diff --git a/Makefile.am b/Makefile.am
index 4da1cee2..74a8f0fd 100644
--- a/Makefile.am
+++ b/Makefile.am
@@ -16,6 +16,7 @@ bin_PROGRAMS	= cpuminer
 dist_man_MANS	= cpuminer.1
 
 cpuminer_SOURCES = \
+  dummy.cpp \
   cpu-miner.c \
   util.c \
   api.c \
@@ -113,7 +114,6 @@ cpuminer_SOURCES = \
   algo/lyra2/phi2-4way.c \
   algo/lyra2/phi2.c \
   algo/m7m/m7m.c \
-  algo/m7m/magimath.cpp \
   algo/nist5/nist5-gate.c \
   algo/nist5/nist5-4way.c \
   algo/nist5/nist5.c \
@@ -289,7 +289,7 @@ if HAVE_WINDOWS
 endif
 
 cpuminer_LDFLAGS	= @LDFLAGS@
-cpuminer_LDADD	= @LIBCURL@ @JANSSON_LIBS@ @PTHREAD_LIBS@ @WS2_LIBS@  -lgmp
+cpuminer_LDADD	= @LIBCURL@ @JANSSON_LIBS@ @PTHREAD_LIBS@ @WS2_LIBS@ -lgmp
 cpuminer_CPPFLAGS = @LIBCURL_CPPFLAGS@ $(ALL_INCLUDES)
 cpuminer_CFLAGS   = -Wno-pointer-sign -Wno-pointer-to-int-cast $(disable_flags)
 
diff --git a/RELEASE_NOTES b/RELEASE_NOTES
index 5ea62c97..5927c158 100644
--- a/RELEASE_NOTES
+++ b/RELEASE_NOTES
@@ -75,6 +75,15 @@ If not what makes it happen or not happen?
 Change Log
 ----------
 
+v24.1
+
+#414: fix bug in merkle error handling.
+#416: change $nproc to $(nproc) in build scripts.
+#420: change some inline function definitions to static inline. 
+#413: Fix formatting error for share result log when using no-color.
+Faster 2 way interleaving.
+Cleanup sha256 architecture targetting.
+
 v23.15
 
 Fixed x11gost (sib) algo for all architectures, broken in v3.23.4.
diff --git a/algo-gate-api.h b/algo-gate-api.h
index 045b306e..e9ac10e0 100644
--- a/algo-gate-api.h
+++ b/algo-gate-api.h
@@ -107,16 +107,16 @@ typedef  uint32_t set_t;
 //  AVX10_256 is compatible with AVX2 + VAES
 
 // return set containing all elements from sets a & b
-inline set_t set_union ( set_t a, set_t b ) { return a | b; }
+static inline set_t set_union ( set_t a, set_t b ) { return a | b; }
 
 // return set contained common elements from sets a & b
-inline set_t set_intsec ( set_t a, set_t b) { return a & b; }
+static inline set_t set_intsec ( set_t a, set_t b) { return a & b; }
 
 // all elements in set a are included in set b
-inline bool set_incl ( set_t a, set_t b ) { return (a & b) == a; }
+static inline bool set_incl ( set_t a, set_t b ) { return (a & b) == a; }
 
 // no elements in set a are included in set b
-inline bool set_excl ( set_t a, set_t b ) { return (a & b) == 0; }
+static inline bool set_excl ( set_t a, set_t b ) { return (a & b) == 0; }
 
 typedef struct
 {
diff --git a/algo/m7m/m7m.c b/algo/m7m/m7m.c
index f5660152..9098f983 100644
--- a/algo/m7m/m7m.c
+++ b/algo/m7m/m7m.c
@@ -21,7 +21,7 @@
 #define EPS1 DBL_EPSILON
 #define EPS2 3.0e-11
 
-inline double exp_n( double xt )
+static inline double exp_n( double xt )
 {
     if ( xt < -700.0 )
         return 0;
@@ -33,7 +33,7 @@ inline double exp_n( double xt )
         return exp( xt );
 }
 
-inline double exp_n2( double x1, double x2 )
+static inline double exp_n2( double x1, double x2 )
 {
     double p1 = -700., p2 = -37., p3 = -0.8e-8, p4 = 0.8e-8,
            p5 = 37., p6 = 700.;
diff --git a/algo/m7m/magimath.cpp b/algo/m7m/magimath.cpp
deleted file mode 100644
index c8c64e23..00000000
--- a/algo/m7m/magimath.cpp
+++ /dev/null
@@ -1,75 +0,0 @@
-// Copyright (c) 2014 The Magi developers
-// Distributed under the MIT/X11 software license, see the accompanying
-// file COPYING or http://www.opensource.org/licenses/mit-license.php.
-
-#include <iostream>
-#include <cfloat>
-#include <limits>
-#include <math.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <stdint.h>
-
-#include "magimath.h"
-
-#define EPS1 (std::numeric_limits<double>::epsilon())
-#define EPS2 3.0e-11
-
-static void gauleg(double x1, double x2, double x[], double w[], const int n)
-{
-	int m,j,i;
-	double z1, z, xm, xl, pp, p3, p2, p1;
-	m=(n+1)/2;
-	xm=0.5*(x2+x1);
-	xl=0.5*(x2-x1);
-	for (i=1;i<=m;i++) {
-		z=cos(3.141592654*(i-0.25)/(n+0.5));
-		do {
-			p1=1.0;
-			p2=0.0;
-			for (j=1;j<=n;j++) {
-				p3=p2;
-				p2=p1;
-				p1=((2.0*j-1.0)*z*p2-(j-1.0)*p3)/j;
-			}
-			pp=n*(z*p1-p2)/(z*z-1.0);
-			z1=z;
-			z=z1-p1/pp;
-		} while (fabs(z-z1) > EPS2);
-		x[i]=xm-xl*z;
-		x[n+1-i]=xm+xl*z;
-		w[i]=2.0*xl/((1.0-z*z)*pp*pp);
-		w[n+1-i]=w[i];
-	}
-}
-
-static double GaussianQuad_N(double func(const double), const double a2, const double b2, const int NptGQ)
-{
-	double s=0.0;
-#ifdef _MSC_VER
-#define SW_DIVS 23
-	double x[SW_DIVS+1], w[SW_DIVS+1];
-#else
-	double x[NptGQ+1], w[NptGQ+1];
-#endif
-
-	gauleg(a2, b2, x, w, NptGQ);
-
-	for (int j=1; j<=NptGQ; j++) {
-		s += w[j]*func(x[j]);
-	}
-
-	return s;
-}
-
-static double swit_(double wvnmb)
-{
-	return pow( (5.55243*(exp_n(-0.3*wvnmb/15.762) - exp_n(-0.6*wvnmb/15.762)))*wvnmb, 0.5)
-		/ 1034.66 * pow(sin(wvnmb/65.), 2.);
-}
-
-uint32_t sw_(int nnounce, int divs)
-{
-	double wmax = ((sqrt((double)(nnounce))*(1.+EPS1))/450+100);
-	return ((uint32_t)(GaussianQuad_N(swit_, 0., wmax, divs)*(1.+EPS1)*1.e6));
-}
diff --git a/algo/m7m/magimath.h b/algo/m7m/magimath.h
deleted file mode 100644
index b57eb806..00000000
--- a/algo/m7m/magimath.h
+++ /dev/null
@@ -1,54 +0,0 @@
-// Copyright (c) 2014 The Magi developers
-// Distributed under the MIT/X11 software license, see the accompanying
-// file COPYING or http://www.opensource.org/licenses/mit-license.php.
-#ifndef MAGI_MATH_H
-#define MAGI_MATH_H
-
-#include <math.h>
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-uint32_t sw_(int nnounce, int divs);
-
-#ifdef __cplusplus
-}
-#endif
-
-
-inline double exp_n(double xt)
-{
-	double p1 = -700.0, p3 = -0.8e-8, p4 = 0.8e-8, p6 = 700.0;
-	if(xt < p1)
-		return 0;
-	else if(xt > p6)
-		return 1e200;
-	else if(xt > p3 && xt < p4)
-		return (1.0 + xt);
-	else
-		return exp(xt);
-}
-
-// 1 / (1 + exp(x1-x2))
-inline double exp_n2(double x1, double x2)
-{
-	double p1 = -700., p2 = -37., p3 = -0.8e-8, p4 = 0.8e-8, p5 = 37., p6 = 700.;
-	double xt = x1 - x2;
-	if (xt < p1+1.e-200)
-		return 1.;
-	else if (xt > p1 && xt < p2 + 1.e-200)
-		return ( 1. - exp(xt) );
-	else if (xt > p2 && xt < p3 + 1.e-200)
-		return ( 1. / (1. + exp(xt)) );
-	else if (xt > p3 && xt < p4)
-		return ( 1. / (2. + xt) );
-	else if (xt > p4 - 1.e-200 && xt < p5)
-		return ( exp(-xt) / (1. + exp(-xt)) );
-	else if (xt > p5 - 1.e-200 && xt < p6)
-		return ( exp(-xt) );
-	else //if (xt > p6 - 1.e-200)
-		return 0.;
-}
-
-#endif
diff --git a/algo/sha/sha1-hash.c b/algo/sha/sha1-hash.c
index 6f1928df..cfe02d30 100644
--- a/algo/sha/sha1-hash.c
+++ b/algo/sha/sha1-hash.c
@@ -205,7 +205,7 @@ void sha1_x86_sha_transform_be( uint32_t *state_out, const void *input,
 
 #endif
 
-#if defined(__aarch64__) && defined(__ARM_FEATURE_SHA2)
+#if defined(__ARM_NEON) && defined(__ARM_FEATURE_SHA2)
 
 #define sha1_neon_rounds( state_out, data, state_in ) \
 { \
diff --git a/algo/sha/sha256-hash.c b/algo/sha/sha256-hash.c
index 51971101..e2c10e94 100644
--- a/algo/sha/sha256-hash.c
+++ b/algo/sha/sha256-hash.c
@@ -1,6 +1,6 @@
 #include "sha256-hash.h"
 
-#if ( defined(__x86_64__) && defined(__SHA__) ) || defined(__ARM_NEON) && defined(__ARM_FEATURE_SHA2)
+#if ( defined(__x86_64__) && defined(__SHA__) ) || ( defined(__ARM_NEON) && defined(__ARM_FEATURE_SHA2) )
 
 static const uint32_t SHA256_IV[8] =
 {
@@ -189,7 +189,7 @@ static const uint32_t SHA256_IV[8] =
     _mm_store_si128( (__m128i*) &state_out[4], STATE1 ); \
 }
 
-void sha256_opt_transform_le( uint32_t *state_out, const void *input,
+void sha256_x86_sha_transform_le( uint32_t *state_out, const void *input,
                               const uint32_t *state_in )
 {
 #define load_msg( m, i ) casti_v128( m, i )
@@ -197,7 +197,7 @@ void sha256_opt_transform_le( uint32_t *state_out, const void *input,
 #undef load_msg
 }
 
-void sha256_opt_transform_be( uint32_t *state_out, const void *input,
+void sha256_x86_sha_transform_be( uint32_t *state_out, const void *input,
                               const uint32_t *state_in )
 {
 #define load_msg( m, i ) v128_bswap32( casti_v128( m, i ) )
@@ -517,7 +517,7 @@ void sha256_opt_transform_be( uint32_t *state_out, const void *input,
     _mm_store_si128( (__m128i*) &out_Y[4], STATE1_Y ); \
 }
 
-void sha256_ni2x_transform_le( uint32_t *out_X, uint32_t*out_Y,
+void sha256_x86_x2sha_transform_le( uint32_t *out_X, uint32_t*out_Y,
                                  const void *msg_X, const void *msg_Y,
                                  const uint32_t *in_X, const uint32_t *in_Y )
 {
@@ -526,7 +526,7 @@ void sha256_ni2x_transform_le( uint32_t *out_X, uint32_t*out_Y,
 #undef load_msg
 }
 
-void sha256_ni2x_transform_be( uint32_t *out_X, uint32_t*out_Y,
+void sha256_x86_x2sha_transform_be( uint32_t *out_X, uint32_t*out_Y,
                               const void *msg_X, const void *msg_Y,
                               const uint32_t *in_X, const uint32_t *in_Y )
 {
@@ -541,7 +541,7 @@ void sha256_ni2x_transform_be( uint32_t *out_X, uint32_t*out_Y,
 // The goal is to avoid any redundant processing in final. Prehash is almost
 // 4 rounds total, only missing the final addition of the nonce.
 // Nonce must be set to zero for prehash.
-void sha256_ni_prehash_3rounds( uint32_t *ostate, const void *msg,
+void sha256_x86_sha_prehash_3rounds( uint32_t *ostate, const void *msg,
                                 uint32_t *sstate, const uint32_t *istate )
 {
    __m128i STATE0, STATE1, MSG, TMP;
@@ -569,7 +569,7 @@ void sha256_ni_prehash_3rounds( uint32_t *ostate, const void *msg,
    casti_m128i( ostate, 1 ) = STATE1;
 }
 
-void sha256_ni2x_final_rounds( uint32_t *out_X, uint32_t *out_Y,
+void sha256_x86_x2sha_final_rounds( uint32_t *out_X, uint32_t *out_Y,
                  const void *msg_X, const void *msg_Y,
                  const uint32_t *state_mid_X, const uint32_t *state_mid_Y,
                  const uint32_t *state_save_X, const uint32_t *state_save_Y )
diff --git a/algo/sha/sha256-hash.h b/algo/sha/sha256-hash.h
index b0917982..4a201110 100644
--- a/algo/sha/sha256-hash.h
+++ b/algo/sha/sha256-hash.h
@@ -5,27 +5,21 @@
 #include "simd-utils.h"
 #include "cpuminer-config.h"
 
-// generic interface 
+static const uint32_t SHA256_IV[8];
+
+#if defined(__x86_64__) && defined(__SHA__)
 
 typedef struct
 {
-   unsigned char buf[64];    /* first field, for alignment */
+   unsigned char buf[64];
    uint32_t state[8];
    uint64_t count;
 } sha256_context __attribute__((aligned(64)));
 
-static const uint32_t SHA256_IV[8];
-
 void sha256_full( void *hash, const void *data, size_t len );
 void sha256_update( sha256_context *ctx, const void *data, size_t len );
 void sha256_final( sha256_context *ctx, void *hash );
 void sha256_ctx_init( sha256_context *ctx );
-void sha256_transform_le( uint32_t *state_out, const uint32_t *data,
-                          const uint32_t *state_in );
-void sha256_transform_be( uint32_t *state_out, const uint32_t *data,
-                          const uint32_t *state_in );
-
-#if defined(__x86_64__) && defined(__SHA__)
 
 void sha256_x86_sha_transform_le( uint32_t *state_out, const void *input,
                                   const uint32_t *state_in );
@@ -50,14 +44,6 @@ void sha256_x86_x2sha_final_rounds( uint32_t *state_out_X, uint32_t *state_out_Y
                  const uint32_t *state_mid_X, const uint32_t *state_mid_Y,
                  const uint32_t *state_save_X, const uint32_t *state_save_Y );
 
-// Temporary during name transition
-#define sha256_opt_transform_le   sha256_x86_sha_transform_le
-#define sha256_opt_transform_be   sha256_x86_sha_transform_be
-#define sha256_ni2x_transform_le  sha256_x86_x2sha_transform_le
-#define sha256_ni2x_transform_be  sha256_x86_x2sha_transform_be
-#define sha256_ni_prehash_3rounds sha256_x86_sha_prehash_3rounds
-#define sha256_ni2x_final_rounds  sha256_x86_x2sha_final_rounds
-
 // generic API
 #define sha256_transform_le        sha256_x86_sha_transform_le
 #define sha256_transform_be        sha256_x86_sha_transform_be
@@ -68,6 +54,20 @@ void sha256_x86_x2sha_final_rounds( uint32_t *state_out_X, uint32_t *state_out_Y
 
