aboutsummaryrefslogtreecommitdiff
path: root/target/i386/ops_sse.h
diff options
context:
space:
mode:
Diffstat (limited to 'target/i386/ops_sse.h')
-rw-r--r--target/i386/ops_sse.h1835
1 files changed, 918 insertions, 917 deletions
diff --git a/target/i386/ops_sse.h b/target/i386/ops_sse.h
index 535440f882..c0766de18d 100644
--- a/target/i386/ops_sse.h
+++ b/target/i386/ops_sse.h
@@ -22,7 +22,6 @@
#if SHIFT == 0
#define Reg MMXReg
-#define SIZE 8
#define XMM_ONLY(...)
#define B(n) MMX_B(n)
#define W(n) MMX_W(n)
@@ -31,7 +30,6 @@
#define SUFFIX _mmx
#else
#define Reg ZMMReg
-#define SIZE 16
#define XMM_ONLY(...) __VA_ARGS__
#define B(n) ZMM_B(n)
#define W(n) ZMM_W(n)
@@ -40,275 +38,210 @@
#define SUFFIX _xmm
#endif
-/*
- * Copy the relevant parts of a Reg value around. In the case where
- * sizeof(Reg) > SIZE, these helpers operate only on the lower bytes of
- * a 64 byte ZMMReg, so we must copy only those and keep the top bytes
- * untouched in the guest-visible destination destination register.
- * Note that the "lower bytes" are placed last in memory on big-endian
- * hosts, which store the vector backwards in memory. In that case the
- * copy *starts* at B(SIZE - 1) and ends at B(0), the opposite of
- * the little-endian case.
- */
-#if HOST_BIG_ENDIAN
-#define MOVE(d, r) memcpy(&((d).B(SIZE - 1)), &(r).B(SIZE - 1), SIZE)
-#else
-#define MOVE(d, r) memcpy(&(d).B(0), &(r).B(0), SIZE)
+#define LANE_WIDTH (SHIFT ? 16 : 8)
+#define PACK_WIDTH (LANE_WIDTH / 2)
+
+#if SHIFT == 0
+#define FPSRL(x, c) ((x) >> shift)
+#define FPSRAW(x, c) ((int16_t)(x) >> shift)
+#define FPSRAL(x, c) ((int32_t)(x) >> shift)
+#define FPSLL(x, c) ((x) << shift)
#endif
-void glue(helper_psrlw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+void glue(helper_psrlw, SUFFIX)(CPUX86State *env, Reg *d, Reg *c)
{
+ Reg *s = d;
int shift;
-
- if (s->Q(0) > 15) {
- d->Q(0) = 0;
-#if SHIFT == 1
- d->Q(1) = 0;
-#endif
+ if (c->Q(0) > 15) {
+ for (int i = 0; i < 1 << SHIFT; i++) {
+ d->Q(i) = 0;
+ }
} else {
- shift = s->B(0);
- d->W(0) >>= shift;
- d->W(1) >>= shift;
- d->W(2) >>= shift;
- d->W(3) >>= shift;
-#if SHIFT == 1
- d->W(4) >>= shift;
- d->W(5) >>= shift;
- d->W(6) >>= shift;
- d->W(7) >>= shift;
-#endif
+ shift = c->B(0);
+ for (int i = 0; i < 4 << SHIFT; i++) {
+ d->W(i) = FPSRL(s->W(i), shift);
+ }
}
}
-void glue(helper_psraw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+void glue(helper_psllw, SUFFIX)(CPUX86State *env, Reg *d, Reg *c)
{
+ Reg *s = d;
int shift;
-
- if (s->Q(0) > 15) {
- shift = 15;
+ if (c->Q(0) > 15) {
+ for (int i = 0; i < 1 << SHIFT; i++) {
+ d->Q(i) = 0;
+ }
} else {
- shift = s->B(0);
+ shift = c->B(0);
+ for (int i = 0; i < 4 << SHIFT; i++) {
+ d->W(i) = FPSLL(s->W(i), shift);
+ }
}
- d->W(0) = (int16_t)d->W(0) >> shift;
- d->W(1) = (int16_t)d->W(1) >> shift;
- d->W(2) = (int16_t)d->W(2) >> shift;
- d->W(3) = (int16_t)d->W(3) >> shift;
-#if SHIFT == 1
- d->W(4) = (int16_t)d->W(4) >> shift;
- d->W(5) = (int16_t)d->W(5) >> shift;
- d->W(6) = (int16_t)d->W(6) >> shift;
- d->W(7) = (int16_t)d->W(7) >> shift;
-#endif
}
-void glue(helper_psllw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+void glue(helper_psraw, SUFFIX)(CPUX86State *env, Reg *d, Reg *c)
{
+ Reg *s = d;
int shift;
-
- if (s->Q(0) > 15) {
- d->Q(0) = 0;
-#if SHIFT == 1
- d->Q(1) = 0;
-#endif
+ if (c->Q(0) > 15) {
+ shift = 15;
} else {
- shift = s->B(0);
- d->W(0) <<= shift;
- d->W(1) <<= shift;
- d->W(2) <<= shift;
- d->W(3) <<= shift;
-#if SHIFT == 1
- d->W(4) <<= shift;
- d->W(5) <<= shift;
- d->W(6) <<= shift;
- d->W(7) <<= shift;
-#endif
+ shift = c->B(0);
+ }
+ for (int i = 0; i < 4 << SHIFT; i++) {
+ d->W(i) = FPSRAW(s->W(i), shift);
}
}
-void glue(helper_psrld, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+void glue(helper_psrld, SUFFIX)(CPUX86State *env, Reg *d, Reg *c)
