rax,32
-	mov	DWORD PTR[64+rcx],eax
-	lea	rcx,QWORD PTR[128+rcx]
+	mov	DWORD[64+rcx],eax
+	lea	rcx,[128+rcx]
 	dec	r9d
-	jnz	$L$oop_scatter
+	jnz	NEAR $L$oop_scatter
 	DB	0F3h,0C3h		;repret
-rsaz_512_scatter4	ENDP
 
-PUBLIC	rsaz_512_gather4
+
+global	rsaz_512_gather4
 
 ALIGN	16
-rsaz_512_gather4	PROC PUBLIC
-	lea	rdx,QWORD PTR[r8*4+rdx]
+rsaz_512_gather4:
+	lea	rdx,[r8*4+rdx]
 	mov	r9d,8
-	jmp	$L$oop_gather
+	jmp	NEAR $L$oop_gather
 ALIGN	16
-$L$oop_gather::
-	mov	eax,DWORD PTR[rdx]
-	mov	r8d,DWORD PTR[64+rdx]
-	lea	rdx,QWORD PTR[128+rdx]
+$L$oop_gather:
+	mov	eax,DWORD[rdx]
+	mov	r8d,DWORD[64+rdx]
+	lea	rdx,[128+rdx]
 	shl	r8,32
 	or	rax,r8
-	mov	QWORD PTR[rcx],rax
-	lea	rcx,QWORD PTR[8+rcx]
+	mov	QWORD[rcx],rax
+	lea	rcx,[8+rcx]
 	dec	r9d
-	jnz	$L$oop_gather
+	jnz	NEAR $L$oop_gather
 	DB	0F3h,0C3h		;repret
-rsaz_512_gather4	ENDP
-EXTERN	__imp_RtlVirtualUnwind:NEAR
+
+EXTERN	__imp_RtlVirtualUnwind
 
 ALIGN	16
-se_handler	PROC PRIVATE
+se_handler:
 	push	rsi
 	push	rdi
 	push	rbx
@@ -1202,64 +1201,64 @@ se_handler	PROC PRIVATE
 	pushfq
 	sub	rsp,64
 
-	mov	rax,QWORD PTR[120+r8]
-	mov	rbx,QWORD PTR[248+r8]
+	mov	rax,QWORD[120+r8]
+	mov	rbx,QWORD[248+r8]
 
-	mov	rsi,QWORD PTR[8+r9]
-	mov	r11,QWORD PTR[56+r9]
+	mov	rsi,QWORD[8+r9]
+	mov	r11,QWORD[56+r9]
 
-	mov	r10d,DWORD PTR[r11]
-	lea	r10,QWORD PTR[r10*1+rsi]
+	mov	r10d,DWORD[r11]
+	lea	r10,[r10*1+rsi]
 	cmp	rbx,r10
-	jb	$L$common_seh_tail
+	jb	NEAR $L$common_seh_tail
 
-	mov	rax,QWORD PTR[152+r8]
+	mov	rax,QWORD[152+r8]
 
-	mov	r10d,DWORD PTR[4+r11]
-	lea	r10,QWORD PTR[r10*1+rsi]
+	mov	r10d,DWORD[4+r11]
+	lea	r10,[r10*1+rsi]
 	cmp	rbx,r10
-	jae	$L$common_seh_tail
-
-	lea	rax,QWORD PTR[((128+24+48))+rax]
-
-	mov	rbx,QWORD PTR[((-8))+rax]
-	mov	rbp,QWORD PTR[((-16))+rax]
-	mov	r12,QWORD PTR[((-24))+rax]
-	mov	r13,QWORD PTR[((-32))+rax]
-	mov	r14,QWORD PTR[((-40))+rax]
-	mov	r15,QWORD PTR[((-48))+rax]
-	mov	QWORD PTR[144+r8],rbx
-	mov	QWORD PTR[160+r8],rbp
-	mov	QWORD PTR[216+r8],r12
-	mov	QWORD PTR[224+r8],r13
-	mov	QWORD PTR[232+r8],r14
-	mov	QWORD PTR[240+r8],r15
-
-$L$common_seh_tail::
-	mov	rdi,QWORD PTR[8+rax]
-	mov	rsi,QWORD PTR[16+rax]
-	mov	QWORD PTR[152+r8],rax
-	mov	QWORD PTR[168+r8],rsi
-	mov	QWORD PTR[176+r8],rdi
-
-	mov	rdi,QWORD PTR[40+r9]
+	jae	NEAR $L$common_seh_tail
+
+	lea	rax,[((128+24+48))+rax]
+
+	mov	rbx,QWORD[((-8))+rax]
+	mov	rbp,QWORD[((-16))+rax]
+	mov	r12,QWORD[((-24))+rax]
+	mov	r13,QWORD[((-32))+rax]
+	mov	r14,QWORD[((-40))+rax]
+	mov	r15,QWORD[((-48))+rax]
+	mov	QWORD[144+r8],rbx
+	mov	QWORD[160+r8],rbp
+	mov	QWORD[216+r8],r12
+	mov	QWORD[224+r8],r13
+	mov	QWORD[232+r8],r14
+	mov	QWORD[240+r8],r15
+
+$L$common_seh_tail:
+	mov	rdi,QWORD[8+rax]
+	mov	rsi,QWORD[16+rax]
+	mov	QWORD[152+r8],rax
+	mov	QWORD[168+r8],rsi
+	mov	QWORD[176+r8],rdi
+
+	mov	rdi,QWORD[40+r9]
 	mov	rsi,r8
 	mov	ecx,154
-	DD	0a548f3fch
+	DD	0xa548f3fc
 
 	mov	rsi,r9
 	xor	rcx,rcx
-	mov	rdx,QWORD PTR[8+rsi]
-	mov	r8,QWORD PTR[rsi]
-	mov	r9,QWORD PTR[16+rsi]
-	mov	r10,QWORD PTR[40+rsi]
-	lea	r11,QWORD PTR[56+rsi]
-	lea	r12,QWORD PTR[24+rsi]
-	mov	QWORD PTR[32+rsp],r10
-	mov	QWORD PTR[40+rsp],r11
-	mov	QWORD PTR[48+rsp],r12
-	mov	QWORD PTR[56+rsp],rcx
-	call	QWORD PTR[__imp_RtlVirtualUnwind]
+	mov	rdx,QWORD[8+rsi]
+	mov	r8,QWORD[rsi]
+	mov	r9,QWORD[16+rsi]
+	mov	r10,QWORD[40+rsi]
+	lea	r11,[56+rsi]
+	lea	r12,[24+rsi]
+	mov	QWORD[32+rsp],r10
+	mov	QWORD[40+rsp],r11
+	mov	QWORD[48+rsp],r12
+	mov	QWORD[56+rsp],rcx
+	call	QWORD[__imp_RtlVirtualUnwind]
 
 	mov	eax,1
 	add	rsp,64
@@ -1273,54 +1272,49 @@ $L$common_seh_tail::
 	pop	rdi
 	pop	rsi
 	DB	0F3h,0C3h		;repret
-se_handler	ENDP
 
-.text$	ENDS
-.pdata	SEGMENT READONLY ALIGN(4)
+
+section	.pdata rdata align=4
 ALIGN	4
-	DD	imagerel $L$SEH_begin_rsaz_512_sqr
-	DD	imagerel $L$SEH_end_rsaz_512_sqr
-	DD	imagerel $L$SEH_info_rsaz_512_sqr
+	DD	$L$SEH_begin_rsaz_512_sqr wrt ..imagebase
+	DD	$L$SEH_end_rsaz_512_sqr wrt ..imagebase
+	DD	$L$SEH_info_rsaz_512_sqr wrt ..imagebase
 
-	DD	imagerel $L$SEH_begin_rsaz_512_mul
-	DD	imagerel $L$SEH_end_rsaz_512_mul
-	DD	imagerel $L$SEH_info_rsaz_512_mul
+	DD	$L$SEH_begin_rsaz_512_mul wrt ..imagebase
+	DD	$L$SEH_end_rsaz_512_mul wrt ..imagebase
+	DD	$L$SEH_info_rsaz_512_mul wrt ..imagebase
 
-	DD	imagerel $L$SEH_begin_rsaz_512_mul_gather4
-	DD	imagerel $L$SEH_end_rsaz_512_mul_gather4
-	DD	imagerel $L$SEH_info_rsaz_512_mul_gather4
+	DD	$L$SEH_begin_rsaz_512_mul_gather4 wrt ..imagebase
+	DD	$L$SEH_end_rsaz_512_mul_gather4 wrt ..imagebase
+	DD	$L$SEH_info_rsaz_512_mul_gather4 wrt ..imagebase
 
-	DD	imagerel $L$SEH_begin_rsaz_512_mul_scatter4
-	DD	imagerel $L$SEH_end_rsaz_512_mul_scatter4
-	DD	imagerel $L$SEH_info_rsaz_512_mul_scatter4
+	DD	$L$SEH_begin_rsaz_512_mul_scatter4 wrt ..imagebase
+	DD	$L$SEH_end_rsaz_512_mul_scatter4 wrt ..imagebase
+	DD	$L$SEH_info_rsaz_512_mul_scatter4 wrt ..imagebase
 
-	DD	imagerel $L$SEH_begin_rsaz_512_mul_by_one
-	DD	imagerel $L$SEH_end_rsaz_512_mul_by_one
-	DD	imagerel $L$SEH_info_rsaz_512_mul_by_one
+	DD	$L$SEH_begin_rsaz_512_mul_by_one wrt ..imagebase
+	DD	$L$SEH_end_rsaz_512_mul_by_one wrt ..imagebase
+	DD	$L$SEH_info_rsaz_512_mul_by_one wrt ..imagebase
 
-.pdata	ENDS
-.xdata	SEGMENT READONLY ALIGN(8)
+section	.xdata rdata align=8
 ALIGN	8
-$L$SEH_info_rsaz_512_sqr::
+$L$SEH_info_rsaz_512_sqr:
 DB	9,0,0,0
-	DD	imagerel se_handler
-	DD	imagerel $L$sqr_body,imagerel $L$sqr_epilogue
-$L$SEH_info_rsaz_512_mul::
+	DD	se_handler wrt ..imagebase
+	DD	$L$sqr_body wrt ..imagebase,$L$sqr_epilogue wrt ..imagebase
+$L$SEH_info_rsaz_512_mul:
 DB	9,0,0,0
-	DD	imagerel se_handler
-	DD	imagerel $L$mul_body,imagerel $L$mul_epilogue
-$L$SEH_info_rsaz_512_mul_gather4::
+	DD	se_handler wrt ..imagebase
+	DD	$L$mul_body wrt ..imagebase,$L$mul_epilogue wrt ..imagebase
+$L$SEH_info_rsaz_512_mul_gather4:
 DB	9,0,0,0
-	DD	imagerel se_handler
-	DD	imagerel $L$mul_gather4_body,imagerel $L$mul_gather4_epilogue
-$L$SEH_info_rsaz_512_mul_scatter4::
+	DD	se_handler wrt ..imagebase
+	DD	$L$mul_gather4_body wrt ..imagebase,$L$mul_gather4_epilogue wrt ..imagebase
+$L$SEH_info_rsaz_512_mul_scatter4:
 DB	9,0,0,0
-	DD	imagerel se_handler
-	DD	imagerel $L$mul_scatter4_body,imagerel $L$mul_scatter4_epilogue
-$L$SEH_info_rsaz_512_mul_by_one::
+	DD	se_handler wrt ..imagebase
+	DD	$L$mul_scatter4_body wrt ..imagebase,$L$mul_scatter4_epilogue wrt ..imagebase
+$L$SEH_info_rsaz_512_mul_by_one:
 DB	9,0,0,0
-	DD	imagerel se_handler
-	DD	imagerel $L$mul_by_one_body,imagerel $L$mul_by_one_epilogue
-
-.xdata	ENDS
-END
+	DD	se_handler wrt ..imagebase
+	DD	$L$mul_by_one_body wrt ..imagebase,$L$mul_by_one_epilogue wrt ..imagebase
diff --git a/win-x86_64/crypto/bn/x86_64-mont.asm b/win-x86_64/crypto/bn/x86_64-mont.asm
index a409325..db0d1b9 100644
--- a/win-x86_64/crypto/bn/x86_64-mont.asm
+++ b/win-x86_64/crypto/bn/x86_64-mont.asm
@@ -1,36 +1,40 @@
-OPTION	DOTNAME
-.text$	SEGMENT ALIGN(256) 'CODE'
+default	rel
+%define XMMWORD
+%define YMMWORD
+%define ZMMWORD
+section	.text code align=64
 
-EXTERN	OPENSSL_ia32cap_P:NEAR
 
-PUBLIC	bn_mul_mont
+EXTERN	OPENSSL_ia32cap_P
+
+global	bn_mul_mont
 
 ALIGN	16
-bn_mul_mont	PROC PUBLIC
-	mov	QWORD PTR[8+rsp],rdi	;WIN64 prologue
-	mov	QWORD PTR[16+rsp],rsi
+bn_mul_mont:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
 	mov	rax,rsp
-$L$SEH_begin_bn_mul_mont::
+$L$SEH_begin_bn_mul_mont:
 	mov	rdi,rcx
 	mov	rsi,rdx
 	mov	rdx,r8
 	mov	rcx,r9
-	mov	r8,QWORD PTR[40+rsp]
-	mov	r9,QWORD PTR[48+rsp]
+	mov	r8,QWORD[40+rsp]
+	mov	r9,QWORD[48+rsp]
 
 
 	test	r9d,3
-	jnz	$L$mul_enter
+	jnz	NEAR $L$mul_enter
 	cmp	r9d,8
-	jb	$L$mul_enter
+	jb	NEAR $L$mul_enter
 	cmp	rdx,rsi
-	jne	$L$mul4x_enter
+	jne	NEAR $L$mul4x_enter
 	test	r9d,7
-	jz	$L$sqr8x_enter
-	jmp	$L$mul4x_enter
+	jz	NEAR $L$sqr8x_enter
+	jmp	NEAR $L$mul4x_enter
 
 ALIGN	16
-$L$mul_enter::
+$L$mul_enter:
 	push	rbx
 	push	rbp
 	push	r12
@@ -39,18 +43,18 @@ $L$mul_enter::
 	push	r15
 
 	mov	r9d,r9d
-	lea	r10,QWORD PTR[2+r9]
+	lea	r10,[2+r9]
 	mov	r11,rsp
 	neg	r10
-	lea	rsp,QWORD PTR[r10*8+rsp]
+	lea	rsp,[r10*8+rsp]
 	and	rsp,-1024
 
-	mov	QWORD PTR[8+r9*8+rsp],r11
-$L$mul_body::
+	mov	QWORD[8+r9*8+rsp],r11
+$L$mul_body:
 	mov	r12,rdx
-	mov	r8,QWORD PTR[r8]
-	mov	rbx,QWORD PTR[r12]
-	mov	rax,QWORD PTR[rsi]
+	mov	r8,QWORD[r8]
+	mov	rbx,QWORD[r12]
+	mov	rax,QWORD[rsi]
 
 	xor	r14,r14
 	xor	r15,r15
@@ -58,69 +62,69 @@ $L$mul_body::
 	mov	rbp,r8
 	mul	rbx
 	mov	r10,rax
-	mov	rax,QWORD PTR[rcx]
+	mov	rax,QWORD[rcx]
 
 	imul	rbp,r10
 	mov	r11,rdx
 
 	mul	rbp
 	add	r10,rax
-	mov	rax,QWORD PTR[8+rsi]
+	mov	rax,QWORD[8+rsi]
 	adc	rdx,0
 	mov	r13,rdx
 
-	lea	r15,QWORD PTR[1+r15]
-	jmp	$L$1st_enter
+	lea	r15,[1+r15]
+	jmp	NEAR $L$1st_enter
 
 ALIGN	16
-$L$1st::
+$L$1st:
 	add	r13,rax
-	mov	rax,QWORD PTR[r15*8+rsi]
+	mov	rax,QWORD[r15*8+rsi]
 	adc	rdx,0
 	add	r13,r11
 	mov	r11,r10
 	adc	rdx,0
-	mov	QWORD PTR[((-16))+r15*8+rsp],r13
+	mov	QWORD[((-16))+r15*8+rsp],r13
 	mov	r13,rdx
 
-$L$1st_enter::
+$L$1st_enter:
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD PTR[r15*8+rcx]
+	mov	rax,QWORD[r15*8+rcx]
 	adc	rdx,0
-	lea	r15,QWORD PTR[1+r15]
+	lea	r15,[1+r15]
 	mov	r10,rdx
 
 	mul	rbp
 	cmp	r15,r9
-	jne	$L$1st
+	jne	NEAR $L$1st
 
 	add	r13,rax
-	mov	rax,QWORD PTR[rsi]
+	mov	rax,QWORD[rsi]
 	adc	rdx,0
 	add	r13,r11
 	adc	rdx,0
-	mov	QWORD PTR[((-16))+r15*8+rsp],r13
+	mov	QWORD[((-16))+r15*8+rsp],r13
 	mov	r13,rdx
 	mov	r11,r10
 
 	xor	rdx,rdx
 	add	r13,r11
 	adc	rdx,0
-	mov	QWORD PTR[((-8))+r9*8+rsp],r13
-	mov	QWORD PTR[r9*8+rsp],rdx
+	mov	QWORD[((-8))+r9*8+rsp],r13
+	mov	QWORD[r9*8+rsp],rdx
 
-	lea	r14,QWORD PTR[1+r14]
-	jmp	$L$outer
+	lea	r14,[1+r14]
+	jmp	NEAR $L$outer
 ALIGN	16
-$L$outer::
-	mov	rbx,QWORD PTR[r14*8+r12]
+$L$outer:
+	mov	rbx,QWORD[r14*8+r12]
 	xor	r15,r15
 	mov	rbp,r8
-	mov	r10,QWORD PTR[rsp]
+	mov	r10,QWORD[rsp]
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD PTR[rcx]
+	mov	rax,QWORD[rcx]
 	adc	rdx,0
 
 	imul	rbp,r10
@@ -128,46 +132,46 @@ $L$outer::
 
 	mul	rbp
 	add	r10,rax
-	mov	rax,QWORD PTR[8+rsi]
+	mov	rax,QWORD[8+rsi]
 	adc	rdx,0
-	mov	r10,QWORD PTR[8+rsp]
+	mov	r10,QWORD[8+rsp]
 	mov	r13,rdx
 
-	lea	r15,QWORD PTR[1+r15]
-	jmp	$L$inner_enter
+	lea	r15,[1+r15]
+	jmp	NEAR $L$inner_enter
 
 ALIGN	16
-$L$inner::
+$L$inner:
 	add	r13,rax
-	mov	rax,QWORD PTR[r15*8+rsi]
+	mov	rax,QWORD[r15*8+rsi]
 	adc	rdx,0
 	add	r13,r10
-	mov	r10,QWORD PTR[r15*8+rsp]
+	mov	r10,QWORD[r15*8+rsp]
 	adc	rdx,0
-	mov	QWORD PTR[((-16))+r15*8+rsp],r13
+	mov	QWORD[((-16))+r15*8+rsp],r13
 	mov	r13,rdx
 
-$L$inner_enter::
+$L$inner_enter:
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD PTR[r15*8+rcx]
+	mov	rax,QWORD[r15*8+rcx]
 	adc	rdx,0
 	add	r10,r11
 	mov	r11,rdx
 	adc	r11,0
-	lea	r15,QWORD PTR[1+r15]
+	lea	r15,[1+r15]
 
 	mul	rbp
 	cmp	r15,r9
-	jne	$L$inner
+	jne	NEAR $L$inner
 
 	add	r13,rax
-	mov	rax,QWORD PTR[rsi]
+	mov	rax,QWORD[rsi]
 	adc	rdx,0
 	add	r13,r10
-	mov	r10,QWORD PTR[r15*8+rsp]
+	mov	r10,QWORD[r15*8+rsp]
 	adc	rdx,0
-	mov	QWORD PTR[((-16))+r15*8+rsp],r13
+	mov	QWORD[((-16))+r15*8+rsp],r13
 	mov	r13,rdx
 
 	xor	rdx,rdx
@@ -175,73 +179,72 @@ $L$inner_enter::
 	adc	rdx,0
 	add	r13,r10
 	adc	rdx,0
-	mov	QWORD PTR[((-8))+r9*8+rsp],r13
-	mov	QWORD PTR[r9*8+rsp],rdx
+	mov	QWORD[((-8))+r9*8+rsp],r13
+	mov	QWORD[r9*8+rsp],rdx
 