 #elif defined(__ARM_NEON) && defined(__ARM_FEATURE_SHA2)
 
+// SHA-256 AArch64 with NEON & SHA2
+
+typedef struct
+{
+   unsigned char buf[64];
+   uint32_t state[8];
+   uint64_t count;
+} sha256_context __attribute__((aligned(64)));
+
+void sha256_full( void *hash, const void *data, size_t len );
+void sha256_update( sha256_context *ctx, const void *data, size_t len );
+void sha256_final( sha256_context *ctx, void *hash );
+void sha256_ctx_init( sha256_context *ctx );
+
 void sha256_neon_sha_transform_be( uint32_t *state_out, const void *input,
                                    const uint32_t *state_in );
 void sha256_neon_sha_transform_le( uint32_t *state_out, const void *input,
@@ -89,14 +89,6 @@ void sha256_neon_x2sha_final_rounds( uint32_t *state_out_X,
                  const uint32_t *state_mid_X, const uint32_t *state_mid_Y,
                  const uint32_t *state_save_X, const uint32_t *state_save_Y );
 
-// Temporary during name transition
-#define sha256_transform_le         sha256_neon_sha_transform_le
-#define sha256_transform_be         sha256_neon_sha_transform_be
-#define sha256_2x_transform_le      sha256_neon_x2sha_transform_le
-#define sha256_2x_transform_be      sha256_neon_x2sha_transform_be
-#define sha256_prehash_3rounds      sha256_neon_sha_prehash_3rounds
-#define sha256_2x_final_rounds      sha256_neon_x2sha_final_rounds
-
 // generic API
 #define sha256_transform_le        sha256_neon_sha_transform_le
 #define sha256_transform_be        sha256_neon_sha_transform_be
@@ -106,9 +98,11 @@ void sha256_neon_x2sha_final_rounds( uint32_t *state_out_X,
 #define sha256_2x_final_rounds     sha256_neon_x2sha_final_rounds
 
 #else
+
 // without HW acceleration...
 #include "sph_sha2.h"
 
+#define sha256_context              sph_sha256_context
 #define sha256_full                 sph_sha256_full
 #define sha256_ctx_init             sph_sha256_init
 #define sha256_update               sph_sha256
@@ -117,12 +111,11 @@ void sha256_neon_x2sha_final_rounds( uint32_t *state_out_X,
 #define sha256_transform_be         sph_sha256_transform_be
 #define sha256_prehash_3rounds      sph_sha256_prehash_3rounds
 
-
 #endif
 
 #if defined(__AVX512F__) && defined(__AVX512VL__) && defined(__AVX512DQ__) && defined(__AVX512BW__)
 
-// SHA-256 16 way
+// SHA-256 16 way x86_64
 
 typedef struct
 {
@@ -147,7 +140,7 @@ void sha256_16x32_final_rounds( __m512i *state_out, const __m512i *data,
 int sha256_16x32_transform_le_short( __m512i *state_out, const __m512i *data,
                             const __m512i *state_in, const uint32_t *target );
 
-#define sha256_16way_context sha256_16x32_context
+#define sha256_16way_context               sha256_16x32_context
 #define sha256_16way_init                  sha256_16x32_init
 #define sha256_16way_update                sha256_16x32_update
 #define sha256_16way_close                 sha256_16x32_close
@@ -162,7 +155,7 @@ int sha256_16x32_transform_le_short( __m512i *state_out, const __m512i *data,
 
 #if defined (__AVX2__)
 
-// SHA-256 8 way
+// SHA-256 8 way x86_64
 
 typedef struct
 {
@@ -201,7 +194,7 @@ int sha256_8x32_transform_le_short( __m256i *state_out, const __m256i *data,
 
 #endif  // AVX2
 
-// SHA-256 4 way
+// SHA-256 4 way x86_64 with SSE2 or AArch64 with NEON
 
 typedef struct
 {
diff --git a/algo/x11/timetravel-gate.c b/algo/x11/timetravel-gate.c
index 370ef394..f4996925 100644
--- a/algo/x11/timetravel-gate.c
+++ b/algo/x11/timetravel-gate.c
@@ -16,14 +16,14 @@ bool register_timetravel_algo( algo_gate_t* gate )
   return true;
 };
 
-inline void tt_swap( int *a, int *b )
+static inline void tt_swap( int *a, int *b )
 {
         int c = *a;
         *a = *b;
         *b = c;
 }
 
-inline void reverse( int *pbegin, int *pend )
+static inline void reverse( int *pbegin, int *pend )
 {
    while ( (pbegin != pend) && (pbegin != --pend) )
    {
diff --git a/algo/x11/timetravel10-gate.c b/algo/x11/timetravel10-gate.c
index 8c212298..b3214823 100644
--- a/algo/x11/timetravel10-gate.c
+++ b/algo/x11/timetravel10-gate.c
@@ -16,14 +16,14 @@ bool register_timetravel10_algo( algo_gate_t* gate )
   return true;
 };
 
-inline void tt10_swap( int *a, int *b )
+static inline void tt10_swap( int *a, int *b )
 {
         int c = *a;
         *a = *b;
         *b = c;
 }
 
-inline void reverse( int *pbegin, int *pend )
+static inline void reverse( int *pbegin, int *pend )
 {
    while ( (pbegin != pend) && (pbegin != --pend) )
    {
diff --git a/algo/x16/x16rv2-4way.c b/algo/x16/x16rv2-4way.c
index ff55048b..b79b4a3c 100644
--- a/algo/x16/x16rv2-4way.c
+++ b/algo/x16/x16rv2-4way.c
@@ -730,7 +730,7 @@ typedef union _x16rv2_4way_context_overlay x16rv2_4way_context_overlay;
 static __thread x16rv2_4way_context_overlay x16rv2_ctx;
 
 // Pad the 24 bytes tiger hash to 64 bytes
-inline void padtiger512( uint32_t* hash )
+static inline void padtiger512( uint32_t* hash )
 {
   for ( int i = 6; i < 16; i++ ) hash[i] = 0;
 }
diff --git a/algo/x16/x16rv2.c b/algo/x16/x16rv2.c
index b7e51b16..4ad201bc 100644
--- a/algo/x16/x16rv2.c
+++ b/algo/x16/x16rv2.c
@@ -33,7 +33,7 @@ union _x16rv2_context_overlay
 typedef union _x16rv2_context_overlay x16rv2_context_overlay;
 
 // Pad the 24 bytes tiger hash to 64 bytes
-inline void padtiger512(uint32_t* hash) {
+static inline void padtiger512(uint32_t* hash) {
    for (int i = (24/4); i < (64/4); i++) hash[i] = 0;
 }
 
diff --git a/arm-build.sh b/arm-build.sh
index b8a8a7b6..ecb297bc 100755
--- a/arm-build.sh
+++ b/arm-build.sh
@@ -9,6 +9,6 @@ rm -f config.status
 
 CFLAGS="-O3 -march=native -Wall -flax-vector-conversions" ./configure  --with-curl 
 
-make -j $nproc
+make -j $(nproc)
 
 strip -s cpuminer
diff --git a/armbuild-all.sh b/armbuild-all.sh
index 328cb33b..328fd71c 100755
--- a/armbuild-all.sh
+++ b/armbuild-all.sh
@@ -10,33 +10,33 @@ make distclean || echo clean
 rm -f config.status
 ./autogen.sh || echo done
 CFLAGS="-O3 -march=armv8-a+crypto+sha2+aes -Wall -flax-vector-conversions" ./configure  --with-curl 
-make -j $nproc
+make -j $(nproc)
 strip -s cpuminer
 mv cpuminer cpuminer-armv8-aes-sha2
 
 make clean || echo clean
 rm -f config.status
 CFLAGS="-O3 -march=armv8-a+crypto+sha2 -Wall -flax-vector-conversions" ./configure  --with-curl      
-make -j $nproc
+make -j $(nproc)
 strip -s cpuminer
 mv cpuminer cpuminer-armv8-sha2
 
 make clean || echo clean
 rm -f config.status
 CFLAGS="-O3 -march=armv8-a+crypto+aes -Wall -flax-vector-conversions" ./configure  --with-curl      
-make -j $nproc
+make -j $(nproc)
 strip -s cpuminer
 mv cpuminer cpuminer-armv8-aes
 
 make clean || echo clean
 rm -f config.status
 CFLAGS="-O3 -march=armv8-a -Wall -flax-vector-conversions" ./configure  --with-curl
-make -j $nproc
+make -j $(nproc)
 strip -s cpuminer
 mv cpuminer cpuminer-armv8
 
 make clean || echo clean
 rm -f config.status
 CFLAGS="-O3 -march=native -Wall -flax-vector-conversions" ./configure  --with-curl     
-make -j $nproc
+make -j $(nproc)
 strip -s cpuminer
diff --git a/build-allarch.sh b/build-allarch.sh
index 7f85a2e8..7fbebc27 100755
--- a/build-allarch.sh
+++ b/build-allarch.sh
@@ -13,7 +13,7 @@ rm -f config.status
 CFLAGS="-O3 -march=icelake-client -Wall" ./configure --with-curl
 # Rocketlake needs gcc-11
 #CFLAGS="-O3 -march=rocketlake -Wall" ./configure --with-curl
-make -j $nproc
+make -j $(nproc)
 strip -s cpuminer
 mv cpuminer cpuminer-avx512-sha-vaes
 
@@ -34,7 +34,7 @@ rm -f config.status
 # Inclomplete list of Zen4 AVX512 extensions but includes all extensions used by cpuminer.
 CFLAGS="-O3 -march=znver3 -mavx512f -mavx512cd -mavx512dq -mavx512bw -mavx512vl -mavx512vbmi -mavx512vbmi2 -mavx512bitalg -mavx512vpopcntdq -Wall" ./configure --with-curl
 #CFLAGS="-O3 -march=znver2 -mvaes -mavx512f -mavx512dq -mavx512bw -mavx512vl -mavx512vbmi -Wall" ./configure --with-curl
-make -j $nproc
+make -j $(nproc)
 strip -s cpuminer
 mv cpuminer cpuminer-zen4
 
@@ -43,7 +43,7 @@ make clean || echo clean
 rm -f config.status
 #CFLAGS="-O3 -march=znver2 -mvaes" ./configure --with-curl
 CFLAGS="-O3 -march=znver3 -fno-common " ./configure --with-curl
-make -j $nproc
+make -j $(nproc)
 strip -s cpuminer
 mv cpuminer cpuminer-zen3
 
@@ -51,7 +51,7 @@ mv cpuminer cpuminer-zen3
 make clean || echo clean
 rm -f config.status
 CFLAGS="-O3 -march=skylake-avx512 -maes -Wall" ./configure --with-curl
-make -j $nproc
+make -j $(nproc)
 strip -s cpuminer
 mv cpuminer cpuminer-avx512
 
@@ -60,7 +60,7 @@ make clean || echo done
 rm -f config.status
 # vaes doesn't include aes
 CFLAGS="-O3 -maes -mavx2 -msha -mvaes -Wall" ./configure --with-curl
-make -j $nproc
+make -j $(nproc)
 strip -s cpuminer
 mv cpuminer cpuminer-avx2-sha-vaes
 
@@ -69,7 +69,7 @@ make clean || echo done
 rm -f config.status
 #CFLAGS="-O3 -march=znver1 -maes -Wall" ./configure --with-curl
 CFLAGS="-O3 -maes -mavx2 -msha -Wall" ./configure --with-curl
-make -j $nproc
+make -j $(nproc)
 strip -s cpuminer
 mv cpuminer cpuminer-avx2-sha
 
@@ -78,7 +78,7 @@ make clean || echo clean
 rm -f config.status
 # GCC 9 doesn't include AES with core-avx2
 CFLAGS="-O3 -march=core-avx2 -maes -Wall" ./configure --with-curl
-make -j $nproc
+make -j $(nproc)
 strip -s cpuminer
 mv cpuminer cpuminer-avx2
 
@@ -86,7 +86,7 @@ mv cpuminer cpuminer-avx2
 make clean || echo clean
 rm -f config.status
 CFLAGS="-O3 -march=corei7-avx -maes -Wall" ./configure --with-curl
-make -j $nproc
+make -j $(nproc)
 strip -s cpuminer
 mv cpuminer cpuminer-avx
 
@@ -94,7 +94,7 @@ mv cpuminer cpuminer-avx
 make clean || echo clean
 rm -f config.status
 CFLAGS="-O3 -march=westmere -maes -Wall" ./configure --with-curl
-make -j $nproc
+make -j $(nproc)
 strip -s cpuminer
 mv cpuminer cpuminer-aes-sse42
 
@@ -102,7 +102,7 @@ mv cpuminer cpuminer-aes-sse42
 make clean || echo clean
 rm -f config.status
 CFLAGS="-O3 -march=corei7 -Wall" ./configure --with-curl
-make -j $nproc
+make -j $(nproc)
 strip -s cpuminer
 mv cpuminer cpuminer-sse42
 
@@ -110,7 +110,7 @@ mv cpuminer cpuminer-sse42
 make clean || echo clean
 rm -f config.status
 CFLAGS="-O3 -march=core2 -Wall" ./configure --with-curl
-make -j $nproc
+make -j $(nproc)
 strip -s cpuminer
 mv cpuminer cpuminer-ssse3
 
@@ -118,7 +118,7 @@ mv cpuminer cpuminer-ssse3
 make clean || echo clean
 rm -f config.status
 CFLAGS="-O3 -msse2 -Wall" ./configure --with-curl
-make -j $nproc
+make -j $(nproc)
 strip -s cpuminer
 mv cpuminer cpuminer-sse2
 
@@ -126,7 +126,7 @@ mv cpuminer cpuminer-sse2
 make clean || echo clean
 rm -f config.status
 CFLAGS="-O3 -march=x86-64 -Wall" ./configure --with-curl
-make -j $nproc
+make -j $(nproc)
 strip -s cpuminer
 mv cpuminer cpuminer-x64
 
@@ -134,6 +134,6 @@ mv cpuminer cpuminer-x64
 make clean || echo done
 rm -f config.status
 CFLAGS="-O3 -march=native -Wall" ./configure --with-curl
-make -j $nproc
+make -j $(nproc)
 strip -s cpuminer
 
diff --git a/build-armv8.sh b/build-armv8.sh
index 0d68f1f8..512d72fd 100755
--- a/build-armv8.sh
+++ b/build-armv8.sh
@@ -10,6 +10,6 @@ rm -f config.status
 CFLAGS="-O2 -march=armv8-a+crypto+sha2+aes -Wall -flax-vector-conversions" ./configure  --with-curl  --host=aarch64-cortexa76-elf --build=x86_64-pc-linux-gnu --target=aarch64-cortexa76-elf
 #CFLAGS="-O2 -march=armv8-a+crypto+sha2+aes -Wall -flax-vector-conversions" ./configure  --with-curl
 
-make -j $nproc
+make -j $(nproc)
 
 strip -s cpuminer
diff --git a/build-avx2.sh b/build-avx2.sh
index aeca8889..25ac4b39 100755
--- a/build-avx2.sh
+++ b/build-avx2.sh
@@ -22,6 +22,6 @@ rm -f config.status
 CFLAGS="-O3 -march=haswell -maes -Wall" ./configure --with-curl
 #CFLAGS="-O3 -march=native -Wall" CXXFLAGS="$CFLAGS -std=gnu++11" ./configure --with-curl
 
-make -j $nproc
+make -j $(nproc)
 
 strip -s cpuminer
diff --git a/build-msys2.sh b/build-msys2.sh
index eee2b8db..ed57783a 100755
--- a/build-msys2.sh
+++ b/build-msys2.sh
@@ -6,5 +6,5 @@ make distclean || echo clean
 rm -f config.status
 ./autogen.sh || echo done
 CFLAGS="-O3 -march=native -Wall -D_WIN32_WINNT=0x0601" ./configure --with-curl
-make -j 4
+make -j $(nproc)
 strip -s cpuminer
diff --git a/build.sh b/build.sh
index c6f895c5..5e5cfa91 100755
--- a/build.sh
+++ b/build.sh
@@ -15,6 +15,6 @@ rm -f config.status
 #CFLAGS="-O3 -march=native -Wall" ./configure --with-curl --with-crypto=$HOME/usr
 CFLAGS="-O3 -march=native -Wall" ./configure --with-curl
 
-make -j $nproc
+make -j $(nproc)
 
 strip -s cpuminer
diff --git a/clean-all.sh b/clean-all.sh
index 855b54f2..8364e408 100755
--- a/clean-all.sh
+++ b/clean-all.sh
@@ -2,7 +2,7 @@
 #
 # make clean and rm all the targetted executables.
 