{
+ Reg *s = d;
int shift;
-
- if (s->Q(0) > 31) {
- d->Q(0) = 0;
-#if SHIFT == 1
- d->Q(1) = 0;
-#endif
+ if (c->Q(0) > 31) {
+ for (int i = 0; i < 1 << SHIFT; i++) {
+ d->Q(i) = 0;
+ }
} else {
- shift = s->B(0);
- d->L(0) >>= shift;
- d->L(1) >>= shift;
-#if SHIFT == 1
- d->L(2) >>= shift;
- d->L(3) >>= shift;
-#endif
+ shift = c->B(0);
+ for (int i = 0; i < 2 << SHIFT; i++) {
+ d->L(i) = FPSRL(s->L(i), shift);
+ }
}
}
-void glue(helper_psrad, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+void glue(helper_pslld, SUFFIX)(CPUX86State *env, Reg *d, Reg *c)
{
+ Reg *s = d;
int shift;
-
- if (s->Q(0) > 31) {
- shift = 31;
+ if (c->Q(0) > 31) {
+ for (int i = 0; i < 1 << SHIFT; i++) {
+ d->Q(i) = 0;
+ }
} else {
- shift = s->B(0);
+ shift = c->B(0);
+ for (int i = 0; i < 2 << SHIFT; i++) {
+ d->L(i) = FPSLL(s->L(i), shift);
+ }
}
- d->L(0) = (int32_t)d->L(0) >> shift;
- d->L(1) = (int32_t)d->L(1) >> shift;
-#if SHIFT == 1
- d->L(2) = (int32_t)d->L(2) >> shift;
- d->L(3) = (int32_t)d->L(3) >> shift;
-#endif
}
-void glue(helper_pslld, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+void glue(helper_psrad, SUFFIX)(CPUX86State *env, Reg *d, Reg *c)
{
+ Reg *s = d;
int shift;
-
- if (s->Q(0) > 31) {
- d->Q(0) = 0;
-#if SHIFT == 1
- d->Q(1) = 0;
-#endif
+ if (c->Q(0) > 31) {
+ shift = 31;
} else {
- shift = s->B(0);
- d->L(0) <<= shift;
- d->L(1) <<= shift;
-#if SHIFT == 1
- d->L(2) <<= shift;
- d->L(3) <<= shift;
-#endif
+ shift = c->B(0);
+ }
+ for (int i = 0; i < 2 << SHIFT; i++) {
+ d->L(i) = FPSRAL(s->L(i), shift);
}
}
-void glue(helper_psrlq, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+void glue(helper_psrlq, SUFFIX)(CPUX86State *env, Reg *d, Reg *c)
{
+ Reg *s = d;
int shift;
-
- if (s->Q(0) > 63) {
- d->Q(0) = 0;
-#if SHIFT == 1
- d->Q(1) = 0;
-#endif
+ if (c->Q(0) > 63) {
+ for (int i = 0; i < 1 << SHIFT; i++) {
+ d->Q(i) = 0;
+ }
} else {
- shift = s->B(0);
- d->Q(0) >>= shift;
-#if SHIFT == 1
- d->Q(1) >>= shift;
-#endif
+ shift = c->B(0);
+ for (int i = 0; i < 1 << SHIFT; i++) {
+ d->Q(i) = FPSRL(s->Q(i), shift);
+ }
}
}
-void glue(helper_psllq, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+void glue(helper_psllq, SUFFIX)(CPUX86State *env, Reg *d, Reg *c)
{
+ Reg *s = d;
int shift;
-
- if (s->Q(0) > 63) {
- d->Q(0) = 0;
-#if SHIFT == 1
- d->Q(1) = 0;
-#endif
+ if (c->Q(0) > 63) {
+ for (int i = 0; i < 1 << SHIFT; i++) {
+ d->Q(i) = 0;
+ }
} else {
- shift = s->B(0);
- d->Q(0) <<= shift;
-#if SHIFT == 1
- d->Q(1) <<= shift;
-#endif
+ shift = c->B(0);
+ for (int i = 0; i < 1 << SHIFT; i++) {
+ d->Q(i) = FPSLL(s->Q(i), shift);
+ }
}
}
-#if SHIFT == 1
-void glue(helper_psrldq, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+#if SHIFT >= 1
+void glue(helper_psrldq, SUFFIX)(CPUX86State *env, Reg *d, Reg *c)
{
- int shift, i;
+ Reg *s = d;
+ int shift, i, j;
- shift = s->L(0);
+ shift = c->L(0);
if (shift > 16) {
shift = 16;
}
- for (i = 0; i < 16 - shift; i++) {
- d->B(i) = d->B(i + shift);
- }
- for (i = 16 - shift; i < 16; i++) {
- d->B(i) = 0;
+ for (j = 0; j < 8 << SHIFT; j += LANE_WIDTH) {
+ for (i = 0; i < 16 - shift; i++) {
+ d->B(j + i) = s->B(j + i + shift);
+ }
+ for (i = 16 - shift; i < 16; i++) {
+ d->B(j + i) = 0;
+ }
}
}
-void glue(helper_pslldq, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+void glue(helper_pslldq, SUFFIX)(CPUX86State *env, Reg *d, Reg *c)
{
- int shift, i;
+ Reg *s = d;
+ int shift, i, j;
- shift = s->L(0);
+ shift = c->L(0);
if (shift > 16) {
shift = 16;
}
- for (i = 15; i >= shift; i--) {
- d->B(i) = d->B(i - shift);
- }
- for (i = 0; i < shift; i++) {
- d->B(i) = 0;
+ for (j = 0; j < 8 << SHIFT; j += LANE_WIDTH) {
+ for (i = 15; i >= shift; i--) {
+ d->B(j + i) = s->B(j + i - shift);
+ }
+ for (i = 0; i < shift; i++) {
+ d->B(j + i) = 0;
+ }
}
}
#endif