-	lea	r14,QWORD PTR[1+r14]
+	lea	r14,[1+r14]
 	cmp	r14,r9
-	jb	$L$outer
+	jb	NEAR $L$outer
 
 	xor	r14,r14
-	mov	rax,QWORD PTR[rsp]
-	lea	rsi,QWORD PTR[rsp]
+	mov	rax,QWORD[rsp]
+	lea	rsi,[rsp]
 	mov	r15,r9
-	jmp	$L$sub
+	jmp	NEAR $L$sub
 ALIGN	16
-$L$sub::	sbb	rax,QWORD PTR[r14*8+rcx]
-	mov	QWORD PTR[r14*8+rdi],rax
-	mov	rax,QWORD PTR[8+r14*8+rsi]
-	lea	r14,QWORD PTR[1+r14]
+$L$sub:	sbb	rax,QWORD[r14*8+rcx]
+	mov	QWORD[r14*8+rdi],rax
+	mov	rax,QWORD[8+r14*8+rsi]
+	lea	r14,[1+r14]
 	dec	r15
-	jnz	$L$sub
+	jnz	NEAR $L$sub
 
 	sbb	rax,0
 	xor	r14,r14
 	mov	r15,r9
 ALIGN	16
-$L$copy::
-	mov	rsi,QWORD PTR[r14*8+rsp]
-	mov	rcx,QWORD PTR[r14*8+rdi]
+$L$copy:
+	mov	rsi,QWORD[r14*8+rsp]
+	mov	rcx,QWORD[r14*8+rdi]
 	xor	rsi,rcx
 	and	rsi,rax
 	xor	rsi,rcx
-	mov	QWORD PTR[r14*8+rsp],r14
-	mov	QWORD PTR[r14*8+rdi],rsi
-	lea	r14,QWORD PTR[1+r14]
+	mov	QWORD[r14*8+rsp],r14
+	mov	QWORD[r14*8+rdi],rsi
+	lea	r14,[1+r14]
 	sub	r15,1
-	jnz	$L$copy
+	jnz	NEAR $L$copy
 
-	mov	rsi,QWORD PTR[8+r9*8+rsp]
+	mov	rsi,QWORD[8+r9*8+rsp]
 	mov	rax,1
-	mov	r15,QWORD PTR[rsi]
-	mov	r14,QWORD PTR[8+rsi]
-	mov	r13,QWORD PTR[16+rsi]
-	mov	r12,QWORD PTR[24+rsi]
-	mov	rbp,QWORD PTR[32+rsi]
-	mov	rbx,QWORD PTR[40+rsi]
-	lea	rsp,QWORD PTR[48+rsi]
-$L$mul_epilogue::
-	mov	rdi,QWORD PTR[8+rsp]	;WIN64 epilogue
-	mov	rsi,QWORD PTR[16+rsp]
+	mov	r15,QWORD[rsi]
+	mov	r14,QWORD[8+rsi]
+	mov	r13,QWORD[16+rsi]
+	mov	r12,QWORD[24+rsi]
+	mov	rbp,QWORD[32+rsi]
+	mov	rbx,QWORD[40+rsi]
+	lea	rsp,[48+rsi]
+$L$mul_epilogue:
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
-$L$SEH_end_bn_mul_mont::
-bn_mul_mont	ENDP
+$L$SEH_end_bn_mul_mont:
 
 ALIGN	16
-bn_mul4x_mont	PROC PRIVATE
-	mov	QWORD PTR[8+rsp],rdi	;WIN64 prologue
-	mov	QWORD PTR[16+rsp],rsi
+bn_mul4x_mont:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
 	mov	rax,rsp
-$L$SEH_begin_bn_mul4x_mont::
+$L$SEH_begin_bn_mul4x_mont:
 	mov	rdi,rcx
 	mov	rsi,rdx
 	mov	rdx,r8
 	mov	rcx,r9
-	mov	r8,QWORD PTR[40+rsp]
-	mov	r9,QWORD PTR[48+rsp]
+	mov	r8,QWORD[40+rsp]
+	mov	r9,QWORD[48+rsp]
 
 
-$L$mul4x_enter::
+$L$mul4x_enter:
 	push	rbx
 	push	rbp
 	push	r12
@@ -250,19 +253,19 @@ $L$mul4x_enter::
 	push	r15
 
 	mov	r9d,r9d
-	lea	r10,QWORD PTR[4+r9]
+	lea	r10,[4+r9]
 	mov	r11,rsp
 	neg	r10
-	lea	rsp,QWORD PTR[r10*8+rsp]
+	lea	rsp,[r10*8+rsp]
 	and	rsp,-1024
 
-	mov	QWORD PTR[8+r9*8+rsp],r11
-$L$mul4x_body::
-	mov	QWORD PTR[16+r9*8+rsp],rdi
+	mov	QWORD[8+r9*8+rsp],r11
+$L$mul4x_body:
+	mov	QWORD[16+r9*8+rsp],rdi
 	mov	r12,rdx
-	mov	r8,QWORD PTR[r8]
-	mov	rbx,QWORD PTR[r12]
-	mov	rax,QWORD PTR[rsi]
+	mov	r8,QWORD[r8]
+	mov	rbx,QWORD[r12]
+	mov	rax,QWORD[rsi]
 
 	xor	r14,r14
 	xor	r15,r15
@@ -270,144 +273,144 @@ $L$mul4x_body::
 	mov	rbp,r8
 	mul	rbx
 	mov	r10,rax
-	mov	rax,QWORD PTR[rcx]
+	mov	rax,QWORD[rcx]
 
 	imul	rbp,r10
 	mov	r11,rdx
 
 	mul	rbp
 	add	r10,rax
-	mov	rax,QWORD PTR[8+rsi]
+	mov	rax,QWORD[8+rsi]
 	adc	rdx,0
 	mov	rdi,rdx
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD PTR[8+rcx]
+	mov	rax,QWORD[8+rcx]
 	adc	rdx,0
 	mov	r10,rdx
 
 	mul	rbp
 	add	rdi,rax
-	mov	rax,QWORD PTR[16+rsi]
+	mov	rax,QWORD[16+rsi]
 	adc	rdx,0
 	add	rdi,r11
-	lea	r15,QWORD PTR[4+r15]
+	lea	r15,[4+r15]
 	adc	rdx,0
-	mov	QWORD PTR[rsp],rdi
+	mov	QWORD[rsp],rdi
 	mov	r13,rdx
-	jmp	$L$1st4x
+	jmp	NEAR $L$1st4x
 ALIGN	16
-$L$1st4x::
+$L$1st4x:
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD PTR[((-16))+r15*8+rcx]
+	mov	rax,QWORD[((-16))+r15*8+rcx]
 	adc	rdx,0
 	mov	r11,rdx
 
 	mul	rbp
 	add	r13,rax
-	mov	rax,QWORD PTR[((-8))+r15*8+rsi]
+	mov	rax,QWORD[((-8))+r15*8+rsi]
 	adc	rdx,0
 	add	r13,r10
 	adc	rdx,0
-	mov	QWORD PTR[((-24))+r15*8+rsp],r13
+	mov	QWORD[((-24))+r15*8+rsp],r13
 	mov	rdi,rdx
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD PTR[((-8))+r15*8+rcx]
+	mov	rax,QWORD[((-8))+r15*8+rcx]
 	adc	rdx,0
 	mov	r10,rdx
 
 	mul	rbp
 	add	rdi,rax
-	mov	rax,QWORD PTR[r15*8+rsi]
+	mov	rax,QWORD[r15*8+rsi]
 	adc	rdx,0
 	add	rdi,r11
 	adc	rdx,0
-	mov	QWORD PTR[((-16))+r15*8+rsp],rdi
+	mov	QWORD[((-16))+r15*8+rsp],rdi
 	mov	r13,rdx
 
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD PTR[r15*8+rcx]
+	mov	rax,QWORD[r15*8+rcx]
 	adc	rdx,0
 	mov	r11,rdx
 
 	mul	rbp
 	add	r13,rax
-	mov	rax,QWORD PTR[8+r15*8+rsi]
+	mov	rax,QWORD[8+r15*8+rsi]
 	adc	rdx,0
 	add	r13,r10
 	adc	rdx,0
-	mov	QWORD PTR[((-8))+r15*8+rsp],r13
+	mov	QWORD[((-8))+r15*8+rsp],r13
 	mov	rdi,rdx
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD PTR[8+r15*8+rcx]
+	mov	rax,QWORD[8+r15*8+rcx]
 	adc	rdx,0
-	lea	r15,QWORD PTR[4+r15]
+	lea	r15,[4+r15]
 	mov	r10,rdx
 
 	mul	rbp
 	add	rdi,rax
-	mov	rax,QWORD PTR[((-16))+r15*8+rsi]
+	mov	rax,QWORD[((-16))+r15*8+rsi]
 	adc	rdx,0
 	add	rdi,r11
 	adc	rdx,0
-	mov	QWORD PTR[((-32))+r15*8+rsp],rdi
+	mov	QWORD[((-32))+r15*8+rsp],rdi
 	mov	r13,rdx
 	cmp	r15,r9
-	jb	$L$1st4x
+	jb	NEAR $L$1st4x
 
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD PTR[((-16))+r15*8+rcx]
+	mov	rax,QWORD[((-16))+r15*8+rcx]
 	adc	rdx,0
 	mov	r11,rdx
 
 	mul	rbp
 	add	r13,rax
-	mov	rax,QWORD PTR[((-8))+r15*8+rsi]
+	mov	rax,QWORD[((-8))+r15*8+rsi]
 	adc	rdx,0
 	add	r13,r10
 	adc	rdx,0
-	mov	QWORD PTR[((-24))+r15*8+rsp],r13
+	mov	QWORD[((-24))+r15*8+rsp],r13
 	mov	rdi,rdx
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD PTR[((-8))+r15*8+rcx]
+	mov	rax,QWORD[((-8))+r15*8+rcx]
 	adc	rdx,0
 	mov	r10,rdx
 
 	mul	rbp
 	add	rdi,rax
-	mov	rax,QWORD PTR[rsi]
+	mov	rax,QWORD[rsi]
 	adc	rdx,0
 	add	rdi,r11
 	adc	rdx,0
-	mov	QWORD PTR[((-16))+r15*8+rsp],rdi
+	mov	QWORD[((-16))+r15*8+rsp],rdi
 	mov	r13,rdx
 
 	xor	rdi,rdi
 	add	r13,r10
 	adc	rdi,0
-	mov	QWORD PTR[((-8))+r15*8+rsp],r13
-	mov	QWORD PTR[r15*8+rsp],rdi
+	mov	QWORD[((-8))+r15*8+rsp],r13
+	mov	QWORD[r15*8+rsp],rdi
 
-	lea	r14,QWORD PTR[1+r14]
+	lea	r14,[1+r14]
 ALIGN	4
-$L$outer4x::
-	mov	rbx,QWORD PTR[r14*8+r12]
+$L$outer4x:
+	mov	rbx,QWORD[r14*8+r12]
 	xor	r15,r15
-	mov	r10,QWORD PTR[rsp]
+	mov	r10,QWORD[rsp]
 	mov	rbp,r8
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD PTR[rcx]
+	mov	rax,QWORD[rcx]
 	adc	rdx,0
 
 	imul	rbp,r10
@@ -415,248 +418,247 @@ $L$outer4x::
 
 	mul	rbp
 	add	r10,rax
-	mov	rax,QWORD PTR[8+rsi]
+	mov	rax,QWORD[8+rsi]
 	adc	rdx,0
 	mov	rdi,rdx
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD PTR[8+rcx]
+	mov	rax,QWORD[8+rcx]
 	adc	rdx,0
-	add	r11,QWORD PTR[8+rsp]
+	add	r11,QWORD[8+rsp]
 	adc	rdx,0
 	mov	r10,rdx
 
 	mul	rbp
 	add	rdi,rax
-	mov	rax,QWORD PTR[16+rsi]
+	mov	rax,QWORD[16+rsi]
 	adc	rdx,0
 	add	rdi,r11
-	lea	r15,QWORD PTR[4+r15]
+	lea	r15,[4+r15]
 	adc	rdx,0
-	mov	QWORD PTR[rsp],rdi
+	mov	QWORD[rsp],rdi
 	mov	r13,rdx
-	jmp	$L$inner4x
+	jmp	NEAR $L$inner4x
 ALIGN	16
-$L$inner4x::
+$L$inner4x:
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD PTR[((-16))+r15*8+rcx]
+	mov	rax,QWORD[((-16))+r15*8+rcx]
 	adc	rdx,0
-	add	r10,QWORD PTR[((-16))+r15*8+rsp]
+	add	r10,QWORD[((-16))+r15*8+rsp]
 	adc	rdx,0
 	mov	r11,rdx
 
 	mul	rbp
 	add	r13,rax
-	mov	rax,QWORD PTR[((-8))+r15*8+rsi]
+	mov	rax,QWORD[((-8))+r15*8+rsi]
 	adc	rdx,0
 	add	r13,r10
 	adc	rdx,0
-	mov	QWORD PTR[((-24))+r15*8+rsp],r13
+	mov	QWORD[((-24))+r15*8+rsp],r13
 	mov	rdi,rdx
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD PTR[((-8))+r15*8+rcx]
+	mov	rax,QWORD[((-8))+r15*8+rcx]
 	adc	rdx,0
-	add	r11,QWORD PTR[((-8))+r15*8+rsp]
+	add	r11,QWORD[((-8))+r15*8+rsp]
 	adc	rdx,0
 	mov	r10,rdx
 
 	mul	rbp
 	add	rdi,rax
-	mov	rax,QWORD PTR[r15*8+rsi]
+	mov	rax,QWORD[r15*8+rsi]
 	adc	rdx,0
 	add	rdi,r11
 	adc	rdx,0
-	mov	QWORD PTR[((-16))+r15*8+rsp],rdi
+	mov	QWORD[((-16))+r15*8+rsp],rdi
 	mov	r13,rdx
 
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD PTR[r15*8+rcx]
+	mov	rax,QWORD[r15*8+rcx]
 	adc	rdx,0
-	add	r10,QWORD PTR[r15*8+rsp]
+	add	r10,QWORD[r15*8+rsp]
 	adc	rdx,0
 	mov	r11,rdx
 
 	mul	rbp
 	add	r13,rax
-	mov	rax,QWORD PTR[8+r15*8+rsi]
+	mov	rax,QWORD[8+r15*8+rsi]
 	adc	rdx,0
 	add	r13,r10
 	adc	rdx,0
-	mov	QWORD PTR[((-8))+r15*8+rsp],r13
+	mov	QWORD[((-8))+r15*8+rsp],r13
 	mov	rdi,rdx
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD PTR[8+r15*8+rcx]
+	mov	rax,QWORD[8+r15*8+rcx]
 	adc	rdx,0
-	add	r11,QWORD PTR[8+r15*8+rsp]
+	add	r11,QWORD[8+r15*8+rsp]
 	adc	rdx,0
-	lea	r15,QWORD PTR[4+r15]
+	lea	r15,[4+r15]
 	mov	r10,rdx
 
 	mul	rbp
 	add	rdi,rax
-	mov	rax,QWORD PTR[((-16))+r15*8+rsi]
+	mov	rax,QWORD[((-16))+r15*8+rsi]
 	adc	rdx,0
 	add	rdi,r11
 	adc	rdx,0
-	mov	QWORD PTR[((-32))+r15*8+rsp],rdi
+	mov	QWORD[((-32))+r15*8+rsp],rdi
 	mov	r13,rdx
 	cmp	r15,r9
-	jb	$L$inner4x
+	jb	NEAR $L$inner4x
 
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD PTR[((-16))+r15*8+rcx]
+	mov	rax,QWORD[((-16))+r15*8+rcx]
 	adc	rdx,0
-	add	r10,QWORD PTR[((-16))+r15*8+rsp]
+	add	r10,QWORD[((-16))+r15*8+rsp]
 	adc	rdx,0
 	mov	r11,rdx
 
 	mul	rbp
 	add	r13,rax
-	mov	rax,QWORD PTR[((-8))+r15*8+rsi]
+	mov	rax,QWORD[((-8))+r15*8+rsi]
 	adc	rdx,0
 	add	r13,r10
 	adc	rdx,0
-	mov	QWORD PTR[((-24))+r15*8+rsp],r13
+	mov	QWORD[((-24))+r15*8+rsp],r13
 	mov	rdi,rdx
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD PTR[((-8))+r15*8+rcx]
+	mov	rax,QWORD[((-8))+r15*8+rcx]
 	adc	rdx,0
-	add	r11,QWORD PTR[((-8))+r15*8+rsp]
+	add	r11,QWORD[((-8))+r15*8+rsp]
 	adc	rdx,0
-	lea	r14,QWORD PTR[1+r14]
+	lea	r14,[1+r14]
 	mov	r10,rdx
 
 	mul	rbp
 	add	rdi,rax
-	mov	rax,QWORD PTR[rsi]
+	mov	rax,QWORD[rsi]
 	adc	rdx,0
 	add	rdi,r11
 	adc	rdx,0
-	mov	QWORD PTR[((-16))+r15*8+rsp],rdi
+	mov	QWORD[((-16))+r15*8+rsp],rdi
 	mov	r13,rdx
 
 	xor	rdi,rdi
 	add	r13,r10
 	adc	rdi,0
-	add	r13,QWORD PTR[r9*8+rsp]
+	add	r13,QWORD[r9*8+rsp]
 	adc	rdi,0
-	mov	QWORD PTR[((-8))+r15*8+rsp],r13
-	mov	QWORD PTR[r15*8+rsp],rdi
+	mov	QWORD[((-8))+r15*8+rsp],r13
+	mov	QWORD[r15*8+rsp],rdi
 
 	cmp	r14,r9
-	jb	$L$outer4x
-	mov	rdi,QWORD PTR[16+r9*8+rsp]
-	mov	rax,QWORD PTR[rsp]
-	mov	rdx,QWORD PTR[8+rsp]
+	jb	NEAR $L$outer4x
+	mov	rdi,QWORD[16+r9*8+rsp]
+	mov	rax,QWORD[rsp]
+	mov	rdx,QWORD[8+rsp]
 	shr	r9,2
-	lea	rsi,QWORD PTR[rsp]
+	lea	rsi,[rsp]
 	xor	r14,r14
 
-	sub	rax,QWORD PTR[rcx]
-	mov	rbx,QWORD PTR[16+rsi]
-	mov	rbp,QWORD PTR[24+rsi]
-	sbb	rdx,QWORD PTR[8+rcx]
-	lea	r15,QWORD PTR[((-1))+r9]
-	jmp	$L$sub4x
+	sub	rax,QWORD[rcx]
+	mov	rbx,QWORD[16+rsi]
+	mov	rbp,QWORD[24+rsi]
+	sbb	rdx,QWORD[8+rcx]
+	lea	r15,[((-1))+r9]
+	jmp	NEAR $L$sub4x
 ALIGN	16
-$L$sub4x::
-	mov	QWORD PTR[r14*8+rdi],rax
-	mov	QWORD PTR[8+r14*8+rdi],rdx
-	sbb	rbx,QWORD PTR[16+r14*8+rcx]
-	mov	rax,QWORD PTR[32+r14*8+rsi]
-	mov	rdx,QWORD PTR[40+r14*8+rsi]
-	sbb	rbp,QWORD PTR[24+r14*8+rcx]
-	mov	QWORD PTR[16+r14*8+rdi],rbx
-	mov	QWORD PTR[24+r14*8+rdi],rbp
-	sbb	rax,QWORD PTR[32+r14*8+rcx]
-	mov	rbx,QWORD PTR[48+r14*8+rsi]
-	mov	rbp,QWORD PTR[56+r14*8+rsi]
-	sbb	rdx,QWORD PTR[40+r14*8+rcx]
-	lea	r14,QWORD PTR[4+r14]
+$L$sub4x:
+	mov	QWORD[r14*8+rdi],rax
+	mov	QWORD[8+r14*8+rdi],rdx
+	sbb	rbx,QWORD[16+r14*8+rcx]
+	mov	rax,QWORD[32+r14*8+rsi]
+	mov	rdx,QWORD[40+r14*8+rsi]
+	sbb	rbp,QWORD[24+r14*8+rcx]
+	mov	QWORD[16+r14*8+rdi],rbx
+	mov	QWORD[24+r14*8+rdi],rbp
+	sbb	rax,QWORD[32+r14*8+rcx]
+	mov	rbx,QWORD[48+r14*8+rsi]
+	mov	rbp,QWORD[56+r14*8+rsi]
+	sbb	rdx,QWORD[40+r14*8+rcx]
+	lea	r14,[4+r14]
 	dec	r15
-	jnz	$L$sub4x
+	jnz	NEAR $L$sub4x
 
-	mov	QWORD PTR[r14*8+rdi],rax
-	mov	rax,QWORD PTR[32+r14*8+rsi]
-	sbb	rbx,QWORD PTR[16+r14*8+rcx]
-	mov	QWORD PTR[8+r14*8+rdi],rdx
-	sbb	rbp,QWORD PTR[24+r14*8+rcx]
-	mov	QWORD PTR[16+r14*8+rdi],rbx
+	mov	QWORD[r14*8+rdi],rax
+	mov	rax,QWORD[32+r14*8+rsi]
+	sbb	rbx,QWORD[16+r14*8+rcx]
+	mov	QWORD[8+r14*8+rdi],rdx
+	sbb	rbp,QWORD[24+r14*8+rcx]
+	mov	QWORD[16+r14*8+rdi],rbx
 
 	sbb	rax,0
 DB 66h, 48h, 0fh, 6eh, 0c0h
 	punpcklqdq	xmm0,xmm0
-	mov	QWORD PTR[24+r14*8+rdi],rbp
+	mov	QWORD[24+r14*8+rdi],rbp
 	xor	r14,r14
 
 	mov	r15,r9
 	pxor	xmm5,xmm5
-	jmp	$L$copy4x
+	jmp	NEAR $L$copy4x
 ALIGN	16
-$L$copy4x::
-	movdqu	xmm2,XMMWORD PTR[r14*1+rsp]
-	movdqu	xmm4,XMMWORD PTR[16+r14*1+rsp]
-	movdqu	xmm1,XMMWORD PTR[r14*1+rdi]
-	movdqu	xmm3,XMMWORD PTR[16+r14*1+rdi]
+$L$copy4x:
+	movdqu	xmm2,XMMWORD[r14*1+rsp]
+	movdqu	xmm4,XMMWORD[16+r14*1+rsp]
+	movdqu	xmm1,XMMWORD[r14*1+rdi]
+	movdqu	xmm3,XMMWORD[16+r14*1+rdi]
 	pxor	xmm2,xmm1
 	pxor	xmm4,xmm3
 	pand	xmm2,xmm0
 	pand	xmm4,xmm0
 	pxor	xmm2,xmm1
 	pxor	xmm4,xmm3
-	movdqu	XMMWORD PTR[r14*1+rdi],xmm2
-	movdqu	XMMWORD PTR[16+r14*1+rdi],xmm4
-	movdqa	XMMWORD PTR[r14*1+rsp],xmm5
-	movdqa	XMMWORD PTR[16+r14*1+rsp],xmm5
+	movdqu	XMMWORD[r14*1+rdi],xmm2
+	movdqu	XMMWORD[16+r14*1+rdi],xmm4
+	movdqa	XMMWORD[r14*1+rsp],xmm5
+	movdqa	XMMWORD[16+r14*1+rsp],xmm5
 