-rm cpuminer-avx512-sha-vaes cpuminer-avx512 cpuminer-avx2 cpuminer-avx cpuminer-aes-sse42 cpuminer-sse2 cpuminer-avx2-sha cpuminer-sse42 cpuminer-ssse3 cpuminer-avx2-sha-vaes cpuminer-zen3 cpuminer-zen4 cpuminer-x64 > /dev/null
+rm cpuminer-avx512-sha-vaes cpuminer-avx512 cpuminer-avx2 cpuminer-avx cpuminer-aes-sse42 cpuminer-sse2 cpuminer-avx2-sha cpuminer-sse42 cpuminer-ssse3 cpuminer-avx2-sha-vaes cpuminer-zen3 cpuminer-zen4 cpuminer-x64 cpuminer-armv8 cpuminer-armv8-aes cpuminer-armv8-aes-sha2 cpuminer-armv8-sha2 > /dev/null
 
 rm cpuminer-avx512-sha-vaes.exe cpuminer-avx512-sha.exe cpuminer-avx512.exe cpuminer-avx2.exe cpuminer-avx.exe cpuminer-aes-sse42.exe cpuminer-sse2.exe cpuminer-avx2-sha.exe cpuminer-sse42.exe cpuminer-ssse3.exe cpuminer-avx2-sha-vaes.exe cpuminer-zen3.exe cpuminer-zen4.exe cpuminer-x64.exe > /dev/null
 
diff --git a/configure b/configure
index f919fd81..dd6ce7fc 100755
--- a/configure
+++ b/configure
@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.71 for cpuminer-opt 23.15.
+# Generated by GNU Autoconf 2.71 for cpuminer-opt 24.1.
 #
 #
 # Copyright (C) 1992-1996, 1998-2017, 2020-2021 Free Software Foundation,
@@ -608,8 +608,8 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='cpuminer-opt'
 PACKAGE_TARNAME='cpuminer-opt'
-PACKAGE_VERSION='23.15'
-PACKAGE_STRING='cpuminer-opt 23.15'
+PACKAGE_VERSION='24.1'
+PACKAGE_STRING='cpuminer-opt 24.1'
 PACKAGE_BUGREPORT=''
 PACKAGE_URL=''
 
@@ -1360,7 +1360,7 @@ if test "$ac_init_help" = "long"; then
   # Omit some internal or obsolete options to make the list less imposing.
   # This message is too long to be a string in the A/UX 3.1 sh.
   cat <<_ACEOF
-\`configure' configures cpuminer-opt 23.15 to adapt to many kinds of systems.
+\`configure' configures cpuminer-opt 24.1 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1432,7 +1432,7 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of cpuminer-opt 23.15:";;
+     short | recursive ) echo "Configuration of cpuminer-opt 24.1:";;
    esac
   cat <<\_ACEOF
 
@@ -1538,7 +1538,7 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-cpuminer-opt configure 23.15
+cpuminer-opt configure 24.1
 generated by GNU Autoconf 2.71
 
 Copyright (C) 2021 Free Software Foundation, Inc.
@@ -1985,7 +1985,7 @@ cat >config.log <<_ACEOF
 This file contains any messages produced by compilers while
 running configure, to aid debugging if configure makes a mistake.
 
-It was created by cpuminer-opt $as_me 23.15, which was
+It was created by cpuminer-opt $as_me 24.1, which was
 generated by GNU Autoconf 2.71.  Invocation command line was
 
   $ $0$ac_configure_args_raw
@@ -3593,7 +3593,7 @@ fi
 
 # Define the identity of the package.
  PACKAGE='cpuminer-opt'
- VERSION='23.15'
+ VERSION='24.1'
 
 
 printf "%s\n" "#define PACKAGE \"$PACKAGE\"" >>confdefs.h
@@ -7508,7 +7508,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1
 # report actual input values of CONFIG_FILES etc. instead of their
 # values after options handling.
 ac_log="
-This file was extended by cpuminer-opt $as_me 23.15, which was
+This file was extended by cpuminer-opt $as_me 24.1, which was
 generated by GNU Autoconf 2.71.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -7576,7 +7576,7 @@ ac_cs_config_escaped=`printf "%s\n" "$ac_cs_config" | sed "s/^ //; s/'/'\\\\\\\\
 cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
 ac_cs_config='$ac_cs_config_escaped'
 ac_cs_version="\\
-cpuminer-opt config.status 23.15
+cpuminer-opt config.status 24.1
 configured by $0, generated by GNU Autoconf 2.71,
   with options \\"\$ac_cs_config\\"
 
diff --git a/configure.ac b/configure.ac
index 1d7b3d16..09fbbdb2 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1,4 +1,4 @@
-AC_INIT([cpuminer-opt], [23.15])
+AC_INIT([cpuminer-opt], [24.1])
 
 AC_PREREQ([2.59c])
 AC_CANONICAL_SYSTEM
diff --git a/configure~ b/configure~
index e8088bfc..dab87859 100755
--- a/configure~
+++ b/configure~
@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.71 for cpuminer-opt 23.14.
+# Generated by GNU Autoconf 2.71 for cpuminer-opt 23.16.
 #
 #
 # Copyright (C) 1992-1996, 1998-2017, 2020-2021 Free Software Foundation,
@@ -608,8 +608,8 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='cpuminer-opt'
 PACKAGE_TARNAME='cpuminer-opt'
-PACKAGE_VERSION='23.14'
-PACKAGE_STRING='cpuminer-opt 23.14'
+PACKAGE_VERSION='23.16'
+PACKAGE_STRING='cpuminer-opt 23.16'
 PACKAGE_BUGREPORT=''
 PACKAGE_URL=''
 
@@ -1360,7 +1360,7 @@ if test "$ac_init_help" = "long"; then
   # Omit some internal or obsolete options to make the list less imposing.
   # This message is too long to be a string in the A/UX 3.1 sh.
   cat <<_ACEOF
-\`configure' configures cpuminer-opt 23.14 to adapt to many kinds of systems.
+\`configure' configures cpuminer-opt 23.16 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1432,7 +1432,7 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of cpuminer-opt 23.14:";;
+     short | recursive ) echo "Configuration of cpuminer-opt 23.16:";;
    esac
   cat <<\_ACEOF
 
@@ -1538,7 +1538,7 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-cpuminer-opt configure 23.14
+cpuminer-opt configure 23.16
 generated by GNU Autoconf 2.71
 
 Copyright (C) 2021 Free Software Foundation, Inc.
@@ -1985,7 +1985,7 @@ cat >config.log <<_ACEOF
 This file contains any messages produced by compilers while
 running configure, to aid debugging if configure makes a mistake.
 
-It was created by cpuminer-opt $as_me 23.14, which was
+It was created by cpuminer-opt $as_me 23.16, which was
 generated by GNU Autoconf 2.71.  Invocation command line was
 
   $ $0$ac_configure_args_raw
@@ -3593,7 +3593,7 @@ fi
 
 # Define the identity of the package.
  PACKAGE='cpuminer-opt'
- VERSION='23.14'
+ VERSION='23.16'
 
 
 printf "%s\n" "#define PACKAGE \"$PACKAGE\"" >>confdefs.h
@@ -7508,7 +7508,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1
 # report actual input values of CONFIG_FILES etc. instead of their
 # values after options handling.
 ac_log="
-This file was extended by cpuminer-opt $as_me 23.14, which was
+This file was extended by cpuminer-opt $as_me 23.16, which was
 generated by GNU Autoconf 2.71.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -7576,7 +7576,7 @@ ac_cs_config_escaped=`printf "%s\n" "$ac_cs_config" | sed "s/^ //; s/'/'\\\\\\\\
 cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
 ac_cs_config='$ac_cs_config_escaped'
 ac_cs_version="\\
-cpuminer-opt config.status 23.14
+cpuminer-opt config.status 23.16
 configured by $0, generated by GNU Autoconf 2.71,
   with options \\"\$ac_cs_config\\"
 
diff --git a/cpu-miner.c b/cpu-miner.c
index 5d87a683..ad7cc03e 100644
--- a/cpu-miner.c
+++ b/cpu-miner.c
@@ -1294,7 +1294,7 @@ static int share_result( int result, struct work *work,
    const char *bell = !result && opt_bell ? &ASCII_BELL : "";
    applog( LOG_INFO, "%s%d %s%s %s%s %s%s %s%s%s, %.3f sec (%dms)",
            bell, my_stats.share_count, acol, ares, scol, sres, rcol, rres,
-           bcol, bres, CL_N, share_time, latency );
+           bcol, bres, use_colors ? CL_N : "", share_time, latency );
    if ( unlikely( !( opt_quiet || result || stale ) ) )
    {
       applog2( LOG_INFO, "%sReject reason: %s", bell, reason ? reason : "" );
diff --git a/dummy.cpp b/dummy.cpp
new file mode 100644
index 00000000..31139546
--- /dev/null
+++ b/dummy.cpp
@@ -0,0 +1,6 @@
+// This file exists to force the use of g++ as the linker which in turn
+// links the math library with the inclusion of math.h. gcc will not 
+// automatically link math. Without this file linking will fail for m7m.c.
+// Linking math manually, allowing gcc to do the linking work on Linux
+// but on Windows it segfaults. Until that is solved this file must continue
+// to exist.
diff --git a/miner.h b/miner.h
index 5d0cebf0..9ca8b936 100644
--- a/miner.h
+++ b/miner.h
@@ -185,13 +185,13 @@ static inline bool is_windows(void)
 */
 #endif
 
-static inline uint32_t swab32(uint32_t v)
+static inline uint32_t swab32(uint32_t x)
 {
 #ifdef WANT_BUILTIN_BSWAP
-   return __builtin_bswap32(v);
+   return __builtin_bswap32(x);
 #else
-   return ( (x << 24) & 0xff000000u ) | ( (x <<  8) & 0x00ff0000u )
-        | ( (x >>  8) & 0x0000ff00u ) | ( (x >> 24) & 0x000000ffu )
+   return ( ( (x) << 24 ) & 0xff000000u ) | ( ( (x) <<  8 ) & 0x00ff0000u )
+        | ( ( (x) >>  8 ) & 0x0000ff00u ) | ( ( (x) >> 24 ) & 0x000000ffu )
 
 
 //   return bswap_32(v);
diff --git a/simd-utils/intrlv.h b/simd-utils/intrlv.h
index bcf85dbe..d5a87fd8 100644
--- a/simd-utils/intrlv.h
+++ b/simd-utils/intrlv.h
@@ -86,29 +86,28 @@ static inline void extr_lane_2x32( void *dst, const void *src,
 
 // 4x32
 
-#if ( defined(__x86_64__) && defined(__SSE4_1__) ) || ( defined(__aarch64__) && defined(__ARM_NEON) )
+#if ( defined(__x86_64__) && defined(__SSE2__) ) || ( defined(__aarch64__) && defined(__ARM_NEON) )
 
 #define ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 ) \
-   D0 = v128_movlane32( S0, 1, S1, 0 ); \
-   D1 = v128_movlane32( S1, 0, S0, 1 ); \
-   D2 = v128_movlane32( S2, 0, S0, 2 ); \
-   D3 = v128_movlane32( S3, 0, S0, 3 ); \
-   D0 = v128_movlane32( D0, 2, S2, 0 ); \
-   D1 = v128_movlane32( D1, 2, S2, 1 ); \
-   D2 = v128_movlane32( D2, 1, S1, 2 ); \
-   D3 = v128_movlane32( D3, 1, S1, 3 ); \
-   D0 = v128_movlane32( D0, 3, S3, 0 ); \
-   D1 = v128_movlane32( D1, 3, S3, 1 ); \
-   D2 = v128_movlane32( D2, 3, S3, 2 ); \
-   D3 = v128_movlane32( D3, 2, S2, 3 ); 
-
-#define LOAD_SRCE( S0, S1, S2, S3, src0, i0, src1, i1, src2, i2, src3, i3 ) \
+{ \
+  v128_t T; \
+  T  = v128_unpacklo32( S0, S1 ); \
+  S0 = v128_unpackhi32( S0, S1 ); \
+  S1 = v128_unpacklo32( S2, S3 ); \
+  S2 = v128_unpackhi32( S2, S3 ); \
+  D0 = v128_unpacklo64( T,  S1 ); \
+  D1 = v128_unpackhi64( T,  S1 ); \
+  D2 = v128_unpacklo64( S0, S2 ); \
+  D3 = v128_unpackhi64( S0, S2 ); \
+}
+
+#define LOAD_SRCE_4x32( S0, S1, S2, S3, src0, i0, src1, i1, src2, i2, src3, i3 ) \
    S0 = v128_load( (const v128_t*)(src0) + (i0) ); \
    S1 = v128_load( (const v128_t*)(src1) + (i1) ); \
    S2 = v128_load( (const v128_t*)(src2) + (i2) ); \
    S3 = v128_load( (const v128_t*)(src3) + (i3) );
 
-#define STORE_DEST( D0, D1, D2, D3, dst0, i0, dst1, i1, dst2, i2, dst3, i3 ) \
+#define STOR_DEST_4x32( D0, D1, D2, D3, dst0, i0, dst1, i1, dst2, i2, dst3, i3 ) \
    v128_store( (v128_t*)(dst0) + (i0), D0 ); \
    v128_store( (v128_t*)(dst1) + (i1), D1 ); \
    v128_store( (v128_t*)(dst2) + (i2), D2 ); \
@@ -119,39 +118,39 @@ static inline void intrlv_4x32( void *dst, const void *src0, const void *src1,
 {
    v128_t D0, D1, D2, D3, S0, S1, S2, S3;
 
-   LOAD_SRCE( S0, S1, S2, S3, src0, 0, src1, 0, src2, 0, src3, 0 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src0, 0, src1, 0, src2, 0, src3, 0 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src0, 1, src1, 1, src2, 1, src3, 1 );
-   STORE_DEST( D0, D1, D2, D3, dst, 0, dst, 1, dst, 2, dst, 3 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src0, 1, src1, 1, src2, 1, src3, 1 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 0, dst, 1, dst, 2, dst, 3 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst, 4, dst, 5, dst, 6, dst, 7 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 4, dst, 5, dst, 6, dst, 7 );
 
    if ( bit_len <= 256 ) return;
 
-   LOAD_SRCE( S0, S1, S2, S3, src0, 2, src1, 2, src2, 2, src3, 2 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src0, 2, src1, 2, src2, 2, src3, 2 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src0, 3, src1, 3, src2, 3, src3, 3 );
-   STORE_DEST( D0, D1, D2, D3, dst, 8, dst, 9, dst, 10, dst, 11 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src0, 3, src1, 3, src2, 3, src3, 3 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 8, dst, 9, dst, 10, dst, 11 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst, 12, dst, 13, dst, 14, dst, 15 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 12, dst, 13, dst, 14, dst, 15 );
 
    if ( bit_len <= 512 ) return;
 