-#define SSE_HELPER_B(name, F) \
+#define SSE_HELPER_1(name, elem, num, F) \
void glue(name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s) \
{ \
- d->B(0) = F(d->B(0), s->B(0)); \
- d->B(1) = F(d->B(1), s->B(1)); \
- d->B(2) = F(d->B(2), s->B(2)); \
- d->B(3) = F(d->B(3), s->B(3)); \
- d->B(4) = F(d->B(4), s->B(4)); \
- d->B(5) = F(d->B(5), s->B(5)); \
- d->B(6) = F(d->B(6), s->B(6)); \
- d->B(7) = F(d->B(7), s->B(7)); \
- XMM_ONLY( \
- d->B(8) = F(d->B(8), s->B(8)); \
- d->B(9) = F(d->B(9), s->B(9)); \
- d->B(10) = F(d->B(10), s->B(10)); \
- d->B(11) = F(d->B(11), s->B(11)); \
- d->B(12) = F(d->B(12), s->B(12)); \
- d->B(13) = F(d->B(13), s->B(13)); \
- d->B(14) = F(d->B(14), s->B(14)); \
- d->B(15) = F(d->B(15), s->B(15)); \
- ) \
- }
+ int n = num; \
+ for (int i = 0; i < n; i++) { \
+ d->elem(i) = F(s->elem(i)); \
+ } \
+ }
-#define SSE_HELPER_W(name, F) \
+#define SSE_HELPER_2(name, elem, num, F) \
void glue(name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s) \
{ \
- d->W(0) = F(d->W(0), s->W(0)); \
- d->W(1) = F(d->W(1), s->W(1)); \
- d->W(2) = F(d->W(2), s->W(2)); \
- d->W(3) = F(d->W(3), s->W(3)); \
- XMM_ONLY( \
- d->W(4) = F(d->W(4), s->W(4)); \
- d->W(5) = F(d->W(5), s->W(5)); \
- d->W(6) = F(d->W(6), s->W(6)); \
- d->W(7) = F(d->W(7), s->W(7)); \
- ) \
- }
+ Reg *v = d; \
+ int n = num; \
+ for (int i = 0; i < n; i++) { \
+ d->elem(i) = F(v->elem(i), s->elem(i)); \
+ } \
+ }
+
+#define SSE_HELPER_B(name, F) \
+ SSE_HELPER_2(name, B, 8 << SHIFT, F)
+
+#define SSE_HELPER_W(name, F) \
+ SSE_HELPER_2(name, W, 4 << SHIFT, F)
#define SSE_HELPER_L(name, F) \
- void glue(name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s) \
- { \
- d->L(0) = F(d->L(0), s->L(0)); \
- d->L(1) = F(d->L(1), s->L(1)); \
- XMM_ONLY( \
- d->L(2) = F(d->L(2), s->L(2)); \
- d->L(3) = F(d->L(3), s->L(3)); \
- ) \
- }
+ SSE_HELPER_2(name, L, 2 << SHIFT, F)
#define SSE_HELPER_Q(name, F) \
- void glue(name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s) \
- { \
- d->Q(0) = F(d->Q(0), s->Q(0)); \
- XMM_ONLY( \
- d->Q(1) = F(d->Q(1), s->Q(1)); \
- ) \
- }
+ SSE_HELPER_2(name, Q, 1 << SHIFT, F)
#if SHIFT == 0
static inline int satub(int x)
@@ -440,19 +373,22 @@ SSE_HELPER_W(helper_pavgw, FAVG)
void glue(helper_pmuludq, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
{
- d->Q(0) = (uint64_t)s->L(0) * (uint64_t)d->L(0);
-#if SHIFT == 1
- d->Q(1) = (uint64_t)s->L(2) * (uint64_t)d->L(2);
-#endif
+ Reg *v = d;
+ int i;
+
+ for (i = 0; i < (1 << SHIFT); i++) {
+ d->Q(i) = (uint64_t)s->L(i * 2) * (uint64_t)v->L(i * 2);
+ }
}
void glue(helper_pmaddwd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
{
+ Reg *v = d;
int i;
for (i = 0; i < (2 << SHIFT); i++) {
- d->L(i) = (int16_t)s->W(2 * i) * (int16_t)d->W(2 * i) +
- (int16_t)s->W(2 * i + 1) * (int16_t)d->W(2 * i + 1);
+ d->L(i) = (int16_t)s->W(2 * i) * (int16_t)v->W(2 * i) +
+ (int16_t)s->W(2 * i + 1) * (int16_t)v->W(2 * i + 1);
}
}
@@ -466,34 +402,27 @@ static inline int abs1(int a)
}
}
#endif
+
void glue(helper_psadbw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
{
- unsigned int val;
+ Reg *v = d;
+ int i;
- val = 0;
- val += abs1(d->B(0) - s->B(0));
- val += abs1(d->B(1) - s->B(1));
- val += abs1(d->B(2) - s->B(2));
- val += abs1(d->B(3) - s->B(3));
- val += abs1(d->B(4) - s->B(4));
- val += abs1(d->B(5) - s->B(5));
- val += abs1(d->B(6) - s->B(6));
- val += abs1(d->B(7) - s->B(7));
- d->Q(0) = val;
-#if SHIFT == 1
- val = 0;
- val += abs1(d->B(8) - s->B(8));
- val += abs1(d->B(9) - s->B(9));
- val += abs1(d->B(10) - s->B(10));
- val += abs1(d->B(11) - s->B(11));
- val += abs1(d->B(12) - s->B(12));
- val += abs1(d->B(13) - s->B(13));
- val += abs1(d->B(14) - s->B(14));
- val += abs1(d->B(15) - s->B(15));
- d->Q(1) = val;
-#endif
+ for (i = 0; i < (1 << SHIFT); i++) {
+ unsigned int val = 0;