-	lea	r14,QWORD PTR[32+r14]
+	lea	r14,[32+r14]
 	dec	r15
-	jnz	$L$copy4x
+	jnz	NEAR $L$copy4x
 
 	shl	r9,2
-	mov	rsi,QWORD PTR[8+r9*8+rsp]
+	mov	rsi,QWORD[8+r9*8+rsp]
 	mov	rax,1
-	mov	r15,QWORD PTR[rsi]
-	mov	r14,QWORD PTR[8+rsi]
-	mov	r13,QWORD PTR[16+rsi]
-	mov	r12,QWORD PTR[24+rsi]
-	mov	rbp,QWORD PTR[32+rsi]
-	mov	rbx,QWORD PTR[40+rsi]
-	lea	rsp,QWORD PTR[48+rsi]
-$L$mul4x_epilogue::
-	mov	rdi,QWORD PTR[8+rsp]	;WIN64 epilogue
-	mov	rsi,QWORD PTR[16+rsp]
+	mov	r15,QWORD[rsi]
+	mov	r14,QWORD[8+rsi]
+	mov	r13,QWORD[16+rsi]
+	mov	r12,QWORD[24+rsi]
+	mov	rbp,QWORD[32+rsi]
+	mov	rbx,QWORD[40+rsi]
+	lea	rsp,[48+rsi]
+$L$mul4x_epilogue:
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
-$L$SEH_end_bn_mul4x_mont::
-bn_mul4x_mont	ENDP
-EXTERN	bn_sqr8x_internal:NEAR
+$L$SEH_end_bn_mul4x_mont:
+EXTERN	bn_sqr8x_internal
 
 
 ALIGN	32
-bn_sqr8x_mont	PROC PRIVATE
-	mov	QWORD PTR[8+rsp],rdi	;WIN64 prologue
-	mov	QWORD PTR[16+rsp],rsi
+bn_sqr8x_mont:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
 	mov	rax,rsp
-$L$SEH_begin_bn_sqr8x_mont::
+$L$SEH_begin_bn_sqr8x_mont:
 	mov	rdi,rcx
 	mov	rsi,rdx
 	mov	rdx,r8
 	mov	rcx,r9
-	mov	r8,QWORD PTR[40+rsp]
-	mov	r9,QWORD PTR[48+rsp]
+	mov	r8,QWORD[40+rsp]
+	mov	r9,QWORD[48+rsp]
 
 
-$L$sqr8x_enter::
+$L$sqr8x_enter:
 	mov	rax,rsp
 	push	rbx
 	push	rbp
@@ -675,54 +677,54 @@ $L$sqr8x_enter::
 
 
 
-	lea	r11,QWORD PTR[((-64))+r9*4+rsp]
-	mov	r8,QWORD PTR[r8]
+	lea	r11,[((-64))+r9*4+rsp]
+	mov	r8,QWORD[r8]
 	sub	r11,rsi
 	and	r11,4095
 	cmp	r10,r11
-	jb	$L$sqr8x_sp_alt
+	jb	NEAR $L$sqr8x_sp_alt
 	sub	rsp,r11
-	lea	rsp,QWORD PTR[((-64))+r9*4+rsp]
-	jmp	$L$sqr8x_sp_done
+	lea	rsp,[((-64))+r9*4+rsp]
+	jmp	NEAR $L$sqr8x_sp_done
 
 ALIGN	32
-$L$sqr8x_sp_alt::
-	lea	r10,QWORD PTR[((4096-64))+r9*4]
-	lea	rsp,QWORD PTR[((-64))+r9*4+rsp]
+$L$sqr8x_sp_alt:
+	lea	r10,[((4096-64))+r9*4]
+	lea	rsp,[((-64))+r9*4+rsp]
 	sub	r11,r10
 	mov	r10,0
 	cmovc	r11,r10
 	sub	rsp,r11
-$L$sqr8x_sp_done::
+$L$sqr8x_sp_done:
 	and	rsp,-64
 	mov	r10,r9
 	neg	r9
 
-	lea	r11,QWORD PTR[64+r9*2+rsp]
-	mov	QWORD PTR[32+rsp],r8
-	mov	QWORD PTR[40+rsp],rax
-$L$sqr8x_body::
+	lea	r11,[64+r9*2+rsp]
+	mov	QWORD[32+rsp],r8
+	mov	QWORD[40+rsp],rax
+$L$sqr8x_body:
 
 	mov	rbp,r9
 DB	102,73,15,110,211
 	shr	rbp,3+2
-	mov	eax,DWORD PTR[((OPENSSL_ia32cap_P+8))]
-	jmp	$L$sqr8x_copy_n
+	mov	eax,DWORD[((OPENSSL_ia32cap_P+8))]
+	jmp	NEAR $L$sqr8x_copy_n
 
 ALIGN	32
-$L$sqr8x_copy_n::
-	movq	xmm0,QWORD PTR[rcx]
-	movq	xmm1,QWORD PTR[8+rcx]
-	movq	xmm3,QWORD PTR[16+rcx]
-	movq	xmm4,QWORD PTR[24+rcx]
-	lea	rcx,QWORD PTR[32+rcx]
-	movdqa	XMMWORD PTR[r11],xmm0
-	movdqa	XMMWORD PTR[16+r11],xmm1
-	movdqa	XMMWORD PTR[32+r11],xmm3
-	movdqa	XMMWORD PTR[48+r11],xmm4
-	lea	r11,QWORD PTR[64+r11]
+$L$sqr8x_copy_n:
+	movq	xmm0,QWORD[rcx]
+	movq	xmm1,QWORD[8+rcx]
+	movq	xmm3,QWORD[16+rcx]
+	movq	xmm4,QWORD[24+rcx]
+	lea	rcx,[32+rcx]
+	movdqa	XMMWORD[r11],xmm0
+	movdqa	XMMWORD[16+r11],xmm1
+	movdqa	XMMWORD[32+r11],xmm3
+	movdqa	XMMWORD[48+r11],xmm4
+	lea	r11,[64+r11]
 	dec	rbp
-	jnz	$L$sqr8x_copy_n
+	jnz	NEAR $L$sqr8x_copy_n
 
 	pxor	xmm0,xmm0
 DB	102,72,15,110,207
@@ -730,51 +732,50 @@ DB	102,73,15,110,218
 	call	bn_sqr8x_internal
 
 	pxor	xmm0,xmm0
-	lea	rax,QWORD PTR[48+rsp]
-	lea	rdx,QWORD PTR[64+r9*2+rsp]
+	lea	rax,[48+rsp]
+	lea	rdx,[64+r9*2+rsp]
 	shr	r9,3+2
-	mov	rsi,QWORD PTR[40+rsp]
-	jmp	$L$sqr8x_zero
+	mov	rsi,QWORD[40+rsp]
+	jmp	NEAR $L$sqr8x_zero
 
 ALIGN	32
-$L$sqr8x_zero::
-	movdqa	XMMWORD PTR[rax],xmm0
-	movdqa	XMMWORD PTR[16+rax],xmm0
-	movdqa	XMMWORD PTR[32+rax],xmm0
-	movdqa	XMMWORD PTR[48+rax],xmm0
-	lea	rax,QWORD PTR[64+rax]
-	movdqa	XMMWORD PTR[rdx],xmm0
-	movdqa	XMMWORD PTR[16+rdx],xmm0
-	movdqa	XMMWORD PTR[32+rdx],xmm0
-	movdqa	XMMWORD PTR[48+rdx],xmm0
-	lea	rdx,QWORD PTR[64+rdx]
+$L$sqr8x_zero:
+	movdqa	XMMWORD[rax],xmm0
+	movdqa	XMMWORD[16+rax],xmm0
+	movdqa	XMMWORD[32+rax],xmm0
+	movdqa	XMMWORD[48+rax],xmm0
+	lea	rax,[64+rax]
+	movdqa	XMMWORD[rdx],xmm0
+	movdqa	XMMWORD[16+rdx],xmm0
+	movdqa	XMMWORD[32+rdx],xmm0
+	movdqa	XMMWORD[48+rdx],xmm0
+	lea	rdx,[64+rdx]
 	dec	r9
-	jnz	$L$sqr8x_zero
+	jnz	NEAR $L$sqr8x_zero
 
 	mov	rax,1
-	mov	r15,QWORD PTR[((-48))+rsi]
-	mov	r14,QWORD PTR[((-40))+rsi]
-	mov	r13,QWORD PTR[((-32))+rsi]
-	mov	r12,QWORD PTR[((-24))+rsi]
-	mov	rbp,QWORD PTR[((-16))+rsi]
-	mov	rbx,QWORD PTR[((-8))+rsi]
-	lea	rsp,QWORD PTR[rsi]
-$L$sqr8x_epilogue::
-	mov	rdi,QWORD PTR[8+rsp]	;WIN64 epilogue
-	mov	rsi,QWORD PTR[16+rsp]
+	mov	r15,QWORD[((-48))+rsi]
+	mov	r14,QWORD[((-40))+rsi]
+	mov	r13,QWORD[((-32))+rsi]
+	mov	r12,QWORD[((-24))+rsi]
+	mov	rbp,QWORD[((-16))+rsi]
+	mov	rbx,QWORD[((-8))+rsi]
+	lea	rsp,[rsi]
+$L$sqr8x_epilogue:
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
-$L$SEH_end_bn_sqr8x_mont::
-bn_sqr8x_mont	ENDP
+$L$SEH_end_bn_sqr8x_mont:
 DB	77,111,110,116,103,111,109,101,114,121,32,77,117,108,116,105
 DB	112,108,105,99,97,116,105,111,110,32,102,111,114,32,120,56
 DB	54,95,54,52,44,32,67,82,89,80,84,79,71,65,77,83
 DB	32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115
 DB	115,108,46,111,114,103,62,0
 ALIGN	16
-EXTERN	__imp_RtlVirtualUnwind:NEAR
+EXTERN	__imp_RtlVirtualUnwind
 
 ALIGN	16
-mul_handler	PROC PRIVATE
+mul_handler:
 	push	rsi
 	push	rdi
 	push	rbx
@@ -786,47 +787,47 @@ mul_handler	PROC PRIVATE
 	pushfq
 	sub	rsp,64
 
-	mov	rax,QWORD PTR[120+r8]
-	mov	rbx,QWORD PTR[248+r8]
+	mov	rax,QWORD[120+r8]
+	mov	rbx,QWORD[248+r8]
 
-	mov	rsi,QWORD PTR[8+r9]
-	mov	r11,QWORD PTR[56+r9]
+	mov	rsi,QWORD[8+r9]
+	mov	r11,QWORD[56+r9]
 
-	mov	r10d,DWORD PTR[r11]
-	lea	r10,QWORD PTR[r10*1+rsi]
+	mov	r10d,DWORD[r11]
+	lea	r10,[r10*1+rsi]
 	cmp	rbx,r10
-	jb	$L$common_seh_tail
+	jb	NEAR $L$common_seh_tail
 
-	mov	rax,QWORD PTR[152+r8]
+	mov	rax,QWORD[152+r8]
 
-	mov	r10d,DWORD PTR[4+r11]
-	lea	r10,QWORD PTR[r10*1+rsi]
+	mov	r10d,DWORD[4+r11]
+	lea	r10,[r10*1+rsi]
 	cmp	rbx,r10
-	jae	$L$common_seh_tail
+	jae	NEAR $L$common_seh_tail
+
+	mov	r10,QWORD[192+r8]
+	mov	rax,QWORD[8+r10*8+rax]
+	lea	rax,[48+rax]
 
-	mov	r10,QWORD PTR[192+r8]
-	mov	rax,QWORD PTR[8+r10*8+rax]
-	lea	rax,QWORD PTR[48+rax]
+	mov	rbx,QWORD[((-8))+rax]
+	mov	rbp,QWORD[((-16))+rax]
+	mov	r12,QWORD[((-24))+rax]
+	mov	r13,QWORD[((-32))+rax]
+	mov	r14,QWORD[((-40))+rax]
+	mov	r15,QWORD[((-48))+rax]
+	mov	QWORD[144+r8],rbx
+	mov	QWORD[160+r8],rbp
+	mov	QWORD[216+r8],r12
+	mov	QWORD[224+r8],r13
+	mov	QWORD[232+r8],r14
+	mov	QWORD[240+r8],r15
 
-	mov	rbx,QWORD PTR[((-8))+rax]
-	mov	rbp,QWORD PTR[((-16))+rax]
-	mov	r12,QWORD PTR[((-24))+rax]
-	mov	r13,QWORD PTR[((-32))+rax]
-	mov	r14,QWORD PTR[((-40))+rax]
-	mov	r15,QWORD PTR[((-48))+rax]
-	mov	QWORD PTR[144+r8],rbx
-	mov	QWORD PTR[160+r8],rbp
-	mov	QWORD PTR[216+r8],r12
-	mov	QWORD PTR[224+r8],r13
-	mov	QWORD PTR[232+r8],r14
-	mov	QWORD PTR[240+r8],r15
+	jmp	NEAR $L$common_seh_tail
 
-	jmp	$L$common_seh_tail
-mul_handler	ENDP
 
 
 ALIGN	16
-sqr_handler	PROC PRIVATE
+sqr_handler:
 	push	rsi
 	push	rdi
 	push	rbx
@@ -838,64 +839,64 @@ sqr_handler	PROC PRIVATE
 	pushfq
 	sub	rsp,64
 
-	mov	rax,QWORD PTR[120+r8]
-	mov	rbx,QWORD PTR[248+r8]
+	mov	rax,QWORD[120+r8]
+	mov	rbx,QWORD[248+r8]
 
-	mov	rsi,QWORD PTR[8+r9]
-	mov	r11,QWORD PTR[56+r9]
+	mov	rsi,QWORD[8+r9]
+	mov	r11,QWORD[56+r9]
 
-	mov	r10d,DWORD PTR[r11]
-	lea	r10,QWORD PTR[r10*1+rsi]
+	mov	r10d,DWORD[r11]
+	lea	r10,[r10*1+rsi]
 	cmp	rbx,r10
-	jb	$L$common_seh_tail
+	jb	NEAR $L$common_seh_tail
 
-	mov	rax,QWORD PTR[152+r8]
+	mov	rax,QWORD[152+r8]
 
-	mov	r10d,DWORD PTR[4+r11]
-	lea	r10,QWORD PTR[r10*1+rsi]
+	mov	r10d,DWORD[4+r11]
+	lea	r10,[r10*1+rsi]
 	cmp	rbx,r10
-	jae	$L$common_seh_tail
-
-	mov	rax,QWORD PTR[40+rax]
-
-	mov	rbx,QWORD PTR[((-8))+rax]
-	mov	rbp,QWORD PTR[((-16))+rax]
-	mov	r12,QWORD PTR[((-24))+rax]
-	mov	r13,QWORD PTR[((-32))+rax]
-	mov	r14,QWORD PTR[((-40))+rax]
-	mov	r15,QWORD PTR[((-48))+rax]
-	mov	QWORD PTR[144+r8],rbx
-	mov	QWORD PTR[160+r8],rbp
-	mov	QWORD PTR[216+r8],r12
-	mov	QWORD PTR[224+r8],r13
-	mov	QWORD PTR[232+r8],r14
-	mov	QWORD PTR[240+r8],r15
-
-$L$common_seh_tail::
-	mov	rdi,QWORD PTR[8+rax]
-	mov	rsi,QWORD PTR[16+rax]
-	mov	QWORD PTR[152+r8],rax
-	mov	QWORD PTR[168+r8],rsi
-	mov	QWORD PTR[176+r8],rdi
-
-	mov	rdi,QWORD PTR[40+r9]
+	jae	NEAR $L$common_seh_tail
+
+	mov	rax,QWORD[40+rax]
+
+	mov	rbx,QWORD[((-8))+rax]
+	mov	rbp,QWORD[((-16))+rax]
+	mov	r12,QWORD[((-24))+rax]
+	mov	r13,QWORD[((-32))+rax]
+	mov	r14,QWORD[((-40))+rax]
+	mov	r15,QWORD[((-48))+rax]
+	mov	QWORD[144+r8],rbx
+	mov	QWORD[160+r8],rbp
+	mov	QWORD[216+r8],r12
+	mov	QWORD[224+r8],r13
+	mov	QWORD[232+r8],r14
+	mov	QWORD[240+r8],r15
+
+$L$common_seh_tail:
+	mov	rdi,QWORD[8+rax]
+	mov	rsi,QWORD[16+rax]
+	mov	QWORD[152+r8],rax
+	mov	QWORD[168+r8],rsi
+	mov	QWORD[176+r8],rdi
+
+	mov	rdi,QWORD[40+r9]
 	mov	rsi,r8
 	mov	ecx,154
-	DD	0a548f3fch
+	DD	0xa548f3fc
 
 	mov	rsi,r9
 	xor	rcx,rcx
-	mov	rdx,QWORD PTR[8+rsi]
-	mov	r8,QWORD PTR[rsi]
-	mov	r9,QWORD PTR[16+rsi]
-	mov	r10,QWORD PTR[40+rsi]
-	lea	r11,QWORD PTR[56+rsi]
-	lea	r12,QWORD PTR[24+rsi]
-	mov	QWORD PTR[32+rsp],r10
-	mov	QWORD PTR[40+rsp],r11
-	mov	QWORD PTR[48+rsp],r12
-	mov	QWORD PTR[56+rsp],rcx
-	call	QWORD PTR[__imp_RtlVirtualUnwind]
+	mov	rdx,QWORD[8+rsi]
+	mov	r8,QWORD[rsi]
+	mov	r9,QWORD[16+rsi]
+	mov	r10,QWORD[40+rsi]
+	lea	r11,[56+rsi]
+	lea	r12,[24+rsi]
+	mov	QWORD[32+rsp],r10
+	mov	QWORD[40+rsp],r11
+	mov	QWORD[48+rsp],r12
+	mov	QWORD[56+rsp],rcx
+	call	QWORD[__imp_RtlVirtualUnwind]
 
 	mov	eax,1
 	add	rsp,64
@@ -909,37 +910,32 @@ $L$common_seh_tail::
 	pop	rdi
 	pop	rsi
 	DB	0F3h,0C3h		;repret
-sqr_handler	ENDP
 
-.text$	ENDS
-.pdata	SEGMENT READONLY ALIGN(4)
+
+section	.pdata rdata align=4
 ALIGN	4
-	DD	imagerel $L$SEH_begin_bn_mul_mont
-	DD	imagerel $L$SEH_end_bn_mul_mont
-	DD	imagerel $L$SEH_info_bn_mul_mont
-
-	DD	imagerel $L$SEH_begin_bn_mul4x_mont
-	DD	imagerel $L$SEH_end_bn_mul4x_mont
-	DD	imagerel $L$SEH_info_bn_mul4x_mont
-
-	DD	imagerel $L$SEH_begin_bn_sqr8x_mont
-	DD	imagerel $L$SEH_end_bn_sqr8x_mont
-	DD	imagerel $L$SEH_info_bn_sqr8x_mont
-.pdata	ENDS
-.xdata	SEGMENT READONLY ALIGN(8)
+	DD	$L$SEH_begin_bn_mul_mont wrt ..imagebase
+	DD	$L$SEH_end_bn_mul_mont wrt ..imagebase
+	DD	$L$SEH_info_bn_mul_mont wrt ..imagebase
+
+	DD	$L$SEH_begin_bn_mul4x_mont wrt ..imagebase
+	DD	$L$SEH_end_bn_mul4x_mont wrt ..imagebase
+	DD	$L$SEH_info_bn_mul4x_mont wrt ..imagebase
+
+	DD	$L$SEH_begin_bn_sqr8x_mont wrt ..imagebase
+	DD	$L$SEH_end_bn_sqr8x_mont wrt ..imagebase
+	DD	$L$SEH_info_bn_sqr8x_mont wrt ..imagebase
+section	.xdata rdata align=8
 ALIGN	8
-$L$SEH_info_bn_mul_mont::
+$L$SEH_info_bn_mul_mont:
 DB	9,0,0,0
-	DD	imagerel mul_handler
-	DD	imagerel $L$mul_body,imagerel $L$mul_epilogue
-$L$SEH_info_bn_mul4x_mont::
+	DD	mul_handler wrt ..imagebase
+	DD	$L$mul_body wrt ..imagebase,$L$mul_epilogue wrt ..imagebase
+$L$SEH_info_bn_mul4x_mont:
 DB	9,0,0,0
-	DD	imagerel mul_handler
-	DD	imagerel $L$mul4x_body,imagerel $L$mul4x_epilogue
-$L$SEH_info_bn_sqr8x_mont::
+	DD	mul_handler wrt ..imagebase
+	DD	$L$mul4x_body wrt ..imagebase,$L$mul4x_epilogue wrt ..imagebase
+$L$SEH_info_bn_sqr8x_mont:
 DB	9,0,0,0
-	DD	imagerel sqr_handler
-	DD	imagerel $L$sqr8x_body,imagerel $L$sqr8x_epilogue
-
-.xdata	ENDS
-END
+	DD	sqr_handler wrt ..imagebase
+	DD	$L$sqr8x_body wrt ..imagebase,$L$sqr8x_epilogue wrt ..imagebase
diff --git a/win-x86_64/crypto/bn/x86_64-mont5.asm b/win-x86_64/crypto/bn/x86_64-mont5.asm
index 90c6100..284318a 100644
--- a/win-x86_64/crypto/bn/x86_64-mont5.asm
+++ b/win-x86_64/crypto/bn/x86_64-mont5.asm
@@ -1,95 +1,99 @@
-OPTION	DOTNAME
-.text$	SEGMENT ALIGN(256) 'CODE'
+default	rel
+%define XMMWORD
+%define YMMWORD
+%define ZMMWORD
+section	.text code align=64
 