-   LOAD_SRCE( S0, S1, S2, S3, src0, 4, src1, 4, src2, 4, src3, 4 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src0, 4, src1, 4, src2, 4, src3, 4 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst, 16, dst, 17, dst, 18, dst, 19 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 16, dst, 17, dst, 18, dst, 19 );
 
    if ( bit_len <= 640 ) return;
 
-   LOAD_SRCE( S0, S1, S2, S3, src0, 5, src1, 5, src2, 5, src3, 5 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src0, 5, src1, 5, src2, 5, src3, 5 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src0, 6, src1, 6, src2, 6, src3, 6 );
-   STORE_DEST( D0, D1, D2, D3, dst, 20, dst, 21, dst, 22, dst, 23 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src0, 6, src1, 6, src2, 6, src3, 6 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 20, dst, 21, dst, 22, dst, 23 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src0, 7, src1, 7, src2, 7, src3, 7 ); 
-   STORE_DEST( D0, D1, D2, D3, dst, 24, dst, 25, dst, 26, dst, 27 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src0, 7, src1, 7, src2, 7, src3, 7 ); 
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 24, dst, 25, dst, 26, dst, 27 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst, 28, dst, 29, dst, 30, dst, 31 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 28, dst, 29, dst, 30, dst, 31 );
 
 // if ( bit_len <= 1024 ) return;
 }
@@ -161,18 +160,18 @@ static inline void intrlv_4x32_512( void *dst, const void *src0,
 {
    v128_t D0, D1, D2, D3, S0, S1, S2, S3;
 
-   LOAD_SRCE( S0, S1, S2, S3, src0, 0, src1, 0, src2, 0, src3, 0 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src0, 0, src1, 0, src2, 0, src3, 0 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src0, 1, src1, 1, src2, 1, src3, 1 );
-   STORE_DEST( D0, D1, D2, D3, dst, 0, dst, 1, dst, 2, dst, 3 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src0, 1, src1, 1, src2, 1, src3, 1 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 0, dst, 1, dst, 2, dst, 3 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src0, 2, src1, 2, src2, 2, src3, 2 );
-   STORE_DEST( D0, D1, D2, D3, dst, 4, dst, 5, dst, 6, dst, 7 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src0, 2, src1, 2, src2, 2, src3, 2 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 4, dst, 5, dst, 6, dst, 7 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src0, 3, src1, 3, src2, 3, src3, 3 );
-   STORE_DEST( D0, D1, D2, D3, dst, 8, dst, 9, dst, 10, dst, 11 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src0, 3, src1, 3, src2, 3, src3, 3 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 8, dst, 9, dst, 10, dst, 11 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst, 12, dst, 13, dst, 14, dst, 15 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 12, dst, 13, dst, 14, dst, 15 );
 }
 
 static inline void dintrlv_4x32( void *dst0, void *dst1, void *dst2,
@@ -180,39 +179,39 @@ static inline void dintrlv_4x32( void *dst0, void *dst1, void *dst2,
 {
    v128_t D0, D1, D2, D3, S0, S1, S2, S3;
 
-   LOAD_SRCE( S0, S1, S2, S3, src, 0, src, 1, src, 2, src, 3 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 0, src, 1, src, 2, src, 3 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 4, src, 5, src, 6, src, 7 );
-   STORE_DEST( D0, D1, D2, D3, dst0, 0, dst1, 0, dst2, 0, dst3, 0 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 4, src, 5, src, 6, src, 7 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst0, 0, dst1, 0, dst2, 0, dst3, 0 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst0, 1, dst1, 1, dst2, 1, dst3, 1 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst0, 1, dst1, 1, dst2, 1, dst3, 1 );
 
    if ( bit_len <= 256 ) return;
 
-   LOAD_SRCE( S0, S1, S2, S3, src, 8, src, 9, src, 10, src, 11 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 8, src, 9, src, 10, src, 11 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 12, src, 13, src, 14, src, 15 );
-   STORE_DEST( D0, D1, D2, D3, dst0, 2, dst1, 2, dst2, 2, dst3, 2 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 12, src, 13, src, 14, src, 15 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst0, 2, dst1, 2, dst2, 2, dst3, 2 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst0, 3, dst1, 3, dst2, 3, dst3, 3 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst0, 3, dst1, 3, dst2, 3, dst3, 3 );
 
    if ( bit_len <= 512 ) return;
 
-   LOAD_SRCE( S0, S1, S2, S3, src, 16, src, 17, src, 18, src, 19 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 16, src, 17, src, 18, src, 19 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst0, 4, dst1, 4, dst2, 4, dst3, 4 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst0, 4, dst1, 4, dst2, 4, dst3, 4 );
 
    if ( bit_len <= 640 ) return;
 
-   LOAD_SRCE( S0, S1, S2, S3, src, 20, src, 21, src, 22, src, 23 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 20, src, 21, src, 22, src, 23 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 24, src, 25, src, 26, src, 27 );
-   STORE_DEST( D0, D1, D2, D3, dst0, 5, dst1, 5, dst2, 5, dst3, 5 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 24, src, 25, src, 26, src, 27 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst0, 5, dst1, 5, dst2, 5, dst3, 5 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 28, src, 29, src, 30, src, 31 );
-   STORE_DEST( D0, D1, D2, D3, dst0, 6, dst1, 6, dst2, 6, dst3, 6 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 28, src, 29, src, 30, src, 31 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst0, 6, dst1, 6, dst2, 6, dst3, 6 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst0, 7, dst1, 7, dst2, 7, dst3, 7 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst0, 7, dst1, 7, dst2, 7, dst3, 7 );
 
 // if ( bit_len <= 1024 ) return;
 }
@@ -222,21 +221,21 @@ static inline void dintrlv_4x32_512( void *dst0, void *dst1, void *dst2,
 {
    v128_t D0, D1, D2, D3, S0, S1, S2, S3;
 
-   LOAD_SRCE( S0, S1, S2, S3, src, 0, src, 1, src, 2, src, 3 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 0, src, 1, src, 2, src, 3 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 4, src, 5, src, 6, src, 7 );
-   STORE_DEST( D0, D1, D2, D3, dst0, 0, dst1, 0, dst2, 0, dst3, 0 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 4, src, 5, src, 6, src, 7 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst0, 0, dst1, 0, dst2, 0, dst3, 0 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 8, src, 9, src, 10, src, 11 );
-   STORE_DEST( D0, D1, D2, D3, dst0, 1, dst1, 1, dst2, 1, dst3, 1 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 8, src, 9, src, 10, src, 11 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst0, 1, dst1, 1, dst2, 1, dst3, 1 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 12, src, 13, src, 14, src, 15 );
-   STORE_DEST( D0, D1, D2, D3, dst0, 2, dst1, 2, dst2, 2, dst3, 2 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 12, src, 13, src, 14, src, 15 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst0, 2, dst1, 2, dst2, 2, dst3, 2 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst0, 3, dst1, 3, dst2, 3, dst3, 3 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst0, 3, dst1, 3, dst2, 3, dst3, 3 );
 }
 
-#else  // SSE2
+#else  // !SSE2 && !NEON
 
 static inline void intrlv_4x32( void *dst, const void *src0, const void *src1,
                       const void *src2, const void *src3, const int bit_len )
@@ -381,7 +380,7 @@ static inline void dintrlv_4x32_512( void *dst0, void *dst1, void *dst2,
    d0[15] = s[ 60];   d1[15] = s[ 61];    d2[15] = s[ 62];   d3[15] = s[ 63];
 }
 
-#endif   // SSE4_1 or NEON else SSE2
+#endif   // SSE2 or NEON else
 
 static inline void extr_lane_4x32( void *d, const void *s,
                                    const int lane, const int bit_len )
@@ -410,7 +409,7 @@ static inline void extr_lane_4x32( void *d, const void *s,
 static inline void v128_bswap32_80( void *d, void *s )
 {
   const v128_t bswap_shuf = _mm_set_epi64x( 0x0c0d0e0f08090a0b,
-                                             0x0405060700010203 );
+                                            0x0405060700010203 );
   casti_v128( d, 0 ) = _mm_shuffle_epi8( casti_v128( s, 0 ), bswap_shuf );
   casti_v128( d, 1 ) = _mm_shuffle_epi8( casti_v128( s, 1 ), bswap_shuf );
   casti_v128( d, 2 ) = _mm_shuffle_epi8( casti_v128( s, 2 ), bswap_shuf );
@@ -560,6 +559,132 @@ static inline void v128_bswap32_intrlv80_4x32( void *d, const void *src )
 
 // 8x32
 
+
+#if defined(__AVX2__)
+
+#define ILEAVE_8x32( D0, D1, D2, D3, D4, D5, D6, D7, \
+                     S0, S1, S2, S3, S4, S5, S6, S7 ) \
+{ \
+   D0 = _mm256_unpacklo_epi32( S0, S1 ); \
+   D1 = _mm256_unpackhi_epi32( S0, S1 ); \
+   D2 = _mm256_unpacklo_epi32( S2, S3 ); \
+   D3 = _mm256_unpackhi_epi32( S2, S3 ); \
+   D4 = _mm256_unpacklo_epi32( S4, S5 ); \
+   D5 = _mm256_unpackhi_epi32( S4, S5 ); \
+   D6 = _mm256_unpacklo_epi32( S6, S7 ); \
+   D7 = _mm256_unpackhi_epi32( S6, S7 ); \
+\
+   S0 = _mm256_unpacklo_epi64( D0, D2 ); \
+   S1 = _mm256_unpackhi_epi64( D0, D2 ); \
+   S2 = _mm256_unpacklo_epi64( D1, D3 ); \
+   S3 = _mm256_unpackhi_epi64( D1, D3 ); \
+   S4 = _mm256_unpacklo_epi64( D4, D6 ); \
+   S5 = _mm256_unpackhi_epi64( D4, D6 ); \
+   S6 = _mm256_unpacklo_epi64( D5, D7 ); \
+   S7 = _mm256_unpackhi_epi64( D5, D7 ); \
+\
+   D0 = v256_unpacklo128( S0, S4 ); \
+   D1 = v256_unpackhi128( S0, S4 ); \
+   D2 = v256_unpacklo128( S1, S5 ); \
+   D3 = v256_unpackhi128( S1, S5 ); \
+   D4 = v256_unpacklo128( S2, S6 ); \
+   D5 = v256_unpackhi128( S2, S6 ); \
+   D6 = v256_unpacklo128( S3, S7 ); \
+   D7 = v256_unpackhi128( S3, S7 ); \
+}
+
+#define LOAD_SRCE_8x32( S0, S1, S2, S3, S4, S5, S6, S7, \
+                        src0, i0, src1, i1, src2, i2, src3, i3, \
+                        src4, i4, src5, i5, src6, i6, src7, i7 ) \
+   S0 = _mm256_load_si256( (const __m256i*)(src0) + (i0) ); \
+   S1 = _mm256_load_si256( (const __m256i*)(src1) + (i1) ); \
+   S2 = _mm256_load_si256( (const __m256i*)(src2) + (i2) ); \
+   S3 = _mm256_load_si256( (const __m256i*)(src3) + (i3) ); \
+   S4 = _mm256_load_si256( (const __m256i*)(src4) + (i4) ); \
+   S5 = _mm256_load_si256( (const __m256i*)(src5) + (i5) ); \
+   S6 = _mm256_load_si256( (const __m256i*)(src6) + (i6) ); \
+   S7 = _mm256_load_si256( (const __m256i*)(src7) + (i7) );
+   
+#define STOR_DEST_8x32( D0, D1, D2, D3, D4, D5, D6, D7, \
+                        dst0, i0, dst1, i1, dst2, i2, dst3, i3, \
+                        dst4, i4, dst5, i5, dst6, i6, dst7, i7 ) \
+   _mm256_store_si256( (__m256i*)(dst0) + (i0), D0 ); \
+   _mm256_store_si256( (__m256i*)(dst1) + (i1), D1 ); \
+   _mm256_store_si256( (__m256i*)(dst2) + (i2), D2 ); \
+   _mm256_store_si256( (__m256i*)(dst3) + (i3), D3 ); \
+   _mm256_store_si256( (__m256i*)(dst4) + (i4), D4 ); \
+   _mm256_store_si256( (__m256i*)(dst5) + (i5), D5 ); \
+   _mm256_store_si256( (__m256i*)(dst6) + (i6), D6 ); \
+   _mm256_store_si256( (__m256i*)(dst7) + (i7), D7 ); 
+
+static inline void intrlv_8x32_256( void *dst, const void *s0, const void *s1,
+           const void *s2, const void *s3, const void *s4, const void *s5,
+           const void *s6, const void *s7 )
+{
+  __m256i D0, D1, D2, D3, D4, D5, D6, D7,
+          S0, S1, S2, S3, S4, S5, S6, S7;
+
+  LOAD_SRCE_8x32( S0, S1, S2, S3, S4, S5, S6, S7,
+                  s0, 0, s1, 0, s2, 0, s3, 0, s4, 0, s5, 0, s6, 0, s7, 0 );
+  ILEAVE_8x32( D0, D1, D2, D3, D4, D5, D6, D7, S0, S1, S2, S3, S4, S5, S6, S7 );
+  STOR_DEST_8x32( D0, D1, D2, D3, D4, D5, D6, D7,
+              dst, 0, dst, 4, dst, 1, dst, 5, dst, 2, dst, 6, dst, 3, dst, 7 );
+}
+
+static inline void intrlv_8x32_512( void *dst, const void *s0, const void *s1,
+           const void *s2, const void *s3, const void *s4, const void *s5,
+           const void *s6, const void *s7 )
+{
+  __m256i D0, D1, D2, D3, D4, D5, D6, D7,
+          S0, S1, S2, S3, S4, S5, S6, S7;
+
+  LOAD_SRCE_8x32( S0, S1, S2, S3, S4, S5, S6, S7, 
+                  s0, 0, s1, 0, s2, 0, s3, 0, s4, 0, s5, 0, s6, 0, s7, 0 );
+  ILEAVE_8x32( D0, D1, D2, D3, D4, D5, D6, D7, S0, S1, S2, S3, S4, S5, S6, S7 );
+  LOAD_SRCE_8x32( S0, S1, S2, S3, S4, S5, S6, S7,
+                  s0, 1, s1, 1, s2, 1, s3, 1, s4, 1, s5, 1, s6, 1, s7, 1 );
+  STOR_DEST_8x32( D0, D1, D2, D3, D4, D5, D6, D7, 
+              dst, 0, dst, 4, dst, 1, dst, 5, dst, 2, dst, 6, dst, 3, dst, 7 );
+  ILEAVE_8x32( D0, D1, D2, D3, D4, D5, D6, D7, S0, S1, S2, S3, S4, S5, S6, S7 );
+  STOR_DEST_8x32( D0, D1, D2, D3, D4, D5, D6, D7,
+              dst, 8, dst,12, dst, 9, dst,13, dst,10, dst,14, dst,11, dst,15 );
+}
+
+static inline void dintrlv_8x32_256( void *dst0, void *dst1, void *dst2,
+             void *dst3, void *dst4, void *dst5, void *dst6, void *dst7,
+             const void *src )
+{
+   __m256i D0, D1, D2, D3, D4, D5, D6, D7,
+           S0, S1, S2, S3, S4, S5, S6, S7;
+
+  LOAD_SRCE_8x32( S0, S1, S2, S3, S4, S5, S6, S7,
+              src, 0, src, 1, src, 2, src, 3, src, 4, src, 5, src, 6, src, 7 );
+  ILEAVE_8x32( D0, D1, D2, D3, D4, D5, D6, D7, S0, S1, S2, S3, S4, S5, S6, S7 );
+  STOR_DEST_8x32( D0, D1, D2, D3, D4, D5, D6, D7,
+              dst0,0, dst4,0, dst1,0, dst5,0, dst2,0, dst6,0, dst3,0, dst7,0 );
+}
+
+static inline void dintrlv_8x32_512( void *dst0, void *dst1, void *dst2,
+             void *dst3, void *dst4, void *dst5, void *dst6, void *dst7,
+             const void *src )
+{
+   __m256i D0, D1, D2, D3, D4, D5, D6, D7,
+           S0, S1, S2, S3, S4, S5, S6, S7;
+
+  LOAD_SRCE_8x32( S0, S1, S2, S3, S4, S5, S6, S7,
+              src, 0, src, 1, src, 2, src, 3, src, 4, src, 5, src, 6, src, 7 );
+  ILEAVE_8x32( D0, D1, D2, D3, D4, D5, D6, D7, S0, S1, S2, S3, S4, S5, S6, S7 );
+  LOAD_SRCE_8x32( S0, S1, S2, S3, S4, S5, S6, S7,
+              src, 8, src, 9, src,10, src,11, src,12, src,13, src,14, src,15 );
+  STOR_DEST_8x32( D0, D1, D2, D3, D4, D5, D6, D7,
+              dst0,0, dst4,0, dst1,0, dst5,0, dst2,0, dst6,0, dst3,0, dst7,0 );
+  ILEAVE_8x32( D0, D1, D2, D3, D4, D5, D6, D7, S0, S1, S2, S3, S4, S5, S6, S7 );
+  STOR_DEST_8x32( D0, D1, D2, D3, D4, D5, D6, D7,
+              dst0,1, dst4,1, dst1,1, dst5,1, dst2,1, dst6,1, dst3,1, dst7,1 );
+}
+
+#endif
+
 #if defined(__SSE4_1__)
 
 static inline void intrlv_8x32( void *dst, const void *s0, const void *s1,
@@ -568,98 +693,99 @@ static inline void intrlv_8x32( void *dst, const void *s0, const void *s1,
 {
    v128_t D0, D1, D2, D3, S0, S1, S2, S3;
 