+ val += abs1(v->B(8 * i + 0) - s->B(8 * i + 0));
+ val += abs1(v->B(8 * i + 1) - s->B(8 * i + 1));
+ val += abs1(v->B(8 * i + 2) - s->B(8 * i + 2));
+ val += abs1(v->B(8 * i + 3) - s->B(8 * i + 3));
+ val += abs1(v->B(8 * i + 4) - s->B(8 * i + 4));
+ val += abs1(v->B(8 * i + 5) - s->B(8 * i + 5));
+ val += abs1(v->B(8 * i + 6) - s->B(8 * i + 6));
+ val += abs1(v->B(8 * i + 7) - s->B(8 * i + 7));
+ d->Q(i) = val;
+ }
}
+#if SHIFT < 2
void glue(helper_maskmov, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
target_ulong a0)
{
@@ -505,128 +434,161 @@ void glue(helper_maskmov, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
}
}
}
+#endif
void glue(helper_movl_mm_T0, SUFFIX)(Reg *d, uint32_t val)
{
+ int i;
+
d->L(0) = val;
d->L(1) = 0;
-#if SHIFT == 1
- d->Q(1) = 0;
-#endif
+ for (i = 1; i < (1 << SHIFT); i++) {
+ d->Q(i) = 0;
+ }
}
#ifdef TARGET_X86_64
void glue(helper_movq_mm_T0, SUFFIX)(Reg *d, uint64_t val)
{
+ int i;
+
d->Q(0) = val;
-#if SHIFT == 1
- d->Q(1) = 0;
-#endif
+ for (i = 1; i < (1 << SHIFT); i++) {
+ d->Q(i) = 0;
+ }
}
#endif
+#define SHUFFLE4(F, a, b, offset) do { \
+ r0 = a->F((order & 3) + offset); \
+ r1 = a->F(((order >> 2) & 3) + offset); \
+ r2 = b->F(((order >> 4) & 3) + offset); \
+ r3 = b->F(((order >> 6) & 3) + offset); \
+ d->F(offset) = r0; \
+ d->F(offset + 1) = r1; \
+ d->F(offset + 2) = r2; \
+ d->F(offset + 3) = r3; \
+ } while (0)
+
#if SHIFT == 0
void glue(helper_pshufw, SUFFIX)(Reg *d, Reg *s, int order)
{
- Reg r;
+ uint16_t r0, r1, r2, r3;
- r.W(0) = s->W(order & 3);
- r.W(1) = s->W((order >> 2) & 3);
- r.W(2) = s->W((order >> 4) & 3);
- r.W(3) = s->W((order >> 6) & 3);
- MOVE(*d, r);
+ SHUFFLE4(W, s, s, 0);
}
#else
-void helper_shufps(Reg *d, Reg *s, int order)
+void glue(helper_shufps, SUFFIX)(Reg *d, Reg *s, int order)
{
- Reg r;
+ Reg *v = d;
+ uint32_t r0, r1, r2, r3;
+ int i;
- r.L(0) = d->L(order & 3);
- r.L(1) = d->L((order >> 2) & 3);
- r.L(2) = s->L((order >> 4) & 3);
- r.L(3) = s->L((order >> 6) & 3);
- MOVE(*d, r);
+ for (i = 0; i < 2 << SHIFT; i += 4) {
+ SHUFFLE4(L, v, s, i);
+ }
}
-void helper_shufpd(Reg *d, Reg *s, int order)
+void glue(helper_shufpd, SUFFIX)(Reg *d, Reg *s, int order)
{
- Reg r;
+ Reg *v = d;
+ uint64_t r0, r1;
+ int i;
- r.Q(0) = d->Q(order & 1);
- r.Q(1) = s->Q((order >> 1) & 1);
- MOVE(*d, r);
+ for (i = 0; i < 1 << SHIFT; i += 2) {
+ r0 = v->Q(((order & 1) & 1) + i);
+ r1 = s->Q(((order >> 1) & 1) + i);
+ d->Q(i) = r0;
+ d->Q(i + 1) = r1;
+ order >>= 2;
+ }
}
void glue(helper_pshufd, SUFFIX)(Reg *d, Reg *s, int order)
{
- Reg r;
+ uint32_t r0, r1, r2, r3;
+ int i;
- r.L(0) = s->L(order & 3);
- r.L(1) = s->L((order >> 2) & 3);
- r.L(2) = s->L((order >> 4) & 3);
- r.L(3) = s->L((order >> 6) & 3);
- MOVE(*d, r);
+ for (i = 0; i < 2 << SHIFT; i += 4) {
+ SHUFFLE4(L, s, s, i);
+ }
}
void glue(helper_pshuflw, SUFFIX)(Reg *d, Reg *s, int order)
{
- Reg r;
+ uint16_t r0, r1, r2, r3;
+ int i, j;
- r.W(0) = s->W(order & 3);
- r.W(1) = s->W((order >> 2) & 3);
- r.W(2) = s->W((order >> 4) & 3);
- r.W(3) = s->W((order >> 6) & 3);
- r.Q(1) = s->Q(1);
- MOVE(*d, r);
+ for (i = 0, j = 1; j < 1 << SHIFT; i += 8, j += 2) {
+ SHUFFLE4(W, s, s, i);
+ d->Q(j) = s->Q(j);
+ }
}
void glue(helper_pshufhw, SUFFIX)(Reg *d, Reg *s, int order)
{
- Reg r;
+ uint16_t r0, r1, r2, r3;
+ int i, j;
- r.Q(0) = s->Q(0);
- r.W(4) = s->W(4 + (order & 3));
- r.W(5) = s->W(4 + ((order >> 2) & 3));
- r.W(6) = s->W(4 + ((order >> 4) & 3));
- r.W(7) = s->W(4 + ((order >> 6) & 3));
- MOVE(*d, r);
+ for (i = 4, j = 0; j < 1 << SHIFT; i += 8, j += 2) {
+ d->Q(j) = s->Q(j);
+ SHUFFLE4(W, s, s, i);
+ }
}
#endif
-#if SHIFT == 1
+#if SHIFT >= 1
/* FPU ops */
/* XXX: not accurate */
-#define SSE_HELPER_S(name, F) \
- void helper_ ## name ## ps(CPUX86State *env, Reg *d, Reg *s) \
+#define SSE_HELPER_P(name, F) \