-EXTERN	OPENSSL_ia32cap_P:NEAR
 
-PUBLIC	bn_mul_mont_gather5
+EXTERN	OPENSSL_ia32cap_P
+
+global	bn_mul_mont_gather5
 
 ALIGN	64
-bn_mul_mont_gather5	PROC PUBLIC
-	mov	QWORD PTR[8+rsp],rdi	;WIN64 prologue
-	mov	QWORD PTR[16+rsp],rsi
+bn_mul_mont_gather5:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
 	mov	rax,rsp
-$L$SEH_begin_bn_mul_mont_gather5::
+$L$SEH_begin_bn_mul_mont_gather5:
 	mov	rdi,rcx
 	mov	rsi,rdx
 	mov	rdx,r8
 	mov	rcx,r9
-	mov	r8,QWORD PTR[40+rsp]
-	mov	r9,QWORD PTR[48+rsp]
+	mov	r8,QWORD[40+rsp]
+	mov	r9,QWORD[48+rsp]
 
 
 	test	r9d,7
-	jnz	$L$mul_enter
-	jmp	$L$mul4x_enter
+	jnz	NEAR $L$mul_enter
+	jmp	NEAR $L$mul4x_enter
 
 ALIGN	16
-$L$mul_enter::
+$L$mul_enter:
 	mov	r9d,r9d
 	mov	rax,rsp
-	mov	r10d,DWORD PTR[56+rsp]
+	mov	r10d,DWORD[56+rsp]
 	push	rbx
 	push	rbp
 	push	r12
 	push	r13
 	push	r14
 	push	r15
-	lea	rsp,QWORD PTR[((-40))+rsp]
-	movaps	XMMWORD PTR[rsp],xmm6
-	movaps	XMMWORD PTR[16+rsp],xmm7
-	lea	r11,QWORD PTR[2+r9]
+	lea	rsp,[((-40))+rsp]
+	movaps	XMMWORD[rsp],xmm6
+	movaps	XMMWORD[16+rsp],xmm7
+	lea	r11,[2+r9]
 	neg	r11
-	lea	rsp,QWORD PTR[r11*8+rsp]
+	lea	rsp,[r11*8+rsp]
 	and	rsp,-1024
 
-	mov	QWORD PTR[8+r9*8+rsp],rax
-$L$mul_body::
+	mov	QWORD[8+r9*8+rsp],rax
+$L$mul_body:
 	mov	r12,rdx
 	mov	r11,r10
 	shr	r10,3
 	and	r11,7
 	not	r10
-	lea	rax,QWORD PTR[$L$magic_masks]
+	lea	rax,[$L$magic_masks]
 	and	r10,3
-	lea	r12,QWORD PTR[96+r11*8+r12]
-	movq	xmm4,QWORD PTR[r10*8+rax]
-	movq	xmm5,QWORD PTR[8+r10*8+rax]
-	movq	xmm6,QWORD PTR[16+r10*8+rax]
-	movq	xmm7,QWORD PTR[24+r10*8+rax]
-
-	movq	xmm0,QWORD PTR[(((-96)))+r12]
-	movq	xmm1,QWORD PTR[((-32))+r12]
+	lea	r12,[96+r11*8+r12]
+	movq	xmm4,QWORD[r10*8+rax]
+	movq	xmm5,QWORD[8+r10*8+rax]
+	movq	xmm6,QWORD[16+r10*8+rax]
+	movq	xmm7,QWORD[24+r10*8+rax]
+
+	movq	xmm0,QWORD[(((-96)))+r12]
+	movq	xmm1,QWORD[((-32))+r12]
 	pand	xmm0,xmm4
-	movq	xmm2,QWORD PTR[32+r12]
+	movq	xmm2,QWORD[32+r12]
 	pand	xmm1,xmm5
-	movq	xmm3,QWORD PTR[96+r12]
+	movq	xmm3,QWORD[96+r12]
 	pand	xmm2,xmm6
 	por	xmm0,xmm1
 	pand	xmm3,xmm7
 	por	xmm0,xmm2
-	lea	r12,QWORD PTR[256+r12]
+	lea	r12,[256+r12]
 	por	xmm0,xmm3
 
 DB	102,72,15,126,195
 
-	mov	r8,QWORD PTR[r8]
-	mov	rax,QWORD PTR[rsi]
+	mov	r8,QWORD[r8]
+	mov	rax,QWORD[rsi]
 
 	xor	r14,r14
 	xor	r15,r15
 
-	movq	xmm0,QWORD PTR[(((-96)))+r12]
-	movq	xmm1,QWORD PTR[((-32))+r12]
+	movq	xmm0,QWORD[(((-96)))+r12]
+	movq	xmm1,QWORD[((-32))+r12]
 	pand	xmm0,xmm4
-	movq	xmm2,QWORD PTR[32+r12]
+	movq	xmm2,QWORD[32+r12]
 	pand	xmm1,xmm5
 
 	mov	rbp,r8
 	mul	rbx
 	mov	r10,rax
-	mov	rax,QWORD PTR[rcx]
+	mov	rax,QWORD[rcx]
 
-	movq	xmm3,QWORD PTR[96+r12]
+	movq	xmm3,QWORD[96+r12]
 	pand	xmm2,xmm6
 	por	xmm0,xmm1
 	pand	xmm3,xmm7
@@ -98,78 +102,78 @@ DB	102,72,15,126,195
 	mov	r11,rdx
 
 	por	xmm0,xmm2
-	lea	r12,QWORD PTR[256+r12]
+	lea	r12,[256+r12]
 	por	xmm0,xmm3
 
 	mul	rbp
 	add	r10,rax
-	mov	rax,QWORD PTR[8+rsi]
+	mov	rax,QWORD[8+rsi]
 	adc	rdx,0
 	mov	r13,rdx
 
-	lea	r15,QWORD PTR[1+r15]
-	jmp	$L$1st_enter
+	lea	r15,[1+r15]
+	jmp	NEAR $L$1st_enter
 
 ALIGN	16
-$L$1st::
+$L$1st:
 	add	r13,rax
-	mov	rax,QWORD PTR[r15*8+rsi]
+	mov	rax,QWORD[r15*8+rsi]
 	adc	rdx,0
 	add	r13,r11
 	mov	r11,r10
 	adc	rdx,0
-	mov	QWORD PTR[((-16))+r15*8+rsp],r13
+	mov	QWORD[((-16))+r15*8+rsp],r13
 	mov	r13,rdx
 
-$L$1st_enter::
+$L$1st_enter:
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD PTR[r15*8+rcx]
+	mov	rax,QWORD[r15*8+rcx]
 	adc	rdx,0
-	lea	r15,QWORD PTR[1+r15]
+	lea	r15,[1+r15]
 	mov	r10,rdx
 
 	mul	rbp
 	cmp	r15,r9
-	jne	$L$1st
+	jne	NEAR $L$1st
 
 DB	102,72,15,126,195
 
 	add	r13,rax
-	mov	rax,QWORD PTR[rsi]
+	mov	rax,QWORD[rsi]
 	adc	rdx,0
 	add	r13,r11
 	adc	rdx,0
-	mov	QWORD PTR[((-16))+r15*8+rsp],r13
+	mov	QWORD[((-16))+r15*8+rsp],r13
 	mov	r13,rdx
 	mov	r11,r10
 
 	xor	rdx,rdx
 	add	r13,r11
 	adc	rdx,0
-	mov	QWORD PTR[((-8))+r9*8+rsp],r13
-	mov	QWORD PTR[r9*8+rsp],rdx
+	mov	QWORD[((-8))+r9*8+rsp],r13
+	mov	QWORD[r9*8+rsp],rdx
 
-	lea	r14,QWORD PTR[1+r14]
-	jmp	$L$outer
+	lea	r14,[1+r14]
+	jmp	NEAR $L$outer
 ALIGN	16
-$L$outer::
+$L$outer:
 	xor	r15,r15
 	mov	rbp,r8
-	mov	r10,QWORD PTR[rsp]
+	mov	r10,QWORD[rsp]
 
-	movq	xmm0,QWORD PTR[(((-96)))+r12]
-	movq	xmm1,QWORD PTR[((-32))+r12]
+	movq	xmm0,QWORD[(((-96)))+r12]
+	movq	xmm1,QWORD[((-32))+r12]
 	pand	xmm0,xmm4
-	movq	xmm2,QWORD PTR[32+r12]
+	movq	xmm2,QWORD[32+r12]
 	pand	xmm1,xmm5
 
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD PTR[rcx]
+	mov	rax,QWORD[rcx]
 	adc	rdx,0
 
-	movq	xmm3,QWORD PTR[96+r12]
+	movq	xmm3,QWORD[96+r12]
 	pand	xmm2,xmm6
 	por	xmm0,xmm1
 	pand	xmm3,xmm7
@@ -178,53 +182,53 @@ $L$outer::
 	mov	r11,rdx
 
 	por	xmm0,xmm2
-	lea	r12,QWORD PTR[256+r12]
+	lea	r12,[256+r12]
 	por	xmm0,xmm3
 
 	mul	rbp
 	add	r10,rax
-	mov	rax,QWORD PTR[8+rsi]
+	mov	rax,QWORD[8+rsi]
 	adc	rdx,0
-	mov	r10,QWORD PTR[8+rsp]
+	mov	r10,QWORD[8+rsp]
 	mov	r13,rdx
 
-	lea	r15,QWORD PTR[1+r15]
-	jmp	$L$inner_enter
+	lea	r15,[1+r15]
+	jmp	NEAR $L$inner_enter
 
 ALIGN	16
-$L$inner::
+$L$inner:
 	add	r13,rax
-	mov	rax,QWORD PTR[r15*8+rsi]
+	mov	rax,QWORD[r15*8+rsi]
 	adc	rdx,0
 	add	r13,r10
-	mov	r10,QWORD PTR[r15*8+rsp]
+	mov	r10,QWORD[r15*8+rsp]
 	adc	rdx,0
-	mov	QWORD PTR[((-16))+r15*8+rsp],r13
+	mov	QWORD[((-16))+r15*8+rsp],r13
 	mov	r13,rdx
 
-$L$inner_enter::
+$L$inner_enter:
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD PTR[r15*8+rcx]
+	mov	rax,QWORD[r15*8+rcx]
 	adc	rdx,0
 	add	r10,r11
 	mov	r11,rdx
 	adc	r11,0
-	lea	r15,QWORD PTR[1+r15]
+	lea	r15,[1+r15]
 
 	mul	rbp
 	cmp	r15,r9
-	jne	$L$inner
+	jne	NEAR $L$inner
 
 DB	102,72,15,126,195
 
 	add	r13,rax
-	mov	rax,QWORD PTR[rsi]
+	mov	rax,QWORD[rsi]
 	adc	rdx,0
 	add	r13,r10
-	mov	r10,QWORD PTR[r15*8+rsp]
+	mov	r10,QWORD[r15*8+rsp]
 	adc	rdx,0
-	mov	QWORD PTR[((-16))+r15*8+rsp],r13
+	mov	QWORD[((-16))+r15*8+rsp],r13
 	mov	r13,rdx
 
 	xor	rdx,rdx
@@ -232,76 +236,75 @@ DB	102,72,15,126,195
 	adc	rdx,0
 	add	r13,r10
 	adc	rdx,0
-	mov	QWORD PTR[((-8))+r9*8+rsp],r13
-	mov	QWORD PTR[r9*8+rsp],rdx
+	mov	QWORD[((-8))+r9*8+rsp],r13
+	mov	QWORD[r9*8+rsp],rdx
 
-	lea	r14,QWORD PTR[1+r14]
+	lea	r14,[1+r14]
 	cmp	r14,r9
-	jb	$L$outer
+	jb	NEAR $L$outer
 
 	xor	r14,r14
-	mov	rax,QWORD PTR[rsp]
-	lea	rsi,QWORD PTR[rsp]
+	mov	rax,QWORD[rsp]
+	lea	rsi,[rsp]
 	mov	r15,r9
-	jmp	$L$sub
+	jmp	NEAR $L$sub
 ALIGN	16
-$L$sub::	sbb	rax,QWORD PTR[r14*8+rcx]
-	mov	QWORD PTR[r14*8+rdi],rax
-	mov	rax,QWORD PTR[8+r14*8+rsi]
-	lea	r14,QWORD PTR[1+r14]
+$L$sub:	sbb	rax,QWORD[r14*8+rcx]
+	mov	QWORD[r14*8+rdi],rax
+	mov	rax,QWORD[8+r14*8+rsi]
+	lea	r14,[1+r14]
 	dec	r15
-	jnz	$L$sub
+	jnz	NEAR $L$sub
 
 	sbb	rax,0
 	xor	r14,r14
 	mov	r15,r9
 ALIGN	16
-$L$copy::
-	mov	rsi,QWORD PTR[r14*8+rsp]
-	mov	rcx,QWORD PTR[r14*8+rdi]
+$L$copy:
+	mov	rsi,QWORD[r14*8+rsp]
+	mov	rcx,QWORD[r14*8+rdi]
 	xor	rsi,rcx
 	and	rsi,rax
 	xor	rsi,rcx
-	mov	QWORD PTR[r14*8+rsp],r14
-	mov	QWORD PTR[r14*8+rdi],rsi
-	lea	r14,QWORD PTR[1+r14]
+	mov	QWORD[r14*8+rsp],r14
+	mov	QWORD[r14*8+rdi],rsi
+	lea	r14,[1+r14]
 	sub	r15,1
-	jnz	$L$copy
+	jnz	NEAR $L$copy
 
-	mov	rsi,QWORD PTR[8+r9*8+rsp]
+	mov	rsi,QWORD[8+r9*8+rsp]
 	mov	rax,1
-	movaps	xmm6,XMMWORD PTR[((-88))+rsi]
-	movaps	xmm7,XMMWORD PTR[((-72))+rsi]
-	mov	r15,QWORD PTR[((-48))+rsi]
-	mov	r14,QWORD PTR[((-40))+rsi]
-	mov	r13,QWORD PTR[((-32))+rsi]
-	mov	r12,QWORD PTR[((-24))+rsi]
-	mov	rbp,QWORD PTR[((-16))+rsi]
-	mov	rbx,QWORD PTR[((-8))+rsi]
-	lea	rsp,QWORD PTR[rsi]
-$L$mul_epilogue::
-	mov	rdi,QWORD PTR[8+rsp]	;WIN64 epilogue
-	mov	rsi,QWORD PTR[16+rsp]
+	movaps	xmm6,XMMWORD[((-88))+rsi]
+	movaps	xmm7,XMMWORD[((-72))+rsi]
+	mov	r15,QWORD[((-48))+rsi]
+	mov	r14,QWORD[((-40))+rsi]
+	mov	r13,QWORD[((-32))+rsi]
+	mov	r12,QWORD[((-24))+rsi]
+	mov	rbp,QWORD[((-16))+rsi]
+	mov	rbx,QWORD[((-8))+rsi]
+	lea	rsp,[rsi]
+$L$mul_epilogue:
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
-$L$SEH_end_bn_mul_mont_gather5::
-bn_mul_mont_gather5	ENDP
+$L$SEH_end_bn_mul_mont_gather5:
 
 ALIGN	32
-bn_mul4x_mont_gather5	PROC PRIVATE
-	mov	QWORD PTR[8+rsp],rdi	;WIN64 prologue
-	mov	QWORD PTR[16+rsp],rsi
+bn_mul4x_mont_gather5:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
 	mov	rax,rsp
-$L$SEH_begin_bn_mul4x_mont_gather5::
+$L$SEH_begin_bn_mul4x_mont_gather5:
 	mov	rdi,rcx
 	mov	rsi,rdx
 	mov	rdx,r8
 	mov	rcx,r9
-	mov	r8,QWORD PTR[40+rsp]
-	mov	r9,QWORD PTR[48+rsp]
+	mov	r8,QWORD[40+rsp]
+	mov	r9,QWORD[48+rsp]
 
 
-$L$mul4x_enter::
-DB	067h
+$L$mul4x_enter:
+DB	0x67
 	mov	rax,rsp
 	push	rbx
 	push	rbp
@@ -309,10 +312,10 @@ DB	067h
 	push	r13
 	push	r14
 	push	r15
-	lea	rsp,QWORD PTR[((-40))+rsp]
-	movaps	XMMWORD PTR[rsp],xmm6
-	movaps	XMMWORD PTR[16+rsp],xmm7
-DB	067h
+	lea	rsp,[((-40))+rsp]
+	movaps	XMMWORD[rsp],xmm6
+	movaps	XMMWORD[16+rsp],xmm7
+DB	0x67
 	mov	r10d,r9d
 	shl	r9d,3
 	shl	r10d,3+2
@@ -325,107 +328,106 @@ DB	067h
 
 
 
-	lea	r11,QWORD PTR[((-64))+r9*2+rsp]
+	lea	r11,[((-64))+r9*2+rsp]
 	sub	r11,rsi
 	and	r11,4095
 	cmp	r10,r11
-	jb	$L$mul4xsp_alt
+	jb	NEAR $L$mul4xsp_alt
 	sub	rsp,r11
-	lea	rsp,QWORD PTR[((-64))+r9*2+rsp]
-	jmp	$L$mul4xsp_done
+	lea	rsp,[((-64))+r9*2+rsp]
+	jmp	NEAR $L$mul4xsp_done
 
 ALIGN	32
-$L$mul4xsp_alt::
-	lea	r10,QWORD PTR[((4096-64))+r9*2]
-	lea	rsp,QWORD PTR[((-64))+r9*2+rsp]
+$L$mul4xsp_alt:
+	lea	r10,[((4096-64))+r9*2]
+	lea	rsp,[((-64))+r9*2+rsp]
 	sub	r11,r10
 	mov	r10,0
 	cmovc	r11,r10
 	sub	rsp,r11
-$L$mul4xsp_done::
+$L$mul4xsp_done:
 	and	rsp,-64
 	neg	r9
 
-	mov	QWORD PTR[40+rsp],rax
-$L$mul4x_body::
+	mov	QWORD[40+rsp],rax
+$L$mul4x_body:
 
 	call	mul4x_internal
 
-	mov	rsi,QWORD PTR[40+rsp]
+	mov	rsi,QWORD[40+rsp]
 	mov	rax,1
-	movaps	xmm6,XMMWORD PTR[((-88))+rsi]
-	movaps	xmm7,XMMWORD PTR[((-72))+rsi]
-	mov	r15,QWORD PTR[((-48))+rsi]
-	mov	r14,QWORD PTR[((-40))+rsi]
-	mov	r13,QWORD PTR[((-32))+rsi]
-	mov	r12,QWORD PTR[((-24))+rsi]
-	mov	rbp,QWORD PTR[((-16))+rsi]
-	mov	rbx,QWORD PTR[((-8))+rsi]
-	lea	rsp,QWORD PTR[rsi]
-$L$mul4x_epilogue::
-	mov	rdi,QWORD PTR[8+rsp]	;WIN64 epilogue
-	mov	rsi,QWORD PTR[16+rsp]
+	movaps	xmm6,XMMWORD[((-88))+rsi]
+	movaps	xmm7,XMMWORD[((-72))+rsi]
+	mov	r15,QWORD[((-48))+rsi]
+	mov	r14,QWORD[((-40))+rsi]
+	mov	r13,QWORD[((-32))+rsi]
+	mov	r12,QWORD[((-24))+rsi]
+	mov	rbp,QWORD[((-16))+rsi]
+	mov	rbx,QWORD[((-8))+rsi]
+	lea	rsp,[rsi]
+$L$mul4x_epilogue:
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
-$L$SEH_end_bn_mul4x_mont_gather5::
-bn_mul4x_mont_gather5	ENDP
+$L$SEH_end_bn_mul4x_mont_gather5:
 