-   LOAD_SRCE( S0, S1, S2, S3, s0, 0, s1, 0, s2, 0, s3, 0 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s0, 0, s1, 0, s2, 0, s3, 0 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s4, 0, s5, 0, s6, 0, s7, 0 );
-   STORE_DEST( D0, D1, D2, D3, dst,  0, dst,  2, dst,  4, dst,  6 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s4, 0, s5, 0, s6, 0, s7, 0 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  0, dst,  2, dst,  4, dst,  6 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s0, 1, s1, 1, s2, 1, s3, 1 );
-   STORE_DEST( D0, D1, D2, D3, dst,  1, dst,  3, dst,  5, dst,  7 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s0, 1, s1, 1, s2, 1, s3, 1 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  1, dst,  3, dst,  5, dst,  7 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s4, 1, s5, 1, s6, 1, s7, 1 );
-   STORE_DEST( D0, D1, D2, D3, dst,  8, dst, 10, dst, 12, dst, 14 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s4, 1, s5, 1, s6, 1, s7, 1 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  8, dst, 10, dst, 12, dst, 14 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst,  9, dst, 11, dst, 13, dst, 15 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  9, dst, 11, dst, 13, dst, 15 );
 
    if ( bit_len <= 256 ) return;
 
-   LOAD_SRCE( S0, S1, S2, S3, s0, 2, s1, 2, s2, 2, s3, 2 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s0, 2, s1, 2, s2, 2, s3, 2 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s4, 2, s5, 2, s6, 2, s7, 2 );
-   STORE_DEST( D0, D1, D2, D3, dst, 16, dst, 18, dst, 20, dst, 22 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s4, 2, s5, 2, s6, 2, s7, 2 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 16, dst, 18, dst, 20, dst, 22 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s0, 3, s1, 3, s2, 3, s3, 3 );
-   STORE_DEST( D0, D1, D2, D3, dst, 17, dst, 19, dst, 21, dst, 23 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s0, 3, s1, 3, s2, 3, s3, 3 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 17, dst, 19, dst, 21, dst, 23 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s4, 3, s5, 3, s6, 3, s7, 3 );
-   STORE_DEST( D0, D1, D2, D3, dst, 24, dst, 26, dst, 28, dst, 30 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s4, 3, s5, 3, s6, 3, s7, 3 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 24, dst, 26, dst, 28, dst, 30 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst, 25, dst, 27, dst, 29, dst, 31 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 25, dst, 27, dst, 29, dst, 31 );
 
    if ( bit_len <= 512 ) return;
 
-   LOAD_SRCE( S0, S1, S2, S3, s0, 4, s1, 4, s2, 4, s3, 4 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s0, 4, s1, 4, s2, 4, s3, 4 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s4, 4, s5, 4, s6, 4, s7, 4 );
-   STORE_DEST( D0, D1, D2, D3, dst, 32, dst, 34, dst, 36, dst, 38 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s4, 4, s5, 4, s6, 4, s7, 4 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 32, dst, 34, dst, 36, dst, 38 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst, 33, dst, 35, dst, 37, dst, 39 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 33, dst, 35, dst, 37, dst, 39 );
 
    if ( bit_len <= 640 ) return;
 
-   LOAD_SRCE( S0, S1, S2, S3, s0, 5, s1, 5, s2, 5, s3, 5 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s0, 5, s1, 5, s2, 5, s3, 5 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s4, 5, s5, 5, s6, 5, s7, 5 );
-   STORE_DEST( D0, D1, D2, D3, dst, 40, dst, 42, dst, 44, dst, 46 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s4, 5, s5, 5, s6, 5, s7, 5 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 40, dst, 42, dst, 44, dst, 46 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s0, 6, s1, 6, s2, 6, s3, 6 );
-   STORE_DEST( D0, D1, D2, D3, dst, 41, dst, 43, dst, 45, dst, 47 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s0, 6, s1, 6, s2, 6, s3, 6 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 41, dst, 43, dst, 45, dst, 47 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s4, 6, s5, 6, s6, 6, s7, 6 );
-   STORE_DEST( D0, D1, D2, D3, dst, 48, dst, 50, dst, 52, dst, 54 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s4, 6, s5, 6, s6, 6, s7, 6 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 48, dst, 50, dst, 52, dst, 54 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s0, 7, s1, 7, s2, 7, s3, 7 );
-   STORE_DEST( D0, D1, D2, D3, dst, 49, dst, 51, dst, 53, dst, 55 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s0, 7, s1, 7, s2, 7, s3, 7 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 49, dst, 51, dst, 53, dst, 55 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s4, 7, s5, 7, s6, 7, s7, 7 );
-   STORE_DEST( D0, D1, D2, D3, dst, 56, dst, 58, dst, 60, dst, 62 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s4, 7, s5, 7, s6, 7, s7, 7 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 56, dst, 58, dst, 60, dst, 62 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst, 57, dst, 59, dst, 61, dst, 63 );
-
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 57, dst, 59, dst, 61, dst, 63 );
 // if ( bit_len <= 1024 ) return;
 }
 
+/*
 static inline void intrlv_8x32_512( void *dst, const void *s0, const void *s1,
                const void *s2, const void *s3, const void *s4, const void *s5,
                const void *s6, const void *s7 )
 {
    v128_t D0, D1, D2, D3, S0, S1, S2, S3;
 
-   LOAD_SRCE( S0, S1, S2, S3, s0, 0, s1, 0, s2, 0, s3, 0 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s0, 0, s1, 0, s2, 0, s3, 0 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s4, 0, s5, 0, s6, 0, s7, 0 );
-   STORE_DEST( D0, D1, D2, D3, dst,  0, dst,  2, dst,  4, dst,  6 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s4, 0, s5, 0, s6, 0, s7, 0 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  0, dst,  2, dst,  4, dst,  6 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s0, 1, s1, 1, s2, 1, s3, 1 );
-   STORE_DEST( D0, D1, D2, D3, dst,  1, dst,  3, dst,  5, dst,  7 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s0, 1, s1, 1, s2, 1, s3, 1 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  1, dst,  3, dst,  5, dst,  7 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s4, 1, s5, 1, s6, 1, s7, 1 );
-   STORE_DEST( D0, D1, D2, D3, dst,  8, dst, 10, dst, 12, dst, 14 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s4, 1, s5, 1, s6, 1, s7, 1 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  8, dst, 10, dst, 12, dst, 14 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s0, 2, s1, 2, s2, 2, s3, 2 );
-   STORE_DEST( D0, D1, D2, D3, dst,  9, dst, 11, dst, 13, dst, 15 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s0, 2, s1, 2, s2, 2, s3, 2 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  9, dst, 11, dst, 13, dst, 15 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s4, 2, s5, 2, s6, 2, s7, 2 );
-   STORE_DEST( D0, D1, D2, D3, dst, 16, dst, 18, dst, 20, dst, 22 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s4, 2, s5, 2, s6, 2, s7, 2 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 16, dst, 18, dst, 20, dst, 22 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s0, 3, s1, 3, s2, 3, s3, 3 );
-   STORE_DEST( D0, D1, D2, D3, dst, 17, dst, 19, dst, 21, dst, 23 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s0, 3, s1, 3, s2, 3, s3, 3 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 17, dst, 19, dst, 21, dst, 23 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s4, 3, s5, 3, s6, 3, s7, 3 );
-   STORE_DEST( D0, D1, D2, D3, dst, 24, dst, 26, dst, 28, dst, 30 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s4, 3, s5, 3, s6, 3, s7, 3 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 24, dst, 26, dst, 28, dst, 30 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst, 25, dst, 27, dst, 29, dst, 31 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 25, dst, 27, dst, 29, dst, 31 );
 }
+*/
 
 static inline void dintrlv_8x32( void *dst0, void *dst1, void *dst2, void *dst3,
              void *dst4, void *dst5, void *dst6, void *dst7, const void *src,
@@ -667,98 +793,99 @@ static inline void dintrlv_8x32( void *dst0, void *dst1, void *dst2, void *dst3,
 {
    v128_t D0, D1, D2, D3, S0, S1, S2, S3;
 
-   LOAD_SRCE( S0, S1, S2, S3, src,  0, src,  2, src,  4, src,  6 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  0, src,  2, src,  4, src,  6 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src,  1, src,  3, src,  5, src,  7 );
-   STORE_DEST( D0, D1, D2, D3, dst0, 0, dst1, 0, dst2, 0, dst3, 0 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  1, src,  3, src,  5, src,  7 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst0, 0, dst1, 0, dst2, 0, dst3, 0 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src,  8, src, 10, src, 12, src, 14 );
-   STORE_DEST( D0, D1, D2, D3, dst4, 0, dst5, 0, dst6, 0, dst7, 0 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  8, src, 10, src, 12, src, 14 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst4, 0, dst5, 0, dst6, 0, dst7, 0 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src,  9, src, 11, src, 13, src, 15 );
-   STORE_DEST( D0, D1, D2, D3, dst0, 1, dst1, 1, dst2, 1, dst3, 1 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  9, src, 11, src, 13, src, 15 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst0, 1, dst1, 1, dst2, 1, dst3, 1 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst4, 1, dst5, 1, dst6, 1, dst7, 1 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst4, 1, dst5, 1, dst6, 1, dst7, 1 );
 
    if ( bit_len <= 256 ) return;
 
-   LOAD_SRCE( S0, S1, S2, S3, src, 16, src, 18, src, 20, src, 22 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 16, src, 18, src, 20, src, 22 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 17, src, 19, src, 21, src, 23 );
-   STORE_DEST( D0, D1, D2, D3, dst0, 2, dst1, 2, dst2, 2, dst3, 2 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 17, src, 19, src, 21, src, 23 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst0, 2, dst1, 2, dst2, 2, dst3, 2 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 24, src, 26, src, 28, src, 30 );
-   STORE_DEST( D0, D1, D2, D3, dst4, 2, dst5, 2, dst6, 2, dst7, 2 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 24, src, 26, src, 28, src, 30 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst4, 2, dst5, 2, dst6, 2, dst7, 2 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 25, src, 27, src, 29, src, 31 );
-   STORE_DEST( D0, D1, D2, D3, dst0, 3, dst1, 3, dst2, 3, dst3, 3 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 25, src, 27, src, 29, src, 31 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst0, 3, dst1, 3, dst2, 3, dst3, 3 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst4, 3, dst5, 3, dst6, 3, dst7, 3 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst4, 3, dst5, 3, dst6, 3, dst7, 3 );
 
    if ( bit_len <= 512 ) return;
 
-   LOAD_SRCE( S0, S1, S2, S3, src, 32, src, 34, src, 36, src, 38 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 32, src, 34, src, 36, src, 38 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 33, src, 35, src, 37, src, 39 );
-   STORE_DEST( D0, D1, D2, D3, dst0, 4, dst1, 4, dst2, 4, dst3, 4 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 33, src, 35, src, 37, src, 39 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst0, 4, dst1, 4, dst2, 4, dst3, 4 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst4, 4, dst5, 4, dst6, 4, dst7, 4 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst4, 4, dst5, 4, dst6, 4, dst7, 4 );
 
    if ( bit_len <= 640 ) return;
 
-   LOAD_SRCE( S0, S1, S2, S3, src, 40, src, 42, src, 44, src, 46 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 40, src, 42, src, 44, src, 46 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 41, src, 43, src, 45, src, 47 );
-   STORE_DEST( D0, D1, D2, D3, dst0, 5, dst1, 5, dst2, 5, dst3, 5 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 41, src, 43, src, 45, src, 47 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst0, 5, dst1, 5, dst2, 5, dst3, 5 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 48, src, 50, src, 52, src, 54 );
-   STORE_DEST( D0, D1, D2, D3, dst4, 5, dst5, 5, dst6, 5, dst7, 5 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 48, src, 50, src, 52, src, 54 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst4, 5, dst5, 5, dst6, 5, dst7, 5 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 49, src, 51, src, 53, src, 55 );
-   STORE_DEST( D0, D1, D2, D3, dst0, 6, dst1, 6, dst2, 6, dst3, 6 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 49, src, 51, src, 53, src, 55 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst0, 6, dst1, 6, dst2, 6, dst3, 6 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 56, src, 58, src, 60, src, 62 );
-   STORE_DEST( D0, D1, D2, D3, dst4, 6, dst5, 6, dst6, 6, dst7, 6 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 56, src, 58, src, 60, src, 62 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst4, 6, dst5, 6, dst6, 6, dst7, 6 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 57, src, 59, src, 61, src, 63 );
-   STORE_DEST( D0, D1, D2, D3, dst0, 7, dst1, 7, dst2, 7, dst3, 7 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 57, src, 59, src, 61, src, 63 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst0, 7, dst1, 7, dst2, 7, dst3, 7 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst4, 7, dst5, 7, dst6, 7, dst7, 7 );
-
+   STOR_DEST_4x32( D0, D1, D2, D3, dst4, 7, dst5, 7, dst6, 7, dst7, 7 );
 // if ( bit_len <= 1024 ) return;
 }
 
+/*
 static inline void dintrlv_8x32_512( void *dst0, void *dst1, void *dst2,
              void *dst3, void *dst4, void *dst5, void *dst6, void *dst7,
              const void *src )
 {
    v128_t D0, D1, D2, D3, S0, S1, S2, S3;
 