+ void glue(helper_ ## name ## ps, SUFFIX)(CPUX86State *env, \
+ Reg *d, Reg *s) \
{ \
- d->ZMM_S(0) = F(32, d->ZMM_S(0), s->ZMM_S(0)); \
- d->ZMM_S(1) = F(32, d->ZMM_S(1), s->ZMM_S(1)); \
- d->ZMM_S(2) = F(32, d->ZMM_S(2), s->ZMM_S(2)); \
- d->ZMM_S(3) = F(32, d->ZMM_S(3), s->ZMM_S(3)); \
+ Reg *v = d; \
+ int i; \
+ for (i = 0; i < 2 << SHIFT; i++) { \
+ d->ZMM_S(i) = F(32, v->ZMM_S(i), s->ZMM_S(i)); \
+ } \
} \
\
- void helper_ ## name ## ss(CPUX86State *env, Reg *d, Reg *s) \
+ void glue(helper_ ## name ## pd, SUFFIX)(CPUX86State *env, \
+ Reg *d, Reg *s) \
{ \
- d->ZMM_S(0) = F(32, d->ZMM_S(0), s->ZMM_S(0)); \
- } \
+ Reg *v = d; \
+ int i; \
+ for (i = 0; i < 1 << SHIFT; i++) { \
+ d->ZMM_D(i) = F(64, v->ZMM_D(i), s->ZMM_D(i)); \
+ } \
+ }
+
+#if SHIFT == 1
+
+#define SSE_HELPER_S(name, F) \
+ SSE_HELPER_P(name, F) \
\
- void helper_ ## name ## pd(CPUX86State *env, Reg *d, Reg *s) \
+ void helper_ ## name ## ss(CPUX86State *env, Reg *d, Reg *s)\
{ \
- d->ZMM_D(0) = F(64, d->ZMM_D(0), s->ZMM_D(0)); \
- d->ZMM_D(1) = F(64, d->ZMM_D(1), s->ZMM_D(1)); \
+ Reg *v = d; \
+ d->ZMM_S(0) = F(32, v->ZMM_S(0), s->ZMM_S(0)); \
} \
\
- void helper_ ## name ## sd(CPUX86State *env, Reg *d, Reg *s) \
+ void helper_ ## name ## sd(CPUX86State *env, Reg *d, Reg *s)\
{ \
- d->ZMM_D(0) = F(64, d->ZMM_D(0), s->ZMM_D(0)); \
+ Reg *v = d; \
+ d->ZMM_D(0) = F(64, v->ZMM_D(0), s->ZMM_D(0)); \
}
+#else
+
+#define SSE_HELPER_S(name, F) SSE_HELPER_P(name, F)
+
+#endif
+
#define FPU_ADD(size, a, b) float ## size ## _add(a, b, &env->sse_status)
#define FPU_SUB(size, a, b) float ## size ## _sub(a, b, &env->sse_status)
#define FPU_MUL(size, a, b) float ## size ## _mul(a, b, &env->sse_status)
#define FPU_DIV(size, a, b) float ## size ## _div(a, b, &env->sse_status)
-#define FPU_SQRT(size, a, b) float ## size ## _sqrt(b, &env->sse_status)
/* Note that the choice of comparison op here is important to get the
* special cases right: for min and max Intel specifies that (-0,0),
@@ -643,27 +605,56 @@ SSE_HELPER_S(mul, FPU_MUL)
SSE_HELPER_S(div, FPU_DIV)
SSE_HELPER_S(min, FPU_MIN)
SSE_HELPER_S(max, FPU_MAX)
-SSE_HELPER_S(sqrt, FPU_SQRT)
+void glue(helper_sqrtps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+{
+ int i;
+ for (i = 0; i < 2 << SHIFT; i++) {
+ d->ZMM_S(i) = float32_sqrt(s->ZMM_S(i), &env->sse_status);
+ }
+}
-/* float to float conversions */
-void helper_cvtps2pd(CPUX86State *env, Reg *d, Reg *s)
+void glue(helper_sqrtpd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
{
- float32 s0, s1;
+ int i;
+ for (i = 0; i < 1 << SHIFT; i++) {
+ d->ZMM_D(i) = float64_sqrt(s->ZMM_D(i), &env->sse_status);
+ }
+}
- s0 = s->ZMM_S(0);
- s1 = s->ZMM_S(1);
- d->ZMM_D(0) = float32_to_float64(s0, &env->sse_status);
- d->ZMM_D(1) = float32_to_float64(s1, &env->sse_status);
+#if SHIFT == 1
+void helper_sqrtss(CPUX86State *env, Reg *d, Reg *s)
+{
+ d->ZMM_S(0) = float32_sqrt(s->ZMM_S(0), &env->sse_status);
}
-void helper_cvtpd2ps(CPUX86State *env, Reg *d, Reg *s)
+void helper_sqrtsd(CPUX86State *env, Reg *d, Reg *s)
{
- d->ZMM_S(0) = float64_to_float32(s->ZMM_D(0), &env->sse_status);
- d->ZMM_S(1) = float64_to_float32(s->ZMM_D(1), &env->sse_status);
- d->Q(1) = 0;
+ d->ZMM_D(0) = float64_sqrt(s->ZMM_D(0), &env->sse_status);
}
+#endif
+/* float to float conversions */
+void glue(helper_cvtps2pd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+{
+ int i;
+ for (i = 1 << SHIFT; --i >= 0; ) {
+ d->ZMM_D(i) = float32_to_float64(s->ZMM_S(i), &env->sse_status);
+ }
+}
+
+void glue(helper_cvtpd2ps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+{
+ int i;
+ for (i = 0; i < 1 << SHIFT; i++) {
+ d->ZMM_S(i) = float64_to_float32(s->ZMM_D(i), &env->sse_status);
+ }
+ for (i >>= 1; i < 1 << SHIFT; i++) {
+ d->Q(i) = 0;
+ }
+}
+
+#if SHIFT == 1
void helper_cvtss2sd(CPUX86State *env, Reg *d, Reg *s)