 
 ALIGN	32
-mul4x_internal	PROC PRIVATE
+mul4x_internal:
 	shl	r9,5
-	mov	r10d,DWORD PTR[56+rax]
-	lea	r13,QWORD PTR[256+r9*1+rdx]
+	mov	r10d,DWORD[56+rax]
+	lea	r13,[256+r9*1+rdx]
 	shr	r9,5
 	mov	r11,r10
 	shr	r10,3
 	and	r11,7
 	not	r10
-	lea	rax,QWORD PTR[$L$magic_masks]
+	lea	rax,[$L$magic_masks]
 	and	r10,3
-	lea	r12,QWORD PTR[96+r11*8+rdx]
-	movq	xmm4,QWORD PTR[r10*8+rax]
-	movq	xmm5,QWORD PTR[8+r10*8+rax]
+	lea	r12,[96+r11*8+rdx]
+	movq	xmm4,QWORD[r10*8+rax]
+	movq	xmm5,QWORD[8+r10*8+rax]
 	add	r11,7
-	movq	xmm6,QWORD PTR[16+r10*8+rax]
-	movq	xmm7,QWORD PTR[24+r10*8+rax]
+	movq	xmm6,QWORD[16+r10*8+rax]
+	movq	xmm7,QWORD[24+r10*8+rax]
 	and	r11,7
 
-	movq	xmm0,QWORD PTR[(((-96)))+r12]
-	lea	r14,QWORD PTR[256+r12]
-	movq	xmm1,QWORD PTR[((-32))+r12]
+	movq	xmm0,QWORD[(((-96)))+r12]
+	lea	r14,[256+r12]
+	movq	xmm1,QWORD[((-32))+r12]
 	pand	xmm0,xmm4
-	movq	xmm2,QWORD PTR[32+r12]
+	movq	xmm2,QWORD[32+r12]
 	pand	xmm1,xmm5
-	movq	xmm3,QWORD PTR[96+r12]
+	movq	xmm3,QWORD[96+r12]
 	pand	xmm2,xmm6
-DB	067h
+DB	0x67
 	por	xmm0,xmm1
-	movq	xmm1,QWORD PTR[((-96))+r14]
-DB	067h
+	movq	xmm1,QWORD[((-96))+r14]
+DB	0x67
 	pand	xmm3,xmm7
-DB	067h
+DB	0x67
 	por	xmm0,xmm2
-	movq	xmm2,QWORD PTR[((-32))+r14]
-DB	067h
+	movq	xmm2,QWORD[((-32))+r14]
+DB	0x67
 	pand	xmm1,xmm4
-DB	067h
+DB	0x67
 	por	xmm0,xmm3
-	movq	xmm3,QWORD PTR[32+r14]
+	movq	xmm3,QWORD[32+r14]
 
 DB	102,72,15,126,195
-	movq	xmm0,QWORD PTR[96+r14]
-	mov	QWORD PTR[((16+8))+rsp],r13
-	mov	QWORD PTR[((56+8))+rsp],rdi
+	movq	xmm0,QWORD[96+r14]
+	mov	QWORD[((16+8))+rsp],r13
+	mov	QWORD[((56+8))+rsp],rdi
 
-	mov	r8,QWORD PTR[r8]
-	mov	rax,QWORD PTR[rsi]
-	lea	rsi,QWORD PTR[r9*1+rsi]
+	mov	r8,QWORD[r8]
+	mov	rax,QWORD[rsi]
+	lea	rsi,[r9*1+rsi]
 	neg	r9
 
 	mov	rbp,r8
 	mul	rbx
 	mov	r10,rax
-	mov	rax,QWORD PTR[rcx]
+	mov	rax,QWORD[rcx]
 
 	pand	xmm2,xmm5
 	pand	xmm3,xmm6
@@ -439,349 +441,349 @@ DB	102,72,15,126,195
 
 
 
-	lea	r14,QWORD PTR[((64+8))+r11*8+rsp]
+	lea	r14,[((64+8))+r11*8+rsp]
 	mov	r11,rdx
 
 	pand	xmm0,xmm7
 	por	xmm1,xmm3
-	lea	r12,QWORD PTR[512+r12]
+	lea	r12,[512+r12]
 	por	xmm0,xmm1
 
 	mul	rbp
 	add	r10,rax
-	mov	rax,QWORD PTR[8+r9*1+rsi]
+	mov	rax,QWORD[8+r9*1+rsi]
 	adc	rdx,0
 	mov	rdi,rdx
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD PTR[16+rcx]
+	mov	rax,QWORD[16+rcx]
 	adc	rdx,0
 	mov	r10,rdx
 
 	mul	rbp
 	add	rdi,rax
-	mov	rax,QWORD PTR[16+r9*1+rsi]
+	mov	rax,QWORD[16+r9*1+rsi]
 	adc	rdx,0
 	add	rdi,r11
-	lea	r15,QWORD PTR[32+r9]
-	lea	rcx,QWORD PTR[64+rcx]
+	lea	r15,[32+r9]
+	lea	rcx,[64+rcx]
 	adc	rdx,0
-	mov	QWORD PTR[r14],rdi
+	mov	QWORD[r14],rdi
 	mov	r13,rdx
-	jmp	$L$1st4x
+	jmp	NEAR $L$1st4x
 
 ALIGN	32
-$L$1st4x::
+$L$1st4x:
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD PTR[((-32))+rcx]
-	lea	r14,QWORD PTR[32+r14]
+	mov	rax,QWORD[((-32))+rcx]
+	lea	r14,[32+r14]
 	adc	rdx,0
 	mov	r11,rdx
 
 	mul	rbp
 	add	r13,rax
-	mov	rax,QWORD PTR[((-8))+r15*1+rsi]
+	mov	rax,QWORD[((-8))+r15*1+rsi]
 	adc	rdx,0
 	add	r13,r10
 	adc	rdx,0
-	mov	QWORD PTR[((-24))+r14],r13
+	mov	QWORD[((-24))+r14],r13
 	mov	rdi,rdx
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD PTR[((-16))+rcx]
+	mov	rax,QWORD[((-16))+rcx]
 	adc	rdx,0
 	mov	r10,rdx
 
 	mul	rbp
 	add	rdi,rax
-	mov	rax,QWORD PTR[r15*1+rsi]
+	mov	rax,QWORD[r15*1+rsi]
 	adc	rdx,0
 	add	rdi,r11
 	adc	rdx,0
-	mov	QWORD PTR[((-16))+r14],rdi
+	mov	QWORD[((-16))+r14],rdi
 	mov	r13,rdx
 
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD PTR[rcx]
+	mov	rax,QWORD[rcx]
 	adc	rdx,0
 	mov	r11,rdx
 
 	mul	rbp
 	add	r13,rax
-	mov	rax,QWORD PTR[8+r15*1+rsi]
+	mov	rax,QWORD[8+r15*1+rsi]
 	adc	rdx,0
 	add	r13,r10
 	adc	rdx,0
-	mov	QWORD PTR[((-8))+r14],r13
+	mov	QWORD[((-8))+r14],r13
 	mov	rdi,rdx
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD PTR[16+rcx]
+	mov	rax,QWORD[16+rcx]
 	adc	rdx,0
 	mov	r10,rdx
 
 	mul	rbp
 	add	rdi,rax
-	mov	rax,QWORD PTR[16+r15*1+rsi]
+	mov	rax,QWORD[16+r15*1+rsi]
 	adc	rdx,0
 	add	rdi,r11
-	lea	rcx,QWORD PTR[64+rcx]
+	lea	rcx,[64+rcx]
 	adc	rdx,0
-	mov	QWORD PTR[r14],rdi
+	mov	QWORD[r14],rdi
 	mov	r13,rdx
 
 	add	r15,32
-	jnz	$L$1st4x
+	jnz	NEAR $L$1st4x
 
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD PTR[((-32))+rcx]
-	lea	r14,QWORD PTR[32+r14]
+	mov	rax,QWORD[((-32))+rcx]
+	lea	r14,[32+r14]
 	adc	rdx,0
 	mov	r11,rdx
 
 	mul	rbp
 	add	r13,rax
-	mov	rax,QWORD PTR[((-8))+rsi]
+	mov	rax,QWORD[((-8))+rsi]
 	adc	rdx,0
 	add	r13,r10
 	adc	rdx,0
-	mov	QWORD PTR[((-24))+r14],r13
+	mov	QWORD[((-24))+r14],r13
 	mov	rdi,rdx
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD PTR[((-16))+rcx]
+	mov	rax,QWORD[((-16))+rcx]
 	adc	rdx,0
 	mov	r10,rdx
 
 	mul	rbp
 	add	rdi,rax
-	mov	rax,QWORD PTR[r9*1+rsi]
+	mov	rax,QWORD[r9*1+rsi]
 	adc	rdx,0
 	add	rdi,r11
 	adc	rdx,0
-	mov	QWORD PTR[((-16))+r14],rdi
+	mov	QWORD[((-16))+r14],rdi
 	mov	r13,rdx
 
 DB	102,72,15,126,195
-	lea	rcx,QWORD PTR[r9*2+rcx]
+	lea	rcx,[r9*2+rcx]
 
 	xor	rdi,rdi
 	add	r13,r10
 	adc	rdi,0
-	mov	QWORD PTR[((-8))+r14],r13
+	mov	QWORD[((-8))+r14],r13
 
-	jmp	$L$outer4x
+	jmp	NEAR $L$outer4x
 
 ALIGN	32
-$L$outer4x::
-	mov	r10,QWORD PTR[r9*1+r14]
+$L$outer4x:
+	mov	r10,QWORD[r9*1+r14]
 	mov	rbp,r8
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD PTR[rcx]
+	mov	rax,QWORD[rcx]
 	adc	rdx,0
 
-	movq	xmm0,QWORD PTR[(((-96)))+r12]
-	movq	xmm1,QWORD PTR[((-32))+r12]
+	movq	xmm0,QWORD[(((-96)))+r12]
+	movq	xmm1,QWORD[((-32))+r12]
 	pand	xmm0,xmm4
-	movq	xmm2,QWORD PTR[32+r12]
+	movq	xmm2,QWORD[32+r12]
 	pand	xmm1,xmm5
-	movq	xmm3,QWORD PTR[96+r12]
+	movq	xmm3,QWORD[96+r12]
 
 	imul	rbp,r10
-DB	067h
+DB	0x67
 	mov	r11,rdx
-	mov	QWORD PTR[r14],rdi
+	mov	QWORD[r14],rdi
 
 	pand	xmm2,xmm6
 	por	xmm0,xmm1
 	pand	xmm3,xmm7
 	por	xmm0,xmm2
-	lea	r14,QWORD PTR[r9*1+r14]
-	lea	r12,QWORD PTR[256+r12]
+	lea	r14,[r9*1+r14]
+	lea	r12,[256+r12]
 	por	xmm0,xmm3
 
 	mul	rbp
 	add	r10,rax
-	mov	rax,QWORD PTR[8+r9*1+rsi]
+	mov	rax,QWORD[8+r9*1+rsi]
 	adc	rdx,0
 	mov	rdi,rdx
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD PTR[16+rcx]
+	mov	rax,QWORD[16+rcx]
 	adc	rdx,0
-	add	r11,QWORD PTR[8+r14]
+	add	r11,QWORD[8+r14]
 	adc	rdx,0
 	mov	r10,rdx
 
 	mul	rbp
 	add	rdi,rax
-	mov	rax,QWORD PTR[16+r9*1+rsi]
+	mov	rax,QWORD[16+r9*1+rsi]
 	adc	rdx,0
 	add	rdi,r11
-	lea	r15,QWORD PTR[32+r9]
-	lea	rcx,QWORD PTR[64+rcx]
+	lea	r15,[32+r9]
+	lea	rcx,[64+rcx]
 	adc	rdx,0
 	mov	r13,rdx
-	jmp	$L$inner4x
+	jmp	NEAR $L$inner4x
 
 ALIGN	32
-$L$inner4x::
+$L$inner4x:
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD PTR[((-32))+rcx]
+	mov	rax,QWORD[((-32))+rcx]
 	adc	rdx,0
-	add	r10,QWORD PTR[16+r14]
-	lea	r14,QWORD PTR[32+r14]
+	add	r10,QWORD[16+r14]
+	lea	r14,[32+r14]
 	adc	rdx,0
 	mov	r11,rdx
 
 	mul	rbp
 	add	r13,rax
-	mov	rax,QWORD PTR[((-8))+r15*1+rsi]
+	mov	rax,QWORD[((-8))+r15*1+rsi]
 	adc	rdx,0
 	add	r13,r10
 	adc	rdx,0
-	mov	QWORD PTR[((-32))+r14],rdi
+	mov	QWORD[((-32))+r14],rdi
 	mov	rdi,rdx
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD PTR[((-16))+rcx]
+	mov	rax,QWORD[((-16))+rcx]
 	adc	rdx,0
-	add	r11,QWORD PTR[((-8))+r14]
+	add	r11,QWORD[((-8))+r14]
 	adc	rdx,0
 	mov	r10,rdx
 
 	mul	rbp
 	add	rdi,rax
-	mov	rax,QWORD PTR[r15*1+rsi]
+	mov	rax,QWORD[r15*1+rsi]
 	adc	rdx,0
 	add	rdi,r11
 	adc	rdx,0
-	mov	QWORD PTR[((-24))+r14],r13
+	mov	QWORD[((-24))+r14],r13
 	mov	r13,rdx
 
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD PTR[rcx]
+	mov	rax,QWORD[rcx]
 	adc	rdx,0
-	add	r10,QWORD PTR[r14]
+	add	r10,QWORD[r14]
 	adc	rdx,0
 	mov	r11,rdx
 
 	mul	rbp
 	add	r13,rax
-	mov	rax,QWORD PTR[8+r15*1+rsi]
+	mov	rax,QWORD[8+r15*1+rsi]
 	adc	rdx,0
 	add	r13,r10
 	adc	rdx,0
-	mov	QWORD PTR[((-16))+r14],rdi
+	mov	QWORD[((-16))+r14],rdi
 	mov	rdi,rdx
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD PTR[16+rcx]
+	mov	rax,QWORD[16+rcx]
 	adc	rdx,0
-	add	r11,QWORD PTR[8+r14]
+	add	r11,QWORD[8+r14]
 	adc	rdx,0
 	mov	r10,rdx
 
 	mul	rbp
 	add	rdi,rax
-	mov	rax,QWORD PTR[16+r15*1+rsi]
+	mov	rax,QWORD[16+r15*1+rsi]
 	adc	rdx,0
 	add	rdi,r11
-	lea	rcx,QWORD PTR[64+rcx]
+	lea	rcx,[64+rcx]
 	adc	rdx,0
-	mov	QWORD PTR[((-8))+r14],r13
+	mov	QWORD[((-8))+r14],r13
 	mov	r13,rdx
 
 	add	r15,32
-	jnz	$L$inner4x
+	jnz	NEAR $L$inner4x
 
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD PTR[((-32))+rcx]
+	mov	rax,QWORD[((-32))+rcx]
 	adc	rdx,0
-	add	r10,QWORD PTR[16+r14]
-	lea	r14,QWORD PTR[32+r14]
+	add	r10,QWORD[16+r14]
+	lea	r14,[32+r14]
 	adc	rdx,0
 	mov	r11,rdx
 
 	mul	rbp
 	add	r13,rax
-	mov	rax,QWORD PTR[((-8))+rsi]
+	mov	rax,QWORD[((-8))+rsi]
 	adc	rdx,0
 	add	r13,r10
 	adc	rdx,0
-	mov	QWORD PTR[((-32))+r14],rdi
+	mov	QWORD[((-32))+r14],rdi
 	mov	rdi,rdx
 
 	mul	rbx
 	add	r11,rax
 	mov	rax,rbp
-	mov	rbp,QWORD PTR[((-16))+rcx]
+	mov	rbp,QWORD[((-16))+rcx]
 	adc	rdx,0
-	add	r11,QWORD PTR[((-8))+r14]
+	add	r11,QWORD[((-8))+r14]
 	adc	rdx,0
 	mov	r10,rdx
 
 	mul	rbp
 	add	rdi,rax
-	mov	rax,QWORD PTR[r9*1+rsi]
+	mov	rax,QWORD[r9*1+rsi]
 	adc	rdx,0
 	add	rdi,r11
 	adc	rdx,0
-	mov	QWORD PTR[((-24))+r14],r13
+	mov	QWORD[((-24))+r14],r13
 	mov	r13,rdx
 
 DB	102,72,15,126,195
-	mov	QWORD PTR[((-16))+r14],rdi
-	lea	rcx,QWORD PTR[r9*2+rcx]
+	mov	QWORD[((-16))+r14],rdi
+	lea	rcx,[r9*2+rcx]
 
 	xor	rdi,rdi
 	add	r13,r10
 	adc	rdi,0
-	add	r13,QWORD PTR[r14]
+	add	r13,QWORD[r14]
 	adc	rdi,0
-	mov	QWORD PTR[((-8))+r14],r13
+	mov	QWORD[((-8))+r14],r13
 
-	cmp	r12,QWORD PTR[((16+8))+rsp]
-	jb	$L$outer4x
+	cmp	r12,QWORD[((16+8))+rsp]
+	jb	NEAR $L$outer4x
 	sub	rbp,r13
 	adc	r15,r15
 	or	rdi,r15
 	xor	rdi,1
-	lea	rbx,QWORD PTR[r9*1+r14]
-	lea	rbp,QWORD PTR[rdi*8+rcx]
+	lea	rbx,[r9*1+r14]
+	lea	rbp,[rdi*8+rcx]
 	mov	rcx,r9
 	sar	rcx,3+2
-	mov	rdi,QWORD PTR[((56+8))+rsp]
-	jmp	$L$sqr4x_sub
-mul4x_internal	ENDP
-PUBLIC	bn_power5
+	mov	rdi,QWORD[((56+8))+rsp]
+	jmp	NEAR $L$sqr4x_sub
+
+global	bn_power5
 
 ALIGN	32
-bn_power5	PROC PUBLIC
-	mov	QWORD PTR[8+rsp],rdi	;WIN64 prologue
-	mov	QWORD PTR[16+rsp],rsi
+bn_power5:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
 	mov	rax,rsp
-$L$SEH_begin_bn_power5::
+$L$SEH_begin_bn_power5:
 	mov	rdi,rcx
 	mov	rsi,rdx
 	mov	rdx,r8
 	mov	rcx,r9
-	mov	r8,QWORD PTR[40+rsp]
-	mov	r9,QWORD PTR[48+rsp]
+	mov	r8,QWORD[40+rsp]
+	mov	r9,QWORD[48+rsp]
 
 
 	mov	rax,rsp
@@ -791,14 +793,14 @@ $L$SEH_begin_bn_power5::
 	push	r13
 	push	r14
 	push	r15
-	lea	rsp,QWORD PTR[((-40))+rsp]
-	movaps	XMMWORD PTR[rsp],xmm6
-	movaps	XMMWORD PTR[16+rsp],xmm7
+	lea	rsp,[((-40))+rsp]
+	movaps	XMMWORD[rsp],xmm6
+	movaps	XMMWORD[16+rsp],xmm7
 	mov	r10d,r9d
 	shl	r9d,3
 	shl	r10d,3+2
 	neg	r9
-	mov	r8,QWORD PTR[r8]
+	mov	r8,QWORD[r8]
 
 
 
@@ -806,24 +808,24 @@ $L$SEH_begin_bn_power5::
 
 
 
-	lea	r11,QWORD PTR[((-64))+r9*2+rsp]
+	lea	r11,[((-64))+r9*2+rsp]
 	sub	r11,rsi
 	and	r11,4095
 	cmp	r10,r11
-	jb	$L$pwr_sp_alt
+	jb	NEAR $L$pwr_sp_alt
 	sub	rsp,r11
-	lea	rsp,QWORD PTR[((-64))+r9*2+rsp]
-	jmp	$L$pwr_sp_done
+	lea	rsp,[((-64))+r9*2+rsp]
+	jmp	NEAR $L$pwr_sp_done
 
 ALIGN	32
-$L$pwr_sp_alt::
-	lea	r10,QWORD PTR[((4096-64))+r9*2]
-	lea	rsp,QWORD PTR[((-64))+r9*2+rsp]
+$L$pwr_sp_alt:
+	lea	r10,[((4096-64))+r9*2]
+	lea	rsp,[((-64))+r9*2+rsp]
 	sub	r11,r10
 	mov	r10,0
 	cmovc	r11,r10
 	sub	rsp,r11
-$L$pwr_sp_done::
+$L$pwr_sp_done:
 	and	rsp,-64
 	mov	r10,r9
 	neg	r9
@@ -837,9 +839,9 @@ $L$pwr_sp_done::
 
 
 
-	mov	QWORD PTR[32+rsp],r8
-	mov	QWORD PTR[40+rsp],rax
-$L$power5_body::
+	mov	QWORD[32+rsp],r8
+	mov	QWORD[40+rsp],rax
+$L$power5_body:
 DB	102,72,15,110,207
 DB	102,72,15,110,209
 DB	102,73,15,110,218
@@ -854,33 +856,32 @@ DB	102,72,15,110,226
 DB	102,72,15,126,209
 DB	102,72,15,126,226
 	mov	rdi,rsi
-	mov	rax,QWORD PTR[40+rsp]
-	lea	r8,QWORD PTR[32+rsp]
+	mov	rax,QWORD[40+rsp]
+	lea	r8,[32+rsp]
 
 	call	mul4x_internal
 
-	mov	rsi,QWORD PTR[40+rsp]
+	mov	rsi,QWORD[40+rsp]
 	mov	rax,1
-	mov	r15,QWORD PTR[((-48))+rsi]
-	mov	r14,QWORD PTR[((-40))+rsi]
-	mov	r13,QWORD PTR[((-32))+rsi]
-	mov	r12,QWORD PTR[((-24))+rsi]
-	mov	rbp,QWORD PTR[((-16))+rsi]
-	mov	rbx,QWORD PTR[((-8))+rsi]
-	lea	rsp,QWORD PTR[rsi]
-$L$power5_epilogue::
-	mov	rdi,QWORD PTR[8+rsp]	;WIN64 epilogue
-	mov	rsi,QWORD PTR[16+rsp]
+	mov	r15,QWORD[((-48))+rsi]
+	mov	r14,QWORD[((-40))+rsi]
+	mov	r13,QWORD[((-32))+rsi]
+	mov	r12,QWORD[((-24))+rsi]
+	mov	rbp,QWORD[((-16))+rsi]
+	mov	rbx,QWORD[((-8))+rsi]
+	lea	rsp,[rsi]
+$L$power5_epilogue:
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
-$L$SEH_end_bn_power5::
-bn_power5	ENDP
+$L$SEH_end_bn_power5:
 