-   LOAD_SRCE( S0, S1, S2, S3, src,  0, src,  2, src,  4, src,  6 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  0, src,  2, src,  4, src,  6 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src,  1, src,  3, src,  5, src,  7 );
-   STORE_DEST( D0, D1, D2, D3, dst0, 0, dst1, 0, dst2, 0, dst3, 0 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  1, src,  3, src,  5, src,  7 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst0, 0, dst1, 0, dst2, 0, dst3, 0 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src,  8, src, 10, src, 12, src, 14 );
-   STORE_DEST( D0, D1, D2, D3, dst4, 0, dst5, 0, dst6, 0, dst7, 0 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  8, src, 10, src, 12, src, 14 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst4, 0, dst5, 0, dst6, 0, dst7, 0 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src,  9, src, 11, src, 13, src, 15 );
-   STORE_DEST( D0, D1, D2, D3, dst0, 1, dst1, 1, dst2, 1, dst3, 1 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  9, src, 11, src, 13, src, 15 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst0, 1, dst1, 1, dst2, 1, dst3, 1 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 16, src, 18, src, 20, src, 22 );
-   STORE_DEST( D0, D1, D2, D3, dst4, 1, dst5, 1, dst6, 1, dst7, 1 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 16, src, 18, src, 20, src, 22 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst4, 1, dst5, 1, dst6, 1, dst7, 1 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 17, src, 19, src, 21, src, 23 );
-   STORE_DEST( D0, D1, D2, D3, dst0, 2, dst1, 2, dst2, 2, dst3, 2 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 17, src, 19, src, 21, src, 23 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst0, 2, dst1, 2, dst2, 2, dst3, 2 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 24, src, 26, src, 28, src, 30 );
-   STORE_DEST( D0, D1, D2, D3, dst4, 2, dst5, 2, dst6, 2, dst7, 2 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 24, src, 26, src, 28, src, 30 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst4, 2, dst5, 2, dst6, 2, dst7, 2 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 25, src, 27, src, 29, src, 31 );
-   STORE_DEST( D0, D1, D2, D3, dst0, 3, dst1, 3, dst2, 3, dst3, 3 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 25, src, 27, src, 29, src, 31 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst0, 3, dst1, 3, dst2, 3, dst3, 3 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst4, 3, dst5, 3, dst6, 3, dst7, 3 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst4, 3, dst5, 3, dst6, 3, dst7, 3 );
 }
+*/
 
 #endif  // SSE4_1
 
@@ -923,111 +1050,111 @@ static inline void intrlv_16x32( void *dst, const void *s00,
 {
    v128_t D0, D1, D2, D3, S0, S1, S2, S3;
 
-   LOAD_SRCE( S0, S1, S2, S3, s00, 0, s01, 0, s02, 0, s03, 0 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s00, 0, s01, 0, s02, 0, s03, 0 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s04, 0, s05, 0, s06, 0, s07, 0 );
-   STORE_DEST( D0, D1, D2, D3, dst,   0, dst,   4, dst,   8, dst,  12 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s04, 0, s05, 0, s06, 0, s07, 0 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,   0, dst,   4, dst,   8, dst,  12 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s08, 0, s09, 0, s10, 0, s11, 0 );
-   STORE_DEST( D0, D1, D2, D3, dst,   1, dst,   5, dst,   9, dst,  13 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s08, 0, s09, 0, s10, 0, s11, 0 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,   1, dst,   5, dst,   9, dst,  13 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s12, 0, s13, 0, s14, 0, s15, 0 );
-   STORE_DEST( D0, D1, D2, D3, dst,   2, dst,   6, dst,  10, dst,  14 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s12, 0, s13, 0, s14, 0, s15, 0 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,   2, dst,   6, dst,  10, dst,  14 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s00, 1, s01, 1, s02, 1, s03, 1 );
-   STORE_DEST( D0, D1, D2, D3, dst,   3, dst,   7, dst,  11, dst,  15 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s00, 1, s01, 1, s02, 1, s03, 1 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,   3, dst,   7, dst,  11, dst,  15 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s04, 1, s05, 1, s06, 1, s07, 1 );
-   STORE_DEST( D0, D1, D2, D3, dst,  16, dst,  20, dst,  24, dst,  28 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s04, 1, s05, 1, s06, 1, s07, 1 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  16, dst,  20, dst,  24, dst,  28 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s08, 1, s09, 1, s10, 1, s11, 1 );
-   STORE_DEST( D0, D1, D2, D3, dst,  17, dst,  21, dst,  25, dst,  29 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s08, 1, s09, 1, s10, 1, s11, 1 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  17, dst,  21, dst,  25, dst,  29 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s12, 1, s13, 1, s14, 1, s15, 1 );
-   STORE_DEST( D0, D1, D2, D3, dst,  18, dst,  22, dst,  26, dst,  30 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s12, 1, s13, 1, s14, 1, s15, 1 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  18, dst,  22, dst,  26, dst,  30 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst,  19, dst,  23, dst,  27, dst,  31 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  19, dst,  23, dst,  27, dst,  31 );
 
    if ( bit_len <= 256 ) return;
 
-   LOAD_SRCE( S0, S1, S2, S3, s00, 2, s01, 2, s02, 2, s03, 2 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s00, 2, s01, 2, s02, 2, s03, 2 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s04, 2, s05, 2, s06, 2, s07, 2 );
-   STORE_DEST( D0, D1, D2, D3, dst,  32, dst,  36, dst,  40, dst,  44 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s04, 2, s05, 2, s06, 2, s07, 2 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  32, dst,  36, dst,  40, dst,  44 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s08, 2, s09, 2, s10, 2, s11, 2 );
-   STORE_DEST( D0, D1, D2, D3, dst,  33, dst,  37, dst,  41, dst,  45 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s08, 2, s09, 2, s10, 2, s11, 2 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  33, dst,  37, dst,  41, dst,  45 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s12, 2, s13, 2, s14, 2, s15, 2 );
-   STORE_DEST( D0, D1, D2, D3, dst,  34, dst,  38, dst,  42, dst,  46 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s12, 2, s13, 2, s14, 2, s15, 2 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  34, dst,  38, dst,  42, dst,  46 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s00, 3, s01, 3, s02, 3, s03, 3 );
-   STORE_DEST( D0, D1, D2, D3, dst,  35, dst,  39, dst,  43, dst,  47 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s00, 3, s01, 3, s02, 3, s03, 3 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  35, dst,  39, dst,  43, dst,  47 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s04, 3, s05, 3, s06, 3, s07, 3 );
-   STORE_DEST( D0, D1, D2, D3, dst,  48, dst,  52, dst,  56, dst,  60 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s04, 3, s05, 3, s06, 3, s07, 3 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  48, dst,  52, dst,  56, dst,  60 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s08, 3, s09, 3, s10, 3, s11, 3 );
-   STORE_DEST( D0, D1, D2, D3, dst,  49, dst,  53, dst,  57, dst,  61 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s08, 3, s09, 3, s10, 3, s11, 3 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  49, dst,  53, dst,  57, dst,  61 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s12, 3, s13, 3, s14, 3, s15, 3 );
-   STORE_DEST( D0, D1, D2, D3, dst,  50, dst,  54, dst,  58, dst,  62 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s12, 3, s13, 3, s14, 3, s15, 3 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  50, dst,  54, dst,  58, dst,  62 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst,  51, dst,  55, dst,  59, dst,  63 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  51, dst,  55, dst,  59, dst,  63 );
    
    if ( bit_len <= 512 ) return;
 
-   LOAD_SRCE( S0, S1, S2, S3, s00, 4, s01, 4, s02, 4, s03, 4 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s00, 4, s01, 4, s02, 4, s03, 4 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s04, 4, s05, 4, s06, 4, s07, 4 );
-   STORE_DEST( D0, D1, D2, D3, dst,  64, dst,  68, dst,  72, dst,  76 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s04, 4, s05, 4, s06, 4, s07, 4 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  64, dst,  68, dst,  72, dst,  76 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s08, 4, s09, 4, s10, 4, s11, 4 );
-   STORE_DEST( D0, D1, D2, D3, dst,  65, dst,  69, dst,  73, dst,  77 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s08, 4, s09, 4, s10, 4, s11, 4 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  65, dst,  69, dst,  73, dst,  77 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s12, 4, s13, 4, s14, 4, s15, 4 );
-   STORE_DEST( D0, D1, D2, D3, dst,  66, dst,  70, dst,  74, dst,  78 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s12, 4, s13, 4, s14, 4, s15, 4 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  66, dst,  70, dst,  74, dst,  78 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst,  67, dst,  71, dst,  75, dst,  79 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  67, dst,  71, dst,  75, dst,  79 );
 
    if ( bit_len <= 640 ) return;
 
-   LOAD_SRCE( S0, S1, S2, S3, s00, 5, s01, 5, s02, 5, s03, 5 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s00, 5, s01, 5, s02, 5, s03, 5 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s04, 5, s05, 5, s06, 5, s07, 5 );
-   STORE_DEST( D0, D1, D2, D3, dst,  80, dst,  84, dst,  88, dst,  92 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s04, 5, s05, 5, s06, 5, s07, 5 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  80, dst,  84, dst,  88, dst,  92 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s08, 5, s09, 5, s10, 5, s11, 5 );
-   STORE_DEST( D0, D1, D2, D3, dst,  81, dst,  85, dst,  89, dst,  93 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s08, 5, s09, 5, s10, 5, s11, 5 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  81, dst,  85, dst,  89, dst,  93 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s12, 5, s13, 5, s14, 5, s15, 5 );
-   STORE_DEST( D0, D1, D2, D3, dst,  82, dst,  86, dst,  90, dst,  94 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s12, 5, s13, 5, s14, 5, s15, 5 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  82, dst,  86, dst,  90, dst,  94 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s00, 6, s01, 6, s02, 6, s03, 6 );
-   STORE_DEST( D0, D1, D2, D3, dst,  83, dst,  87, dst,  91, dst,  95 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s00, 6, s01, 6, s02, 6, s03, 6 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  83, dst,  87, dst,  91, dst,  95 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s04, 6, s05, 6, s06, 6, s07, 6 );
-   STORE_DEST( D0, D1, D2, D3, dst,  96, dst, 100, dst, 104, dst, 108 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s04, 6, s05, 6, s06, 6, s07, 6 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  96, dst, 100, dst, 104, dst, 108 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s08, 6, s09, 6, s10, 6, s11, 6 );
-   STORE_DEST( D0, D1, D2, D3, dst,  97, dst, 101, dst, 105, dst, 109 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s08, 6, s09, 6, s10, 6, s11, 6 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  97, dst, 101, dst, 105, dst, 109 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s12, 6, s13, 6, s14, 6, s15, 6 );
-   STORE_DEST( D0, D1, D2, D3, dst,  98, dst, 102, dst, 106, dst, 110 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s12, 6, s13, 6, s14, 6, s15, 6 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  98, dst, 102, dst, 106, dst, 110 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s00, 7, s01, 7, s02, 7, s03, 7 );
-   STORE_DEST( D0, D1, D2, D3, dst,  99, dst, 103, dst, 107, dst, 111 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s00, 7, s01, 7, s02, 7, s03, 7 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  99, dst, 103, dst, 107, dst, 111 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s04, 7, s05, 7, s06, 7, s07, 7 );
-   STORE_DEST( D0, D1, D2, D3, dst, 112, dst, 116, dst, 120, dst, 124 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s04, 7, s05, 7, s06, 7, s07, 7 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 112, dst, 116, dst, 120, dst, 124 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s08, 7, s09, 7, s10, 7, s11, 7 );
-   STORE_DEST( D0, D1, D2, D3, dst, 113, dst, 117, dst, 121, dst, 125 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s08, 7, s09, 7, s10, 7, s11, 7 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 113, dst, 117, dst, 121, dst, 125 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s12, 7, s13, 7, s14, 7, s15, 7 );
-   STORE_DEST( D0, D1, D2, D3, dst, 114, dst, 118, dst, 122, dst, 126 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s12, 7, s13, 7, s14, 7, s15, 7 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 114, dst, 118, dst, 122, dst, 126 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst, 115, dst, 119, dst, 123, dst, 127 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst, 115, dst, 119, dst, 123, dst, 127 );
 
 //    if ( bit_len <= 1024 ) return;
 }
@@ -1041,54 +1168,54 @@ static inline void intrlv_16x32_512( void *dst, const void *s00,
 {
    v128_t D0, D1, D2, D3, S0, S1, S2, S3;
 
-   LOAD_SRCE( S0, S1, S2, S3, s00, 0, s01, 0, s02, 0, s03, 0 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s00, 0, s01, 0, s02, 0, s03, 0 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s04, 0, s05, 0, s06, 0, s07, 0 );
-   STORE_DEST( D0, D1, D2, D3, dst,   0, dst,   4, dst,   8, dst,  12 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s04, 0, s05, 0, s06, 0, s07, 0 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,   0, dst,   4, dst,   8, dst,  12 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s08, 0, s09, 0, s10, 0, s11, 0 );
-   STORE_DEST( D0, D1, D2, D3, dst,   1, dst,   5, dst,   9, dst,  13 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s08, 0, s09, 0, s10, 0, s11, 0 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,   1, dst,   5, dst,   9, dst,  13 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s12, 0, s13, 0, s14, 0, s15, 0 );
-   STORE_DEST( D0, D1, D2, D3, dst,   2, dst,   6, dst,  10, dst,  14 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s12, 0, s13, 0, s14, 0, s15, 0 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,   2, dst,   6, dst,  10, dst,  14 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s00, 1, s01, 1, s02, 1, s03, 1 );
-   STORE_DEST( D0, D1, D2, D3, dst,   3, dst,   7, dst,  11, dst,  15 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s00, 1, s01, 1, s02, 1, s03, 1 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,   3, dst,   7, dst,  11, dst,  15 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s04, 1, s05, 1, s06, 1, s07, 1 );
-   STORE_DEST( D0, D1, D2, D3, dst,  16, dst,  20, dst,  24, dst,  28 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s04, 1, s05, 1, s06, 1, s07, 1 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  16, dst,  20, dst,  24, dst,  28 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s08, 1, s09, 1, s10, 1, s11, 1 );
-   STORE_DEST( D0, D1, D2, D3, dst,  17, dst,  21, dst,  25, dst,  29 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s08, 1, s09, 1, s10, 1, s11, 1 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  17, dst,  21, dst,  25, dst,  29 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s12, 1, s13, 1, s14, 1, s15, 1 );
-   STORE_DEST( D0, D1, D2, D3, dst,  18, dst,  22, dst,  26, dst,  30 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s12, 1, s13, 1, s14, 1, s15, 1 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  18, dst,  22, dst,  26, dst,  30 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s00, 2, s01, 2, s02, 2, s03, 2 );
-   STORE_DEST( D0, D1, D2, D3, dst,  19, dst,  23, dst,  27, dst,  31 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s00, 2, s01, 2, s02, 2, s03, 2 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  19, dst,  23, dst,  27, dst,  31 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s04, 2, s05, 2, s06, 2, s07, 2 );
-   STORE_DEST( D0, D1, D2, D3, dst,  32, dst,  36, dst,  40, dst,  44 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s04, 2, s05, 2, s06, 2, s07, 2 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  32, dst,  36, dst,  40, dst,  44 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s08, 2, s09, 2, s10, 2, s11, 2 );
-   STORE_DEST( D0, D1, D2, D3, dst,  33, dst,  37, dst,  41, dst,  45 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s08, 2, s09, 2, s10, 2, s11, 2 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  33, dst,  37, dst,  41, dst,  45 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s12, 2, s13, 2, s14, 2, s15, 2 );
-   STORE_DEST( D0, D1, D2, D3, dst,  34, dst,  38, dst,  42, dst,  46 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s12, 2, s13, 2, s14, 2, s15, 2 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  34, dst,  38, dst,  42, dst,  46 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s00, 3, s01, 3, s02, 3, s03, 3 );
-   STORE_DEST( D0, D1, D2, D3, dst,  35, dst,  39, dst,  43, dst,  47 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s00, 3, s01, 3, s02, 3, s03, 3 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  35, dst,  39, dst,  43, dst,  47 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s04, 3, s05, 3, s06, 3, s07, 3 );
-   STORE_DEST( D0, D1, D2, D3, dst,  48, dst,  52, dst,  56, dst,  60 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s04, 3, s05, 3, s06, 3, s07, 3 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  48, dst,  52, dst,  56, dst,  60 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s08, 3, s09, 3, s10, 3, s11, 3 );
-   STORE_DEST( D0, D1, D2, D3, dst,  49, dst,  53, dst,  57, dst,  61 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s08, 3, s09, 3, s10, 3, s11, 3 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  49, dst,  53, dst,  57, dst,  61 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, s12, 3, s13, 3, s14, 3, s15, 3 );
-   STORE_DEST( D0, D1, D2, D3, dst,  50, dst,  54, dst,  58, dst,  62 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, s12, 3, s13, 3, s14, 3, s15, 3 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  50, dst,  54, dst,  58, dst,  62 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst,  51, dst,  55, dst,  59, dst,  63 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst,  51, dst,  55, dst,  59, dst,  63 );
 }
 
 static inline void dintrlv_16x32( void *dst00, void *dst01, void *dst02,
@@ -1099,111 +1226,111 @@ static inline void dintrlv_16x32( void *dst00, void *dst01, void *dst02,
 {
    v128_t D0, D1, D2, D3, S0, S1, S2, S3;
 