{
d->ZMM_D(0) = float32_to_float64(s->ZMM_S(0), &env->sse_status);
@@ -673,26 +664,27 @@ void helper_cvtsd2ss(CPUX86State *env, Reg *d, Reg *s)
{
d->ZMM_S(0) = float64_to_float32(s->ZMM_D(0), &env->sse_status);
}
+#endif
/* integer to float */
-void helper_cvtdq2ps(CPUX86State *env, Reg *d, Reg *s)
+void glue(helper_cvtdq2ps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
{
- d->ZMM_S(0) = int32_to_float32(s->ZMM_L(0), &env->sse_status);
- d->ZMM_S(1) = int32_to_float32(s->ZMM_L(1), &env->sse_status);
- d->ZMM_S(2) = int32_to_float32(s->ZMM_L(2), &env->sse_status);
- d->ZMM_S(3) = int32_to_float32(s->ZMM_L(3), &env->sse_status);
+ int i;
+ for (i = 0; i < 2 << SHIFT; i++) {
+ d->ZMM_S(i) = int32_to_float32(s->ZMM_L(i), &env->sse_status);
+ }
}
-void helper_cvtdq2pd(CPUX86State *env, Reg *d, Reg *s)
+void glue(helper_cvtdq2pd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
{
- int32_t l0, l1;
-
- l0 = (int32_t)s->ZMM_L(0);
- l1 = (int32_t)s->ZMM_L(1);
- d->ZMM_D(0) = int32_to_float64(l0, &env->sse_status);
- d->ZMM_D(1) = int32_to_float64(l1, &env->sse_status);
+ int i;
+ for (i = 1 << SHIFT; --i >= 0; ) {
+ int32_t l = s->ZMM_L(i);
+ d->ZMM_D(i) = int32_to_float64(l, &env->sse_status);
+ }
}
+#if SHIFT == 1
void helper_cvtpi2ps(CPUX86State *env, ZMMReg *d, MMXReg *s)
{
d->ZMM_S(0) = int32_to_float32(s->MMX_L(0), &env->sse_status);
@@ -727,8 +719,11 @@ void helper_cvtsq2sd(CPUX86State *env, ZMMReg *d, uint64_t val)
}
#endif
+#endif
+
/* float to integer */
+#if SHIFT == 1
/*
* x86 mandates that we return the indefinite integer value for the result
* of any float-to-integer conversion that raises the 'invalid' exception.
@@ -759,22 +754,28 @@ WRAP_FLOATCONV(int64_t, float32_to_int64, float32, INT64_MIN)
WRAP_FLOATCONV(int64_t, float32_to_int64_round_to_zero, float32, INT64_MIN)
WRAP_FLOATCONV(int64_t, float64_to_int64, float64, INT64_MIN)
WRAP_FLOATCONV(int64_t, float64_to_int64_round_to_zero, float64, INT64_MIN)
+#endif
-void helper_cvtps2dq(CPUX86State *env, ZMMReg *d, ZMMReg *s)
+void glue(helper_cvtps2dq, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
{
- d->ZMM_L(0) = x86_float32_to_int32(s->ZMM_S(0), &env->sse_status);
- d->ZMM_L(1) = x86_float32_to_int32(s->ZMM_S(1), &env->sse_status);
- d->ZMM_L(2) = x86_float32_to_int32(s->ZMM_S(2), &env->sse_status);
- d->ZMM_L(3) = x86_float32_to_int32(s->ZMM_S(3), &env->sse_status);
+ int i;
+ for (i = 0; i < 2 << SHIFT; i++) {
+ d->ZMM_L(i) = x86_float32_to_int32(s->ZMM_S(i), &env->sse_status);
+ }
}
-void helper_cvtpd2dq(CPUX86State *env, ZMMReg *d, ZMMReg *s)
+void glue(helper_cvtpd2dq, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
{
- d->ZMM_L(0) = x86_float64_to_int32(s->ZMM_D(0), &env->sse_status);
- d->ZMM_L(1) = x86_float64_to_int32(s->ZMM_D(1), &env->sse_status);
- d->ZMM_Q(1) = 0;
+ int i;
+ for (i = 0; i < 1 << SHIFT; i++) {
+ d->ZMM_L(i) = x86_float64_to_int32(s->ZMM_D(i), &env->sse_status);
+ }
+ for (i >>= 1; i < 1 << SHIFT; i++) {
+ d->Q(i) = 0;
+ }
}
+#if SHIFT == 1
void helper_cvtps2pi(CPUX86State *env, MMXReg *d, ZMMReg *s)
{
d->MMX_L(0) = x86_float32_to_int32(s->ZMM_S(0), &env->sse_status);
@@ -808,23 +809,31 @@ int64_t helper_cvtsd2sq(CPUX86State *env, ZMMReg *s)
return x86_float64_to_int64(s->ZMM_D(0), &env->sse_status);
}
#endif
+#endif
/* float to integer truncated */
-void helper_cvttps2dq(CPUX86State *env, ZMMReg *d, ZMMReg *s)
+void glue(helper_cvttps2dq, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
{
- d->ZMM_L(0) = x86_float32_to_int32_round_to_zero(s->ZMM_S(0), &env->sse_status);
- d->ZMM_L(1) = x86_float32_to_int32_round_to_zero(s->ZMM_S(1), &env->sse_status);
- d->ZMM_L(2) = x86_float32_to_int32_round_to_zero(s->ZMM_S(2), &env->sse_status);
- d->ZMM_L(3) = x86_float32_to_int32_round_to_zero(s->ZMM_S(3), &env->sse_status);