-PUBLIC	bn_sqr8x_internal
+global	bn_sqr8x_internal
 
 
 ALIGN	32
-bn_sqr8x_internal	PROC PUBLIC
-__bn_sqr8x_internal::
+bn_sqr8x_internal:
+__bn_sqr8x_internal:
 
 
 
@@ -954,40 +955,40 @@ __bn_sqr8x_internal::
 
 
 
-	lea	rbp,QWORD PTR[32+r10]
-	lea	rsi,QWORD PTR[r9*1+rsi]
+	lea	rbp,[32+r10]
+	lea	rsi,[r9*1+rsi]
 
 	mov	rcx,r9
 
 
-	mov	r14,QWORD PTR[((-32))+rbp*1+rsi]
-	lea	rdi,QWORD PTR[((48+8))+r9*2+rsp]
-	mov	rax,QWORD PTR[((-24))+rbp*1+rsi]
-	lea	rdi,QWORD PTR[((-32))+rbp*1+rdi]
-	mov	rbx,QWORD PTR[((-16))+rbp*1+rsi]
+	mov	r14,QWORD[((-32))+rbp*1+rsi]
+	lea	rdi,[((48+8))+r9*2+rsp]
+	mov	rax,QWORD[((-24))+rbp*1+rsi]
+	lea	rdi,[((-32))+rbp*1+rdi]
+	mov	rbx,QWORD[((-16))+rbp*1+rsi]
 	mov	r15,rax
 
 	mul	r14
 	mov	r10,rax
 	mov	rax,rbx
 	mov	r11,rdx
-	mov	QWORD PTR[((-24))+rbp*1+rdi],r10
+	mov	QWORD[((-24))+rbp*1+rdi],r10
 
 	mul	r14
 	add	r11,rax
 	mov	rax,rbx
 	adc	rdx,0
-	mov	QWORD PTR[((-16))+rbp*1+rdi],r11
+	mov	QWORD[((-16))+rbp*1+rdi],r11
 	mov	r10,rdx
 
 
-	mov	rbx,QWORD PTR[((-8))+rbp*1+rsi]
+	mov	rbx,QWORD[((-8))+rbp*1+rsi]
 	mul	r15
 	mov	r12,rax
 	mov	rax,rbx
 	mov	r13,rdx
 
-	lea	rcx,QWORD PTR[rbp]
+	lea	rcx,[rbp]
 	mul	r14
 	add	r10,rax
 	mov	rax,rbx
@@ -995,12 +996,12 @@ __bn_sqr8x_internal::
 	adc	r11,0
 	add	r10,r12
 	adc	r11,0
-	mov	QWORD PTR[((-8))+rcx*1+rdi],r10
-	jmp	$L$sqr4x_1st
+	mov	QWORD[((-8))+rcx*1+rdi],r10
+	jmp	NEAR $L$sqr4x_1st
 
 ALIGN	32
-$L$sqr4x_1st::
-	mov	rbx,QWORD PTR[rcx*1+rsi]
+$L$sqr4x_1st:
+	mov	rbx,QWORD[rcx*1+rsi]
 	mul	r15
 	add	r13,rax
 	mov	rax,rbx
@@ -1010,7 +1011,7 @@ $L$sqr4x_1st::
 	mul	r14
 	add	r11,rax
 	mov	rax,rbx
-	mov	rbx,QWORD PTR[8+rcx*1+rsi]
+	mov	rbx,QWORD[8+rcx*1+rsi]
 	mov	r10,rdx
 	adc	r10,0
 	add	r11,r13
@@ -1020,14 +1021,14 @@ $L$sqr4x_1st::
 	mul	r15
 	add	r12,rax
 	mov	rax,rbx
-	mov	QWORD PTR[rcx*1+rdi],r11
+	mov	QWORD[rcx*1+rdi],r11
 	mov	r13,rdx
 	adc	r13,0
 
 	mul	r14
 	add	r10,rax
 	mov	rax,rbx
-	mov	rbx,QWORD PTR[16+rcx*1+rsi]
+	mov	rbx,QWORD[16+rcx*1+rsi]
 	mov	r11,rdx
 	adc	r11,0
 	add	r10,r12
@@ -1036,14 +1037,14 @@ $L$sqr4x_1st::
 	mul	r15
 	add	r13,rax
 	mov	rax,rbx
-	mov	QWORD PTR[8+rcx*1+rdi],r10
+	mov	QWORD[8+rcx*1+rdi],r10
 	mov	r12,rdx
 	adc	r12,0
 
 	mul	r14
 	add	r11,rax
 	mov	rax,rbx
-	mov	rbx,QWORD PTR[24+rcx*1+rsi]
+	mov	rbx,QWORD[24+rcx*1+rsi]
 	mov	r10,rdx
 	adc	r10,0
 	add	r11,r13
@@ -1053,10 +1054,10 @@ $L$sqr4x_1st::
 	mul	r15
 	add	r12,rax
 	mov	rax,rbx
-	mov	QWORD PTR[16+rcx*1+rdi],r11
+	mov	QWORD[16+rcx*1+rdi],r11
 	mov	r13,rdx
 	adc	r13,0
-	lea	rcx,QWORD PTR[32+rcx]
+	lea	rcx,[32+rcx]
 
 	mul	r14
 	add	r10,rax
@@ -1065,57 +1066,57 @@ $L$sqr4x_1st::
 	adc	r11,0
 	add	r10,r12
 	adc	r11,0
-	mov	QWORD PTR[((-8))+rcx*1+rdi],r10
+	mov	QWORD[((-8))+rcx*1+rdi],r10
 
 	cmp	rcx,0
-	jne	$L$sqr4x_1st
+	jne	NEAR $L$sqr4x_1st
 
 	mul	r15
 	add	r13,rax
-	lea	rbp,QWORD PTR[16+rbp]
+	lea	rbp,[16+rbp]
 	adc	rdx,0
 	add	r13,r11
 	adc	rdx,0
 
-	mov	QWORD PTR[rdi],r13
+	mov	QWORD[rdi],r13
 	mov	r12,rdx
-	mov	QWORD PTR[8+rdi],rdx
-	jmp	$L$sqr4x_outer
+	mov	QWORD[8+rdi],rdx
+	jmp	NEAR $L$sqr4x_outer
 
 ALIGN	32
-$L$sqr4x_outer::
-	mov	r14,QWORD PTR[((-32))+rbp*1+rsi]
-	lea	rdi,QWORD PTR[((48+8))+r9*2+rsp]
-	mov	rax,QWORD PTR[((-24))+rbp*1+rsi]
-	lea	rdi,QWORD PTR[((-32))+rbp*1+rdi]
-	mov	rbx,QWORD PTR[((-16))+rbp*1+rsi]
+$L$sqr4x_outer:
+	mov	r14,QWORD[((-32))+rbp*1+rsi]
+	lea	rdi,[((48+8))+r9*2+rsp]
+	mov	rax,QWORD[((-24))+rbp*1+rsi]
+	lea	rdi,[((-32))+rbp*1+rdi]
+	mov	rbx,QWORD[((-16))+rbp*1+rsi]
 	mov	r15,rax
 
 	mul	r14
-	mov	r10,QWORD PTR[((-24))+rbp*1+rdi]
+	mov	r10,QWORD[((-24))+rbp*1+rdi]
 	add	r10,rax
 	mov	rax,rbx
 	adc	rdx,0
-	mov	QWORD PTR[((-24))+rbp*1+rdi],r10
+	mov	QWORD[((-24))+rbp*1+rdi],r10
 	mov	r11,rdx
 
 	mul	r14
 	add	r11,rax
 	mov	rax,rbx
 	adc	rdx,0
-	add	r11,QWORD PTR[((-16))+rbp*1+rdi]
+	add	r11,QWORD[((-16))+rbp*1+rdi]
 	mov	r10,rdx
 	adc	r10,0
-	mov	QWORD PTR[((-16))+rbp*1+rdi],r11
+	mov	QWORD[((-16))+rbp*1+rdi],r11
 
 	xor	r12,r12
 
-	mov	rbx,QWORD PTR[((-8))+rbp*1+rsi]
+	mov	rbx,QWORD[((-8))+rbp*1+rsi]
 	mul	r15
 	add	r12,rax
 	mov	rax,rbx
 	adc	rdx,0
-	add	r12,QWORD PTR[((-8))+rbp*1+rdi]
+	add	r12,QWORD[((-8))+rbp*1+rdi]
 	mov	r13,rdx
 	adc	r13,0
 
@@ -1126,27 +1127,27 @@ $L$sqr4x_outer::
 	add	r10,r12
 	mov	r11,rdx
 	adc	r11,0
-	mov	QWORD PTR[((-8))+rbp*1+rdi],r10
+	mov	QWORD[((-8))+rbp*1+rdi],r10
 
-	lea	rcx,QWORD PTR[rbp]
-	jmp	$L$sqr4x_inner
+	lea	rcx,[rbp]
+	jmp	NEAR $L$sqr4x_inner
 
 ALIGN	32
-$L$sqr4x_inner::
-	mov	rbx,QWORD PTR[rcx*1+rsi]
+$L$sqr4x_inner:
+	mov	rbx,QWORD[rcx*1+rsi]
 	mul	r15
 	add	r13,rax
 	mov	rax,rbx
 	mov	r12,rdx
 	adc	r12,0
-	add	r13,QWORD PTR[rcx*1+rdi]
+	add	r13,QWORD[rcx*1+rdi]
 	adc	r12,0
 
-DB	067h
+DB	0x67
 	mul	r14
 	add	r11,rax
 	mov	rax,rbx
-	mov	rbx,QWORD PTR[8+rcx*1+rsi]
+	mov	rbx,QWORD[8+rcx*1+rsi]
 	mov	r10,rdx
 	adc	r10,0
 	add	r11,r13
@@ -1154,12 +1155,12 @@ DB	067h
 
 	mul	r15
 	add	r12,rax
-	mov	QWORD PTR[rcx*1+rdi],r11
+	mov	QWORD[rcx*1+rdi],r11
 	mov	rax,rbx
 	mov	r13,rdx
 	adc	r13,0
-	add	r12,QWORD PTR[8+rcx*1+rdi]
-	lea	rcx,QWORD PTR[16+rcx]
+	add	r12,QWORD[8+rcx*1+rdi]
+	lea	rcx,[16+rcx]
 	adc	r13,0
 
 	mul	r14
@@ -1169,31 +1170,31 @@ DB	067h
 	add	r10,r12
 	mov	r11,rdx
 	adc	r11,0
-	mov	QWORD PTR[((-8))+rcx*1+rdi],r10
+	mov	QWORD[((-8))+rcx*1+rdi],r10
 
 	cmp	rcx,0
-	jne	$L$sqr4x_inner
+	jne	NEAR $L$sqr4x_inner
 
-DB	067h
+DB	0x67
 	mul	r15
 	add	r13,rax
 	adc	rdx,0
 	add	r13,r11
 	adc	rdx,0
 
-	mov	QWORD PTR[rdi],r13
+	mov	QWORD[rdi],r13
 	mov	r12,rdx
-	mov	QWORD PTR[8+rdi],rdx
+	mov	QWORD[8+rdi],rdx
 
 	add	rbp,16
-	jnz	$L$sqr4x_outer
+	jnz	NEAR $L$sqr4x_outer
 
 
-	mov	r14,QWORD PTR[((-32))+rsi]
-	lea	rdi,QWORD PTR[((48+8))+r9*2+rsp]
-	mov	rax,QWORD PTR[((-24))+rsi]
-	lea	rdi,QWORD PTR[((-32))+rbp*1+rdi]
-	mov	rbx,QWORD PTR[((-16))+rsi]
+	mov	r14,QWORD[((-32))+rsi]
+	lea	rdi,[((48+8))+r9*2+rsp]
+	mov	rax,QWORD[((-24))+rsi]
+	lea	rdi,[((-32))+rbp*1+rdi]
+	mov	rbx,QWORD[((-16))+rsi]
 	mov	r15,rax
 
 	mul	r14
@@ -1205,17 +1206,17 @@ DB	067h
 	mul	r14
 	add	r11,rax
 	mov	rax,rbx
-	mov	QWORD PTR[((-24))+rdi],r10
+	mov	QWORD[((-24))+rdi],r10
 	mov	r10,rdx
 	adc	r10,0
 	add	r11,r13
-	mov	rbx,QWORD PTR[((-8))+rsi]
+	mov	rbx,QWORD[((-8))+rsi]
 	adc	r10,0
 
 	mul	r15
 	add	r12,rax
 	mov	rax,rbx
-	mov	QWORD PTR[((-16))+rdi],r11
+	mov	QWORD[((-16))+rdi],r11
 	mov	r13,rdx
 	adc	r13,0
 
@@ -1226,18 +1227,18 @@ DB	067h
 	adc	r11,0
 	add	r10,r12
 	adc	r11,0
-	mov	QWORD PTR[((-8))+rdi],r10
+	mov	QWORD[((-8))+rdi],r10
 
 	mul	r15
 	add	r13,rax
-	mov	rax,QWORD PTR[((-16))+rsi]
+	mov	rax,QWORD[((-16))+rsi]
 	adc	rdx,0
 	add	r13,r11
 	adc	rdx,0
 
-	mov	QWORD PTR[rdi],r13
+	mov	QWORD[rdi],r13
 	mov	r12,rdx
-	mov	QWORD PTR[8+rdi],rdx
+	mov	QWORD[8+rdi],rdx
 
 	mul	rbx
 	add	rbp,16
@@ -1247,216 +1248,216 @@ DB	067h
 
 	add	rax,r12
 	adc	rdx,0
-	mov	QWORD PTR[8+rdi],rax
-	mov	QWORD PTR[16+rdi],rdx
-	mov	QWORD PTR[24+rdi],r15
+	mov	QWORD[8+rdi],rax
+	mov	QWORD[16+rdi],rdx
+	mov	QWORD[24+rdi],r15
 
-	mov	rax,QWORD PTR[((-16))+rbp*1+rsi]
-	lea	rdi,QWORD PTR[((48+8))+rsp]
+	mov	rax,QWORD[((-16))+rbp*1+rsi]
+	lea	rdi,[((48+8))+rsp]
 	xor	r10,r10
-	mov	r11,QWORD PTR[8+rdi]
+	mov	r11,QWORD[8+rdi]
 
-	lea	r12,QWORD PTR[r10*2+r14]
+	lea	r12,[r10*2+r14]
 	shr	r10,63
-	lea	r13,QWORD PTR[r11*2+rcx]
+	lea	r13,[r11*2+rcx]
 	shr	r11,63
 	or	r13,r10
-	mov	r10,QWORD PTR[16+rdi]
+	mov	r10,QWORD[16+rdi]
 	mov	r14,r11
 	mul	rax
 	neg	r15
-	mov	r11,QWORD PTR[24+rdi]
+	mov	r11,QWORD[24+rdi]
 	adc	r12,rax
-	mov	rax,QWORD PTR[((-8))+rbp*1+rsi]
-	mov	QWORD PTR[rdi],r12
+	mov	rax,QWORD[((-8))+rbp*1+rsi]
+	mov	QWORD[rdi],r12
 	adc	r13,rdx
 
-	lea	rbx,QWORD PTR[r10*2+r14]
-	mov	QWORD PTR[8+rdi],r13
+	lea	rbx,[r10*2+r14]
+	mov	QWORD[8+rdi],r13
 	sbb	r15,r15
 	shr	r10,63
-	lea	r8,QWORD PTR[r11*2+rcx]
+	lea	r8,[r11*2+rcx]
 	shr	r11,63
 	or	r8,r10
-	mov	r10,QWORD PTR[32+rdi]
+	mov	r10,QWORD[32+rdi]
 	mov	r14,r11
 	mul	rax
 	neg	r15
-	mov	r11,QWORD PTR[40+rdi]
+	mov	r11,QWORD[40+rdi]
 	adc	rbx,rax
-	mov	rax,QWORD PTR[rbp*1+rsi]
-	mov	QWORD PTR[16+rdi],rbx
+	mov	rax,QWORD[rbp*1+rsi]
+	mov	QWORD[16+rdi],rbx
 	adc	r8,rdx
-	lea	rbp,QWORD PTR[16+rbp]
-	mov	QWORD PTR[24+rdi],r8
+	lea	rbp,[16+rbp]
+	mov	QWORD[24+rdi],r8
 	sbb	r15,r15
-	lea	rdi,QWORD PTR[64+rdi]
-	jmp	$L$sqr4x_shift_n_add
+	lea	rdi,[64+rdi]
+	jmp	NEAR $L$sqr4x_shift_n_add
 
 ALIGN	32
-$L$sqr4x_shift_n_add::
-	lea	r12,QWORD PTR[r10*2+r14]
+$L$sqr4x_shift_n_add:
+	lea	r12,[r10*2+r14]
 	shr	r10,63
-	lea	r13,QWORD PTR[r11*2+rcx]
+	lea	r13,[r11*2+rcx]
 	shr	r11,63
 	or	r13,r10
-	mov	r10,QWORD PTR[((-16))+rdi]
+	mov	r10,QWORD[((-16))+rdi]
 	mov	r14,r11
 	mul	rax
 	neg	r15
-	mov	r11,QWORD PTR[((-8))+rdi]
+	mov	r11,QWORD[((-8))+rdi]
 	adc	r12,rax
-	mov	rax,QWORD PTR[((-8))+rbp*1+rsi]
-	mov	QWORD PTR[((-32))+rdi],r12
+	mov	rax,QWORD[((-8))+rbp*1+rsi]
+	mov	QWORD[((-32))+rdi],r12
 	adc	r13,rdx
 
-	lea	rbx,QWORD PTR[r10*2+r14]
-	mov	QWORD PTR[((-24))+rdi],r13
+	lea	rbx,[r10*2+r14]
+	mov	QWORD[((-24))+rdi],r13
 	sbb	r15,r15
 	shr	r10,63
-	lea	r8,QWORD PTR[r11*2+rcx]
+	lea	r8,[r11*2+rcx]
 	shr	r11,63
 	or	r8,r10
-	mov	r10,QWORD PTR[rdi]
+	mov	r10,QWORD[rdi]
 	mov	r14,r11
 	mul	rax
 	neg	r15
-	mov	r11,QWORD PTR[8+rdi]
+	mov	r11,QWORD[8+rdi]
 	adc	rbx,rax
-	mov	rax,QWORD PTR[rbp*1+rsi]
-	mov	QWORD PTR[((-16))+rdi],rbx
+	mov	rax,QWORD[rbp*1+rsi]
+	mov	QWORD[((-16))+rdi],rbx
 	adc	r8,rdx
 
-	lea	r12,QWORD PTR[r10*2+r14]
-	mov	QWORD PTR[((-8))+rdi],r8
+	lea	r12,[r10*2+r14]
+	mov	QWORD[((-8))+rdi],r8
 	sbb	r15,r15
 	shr	r10,63
-	lea	r13,QWORD PTR[r11*2+rcx]
+	lea	r13,[r11*2+rcx]
 	shr	r11,63
 	or	r13,r10
-	mov	r10,QWORD PTR[16+rdi]
+	mov	r10,QWORD[16+rdi]
 	mov	r14,r11
 	mul	rax
 	neg	r15
-	mov	r11,QWORD PTR[24+rdi]
+	mov	r11,QWORD[24+rdi]
 	adc	r12,rax
-	mov	rax,QWORD PTR[8+rbp*1+rsi]
-	mov	QWORD PTR[rdi],r12
+	mov	rax,QWORD[8+rbp*1+rsi]
+	mov	QWORD[rdi],r12
 	adc	r13,rdx
 
-	lea	rbx,QWORD PTR[r10*2+r14]
-	mov	QWORD PTR[8+rdi],r13
+	lea	rbx,[r10*2+r14]
+	mov	QWORD[8+rdi],r13
 	sbb	r15,r15
 	shr	r10,63
-	lea	r8,QWORD PTR[r11*2+rcx]
+	lea	r8,[r11*2+rcx]
 	shr	r11,63
 	or	r8,r10
-	mov	r10,QWORD PTR[32+rdi]
+	mov	r10,QWORD[32+rdi]
 	mov	r14,r11
 	mul	rax
 	neg	r15
-	mov	r11,QWORD PTR[40+rdi]
+	mov	r11,QWORD[40+rdi]
 	adc	rbx,rax
-	mov	rax,QWORD PTR[16+rbp*1+rsi]
-	mov	QWORD PTR[16+rdi],rbx
+	mov	rax,QWORD[16+rbp*1+rsi]
+	mov	QWORD[16+rdi],rbx
 	adc	r8,rdx
-	mov	QWORD PTR[24+rdi],r8
+	mov	QWORD[24+rdi],r8
 	sbb	r15,r15
-	lea	rdi,QWORD PTR[64+rdi]
+	lea	rdi,[64+rdi]
 	add	rbp,32
-	jnz	$L$sqr4x_shift_n_add
+	jnz	NEAR $L$sqr4x_shift_n_add
 
