-# define FIELD_LITERAL(a,b,c,d,e,f,g,h) \
+#define FIELD_LITERAL(a,b,c,d,e,f,g,h) \
{{LIMBLO(a),LIMBLO(e), LIMBHI(a),LIMBHI(e), \
LIMBLO(b),LIMBLO(f), LIMBHI(b),LIMBHI(f), \
LIMBLO(c),LIMBLO(g), LIMBHI(c),LIMBHI(g), \
LIMBLO(d),LIMBLO(h), LIMBHI(d),LIMBHI(h)}}
{{LIMBLO(a),LIMBLO(e), LIMBHI(a),LIMBHI(e), \
LIMBLO(b),LIMBLO(f), LIMBHI(b),LIMBHI(f), \
LIMBLO(c),LIMBLO(g), LIMBHI(c),LIMBHI(g), \
LIMBLO(d),LIMBLO(h), LIMBHI(d),LIMBHI(h)}}
-void gf_add_RAW (gf out, const gf a, const gf b) {
- for (unsigned int i=0; i<sizeof(*out)/sizeof(uint32xn_t); i++) {
- ((uint32xn_t*)out)[i] = ((const uint32xn_t*)a)[i] + ((const uint32xn_t*)b)[i];
+void gf_add_RAW(gf out, const gf a, const gf b)
+{
+ for (unsigned int i = 0; i < sizeof(*out) / sizeof(uint32xn_t); i++) {
+ ((uint32xn_t *) out)[i] =
+ ((const uint32xn_t *)a)[i] + ((const uint32xn_t *)b)[i];
-void gf_sub_RAW (gf out, const gf a, const gf b) {
- for (unsigned int i=0; i<sizeof(*out)/sizeof(uint32xn_t); i++) {
- ((uint32xn_t*)out)[i] = ((const uint32xn_t*)a)[i] - ((const uint32xn_t*)b)[i];
+void gf_sub_RAW(gf out, const gf a, const gf b)
+{
+ for (unsigned int i = 0; i < sizeof(*out) / sizeof(uint32xn_t); i++) {
+ ((uint32xn_t *) out)[i] =
+ ((const uint32xn_t *)a)[i] - ((const uint32xn_t *)b)[i];
- unsigned int i;
- for (i=0; i<sizeof(*out)/sizeof(out->limb[0]); i++) {
- out->limb[i] = a->limb[i] - b->limb[i];
- }
- */
+ * unsigned int i; for (i=0; i<sizeof(*out)/sizeof(out->limb[0]); i++) {
+ * out->limb[i] = a->limb[i] - b->limb[i]; }
+ */
-void gf_bias (gf a, int amt) {
- uint32_t co1 = ((1ull<<28)-1)*amt, co2 = co1-amt;
- uint32x4_t lo = {co1,co2,co1,co1}, hi = {co1,co1,co1,co1};
- uint32x4_t *aa = (uint32x4_t*) a;
+void gf_bias(gf a, int amt)
+{
+ uint32_t co1 = ((1ull << 28) - 1) * amt, co2 = co1 - amt;
+ uint32x4_t lo = { co1, co2, co1, co1 }, hi = {
+ co1, co1, co1, co1};
+ uint32x4_t *aa = (uint32x4_t *) a;
- uint32x2_t *aa = (uint32x2_t*) a, vmask = {(1ull<<28)-1, (1ull<<28)-1}, vm2 = {0,-1},
- tmp = vshr_n_u32(aa[7],28);
-
- for (unsigned int i=7; i>=1; i--) {
- aa[i] = vsra_n_u32(aa[i] & vmask, aa[i-1], 28);
+ uint32x2_t *aa = (uint32x2_t *) a, vmask = {
+ (1ull << 28) - 1, (1ull << 28) - 1}, vm2 = {
+ 0, -1}, tmp = vshr_n_u32(aa[7], 28);
+
+ for (unsigned int i = 7; i >= 1; i--) {
+ aa[i] = vsra_n_u32(aa[i] & vmask, aa[i - 1], 28);