+ int i;
+ for (i = 0; i < 2 << SHIFT; i++) {
+ d->ZMM_L(i) = x86_float32_to_int32_round_to_zero(s->ZMM_S(i),
+ &env->sse_status);
+ }
}
-void helper_cvttpd2dq(CPUX86State *env, ZMMReg *d, ZMMReg *s)
+void glue(helper_cvttpd2dq, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
{
- d->ZMM_L(0) = x86_float64_to_int32_round_to_zero(s->ZMM_D(0), &env->sse_status);
- d->ZMM_L(1) = x86_float64_to_int32_round_to_zero(s->ZMM_D(1), &env->sse_status);
- d->ZMM_Q(1) = 0;
+ int i;
+ for (i = 0; i < 1 << SHIFT; i++) {
+ d->ZMM_L(i) = x86_float64_to_int32_round_to_zero(s->ZMM_D(i),
+ &env->sse_status);
+ }
+ for (i >>= 1; i < 1 << SHIFT; i++) {
+ d->Q(i) = 0;
+ }
}
+#if SHIFT == 1
void helper_cvttps2pi(CPUX86State *env, MMXReg *d, ZMMReg *s)
{
d->MMX_L(0) = x86_float32_to_int32_round_to_zero(s->ZMM_S(0), &env->sse_status);
@@ -858,25 +867,21 @@ int64_t helper_cvttsd2sq(CPUX86State *env, ZMMReg *s)
return x86_float64_to_int64_round_to_zero(s->ZMM_D(0), &env->sse_status);
}
#endif
+#endif
-void helper_rsqrtps(CPUX86State *env, ZMMReg *d, ZMMReg *s)
+void glue(helper_rsqrtps, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
{
uint8_t old_flags = get_float_exception_flags(&env->sse_status);
- d->ZMM_S(0) = float32_div(float32_one,
- float32_sqrt(s->ZMM_S(0), &env->sse_status),
- &env->sse_status);
- d->ZMM_S(1) = float32_div(float32_one,
- float32_sqrt(s->ZMM_S(1), &env->sse_status),
- &env->sse_status);
- d->ZMM_S(2) = float32_div(float32_one,
- float32_sqrt(s->ZMM_S(2), &env->sse_status),
- &env->sse_status);
- d->ZMM_S(3) = float32_div(float32_one,
- float32_sqrt(s->ZMM_S(3), &env->sse_status),
- &env->sse_status);
+ int i;
+ for (i = 0; i < 2 << SHIFT; i++) {
+ d->ZMM_S(i) = float32_div(float32_one,
+ float32_sqrt(s->ZMM_S(i), &env->sse_status),
+ &env->sse_status);
+ }
set_float_exception_flags(old_flags, &env->sse_status);
}
+#if SHIFT == 1
void helper_rsqrtss(CPUX86State *env, ZMMReg *d, ZMMReg *s)
{
uint8_t old_flags = get_float_exception_flags(&env->sse_status);
@@ -885,24 +890,28 @@ void helper_rsqrtss(CPUX86State *env, ZMMReg *d, ZMMReg *s)
&env->sse_status);
set_float_exception_flags(old_flags, &env->sse_status);
}
+#endif
-void helper_rcpps(CPUX86State *env, ZMMReg *d, ZMMReg *s)
+void glue(helper_rcpps, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s)
{
uint8_t old_flags = get_float_exception_flags(&env->sse_status);
- d->ZMM_S(0) = float32_div(float32_one, s->ZMM_S(0), &env->sse_status);
- d->ZMM_S(1) = float32_div(float32_one, s->ZMM_S(1), &env->sse_status);
- d->ZMM_S(2) = float32_div(float32_one, s->ZMM_S(2), &env->sse_status);
- d->ZMM_S(3) = float32_div(float32_one, s->ZMM_S(3), &env->sse_status);
+ int i;
+ for (i = 0; i < 2 << SHIFT; i++) {
+ d->ZMM_S(i) = float32_div(float32_one, s->ZMM_S(i), &env->sse_status);
+ }
set_float_exception_flags(old_flags, &env->sse_status);
}
+#if SHIFT == 1
void helper_rcpss(CPUX86State *env, ZMMReg *d, ZMMReg *s)
{
uint8_t old_flags = get_float_exception_flags(&env->sse_status);
d->ZMM_S(0) = float32_div(float32_one, s->ZMM_S(0), &env->sse_status);
set_float_exception_flags(old_flags, &env->sse_status);
}
+#endif
+#if SHIFT == 1
static inline uint64_t helper_extrq(uint64_t src, int shift, int len)
{
uint64_t mask;
@@ -946,113 +955,134 @@ void helper_insertq_i(CPUX86State *env, ZMMReg *d, int index, int length)
{
d->ZMM_Q(0) = helper_insertq(d->ZMM_Q(0), index, length);
}
+#endif
-void helper_haddps(CPUX86State *env, ZMMReg *d, ZMMReg *s)
-{
- ZMMReg r;
-
- r.ZMM_S(0) = float32_add(d->ZMM_S(0), d->ZMM_S(1), &env->sse_status);
- r.ZMM_S(1) = float32_add(d->ZMM_S(2), d->ZMM_S(3), &env->sse_status);
- r.ZMM_S(2) = float32_add(s->ZMM_S(0), s->ZMM_S(1), &env->sse_status);
- r.ZMM_S(3) = float32_add(s->ZMM_S(2), s->ZMM_S(3), &env->sse_status);
- MOVE(*d, r);
-}
-
-void helper_haddpd(CPUX86State *env, ZMMReg *d, ZMMReg *s)