-	lea	r12,QWORD PTR[r10*2+r14]
-DB	067h
+	lea	r12,[r10*2+r14]
+DB	0x67
 	shr	r10,63
-	lea	r13,QWORD PTR[r11*2+rcx]
+	lea	r13,[r11*2+rcx]
 	shr	r11,63
 	or	r13,r10
-	mov	r10,QWORD PTR[((-16))+rdi]
+	mov	r10,QWORD[((-16))+rdi]
 	mov	r14,r11
 	mul	rax
 	neg	r15
-	mov	r11,QWORD PTR[((-8))+rdi]
+	mov	r11,QWORD[((-8))+rdi]
 	adc	r12,rax
-	mov	rax,QWORD PTR[((-8))+rsi]
-	mov	QWORD PTR[((-32))+rdi],r12
+	mov	rax,QWORD[((-8))+rsi]
+	mov	QWORD[((-32))+rdi],r12
 	adc	r13,rdx
 
-	lea	rbx,QWORD PTR[r10*2+r14]
-	mov	QWORD PTR[((-24))+rdi],r13
+	lea	rbx,[r10*2+r14]
+	mov	QWORD[((-24))+rdi],r13
 	sbb	r15,r15
 	shr	r10,63
-	lea	r8,QWORD PTR[r11*2+rcx]
+	lea	r8,[r11*2+rcx]
 	shr	r11,63
 	or	r8,r10
 	mul	rax
 	neg	r15
 	adc	rbx,rax
 	adc	r8,rdx
-	mov	QWORD PTR[((-16))+rdi],rbx
-	mov	QWORD PTR[((-8))+rdi],r8
+	mov	QWORD[((-16))+rdi],rbx
+	mov	QWORD[((-8))+rdi],r8
 DB	102,72,15,126,213
-sqr8x_reduction::
+sqr8x_reduction:
 	xor	rax,rax
-	lea	rcx,QWORD PTR[r9*2+rbp]
-	lea	rdx,QWORD PTR[((48+8))+r9*2+rsp]
-	mov	QWORD PTR[((0+8))+rsp],rcx
-	lea	rdi,QWORD PTR[((48+8))+r9*1+rsp]
-	mov	QWORD PTR[((8+8))+rsp],rdx
+	lea	rcx,[r9*2+rbp]
+	lea	rdx,[((48+8))+r9*2+rsp]
+	mov	QWORD[((0+8))+rsp],rcx
+	lea	rdi,[((48+8))+r9*1+rsp]
+	mov	QWORD[((8+8))+rsp],rdx
 	neg	r9
-	jmp	$L$8x_reduction_loop
+	jmp	NEAR $L$8x_reduction_loop
 
 ALIGN	32
-$L$8x_reduction_loop::
-	lea	rdi,QWORD PTR[r9*1+rdi]
-DB	066h
-	mov	rbx,QWORD PTR[rdi]
-	mov	r9,QWORD PTR[8+rdi]
-	mov	r10,QWORD PTR[16+rdi]
-	mov	r11,QWORD PTR[24+rdi]
-	mov	r12,QWORD PTR[32+rdi]
-	mov	r13,QWORD PTR[40+rdi]
-	mov	r14,QWORD PTR[48+rdi]
-	mov	r15,QWORD PTR[56+rdi]
-	mov	QWORD PTR[rdx],rax
-	lea	rdi,QWORD PTR[64+rdi]
-
-DB	067h
+$L$8x_reduction_loop:
+	lea	rdi,[r9*1+rdi]
+DB	0x66
+	mov	rbx,QWORD[rdi]
+	mov	r9,QWORD[8+rdi]
+	mov	r10,QWORD[16+rdi]
+	mov	r11,QWORD[24+rdi]
+	mov	r12,QWORD[32+rdi]
+	mov	r13,QWORD[40+rdi]
+	mov	r14,QWORD[48+rdi]
+	mov	r15,QWORD[56+rdi]
+	mov	QWORD[rdx],rax
+	lea	rdi,[64+rdi]
+
+DB	0x67
 	mov	r8,rbx
-	imul	rbx,QWORD PTR[((32+8))+rsp]
-	mov	rax,QWORD PTR[rbp]
+	imul	rbx,QWORD[((32+8))+rsp]
+	mov	rax,QWORD[rbp]
 	mov	ecx,8
-	jmp	$L$8x_reduce
+	jmp	NEAR $L$8x_reduce
 
 ALIGN	32
-$L$8x_reduce::
+$L$8x_reduce:
 	mul	rbx
-	mov	rax,QWORD PTR[16+rbp]
+	mov	rax,QWORD[16+rbp]
 	neg	r8
 	mov	r8,rdx
 	adc	r8,0
 
 	mul	rbx
 	add	r9,rax
-	mov	rax,QWORD PTR[32+rbp]
+	mov	rax,QWORD[32+rbp]
 	adc	rdx,0
 	add	r8,r9
-	mov	QWORD PTR[((48-8+8))+rcx*8+rsp],rbx
+	mov	QWORD[((48-8+8))+rcx*8+rsp],rbx
 	mov	r9,rdx
 	adc	r9,0
 
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD PTR[48+rbp]
+	mov	rax,QWORD[48+rbp]
 	adc	rdx,0
 	add	r9,r10
-	mov	rsi,QWORD PTR[((32+8))+rsp]
+	mov	rsi,QWORD[((32+8))+rsp]
 	mov	r10,rdx
 	adc	r10,0
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD PTR[64+rbp]
+	mov	rax,QWORD[64+rbp]
 	adc	rdx,0
 	imul	rsi,r8
 	add	r10,r11
@@ -1465,7 +1466,7 @@ $L$8x_reduce::
 
 	mul	rbx
 	add	r12,rax
-	mov	rax,QWORD PTR[80+rbp]
+	mov	rax,QWORD[80+rbp]
 	adc	rdx,0
 	add	r11,r12
 	mov	r12,rdx
@@ -1473,7 +1474,7 @@ $L$8x_reduce::
 
 	mul	rbx
 	add	r13,rax
-	mov	rax,QWORD PTR[96+rbp]
+	mov	rax,QWORD[96+rbp]
 	adc	rdx,0
 	add	r12,r13
 	mov	r13,rdx
@@ -1481,7 +1482,7 @@ $L$8x_reduce::
 
 	mul	rbx
 	add	r14,rax
-	mov	rax,QWORD PTR[112+rbp]
+	mov	rax,QWORD[112+rbp]
 	adc	rdx,0
 	add	r13,r14
 	mov	r14,rdx
@@ -1490,58 +1491,58 @@ $L$8x_reduce::
 	mul	rbx
 	mov	rbx,rsi
 	add	r15,rax
-	mov	rax,QWORD PTR[rbp]
+	mov	rax,QWORD[rbp]
 	adc	rdx,0
 	add	r14,r15
 	mov	r15,rdx
 	adc	r15,0
 
 	dec	ecx
-	jnz	$L$8x_reduce
+	jnz	NEAR $L$8x_reduce
 
-	lea	rbp,QWORD PTR[128+rbp]
+	lea	rbp,[128+rbp]
 	xor	rax,rax
-	mov	rdx,QWORD PTR[((8+8))+rsp]
-	cmp	rbp,QWORD PTR[((0+8))+rsp]
-	jae	$L$8x_no_tail
-
-DB	066h
-	add	r8,QWORD PTR[rdi]
-	adc	r9,QWORD PTR[8+rdi]
-	adc	r10,QWORD PTR[16+rdi]
-	adc	r11,QWORD PTR[24+rdi]
-	adc	r12,QWORD PTR[32+rdi]
-	adc	r13,QWORD PTR[40+rdi]
-	adc	r14,QWORD PTR[48+rdi]
-	adc	r15,QWORD PTR[56+rdi]
+	mov	rdx,QWORD[((8+8))+rsp]
+	cmp	rbp,QWORD[((0+8))+rsp]
+	jae	NEAR $L$8x_no_tail
+
+DB	0x66
+	add	r8,QWORD[rdi]
+	adc	r9,QWORD[8+rdi]
+	adc	r10,QWORD[16+rdi]
+	adc	r11,QWORD[24+rdi]
+	adc	r12,QWORD[32+rdi]
+	adc	r13,QWORD[40+rdi]
+	adc	r14,QWORD[48+rdi]
+	adc	r15,QWORD[56+rdi]
 	sbb	rsi,rsi
 
-	mov	rbx,QWORD PTR[((48+56+8))+rsp]
+	mov	rbx,QWORD[((48+56+8))+rsp]
 	mov	ecx,8
-	mov	rax,QWORD PTR[rbp]
-	jmp	$L$8x_tail
+	mov	rax,QWORD[rbp]
+	jmp	NEAR $L$8x_tail
 
 ALIGN	32
-$L$8x_tail::
+$L$8x_tail:
 	mul	rbx
 	add	r8,rax
-	mov	rax,QWORD PTR[16+rbp]
-	mov	QWORD PTR[rdi],r8
+	mov	rax,QWORD[16+rbp]
+	mov	QWORD[rdi],r8
 	mov	r8,rdx
 	adc	r8,0
 
 	mul	rbx
 	add	r9,rax
-	mov	rax,QWORD PTR[32+rbp]
+	mov	rax,QWORD[32+rbp]
 	adc	rdx,0
 	add	r8,r9
-	lea	rdi,QWORD PTR[8+rdi]
+	lea	rdi,[8+rdi]
 	mov	r9,rdx
 	adc	r9,0
 
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD PTR[48+rbp]
+	mov	rax,QWORD[48+rbp]
 	adc	rdx,0
 	add	r9,r10
 	mov	r10,rdx
@@ -1549,7 +1550,7 @@ $L$8x_tail::
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD PTR[64+rbp]
+	mov	rax,QWORD[64+rbp]
 	adc	rdx,0
 	add	r10,r11
 	mov	r11,rdx
@@ -1557,7 +1558,7 @@ $L$8x_tail::
 
 	mul	rbx
 	add	r12,rax
-	mov	rax,QWORD PTR[80+rbp]
+	mov	rax,QWORD[80+rbp]
 	adc	rdx,0
 	add	r11,r12
 	mov	r12,rdx
@@ -1565,7 +1566,7 @@ $L$8x_tail::
 
 	mul	rbx
 	add	r13,rax
-	mov	rax,QWORD PTR[96+rbp]
+	mov	rax,QWORD[96+rbp]
 	adc	rdx,0
 	add	r12,r13
 	mov	r13,rdx
@@ -1573,143 +1574,143 @@ $L$8x_tail::
 
 	mul	rbx
 	add	r14,rax
-	mov	rax,QWORD PTR[112+rbp]
+	mov	rax,QWORD[112+rbp]
 	adc	rdx,0
 	add	r13,r14
 	mov	r14,rdx
 	adc	r14,0
 
 	mul	rbx
-	mov	rbx,QWORD PTR[((48-16+8))+rcx*8+rsp]
+	mov	rbx,QWORD[((48-16+8))+rcx*8+rsp]
 	add	r15,rax
 	adc	rdx,0
 	add	r14,r15
-	mov	rax,QWORD PTR[rbp]
+	mov	rax,QWORD[rbp]
 	mov	r15,rdx
 	adc	r15,0
 
 	dec	ecx
-	jnz	$L$8x_tail
+	jnz	NEAR $L$8x_tail
 
-	lea	rbp,QWORD PTR[128+rbp]
-	mov	rdx,QWORD PTR[((8+8))+rsp]
-	cmp	rbp,QWORD PTR[((0+8))+rsp]
-	jae	$L$8x_tail_done
+	lea	rbp,[128+rbp]
+	mov	rdx,QWORD[((8+8))+rsp]
+	cmp	rbp,QWORD[((0+8))+rsp]
+	jae	NEAR $L$8x_tail_done
 
-	mov	rbx,QWORD PTR[((48+56+8))+rsp]
+	mov	rbx,QWORD[((48+56+8))+rsp]
 	neg	rsi
-	mov	rax,QWORD PTR[rbp]
-	adc	r8,QWORD PTR[rdi]
-	adc	r9,QWORD PTR[8+rdi]
-	adc	r10,QWORD PTR[16+rdi]
-	adc	r11,QWORD PTR[24+rdi]
-	adc	r12,QWORD PTR[32+rdi]
-	adc	r13,QWORD PTR[40+rdi]
-	adc	r14,QWORD PTR[48+rdi]
-	adc	r15,QWORD PTR[56+rdi]
+	mov	rax,QWORD[rbp]
+	adc	r8,QWORD[rdi]
+	adc	r9,QWORD[8+rdi]
+	adc	r10,QWORD[16+rdi]
+	adc	r11,QWORD[24+rdi]
+	adc	r12,QWORD[32+rdi]
+	adc	r13,QWORD[40+rdi]
+	adc	r14,QWORD[48+rdi]
+	adc	r15,QWORD[56+rdi]
 	sbb	rsi,rsi
 
 	mov	ecx,8
-	jmp	$L$8x_tail
+	jmp	NEAR $L$8x_tail
 
 ALIGN	32
-$L$8x_tail_done::
-	add	r8,QWORD PTR[rdx]
+$L$8x_tail_done:
+	add	r8,QWORD[rdx]
 	xor	rax,rax
 
 	neg	rsi
-$L$8x_no_tail::
-	adc	r8,QWORD PTR[rdi]
-	adc	r9,QWORD PTR[8+rdi]
-	adc	r10,QWORD PTR[16+rdi]
-	adc	r11,QWORD PTR[24+rdi]
-	adc	r12,QWORD PTR[32+rdi]
-	adc	r13,QWORD PTR[40+rdi]
-	adc	r14,QWORD PTR[48+rdi]
-	adc	r15,QWORD PTR[56+rdi]
+$L$8x_no_tail:
+	adc	r8,QWORD[rdi]
+	adc	r9,QWORD[8+rdi]
+	adc	r10,QWORD[16+rdi]
+	adc	r11,QWORD[24+rdi]
+	adc	r12,QWORD[32+rdi]
+	adc	r13,QWORD[40+rdi]
+	adc	r14,QWORD[48+rdi]
+	adc	r15,QWORD[56+rdi]
 	adc	rax,0
-	mov	rcx,QWORD PTR[((-16))+rbp]
+	mov	rcx,QWORD[((-16))+rbp]
 	xor	rsi,rsi
 
 DB	102,72,15,126,213
 
-	mov	QWORD PTR[rdi],r8
-	mov	QWORD PTR[8+rdi],r9
+	mov	QWORD[rdi],r8
+	mov	QWORD[8+rdi],r9
 DB	102,73,15,126,217
-	mov	QWORD PTR[16+rdi],r10
-	mov	QWORD PTR[24+rdi],r11
-	mov	QWORD PTR[32+rdi],r12
-	mov	QWORD PTR[40+rdi],r13
-	mov	QWORD PTR[48+rdi],r14
-	mov	QWORD PTR[56+rdi],r15
-	lea	rdi,QWORD PTR[64+rdi]
+	mov	QWORD[16+rdi],r10
+	mov	QWORD[24+rdi],r11
+	mov	QWORD[32+rdi],r12
+	mov	QWORD[40+rdi],r13
+	mov	QWORD[48+rdi],r14
+	mov	QWORD[56+rdi],r15
+	lea	rdi,[64+rdi]
 
 	cmp	rdi,rdx
-	jb	$L$8x_reduction_loop
+	jb	NEAR $L$8x_reduction_loop
 
 	sub	rcx,r15
-	lea	rbx,QWORD PTR[r9*1+rdi]
+	lea	rbx,[r9*1+rdi]
 	adc	rsi,rsi
 	mov	rcx,r9
 	or	rax,rsi
 DB	102,72,15,126,207
 	xor	rax,1
 DB	102,72,15,126,206
-	lea	rbp,QWORD PTR[rax*8+rbp]
+	lea	rbp,[rax*8+rbp]
 	sar	rcx,3+2
-	jmp	$L$sqr4x_sub
+	jmp	NEAR $L$sqr4x_sub
 
 ALIGN	32
-$L$sqr4x_sub::
-DB	066h
-	mov	r12,QWORD PTR[rbx]
-	mov	r13,QWORD PTR[8+rbx]
-	sbb	r12,QWORD PTR[rbp]
-	mov	r14,QWORD PTR[16+rbx]
-	sbb	r13,QWORD PTR[16+rbp]
-	mov	r15,QWORD PTR[24+rbx]
-	lea	rbx,QWORD PTR[32+rbx]
-	sbb	r14,QWORD PTR[32+rbp]
-	mov	QWORD PTR[rdi],r12
-	sbb	r15,QWORD PTR[48+rbp]
-	lea	rbp,QWORD PTR[64+rbp]
-	mov	QWORD PTR[8+rdi],r13
-	mov	QWORD PTR[16+rdi],r14
-	mov	QWORD PTR[24+rdi],r15
-	lea	rdi,QWORD PTR[32+rdi]
+$L$sqr4x_sub:
+DB	0x66
+	mov	r12,QWORD[rbx]
+	mov	r13,QWORD[8+rbx]
+	sbb	r12,QWORD[rbp]
+	mov	r14,QWORD[16+rbx]
+	sbb	r13,QWORD[16+rbp]
+	mov	r15,QWORD[24+rbx]
+	lea	rbx,[32+rbx]
+	sbb	r14,QWORD[32+rbp]
+	mov	QWORD[rdi],r12
+	sbb	r15,QWORD[48+rbp]
+	lea	rbp,[64+rbp]
+	mov	QWORD[8+rdi],r13
+	mov	QWORD[16+rdi],r14
+	mov	QWORD[24+rdi],r15
+	lea	rdi,[32+rdi]
 
 	inc	rcx
-	jnz	$L$sqr4x_sub
+	jnz	NEAR $L$sqr4x_sub
 	mov	r10,r9
 	neg	r9
 	DB	0F3h,0C3h		;repret
-bn_sqr8x_internal	ENDP
-PUBLIC	bn_from_montgomery
+
+global	bn_from_montgomery
 
 ALIGN	32
-bn_from_montgomery	PROC PUBLIC
-	test	DWORD PTR[48+rsp],7
-	jz	bn_from_mont8x
+bn_from_montgomery:
+	test	DWORD[48+rsp],7
+	jz	NEAR bn_from_mont8x
 	xor	eax,eax
 	DB	0F3h,0C3h		;repret
-bn_from_montgomery	ENDP
+
 
 
 ALIGN	32
-bn_from_mont8x	PROC PRIVATE
-	mov	QWORD PTR[8+rsp],rdi	;WIN64 prologue
-	mov	QWORD PTR[16+rsp],rsi
+bn_from_mont8x:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
 	mov	rax,rsp
-$L$SEH_begin_bn_from_mont8x::
+$L$SEH_begin_bn_from_mont8x:
 	mov	rdi,rcx
 	mov	rsi,rdx
 	mov	rdx,r8
 	mov	rcx,r9
-	mov	r8,QWORD PTR[40+rsp]
-	mov	r9,QWORD PTR[48+rsp]
+	mov	r8,QWORD[40+rsp]
+	mov	r9,QWORD[48+rsp]
 
 
-DB	067h
+DB	0x67
 	mov	rax,rsp
 	push	rbx
 	push	rbp
@@ -1717,15 +1718,15 @@ DB	067h
 	push	r13
 	push	r14
 	push	r15
-	lea	rsp,QWORD PTR[((-40))+rsp]
-	movaps	XMMWORD PTR[rsp],xmm6
-	movaps	XMMWORD PTR[16+rsp],xmm7
-DB	067h
+	lea	rsp,[((-40))+rsp]
+	movaps	XMMWORD[rsp],xmm6
+	movaps	XMMWORD[16+rsp],xmm7
+DB	0x67
 	mov	r10d,r9d
 	shl	r9d,3
 	shl	r10d,3+2
 	neg	r9
-	mov	r8,QWORD PTR[r8]
+	mov	r8,QWORD[r8]
 
 
 
@@ -1733,24 +1734,24 @@ DB	067h
 
 
 
-	lea	r11,QWORD PTR[((-64))+r9*2+rsp]
+	lea	r11,[((-64))+r9*2+rsp]
 	sub	r11,rsi
 	and	r11,4095
 	cmp	r10,r11
-	jb	$L$from_sp_alt
+	jb	NEAR $L$from_sp_alt
 	sub	rsp,r11
-	lea	rsp,QWORD PTR[((-64))+r9*2+rsp]
-	jmp	$L$from_sp_done
+	lea	rsp,[((-64))+r9*2+rsp]
+	jmp	NEAR $L$from_sp_done
 
 ALIGN	32
-$L$from_sp_alt::
-	lea	r10,QWORD PTR[((4096-64))+r9*2]
-	lea	rsp,QWORD PTR[((-64))+r9*2+rsp]
+$L$from_sp_alt:
+	lea	r10,[((4096-64))+r9*2]
+	lea	rsp,[((-64))+r9*2+rsp]
 	sub	r11,r10
 	mov	r10,0
 	cmovc	r11,r10
 	sub	rsp,r11
-$L$from_sp_done::
+$L$from_sp_done:
 	and	rsp,-64
 	mov	r10,r9
 	neg	r9
@@ -1764,136 +1765,135 @@ $L$from_sp_done::
 