-   LOAD_SRCE( S0, S1, S2, S3, src,  0, src,  4, src,  8, src, 12 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  0, src,  4, src,  8, src, 12 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src,  1, src,  5, src,  9, src, 13 );
-   STORE_DEST( D0, D1, D2, D3, dst00, 0, dst01, 0, dst02, 0, dst03, 0 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  1, src,  5, src,  9, src, 13 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst00, 0, dst01, 0, dst02, 0, dst03, 0 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src,  2, src,  6, src, 10, src, 14 );
-   STORE_DEST( D0, D1, D2, D3, dst04, 0, dst05, 0, dst06, 0, dst07, 0 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  2, src,  6, src, 10, src, 14 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst04, 0, dst05, 0, dst06, 0, dst07, 0 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src,  3, src,  7, src, 11, src, 15 );
-   STORE_DEST( D0, D1, D2, D3, dst08, 0, dst09, 0, dst10, 0, dst11, 0 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  3, src,  7, src, 11, src, 15 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst08, 0, dst09, 0, dst10, 0, dst11, 0 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 16, src, 20, src, 24, src, 28 );
-   STORE_DEST( D0, D1, D2, D3, dst12, 0, dst13, 0, dst14, 0, dst15, 0 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 16, src, 20, src, 24, src, 28 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst12, 0, dst13, 0, dst14, 0, dst15, 0 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 17, src, 21, src, 25, src, 29 );
-   STORE_DEST( D0, D1, D2, D3, dst00, 1, dst01, 1, dst02, 1, dst03, 1 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 17, src, 21, src, 25, src, 29 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst00, 1, dst01, 1, dst02, 1, dst03, 1 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 18, src, 22, src, 26, src, 30 );
-   STORE_DEST( D0, D1, D2, D3, dst04, 1, dst05, 1, dst06, 1, dst07, 1 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 18, src, 22, src, 26, src, 30 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst04, 1, dst05, 1, dst06, 1, dst07, 1 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 19, src, 23, src, 27, src, 31 );
-   STORE_DEST( D0, D1, D2, D3, dst08, 1, dst09, 1, dst10, 1, dst11, 1 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 19, src, 23, src, 27, src, 31 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst08, 1, dst09, 1, dst10, 1, dst11, 1 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst12, 1, dst13, 1, dst14, 1, dst15, 1 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst12, 1, dst13, 1, dst14, 1, dst15, 1 );
 
    if ( bit_len <= 256 ) return;
 
-   LOAD_SRCE( S0, S1, S2, S3, src, 32, src, 36, src, 40, src, 44 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 32, src, 36, src, 40, src, 44 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 33, src, 37, src, 41, src, 45 );
-   STORE_DEST( D0, D1, D2, D3, dst00, 2, dst01, 2, dst02, 2, dst03, 2 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 33, src, 37, src, 41, src, 45 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst00, 2, dst01, 2, dst02, 2, dst03, 2 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 34, src, 38, src, 42, src, 46 );
-   STORE_DEST( D0, D1, D2, D3, dst04, 2, dst05, 2, dst06, 2, dst07, 2 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 34, src, 38, src, 42, src, 46 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst04, 2, dst05, 2, dst06, 2, dst07, 2 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 35, src, 39, src, 43, src, 47 );
-   STORE_DEST( D0, D1, D2, D3, dst08, 2, dst09, 2, dst10, 2, dst11, 2 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 35, src, 39, src, 43, src, 47 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst08, 2, dst09, 2, dst10, 2, dst11, 2 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 48, src, 52, src, 56, src, 60 );
-   STORE_DEST( D0, D1, D2, D3, dst12, 2, dst13, 2, dst14, 2, dst15, 2 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 48, src, 52, src, 56, src, 60 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst12, 2, dst13, 2, dst14, 2, dst15, 2 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 49, src, 53, src, 57, src, 61 );
-   STORE_DEST( D0, D1, D2, D3, dst00, 3, dst01, 3, dst02, 3, dst03, 3 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 49, src, 53, src, 57, src, 61 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst00, 3, dst01, 3, dst02, 3, dst03, 3 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 50, src, 54, src, 58, src, 62 );
-   STORE_DEST( D0, D1, D2, D3, dst04, 3, dst05, 3, dst06, 3, dst07, 3 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 50, src, 54, src, 58, src, 62 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst04, 3, dst05, 3, dst06, 3, dst07, 3 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 51, src, 55, src, 59, src, 63 );
-   STORE_DEST( D0, D1, D2, D3, dst08, 3, dst09, 3, dst10, 3, dst11, 3 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 51, src, 55, src, 59, src, 63 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst08, 3, dst09, 3, dst10, 3, dst11, 3 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst12, 3, dst13, 3, dst14, 3, dst15, 3 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst12, 3, dst13, 3, dst14, 3, dst15, 3 );
 
    if ( bit_len <= 512 ) return;
 
-   LOAD_SRCE( S0, S1, S2, S3, src,  64, src,  68, src,  72, src,  76 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  64, src,  68, src,  72, src,  76 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src,  65, src,  69, src,  73, src,  77 );
-   STORE_DEST( D0, D1, D2, D3, dst00, 4, dst01, 4, dst02, 4, dst03, 4 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  65, src,  69, src,  73, src,  77 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst00, 4, dst01, 4, dst02, 4, dst03, 4 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src,  66, src,  70, src,  74, src,  78 );
-   STORE_DEST( D0, D1, D2, D3, dst04, 4, dst05, 4, dst06, 4, dst07, 4 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  66, src,  70, src,  74, src,  78 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst04, 4, dst05, 4, dst06, 4, dst07, 4 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src,  67, src,  71, src,  75, src,  79 );
-   STORE_DEST( D0, D1, D2, D3, dst08, 4, dst09, 4, dst10, 4, dst11, 4 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  67, src,  71, src,  75, src,  79 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst08, 4, dst09, 4, dst10, 4, dst11, 4 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst12, 4, dst13, 4, dst14, 4, dst15, 4 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst12, 4, dst13, 4, dst14, 4, dst15, 4 );
    
    if ( bit_len <= 640 ) return;
    
-   LOAD_SRCE( S0, S1, S2, S3, src,  80, src,  84, src,  88, src,  92 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  80, src,  84, src,  88, src,  92 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src,  81, src,  85, src,  89, src,  93 );
-   STORE_DEST( D0, D1, D2, D3, dst00, 5, dst01, 5, dst02, 5, dst03, 5 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  81, src,  85, src,  89, src,  93 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst00, 5, dst01, 5, dst02, 5, dst03, 5 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src,  82, src,  86, src,  90, src,  94 );
-   STORE_DEST( D0, D1, D2, D3, dst04, 5, dst05, 5, dst06, 5, dst07, 5 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  82, src,  86, src,  90, src,  94 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst04, 5, dst05, 5, dst06, 5, dst07, 5 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src,  83, src,  87, src,  91, src,  95 );
-   STORE_DEST( D0, D1, D2, D3, dst08, 5, dst09, 5, dst10, 5, dst11, 5 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  83, src,  87, src,  91, src,  95 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst08, 5, dst09, 5, dst10, 5, dst11, 5 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst12, 5, dst13, 5, dst14, 5, dst15, 5 );
-   LOAD_SRCE( S0, S1, S2, S3, src,  96, src, 100, src, 104, src, 108 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst12, 5, dst13, 5, dst14, 5, dst15, 5 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  96, src, 100, src, 104, src, 108 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src,  97, src, 101, src, 105, src, 109 );
-   STORE_DEST( D0, D1, D2, D3, dst00, 6, dst01, 6, dst02, 6, dst03, 6 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  97, src, 101, src, 105, src, 109 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst00, 6, dst01, 6, dst02, 6, dst03, 6 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src,  98, src, 102, src, 106, src, 110 );
-   STORE_DEST( D0, D1, D2, D3, dst04, 6, dst05, 6, dst06, 6, dst07, 6 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  98, src, 102, src, 106, src, 110 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst04, 6, dst05, 6, dst06, 6, dst07, 6 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src,  99, src, 103, src, 107, src, 111 );
-   STORE_DEST( D0, D1, D2, D3, dst08, 6, dst09, 6, dst10, 6, dst11, 6 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  99, src, 103, src, 107, src, 111 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst08, 6, dst09, 6, dst10, 6, dst11, 6 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 112, src, 116, src, 120, src, 124 );
-   STORE_DEST( D0, D1, D2, D3, dst12, 6, dst13, 6, dst14, 6, dst15, 6 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 112, src, 116, src, 120, src, 124 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst12, 6, dst13, 6, dst14, 6, dst15, 6 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 113, src, 117, src, 121, src, 125 );
-   STORE_DEST( D0, D1, D2, D3, dst00, 7, dst01, 7, dst02, 7, dst03, 7 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 113, src, 117, src, 121, src, 125 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst00, 7, dst01, 7, dst02, 7, dst03, 7 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 114, src, 118, src, 122, src, 126 );
-   STORE_DEST( D0, D1, D2, D3, dst04, 7, dst05, 7, dst06, 7, dst07, 7 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 114, src, 118, src, 122, src, 126 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst04, 7, dst05, 7, dst06, 7, dst07, 7 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 115, src, 119, src, 123, src, 127 );
-   STORE_DEST( D0, D1, D2, D3, dst08, 7, dst09, 7, dst10, 7, dst11, 7 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 115, src, 119, src, 123, src, 127 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst08, 7, dst09, 7, dst10, 7, dst11, 7 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst12, 7, dst13, 7, dst14, 7, dst15, 7 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst12, 7, dst13, 7, dst14, 7, dst15, 7 );
 
 // if ( bit_len <= 1024 ) return;
 }
@@ -1216,54 +1343,54 @@ static inline void dintrlv_16x32_512( void *dst00, void *dst01, void *dst02,
 {
    v128_t D0, D1, D2, D3, S0, S1, S2, S3;
 
-   LOAD_SRCE( S0, S1, S2, S3, src,  0, src,  4, src,  8, src, 12 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  0, src,  4, src,  8, src, 12 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src,  1, src,  5, src,  9, src, 13 );
-   STORE_DEST( D0, D1, D2, D3, dst00, 0, dst01, 0, dst02, 0, dst03, 0 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  1, src,  5, src,  9, src, 13 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst00, 0, dst01, 0, dst02, 0, dst03, 0 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src,  2, src,  6, src, 10, src, 14 );
-   STORE_DEST( D0, D1, D2, D3, dst04, 0, dst05, 0, dst06, 0, dst07, 0 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  2, src,  6, src, 10, src, 14 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst04, 0, dst05, 0, dst06, 0, dst07, 0 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src,  3, src,  7, src, 11, src, 15 );
-   STORE_DEST( D0, D1, D2, D3, dst08, 0, dst09, 0, dst10, 0, dst11, 0 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src,  3, src,  7, src, 11, src, 15 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst08, 0, dst09, 0, dst10, 0, dst11, 0 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 16, src, 20, src, 24, src, 28 );
-   STORE_DEST( D0, D1, D2, D3, dst12, 0, dst13, 0, dst14, 0, dst15, 0 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 16, src, 20, src, 24, src, 28 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst12, 0, dst13, 0, dst14, 0, dst15, 0 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 17, src, 21, src, 25, src, 29 );
-   STORE_DEST( D0, D1, D2, D3, dst00, 1, dst01, 1, dst02, 1, dst03, 1 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 17, src, 21, src, 25, src, 29 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst00, 1, dst01, 1, dst02, 1, dst03, 1 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 18, src, 22, src, 26, src, 30 );
-   STORE_DEST( D0, D1, D2, D3, dst04, 1, dst05, 1, dst06, 1, dst07, 1 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 18, src, 22, src, 26, src, 30 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst04, 1, dst05, 1, dst06, 1, dst07, 1 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 19, src, 23, src, 27, src, 31 );
-   STORE_DEST( D0, D1, D2, D3, dst08, 1, dst09, 1, dst10, 1, dst11, 1 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 19, src, 23, src, 27, src, 31 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst08, 1, dst09, 1, dst10, 1, dst11, 1 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 32, src, 36, src, 40, src, 44 );
-   STORE_DEST( D0, D1, D2, D3, dst12, 1, dst13, 1, dst14, 1, dst15, 1 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 32, src, 36, src, 40, src, 44 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst12, 1, dst13, 1, dst14, 1, dst15, 1 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 33, src, 37, src, 41, src, 45 );
-   STORE_DEST( D0, D1, D2, D3, dst00, 2, dst01, 2, dst02, 2, dst03, 2 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 33, src, 37, src, 41, src, 45 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst00, 2, dst01, 2, dst02, 2, dst03, 2 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 34, src, 38, src, 42, src, 46 );
-   STORE_DEST( D0, D1, D2, D3, dst04, 2, dst05, 2, dst06, 2, dst07, 2 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 34, src, 38, src, 42, src, 46 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst04, 2, dst05, 2, dst06, 2, dst07, 2 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 35, src, 39, src, 43, src, 47 );
-   STORE_DEST( D0, D1, D2, D3, dst08, 2, dst09, 2, dst10, 2, dst11, 2 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 35, src, 39, src, 43, src, 47 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst08, 2, dst09, 2, dst10, 2, dst11, 2 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 48, src, 52, src, 56, src, 60 );
-   STORE_DEST( D0, D1, D2, D3, dst12, 2, dst13, 2, dst14, 2, dst15, 2 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 48, src, 52, src, 56, src, 60 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst12, 2, dst13, 2, dst14, 2, dst15, 2 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 49, src, 53, src, 57, src, 61 );
-   STORE_DEST( D0, D1, D2, D3, dst00, 3, dst01, 3, dst02, 3, dst03, 3 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 49, src, 53, src, 57, src, 61 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst00, 3, dst01, 3, dst02, 3, dst03, 3 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 50, src, 54, src, 58, src, 62 );
-   STORE_DEST( D0, D1, D2, D3, dst04, 3, dst05, 3, dst06, 3, dst07, 3 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 50, src, 54, src, 58, src, 62 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst04, 3, dst05, 3, dst06, 3, dst07, 3 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   LOAD_SRCE( S0, S1, S2, S3, src, 51, src, 55, src, 59, src, 63 );
-   STORE_DEST( D0, D1, D2, D3, dst08, 3, dst09, 3, dst10, 3, dst11, 3 );
+   LOAD_SRCE_4x32( S0, S1, S2, S3, src, 51, src, 55, src, 59, src, 63 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst08, 3, dst09, 3, dst10, 3, dst11, 3 );
    ILEAVE_4x32( D0, D1, D2, D3, S0, S1, S2, S3 );
-   STORE_DEST( D0, D1, D2, D3, dst12, 3, dst13, 3, dst14, 3, dst15, 3 );
+   STOR_DEST_4x32( D0, D1, D2, D3, dst12, 3, dst13, 3, dst14, 3, dst15, 3 );
 }
 
 #endif  // SSE4_1
@@ -1422,6 +1549,63 @@ static inline void mm512_bswap32_intrlv80_16x32( void *d, const void *src )
 