 
 
-	mov	QWORD PTR[32+rsp],r8
-	mov	QWORD PTR[40+rsp],rax
-$L$from_body::
+	mov	QWORD[32+rsp],r8
+	mov	QWORD[40+rsp],rax
+$L$from_body:
 	mov	r11,r9
-	lea	rax,QWORD PTR[48+rsp]
+	lea	rax,[48+rsp]
 	pxor	xmm0,xmm0
-	jmp	$L$mul_by_1
+	jmp	NEAR $L$mul_by_1
 
 ALIGN	32
-$L$mul_by_1::
-	movdqu	xmm1,XMMWORD PTR[rsi]
-	movdqu	xmm2,XMMWORD PTR[16+rsi]
-	movdqu	xmm3,XMMWORD PTR[32+rsi]
-	movdqa	XMMWORD PTR[r9*1+rax],xmm0
-	movdqu	xmm4,XMMWORD PTR[48+rsi]
-	movdqa	XMMWORD PTR[16+r9*1+rax],xmm0
-DB	048h,08dh,0b6h,040h,000h,000h,000h
-	movdqa	XMMWORD PTR[rax],xmm1
-	movdqa	XMMWORD PTR[32+r9*1+rax],xmm0
-	movdqa	XMMWORD PTR[16+rax],xmm2
-	movdqa	XMMWORD PTR[48+r9*1+rax],xmm0
-	movdqa	XMMWORD PTR[32+rax],xmm3
-	movdqa	XMMWORD PTR[48+rax],xmm4
-	lea	rax,QWORD PTR[64+rax]
+$L$mul_by_1:
+	movdqu	xmm1,XMMWORD[rsi]
+	movdqu	xmm2,XMMWORD[16+rsi]
+	movdqu	xmm3,XMMWORD[32+rsi]
+	movdqa	XMMWORD[r9*1+rax],xmm0
+	movdqu	xmm4,XMMWORD[48+rsi]
+	movdqa	XMMWORD[16+r9*1+rax],xmm0
+DB	0x48,0x8d,0xb6,0x40,0x00,0x00,0x00
+	movdqa	XMMWORD[rax],xmm1
+	movdqa	XMMWORD[32+r9*1+rax],xmm0
+	movdqa	XMMWORD[16+rax],xmm2
+	movdqa	XMMWORD[48+r9*1+rax],xmm0
+	movdqa	XMMWORD[32+rax],xmm3
+	movdqa	XMMWORD[48+rax],xmm4
+	lea	rax,[64+rax]
 	sub	r11,64
-	jnz	$L$mul_by_1
+	jnz	NEAR $L$mul_by_1
 
 DB	102,72,15,110,207
 DB	102,72,15,110,209
-DB	067h
+DB	0x67
 	mov	rbp,rcx
 DB	102,73,15,110,218
 	call	sqr8x_reduction
 
 	pxor	xmm0,xmm0
-	lea	rax,QWORD PTR[48+rsp]
-	mov	rsi,QWORD PTR[40+rsp]
-	jmp	$L$from_mont_zero
+	lea	rax,[48+rsp]
+	mov	rsi,QWORD[40+rsp]
+	jmp	NEAR $L$from_mont_zero
 
 ALIGN	32
-$L$from_mont_zero::
-	movdqa	XMMWORD PTR[rax],xmm0
-	movdqa	XMMWORD PTR[16+rax],xmm0
-	movdqa	XMMWORD PTR[32+rax],xmm0
-	movdqa	XMMWORD PTR[48+rax],xmm0
-	lea	rax,QWORD PTR[64+rax]
+$L$from_mont_zero:
+	movdqa	XMMWORD[rax],xmm0
+	movdqa	XMMWORD[16+rax],xmm0
+	movdqa	XMMWORD[32+rax],xmm0
+	movdqa	XMMWORD[48+rax],xmm0
+	lea	rax,[64+rax]
 	sub	r9,32
-	jnz	$L$from_mont_zero
+	jnz	NEAR $L$from_mont_zero
 
 	mov	rax,1
-	mov	r15,QWORD PTR[((-48))+rsi]
-	mov	r14,QWORD PTR[((-40))+rsi]
-	mov	r13,QWORD PTR[((-32))+rsi]
-	mov	r12,QWORD PTR[((-24))+rsi]
-	mov	rbp,QWORD PTR[((-16))+rsi]
-	mov	rbx,QWORD PTR[((-8))+rsi]
-	lea	rsp,QWORD PTR[rsi]
-$L$from_epilogue::
-	mov	rdi,QWORD PTR[8+rsp]	;WIN64 epilogue
-	mov	rsi,QWORD PTR[16+rsp]
+	mov	r15,QWORD[((-48))+rsi]
+	mov	r14,QWORD[((-40))+rsi]
+	mov	r13,QWORD[((-32))+rsi]
+	mov	r12,QWORD[((-24))+rsi]
+	mov	rbp,QWORD[((-16))+rsi]
+	mov	rbx,QWORD[((-8))+rsi]
+	lea	rsp,[rsi]
+$L$from_epilogue:
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
-$L$SEH_end_bn_from_mont8x::
-bn_from_mont8x	ENDP
-PUBLIC	bn_scatter5
+$L$SEH_end_bn_from_mont8x:
+global	bn_scatter5
 
 ALIGN	16
-bn_scatter5	PROC PUBLIC
+bn_scatter5:
 	cmp	edx,0
-	jz	$L$scatter_epilogue
-	lea	r8,QWORD PTR[r9*8+r8]
-$L$scatter::
-	mov	rax,QWORD PTR[rcx]
-	lea	rcx,QWORD PTR[8+rcx]
-	mov	QWORD PTR[r8],rax
-	lea	r8,QWORD PTR[256+r8]
+	jz	NEAR $L$scatter_epilogue
+	lea	r8,[r9*8+r8]
+$L$scatter:
+	mov	rax,QWORD[rcx]
+	lea	rcx,[8+rcx]
+	mov	QWORD[r8],rax
+	lea	r8,[256+r8]
 	sub	edx,1
-	jnz	$L$scatter
-$L$scatter_epilogue::
+	jnz	NEAR $L$scatter
+$L$scatter_epilogue:
 	DB	0F3h,0C3h		;repret
-bn_scatter5	ENDP
 
-PUBLIC	bn_gather5
+
+global	bn_gather5
 
 ALIGN	16
-bn_gather5	PROC PUBLIC
-$L$SEH_begin_bn_gather5::
+bn_gather5:
+$L$SEH_begin_bn_gather5:
 
-DB	048h,083h,0ech,028h
-DB	00fh,029h,034h,024h
-DB	00fh,029h,07ch,024h,010h
+DB	0x48,0x83,0xec,0x28
+DB	0x0f,0x29,0x34,0x24
+DB	0x0f,0x29,0x7c,0x24,0x10
 	mov	r11d,r9d
 	shr	r9d,3
 	and	r11,7
 	not	r9d
-	lea	rax,QWORD PTR[$L$magic_masks]
+	lea	rax,[$L$magic_masks]
 	and	r9d,3
-	lea	r8,QWORD PTR[128+r11*8+r8]
-	movq	xmm4,QWORD PTR[r9*8+rax]
-	movq	xmm5,QWORD PTR[8+r9*8+rax]
-	movq	xmm6,QWORD PTR[16+r9*8+rax]
-	movq	xmm7,QWORD PTR[24+r9*8+rax]
-	jmp	$L$gather
+	lea	r8,[128+r11*8+r8]
+	movq	xmm4,QWORD[r9*8+rax]
+	movq	xmm5,QWORD[8+r9*8+rax]
+	movq	xmm6,QWORD[16+r9*8+rax]
+	movq	xmm7,QWORD[24+r9*8+rax]
+	jmp	NEAR $L$gather
 ALIGN	16
-$L$gather::
-	movq	xmm0,QWORD PTR[(((-128)))+r8]
-	movq	xmm1,QWORD PTR[((-64))+r8]
+$L$gather:
+	movq	xmm0,QWORD[(((-128)))+r8]
+	movq	xmm1,QWORD[((-64))+r8]
 	pand	xmm0,xmm4
-	movq	xmm2,QWORD PTR[r8]
+	movq	xmm2,QWORD[r8]
 	pand	xmm1,xmm5
-	movq	xmm3,QWORD PTR[64+r8]
+	movq	xmm3,QWORD[64+r8]
 	pand	xmm2,xmm6
 	por	xmm0,xmm1
 	pand	xmm3,xmm7
-DB	067h,067h
+DB	0x67,0x67
 	por	xmm0,xmm2
-	lea	r8,QWORD PTR[256+r8]
+	lea	r8,[256+r8]
 	por	xmm0,xmm3
 
-	movq	QWORD PTR[rcx],xmm0
-	lea	rcx,QWORD PTR[8+rcx]
+	movq	QWORD[rcx],xmm0
+	lea	rcx,[8+rcx]
 	sub	edx,1
-	jnz	$L$gather
-	movaps	xmm6,XMMWORD PTR[rsp]
-	movaps	xmm7,XMMWORD PTR[16+rsp]
-	lea	rsp,QWORD PTR[40+rsp]
+	jnz	NEAR $L$gather
+	movaps	xmm6,XMMWORD[rsp]
+	movaps	xmm7,XMMWORD[16+rsp]
+	lea	rsp,[40+rsp]
 	DB	0F3h,0C3h		;repret
-$L$SEH_end_bn_gather5::
-bn_gather5	ENDP
+$L$SEH_end_bn_gather5:
+
 ALIGN	64
-$L$magic_masks::
+$L$magic_masks:
 	DD	0,0,0,0,0,0,-1,-1
 	DD	0,0,0,0,0,0,0,0
 DB	77,111,110,116,103,111,109,101,114,121,32,77,117,108,116,105
@@ -1902,10 +1902,10 @@ DB	99,97,116,116,101,114,47,103,97,116,104,101,114,32,102,111
 DB	114,32,120,56,54,95,54,52,44,32,67,82,89,80,84,79
 DB	71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111
 DB	112,101,110,115,115,108,46,111,114,103,62,0
-EXTERN	__imp_RtlVirtualUnwind:NEAR
+EXTERN	__imp_RtlVirtualUnwind
 
 ALIGN	16
-mul_handler	PROC PRIVATE
+mul_handler:
 	push	rsi
 	push	rdi
 	push	rbx
@@ -1917,79 +1917,79 @@ mul_handler	PROC PRIVATE
 	pushfq
 	sub	rsp,64
 
-	mov	rax,QWORD PTR[120+r8]
-	mov	rbx,QWORD PTR[248+r8]
+	mov	rax,QWORD[120+r8]
+	mov	rbx,QWORD[248+r8]
 
-	mov	rsi,QWORD PTR[8+r9]
-	mov	r11,QWORD PTR[56+r9]
+	mov	rsi,QWORD[8+r9]
+	mov	r11,QWORD[56+r9]
 
-	mov	r10d,DWORD PTR[r11]
-	lea	r10,QWORD PTR[r10*1+rsi]
+	mov	r10d,DWORD[r11]
+	lea	r10,[r10*1+rsi]
 	cmp	rbx,r10
-	jb	$L$common_seh_tail
+	jb	NEAR $L$common_seh_tail
 
-	mov	rax,QWORD PTR[152+r8]
+	mov	rax,QWORD[152+r8]
 
-	mov	r10d,DWORD PTR[4+r11]
-	lea	r10,QWORD PTR[r10*1+rsi]
+	mov	r10d,DWORD[4+r11]
+	lea	r10,[r10*1+rsi]
 	cmp	rbx,r10
-	jae	$L$common_seh_tail
+	jae	NEAR $L$common_seh_tail
 
-	lea	r10,QWORD PTR[$L$mul_epilogue]
+	lea	r10,[$L$mul_epilogue]
 	cmp	rbx,r10
-	jb	$L$body_40
-
-	mov	r10,QWORD PTR[192+r8]
-	mov	rax,QWORD PTR[8+r10*8+rax]
-	jmp	$L$body_proceed
-
-$L$body_40::
-	mov	rax,QWORD PTR[40+rax]
-$L$body_proceed::
-
-	movaps	xmm0,XMMWORD PTR[((-88))+rax]
-	movaps	xmm1,XMMWORD PTR[((-72))+rax]
-
-	mov	rbx,QWORD PTR[((-8))+rax]
-	mov	rbp,QWORD PTR[((-16))+rax]
-	mov	r12,QWORD PTR[((-24))+rax]
-	mov	r13,QWORD PTR[((-32))+rax]
-	mov	r14,QWORD PTR[((-40))+rax]
-	mov	r15,QWORD PTR[((-48))+rax]
-	mov	QWORD PTR[144+r8],rbx
-	mov	QWORD PTR[160+r8],rbp
-	mov	QWORD PTR[216+r8],r12
-	mov	QWORD PTR[224+r8],r13
-	mov	QWORD PTR[232+r8],r14
-	mov	QWORD PTR[240+r8],r15
-	movups	XMMWORD PTR[512+r8],xmm0
-	movups	XMMWORD PTR[528+r8],xmm1
-
-$L$common_seh_tail::
-	mov	rdi,QWORD PTR[8+rax]
-	mov	rsi,QWORD PTR[16+rax]
-	mov	QWORD PTR[152+r8],rax
-	mov	QWORD PTR[168+r8],rsi
-	mov	QWORD PTR[176+r8],rdi
-
-	mov	rdi,QWORD PTR[40+r9]
+	jb	NEAR $L$body_40
+
+	mov	r10,QWORD[192+r8]
+	mov	rax,QWORD[8+r10*8+rax]
+	jmp	NEAR $L$body_proceed
+
+$L$body_40:
+	mov	rax,QWORD[40+rax]
+$L$body_proceed:
+
+	movaps	xmm0,XMMWORD[((-88))+rax]
+	movaps	xmm1,XMMWORD[((-72))+rax]
+
+	mov	rbx,QWORD[((-8))+rax]
+	mov	rbp,QWORD[((-16))+rax]
+	mov	r12,QWORD[((-24))+rax]
+	mov	r13,QWORD[((-32))+rax]
+	mov	r14,QWORD[((-40))+rax]
+	mov	r15,QWORD[((-48))+rax]
+	mov	QWORD[144+r8],rbx
+	mov	QWORD[160+r8],rbp
+	mov	QWORD[216+r8],r12
+	mov	QWORD[224+r8],r13
+	mov	QWORD[232+r8],r14
+	mov	QWORD[240+r8],r15
+	movups	XMMWORD[512+r8],xmm0
+	movups	XMMWORD[528+r8],xmm1
+
+$L$common_seh_tail:
+	mov	rdi,QWORD[8+rax]
+	mov	rsi,QWORD[16+rax]
+	mov	QWORD[152+r8],rax
+	mov	QWORD[168+r8],rsi
+	mov	QWORD[176+r8],rdi
+
+	mov	rdi,QWORD[40+r9]
 	mov	rsi,r8
 	mov	ecx,154
-	DD	0a548f3fch
+	DD	0xa548f3fc
 
 	mov	rsi,r9
 	xor	rcx,rcx
-	mov	rdx,QWORD PTR[8+rsi]
-	mov	r8,QWORD PTR[rsi]
-	mov	r9,QWORD PTR[16+rsi]
-	mov	r10,QWORD PTR[40+rsi]
-	lea	r11,QWORD PTR[56+rsi]
-	lea	r12,QWORD PTR[24+rsi]
-	mov	QWORD PTR[32+rsp],r10
-	mov	QWORD PTR[40+rsp],r11
-	mov	QWORD PTR[48+rsp],r12
-	mov	QWORD PTR[56+rsp],rcx
-	call	QWORD PTR[__imp_RtlVirtualUnwind]
+	mov	rdx,QWORD[8+rsi]
+	mov	r8,QWORD[rsi]
+	mov	r9,QWORD[16+rsi]
+	mov	r10,QWORD[40+rsi]
+	lea	r11,[56+rsi]
+	lea	r12,[24+rsi]
+	mov	QWORD[32+rsp],r10
+	mov	QWORD[40+rsp],r11
+	mov	QWORD[48+rsp],r12
+	mov	QWORD[56+rsp],rcx
+	call	QWORD[__imp_RtlVirtualUnwind]
 
 	mov	eax,1
 	add	rsp,64
@@ -2003,59 +2003,54 @@ $L$common_seh_tail::
 	pop	rdi
 	pop	rsi
 	DB	0F3h,0C3h		;repret
-mul_handler	ENDP
 
-.text$	ENDS
-.pdata	SEGMENT READONLY ALIGN(4)
+
+section	.pdata rdata align=4
 ALIGN	4
-	DD	imagerel $L$SEH_begin_bn_mul_mont_gather5
-	DD	imagerel $L$SEH_end_bn_mul_mont_gather5
-	DD	imagerel $L$SEH_info_bn_mul_mont_gather5
-
-	DD	imagerel $L$SEH_begin_bn_mul4x_mont_gather5
-	DD	imagerel $L$SEH_end_bn_mul4x_mont_gather5
-	DD	imagerel $L$SEH_info_bn_mul4x_mont_gather5
-
-	DD	imagerel $L$SEH_begin_bn_power5
-	DD	imagerel $L$SEH_end_bn_power5
-	DD	imagerel $L$SEH_info_bn_power5
-
-	DD	imagerel $L$SEH_begin_bn_from_mont8x
-	DD	imagerel $L$SEH_end_bn_from_mont8x
-	DD	imagerel $L$SEH_info_bn_from_mont8x
-	DD	imagerel $L$SEH_begin_bn_gather5
-	DD	imagerel $L$SEH_end_bn_gather5
-	DD	imagerel $L$SEH_info_bn_gather5
-
-.pdata	ENDS
-.xdata	SEGMENT READONLY ALIGN(8)
+	DD	$L$SEH_begin_bn_mul_mont_gather5 wrt ..imagebase
+	DD	$L$SEH_end_bn_mul_mont_gather5 wrt ..imagebase
+	DD	$L$SEH_info_bn_mul_mont_gather5 wrt ..imagebase
+
+	DD	$L$SEH_begin_bn_mul4x_mont_gather5 wrt ..imagebase
+	DD	$L$SEH_end_bn_mul4x_mont_gather5 wrt ..imagebase
+	DD	$L$SEH_info_bn_mul4x_mont_gather5 wrt ..imagebase
+
+	DD	$L$SEH_begin_bn_power5 wrt ..imagebase
+	DD	$L$SEH_end_bn_power5 wrt ..imagebase
+	DD	$L$SEH_info_bn_power5 wrt ..imagebase
+
+	DD	$L$SEH_begin_bn_from_mont8x wrt ..imagebase
+	DD	$L$SEH_end_bn_from_mont8x wrt ..imagebase
+	DD	$L$SEH_info_bn_from_mont8x wrt ..imagebase
+	DD	$L$SEH_begin_bn_gather5 wrt ..imagebase
+	DD	$L$SEH_end_bn_gather5 wrt ..imagebase
+	DD	$L$SEH_info_bn_gather5 wrt ..imagebase
+
+section	.xdata rdata align=8
 ALIGN	8
-$L$SEH_info_bn_mul_mont_gather5::
+$L$SEH_info_bn_mul_mont_gather5:
 DB	9,0,0,0
-	DD	imagerel mul_handler
-	DD	imagerel $L$mul_body,imagerel $L$mul_epilogue
+	DD	mul_handler wrt ..imagebase
+	DD	$L$mul_body wrt ..imagebase,$L$mul_epilogue wrt ..imagebase
 ALIGN	8
-$L$SEH_info_bn_mul4x_mont_gather5::
+$L$SEH_info_bn_mul4x_mont_gather5:
 DB	9,0,0,0
-	DD	imagerel mul_handler
-	DD	imagerel $L$mul4x_body,imagerel $L$mul4x_epilogue
+	DD	mul_handler wrt ..imagebase
+	DD	$L$mul4x_body wrt ..imagebase,$L$mul4x_epilogue wrt ..imagebase
 ALIGN	8
-$L$SEH_info_bn_power5::
+$L$SEH_info_bn_power5:
 DB	9,0,0,0
-	DD	imagerel mul_handler
-	DD	imagerel $L$power5_body,imagerel $L$power5_epilogue
+	DD	mul_handler wrt ..imagebase
+	DD	$L$power5_body wrt ..imagebase,$L$power5_epilogue wrt ..imagebase
 ALIGN	8
-$L$SEH_info_bn_from_mont8x::
+$L$SEH_info_bn_from_mont8x:
 DB	9,0,0,0
-	DD	imagerel mul_handler
-	DD	imagerel $L$from_body,imagerel $L$from_epilogue
+	DD	mul_handler wrt ..imagebase
+	DD	$L$from_body wrt ..imagebase,$L$from_epilogue wrt ..imagebase
 ALIGN	8
-$L$SEH_info_bn_gather5::
-DB	001h,00dh,005h,000h
-DB	00dh,078h,001h,000h
-DB	008h,068h,000h,000h
-DB	004h,042h,000h,000h
+$L$SEH_info_bn_gather5:
+DB	0x01,0x0d,0x05,0x00
+DB	0x0d,0x78,0x01,0x00
+DB	0x08,0x68,0x00,0x00
+DB	0x04,0x42,0x00,0x00
 ALIGN	8
-
-.xdata	ENDS
-END