 // 2x64    SSE2, NEON
 
+static inline void intrlv_2x64( void *dst, const void *src0,
+                                const void *src1, const int bit_len )
+{
+   v128u64_t *d = (v128u64_t*)dst;;
+   const v128u64_t *s0 = (const v128u64_t*)src0;
+   const v128u64_t *s1 = (const v128u64_t*)src1;
+
+   d[ 0] = v128_unpacklo64( s0[0], s1[0] );
+   d[ 1] = v128_unpackhi64( s0[0], s1[0] );
+   d[ 2] = v128_unpacklo64( s0[1], s1[1] );
+   d[ 3] = v128_unpackhi64( s0[1], s1[1] );
+   if ( bit_len <= 256 ) return;
+   d[ 4] = v128_unpacklo64( s0[2], s1[2] );
+   d[ 5] = v128_unpackhi64( s0[2], s1[2] );
+   d[ 6] = v128_unpacklo64( s0[3], s1[3] );
+   d[ 7] = v128_unpackhi64( s0[3], s1[3] );
+   if ( bit_len <= 512 ) return;
+   d[ 8] = v128_unpacklo64( s0[4], s1[4] );
+   d[ 9] = v128_unpackhi64( s0[4], s1[4] );
+   if ( bit_len <= 640 ) return;
+   d[10] = v128_unpacklo64( s0[5], s1[5] );
+   d[11] = v128_unpackhi64( s0[5], s1[5] );
+   d[12] = v128_unpacklo64( s0[6], s1[6] );
+   d[13] = v128_unpackhi64( s0[6], s1[6] );
+   d[14] = v128_unpacklo64( s0[7], s1[7] );
+   d[15] = v128_unpackhi64( s0[7], s1[7] );
+}
+
+static inline void dintrlv_2x64( void *dst0, void *dst1,
+                                 const void *src, const int bit_len )
+{
+   v128u64_t *d0 = (v128u64_t*)dst0;
+   v128u64_t *d1 = (v128u64_t*)dst1;
+   const v128u64_t *s = (const v128u64_t*)src;
+
+   d0[0] = v128_unpacklo64( s[ 0], s[ 1] );
+   d1[0] = v128_unpackhi64( s[ 0], s[ 1] );
+   d0[1] = v128_unpacklo64( s[ 2], s[ 3] );
+   d1[1] = v128_unpackhi64( s[ 2], s[ 3] );
+   if ( bit_len <= 256 ) return;
+   d0[2] = v128_unpacklo64( s[ 4], s[ 5] );
+   d1[2] = v128_unpackhi64( s[ 4], s[ 5] );
+   d0[3] = v128_unpacklo64( s[ 6], s[ 7] );
+   d1[3] = v128_unpackhi64( s[ 6], s[ 7] );
+   if ( bit_len <= 512 ) return;
+   d0[4] = v128_unpacklo64( s[ 8], s[ 9] );
+   d1[4] = v128_unpackhi64( s[ 8], s[ 9] );
+   if ( bit_len <= 640 ) return;
+   d0[5] = v128_unpacklo64( s[10], s[11] );
+   d1[5] = v128_unpackhi64( s[10], s[11] );
+   d0[6] = v128_unpacklo64( s[12], s[13] );
+   d1[6] = v128_unpackhi64( s[12], s[13] );
+   d0[7] = v128_unpacklo64( s[14], s[15] );
+   d1[7] = v128_unpackhi64( s[14], s[15] );
+}
+
+/*
 static inline void intrlv_2x64( void *dst, const void *src0,
                                 const void *src1, const int bit_len )
 {
@@ -1440,7 +1624,8 @@ static inline void intrlv_2x64( void *dst, const void *src0,
    d[24] = s0[12];    d[25] = s1[12];   d[26] = s0[13];    d[27] = s1[13];
    d[28] = s0[14];    d[29] = s1[14];   d[30] = s0[15];    d[31] = s1[15];
 }
-
+*/
+/*
 static inline void dintrlv_2x64( void *dst0, void *dst1,
                                  const void *src, const int bit_len )
 {
@@ -1460,6 +1645,7 @@ static inline void dintrlv_2x64( void *dst0, void *dst1,
    d0[12] = s[24];   d1[12] = s[25];   d0[13] = s[26];   d1[13] = s[27];
    d0[14] = s[28];   d1[14] = s[29];   d0[15] = s[30];   d1[15] = s[31];
 }
+*/
 
 static inline void v128_bswap32_intrlv80_2x64( void *d, const void *src )
 {
@@ -1542,6 +1728,61 @@ static inline void extr_lane_2x64( void *dst, const void *src,
 
 // 4x64   (AVX2)
 
+#if defined(__AVX2__)
+
+#define ILEAVE_4x64( D0, D1, D2, D3, S0, S1, S2, S3 ) \
+{ \
+  __m256i T; \
+  T  = _mm256_unpacklo_epi64( S0, S1 ); \
+  S0 = _mm256_unpackhi_epi64( S0, S1 ); \
+  S1 = _mm256_unpacklo_epi64( S2, S3 ); \
+  S2 = _mm256_unpackhi_epi64( S2, S3 ); \
+  D0 = v256_unpacklo128( T,  S1 ); \
+  D1 = v256_unpacklo128( S0, S2 ); \
+  D2 = v256_unpackhi128( T,  S1 ); \
+  D3 = v256_unpackhi128( S0, S2 ); \
+}
+
+#define LOAD_SRCE_4x64( S0, S1, S2, S3, src0, i0, src1, i1, src2, i2, src3, i3 ) \
+   S0 = _mm256_load_si256( (const __m256i*)(src0) + (i0) ); \
+   S1 = _mm256_load_si256( (const __m256i*)(src1) + (i1) ); \
+   S2 = _mm256_load_si256( (const __m256i*)(src2) + (i2) ); \
+   S3 = _mm256_load_si256( (const __m256i*)(src3) + (i3) );
+
+#define STOR_DEST_4x64( D0, D1, D2, D3, dst0, i0, dst1, i1, dst2, i2, dst3, i3 ) \
+   _mm256_store_si256( (__m256i*)(dst0) + (i0), D0 ); \
+   _mm256_store_si256( (__m256i*)(dst1) + (i1), D1 ); \
+   _mm256_store_si256( (__m256i*)(dst2) + (i2), D2 ); \
+   _mm256_store_si256( (__m256i*)(dst3) + (i3), D3 );
+
+/*
+static inline void intrlv_4x64_512( void *dst, const void *src0,
+                         const void *src1, const void *src2, const void *src3 )
+{
+   __m256i D0, D1, D2, D3, S0, S1, S2, S3;
+   LOAD_SRCE_4x64( S0, S1, S2, S3, src0, 0, src1, 0, src2, 0, src3, 0 );
+   ILEAVE_4x64( D0, D1, D2, D3, S0, S1, S2, S3 );
+   LOAD_SRCE_4x64( S0, S1, S2, S3, src0, 1, src1, 1, src2, 1, src3, 1 );
+   STOR_DEST_4x64( D0, D1, D2, D3, dst, 0, dst, 1, dst, 2, dst, 3 );
+   ILEAVE_4x64( D0, D1, D2, D3, S0, S1, S2, S3 );
+   STOR_DEST_4x64( D0, D1, D2, D3, dst, 4, dst, 5, dst, 6, dst, 7 );
+}
+*/
+/*
+static inline void dintrlv_4x64_512( void *dst0, void *dst1, void *dst2,
+                                     void *dst3, const void *src )
+{
+   __m256i D0, D1, D2, D3, S0, S1, S2, S3;
+   LOAD_SRCE_4x64( S0, S1, S2, S3, src, 0, src, 1, src, 2, src, 3 );
+   ILEAVE_4x64( D0, D1, D2, D3, S0, S1, S2, S3 );
+   LOAD_SRCE_4x64( S0, S1, S2, S3, src, 4, src, 5, src, 6, src, 7 );
+   STOR_DEST_4x64( D0, D1, D2, D3, dst0, 0, dst1, 0, dst2, 0, dst3, 0 );
+   ILEAVE_4x64( D0, D1, D2, D3, S0, S1, S2, S3 );
+   STOR_DEST_4x64( D0, D1, D2, D3, dst0, 1, dst1, 1, dst2, 1, dst3, 1 );
+}  
+*/
+#endif
+
 #if defined(__SSE2__)
 
 static inline void intrlv_4x64( void *dst, const void *src0,
@@ -1590,6 +1831,7 @@ static inline void intrlv_4x64( void *dst, const void *src0,
    d[31] = v128_unpackhi64( s2[7], s3[7] );
 }
 
+
 static inline void intrlv_4x64_512( void *dst, const void *src0,
            const void *src1, const void *src2, const void *src3 )
 {
@@ -1616,6 +1858,7 @@ static inline void intrlv_4x64_512( void *dst, const void *src0,
    d[15] = v128_unpackhi64( s2[3], s3[3] );
 }
 
+
 static inline void dintrlv_4x64( void *dst0, void *dst1, void *dst2,
                            void *dst3, const void *src, const int bit_len )
 {
@@ -1661,6 +1904,7 @@ static inline void dintrlv_4x64( void *dst0, void *dst1, void *dst2,
    d3[7] = v128_unpackhi64( s[29], s[31] );
 }
 
+
 static inline void dintrlv_4x64_512( void *dst0, void *dst1, void *dst2,
                                      void *dst3, const void *src )
 {
@@ -3318,7 +3562,13 @@ do { \
 #endif // AVX512
 
 #undef ILEAVE_4x32
-#undef LOAD_SRCE
-#undef ILEAVE_STORE_DEST
+#undef LOAD_SRCE_4x32
+#undef STOR_DEST_4x32
+#undef ILEAVE_8x32
+#undef LOAD_SRCE_8x32
+#undef STOR_DEST_8x32
+#undef ILEAVE_4x64
+#undef LOAD_SRCE_4x64
+#undef STOR_DEST_4x64
 
 #endif // INTERLEAVE_H__
diff --git a/simd-utils/simd-128.h b/simd-utils/simd-128.h
index 655c729e..2fa9898f 100644
--- a/simd-utils/simd-128.h
+++ b/simd-utils/simd-128.h
@@ -141,7 +141,7 @@
 #define v128_aesdeclast                _mm_aesdeclast_si128
 #define v128_aesdeclast_nokey(v)       _mm_aesdeclast_si128( v, v128_zero )
 
-// Used instead if casting.
+// Used instead of casting.
 typedef union
 {
    v128_t   v128;
diff --git a/simd-utils/simd-256.h b/simd-utils/simd-256.h
index 1a894c15..c568dafa 100644
--- a/simd-utils/simd-256.h
+++ b/simd-utils/simd-256.h
@@ -429,6 +429,19 @@ static inline __m256i mm256_not( const __m256i v )
 
 #endif     // AVX512 else AVX2
 
+#if defined(__AVX2__)
+
+// 128 bit version of unpack
+#define v256_unpacklo128( v1, v0 )   _mm256_permute2x128_si256( v1, v0, 0x20 )
+#define v256_unpackhi128( v1, v0 )   _mm256_permute2x128_si256( v1, v0, 0x31 )
+
+#else
+
+#define v256_unpacklo128( v1, v0 )   _mm256_permute2f128_si256( v1, v0, 0x20 )
+#define v256_unpackhi128( v1, v0 )   _mm256_permute2f128_si256( v1, v0, 0x31 )
+
+#endif
+
 //
 // Cross lane shuffles
 //
diff --git a/simd-utils/simd-int.h b/simd-utils/simd-int.h
index 2a4ce0b5..95650c59 100644
--- a/simd-utils/simd-int.h
+++ b/simd-utils/simd-int.h
@@ -164,11 +164,10 @@ static inline uint32_t ror32( uint32_t a, const int c )
 // obsolete test
 // Compiler check for __int128 support
 // Configure also has a test for int128.
-#if ( __GNUC__ > 4 ) || ( ( __GNUC__ == 4 ) && ( __GNUC_MINOR__ >= 8 ) )
+//#if ( __GNUC__ > 4 ) || ( ( __GNUC__ == 4 ) && ( __GNUC_MINOR__ >= 8 ) )
   #define GCC_INT128 1
-#endif
+//#endif
 
-// obsolte test
 #if !defined(GCC_INT128)
   #warning "__int128 not supported, requires GCC-4.8 or newer."
 #endif
diff --git a/sysinfos.c b/sysinfos.c
index c054a85b..18fb507f 100644
--- a/sysinfos.c
+++ b/sysinfos.c
@@ -14,6 +14,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include "miner.h"
+#include "simd-utils.h"
 
 #if defined(__aarch64__) && !defined(__APPLE__)
 // for arm's "cpuid"
@@ -223,8 +224,8 @@ static inline int cpu_fanpercent()
 #define AVX512_F_Flag            (1<<16)
 #define AVX512_DQ_Flag           (1<<17)
 #define AVX512_IFMA_Flag         (1<<21)
-#define AVX512_PF_Flag           (1<<26)
-#define AVX512_ER_Flag           (1<<27)
+#define AVX512_PF_Flag           (1<<26)   // obsolete
+#define AVX512_ER_Flag           (1<<27)   // obsolete
 #define AVX512_CD_Flag           (1<<28)
 #define SHA_Flag                 (1<<29)
 #define AVX512_BW_Flag           (1<<30)
@@ -237,8 +238,8 @@ static inline int cpu_fanpercent()
 #define AVX512_BITALG_Flag       (1<<12)
 #define AVX512_VPOPCNTDQ_Flag    (1<<14)
 // EDX
-#define AVX512_4VNNIW_Flag       (1<< 2)
-#define AVX512_4FMAPS_Flag       (1<< 3)
+#define AVX512_4VNNIW_Flag       (1<< 2)   // obsolete
+#define AVX512_4FMAPS_Flag       (1<< 3)   // obsolete
 #define AVX512_VP2INTERSECT_Flag (1<< 8)
 #define AMX_BF16_Flag            (1<<22)
 #define AVX512_FP16_Flag         (1<<23)
@@ -557,10 +558,15 @@ static inline bool has_aes_ni()
 #elif defined(__aarch64__) && !defined(__APPLE__)
    if ( has_neon() )
    {
-      unsigned int cpu_info[4] = { 0 };
+#if defined(KERNEL_HWCAP_AES)
+      return true;
+#else
+      return false;
+#endif
+/*      unsigned int cpu_info[4] = { 0 };
       cpuid( 0, 0, cpu_info );
       return cpu_info[0] & HWCAP_AES;
-   }
+*/   }
    return false;
 #else
    return false;
@@ -602,10 +608,15 @@ static inline bool has_sha()
 #elif defined(__aarch64__) && !defined(__APPLE__)
     if ( has_neon() )
     {
-       unsigned int cpu_info[4] = { 0 };
+#if defined(KERNEL_HWCAP_SHA2)
+       return true;
+#else
+       return false;
+#endif
+/*       unsigned int cpu_info[4] = { 0 };
        cpuid( 0, 0, cpu_info );
        return cpu_info[0] & HWCAP_SHA2;
-    }
+*/    }
     return false;
 #else
     return false;
diff --git a/util.c b/util.c
index 7f0ca6a4..c1161c32 100644
--- a/util.c
+++ b/util.c
@@ -2075,11 +2075,7 @@ static bool stratum_notify(struct stratum_ctx *sctx, json_t *params)
          const char *s = json_string_value( json_array_get( merkle_arr, i ) );
          if ( !s || strlen(s) != 64 )
          {
-            for ( int j = sctx->job.merkle_buf_size; j > 0; j-- )
-               free( sctx->job.merkle[i] );
-            free( sctx->job.merkle );
-            sctx->job.merkle_count =
-            sctx->job.merkle_buf_size = 0;
+            sctx->job.merkle_count = 0;
             pthread_mutex_unlock( &sctx->work_lock );
             applog( LOG_ERR, "Stratum notify: invalid Merkle branch" );
             goto out;