-{
- ZMMReg r;
-
- r.ZMM_D(0) = float64_add(d->ZMM_D(0), d->ZMM_D(1), &env->sse_status);
- r.ZMM_D(1) = float64_add(s->ZMM_D(0), s->ZMM_D(1), &env->sse_status);
- MOVE(*d, r);
-}
-
-void helper_hsubps(CPUX86State *env, ZMMReg *d, ZMMReg *s)
-{
- ZMMReg r;
-
- r.ZMM_S(0) = float32_sub(d->ZMM_S(0), d->ZMM_S(1), &env->sse_status);
- r.ZMM_S(1) = float32_sub(d->ZMM_S(2), d->ZMM_S(3), &env->sse_status);
- r.ZMM_S(2) = float32_sub(s->ZMM_S(0), s->ZMM_S(1), &env->sse_status);
- r.ZMM_S(3) = float32_sub(s->ZMM_S(2), s->ZMM_S(3), &env->sse_status);
- MOVE(*d, r);
-}
-
-void helper_hsubpd(CPUX86State *env, ZMMReg *d, ZMMReg *s)
-{
- ZMMReg r;
-
- r.ZMM_D(0) = float64_sub(d->ZMM_D(0), d->ZMM_D(1), &env->sse_status);
- r.ZMM_D(1) = float64_sub(s->ZMM_D(0), s->ZMM_D(1), &env->sse_status);
- MOVE(*d, r);
-}
-
-void helper_addsubps(CPUX86State *env, ZMMReg *d, ZMMReg *s)
-{
- d->ZMM_S(0) = float32_sub(d->ZMM_S(0), s->ZMM_S(0), &env->sse_status);
- d->ZMM_S(1) = float32_add(d->ZMM_S(1), s->ZMM_S(1), &env->sse_status);
- d->ZMM_S(2) = float32_sub(d->ZMM_S(2), s->ZMM_S(2), &env->sse_status);
- d->ZMM_S(3) = float32_add(d->ZMM_S(3), s->ZMM_S(3), &env->sse_status);
+#define SSE_HELPER_HPS(name, F) \
+void glue(helper_ ## name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s) \
+{ \
+ Reg *v = d; \
+ float32 r[2 << SHIFT]; \
+ int i, j, k; \
+ for (k = 0; k < 2 << SHIFT; k += LANE_WIDTH / 4) { \
+ for (i = j = 0; j < 4; i++, j += 2) { \
+ r[i + k] = F(v->ZMM_S(j + k), v->ZMM_S(j + k + 1), &env->sse_status); \
+ } \
+ for (j = 0; j < 4; i++, j += 2) { \
+ r[i + k] = F(s->ZMM_S(j + k), s->ZMM_S(j + k + 1), &env->sse_status); \
+ } \
+ } \
+ for (i = 0; i < 2 << SHIFT; i++) { \
+ d->ZMM_S(i) = r[i]; \
+ } \
+}
+
+SSE_HELPER_HPS(haddps, float32_add)
+SSE_HELPER_HPS(hsubps, float32_sub)
+
+#define SSE_HELPER_HPD(name, F) \
+void glue(helper_ ## name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s) \
+{ \
+ Reg *v = d; \
+ float64 r[1 << SHIFT]; \
+ int i, j, k; \
+ for (k = 0; k < 1 << SHIFT; k += LANE_WIDTH / 8) { \
+ for (i = j = 0; j < 2; i++, j += 2) { \
+ r[i + k] = F(v->ZMM_D(j + k), v->ZMM_D(j + k + 1), &env->sse_status); \
+ } \
+ for (j = 0; j < 2; i++, j += 2) { \
+ r[i + k] = F(s->ZMM_D(j + k), s->ZMM_D(j + k + 1), &env->sse_status); \
+ } \
+ } \
+ for (i = 0; i < 1 << SHIFT; i++) { \
+ d->ZMM_D(i) = r[i]; \
+ } \
+}
+
+SSE_HELPER_HPD(haddpd, float64_add)
+SSE_HELPER_HPD(hsubpd, float64_sub)
+
+void glue(helper_addsubps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+{
+ Reg *v = d;
+ int i;
+ for (i = 0; i < 2 << SHIFT; i += 2) {
+ d->ZMM_S(i) = float32_sub(v->ZMM_S(i), s->ZMM_S(i), &env->sse_status);
+ d->ZMM_S(i+1) = float32_add(v->ZMM_S(i+1), s->ZMM_S(i+1), &env->sse_status);
+ }
}
-void helper_addsubpd(CPUX86State *env, ZMMReg *d, ZMMReg *s)
+void glue(helper_addsubpd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
{
- d->ZMM_D(0) = float64_sub(d->ZMM_D(0), s->ZMM_D(0), &env->sse_status);
- d->ZMM_D(1) = float64_add(d->ZMM_D(1), s->ZMM_D(1), &env->sse_status);
+ Reg *v = d;
+ int i;
+ for (i = 0; i < 1 << SHIFT; i += 2) {
+ d->ZMM_D(i) = float64_sub(v->ZMM_D(i), s->ZMM_D(i), &env->sse_status);
+ d->ZMM_D(i+1) = float64_add(v->ZMM_D(i+1), s->ZMM_D(i+1), &env->sse_status);
+ }
}
-/* XXX: unordered */
-#define SSE_HELPER_CMP(name, F) \
- void helper_ ## name ## ps(CPUX86State *env, Reg *d, Reg *s) \
- { \
- d->ZMM_L(0) = F(32, d->ZMM_S(0), s->ZMM_S(0)); \
- d->ZMM_L(1) = F(32, d->ZMM_S(1), s->ZMM_S(1)); \
- d->ZMM_L(2) = F(32, d->ZMM_S(2), s->ZMM_S(2)); \
- d->ZMM_L(3) = F(32, d->ZMM_S(3), s->ZMM_S(3)); \
- } \
- \
- void helper_ ## name ## ss(CPUX86State *env, Reg *d, Reg *s) \
+#define SSE_HELPER_CMP_P(name, F, C) \
+ void glue(helper_ ## name ## ps, SUFFIX)(CPUX86State *env, \
+ Reg *d, Reg *s) \
{ \
- d->ZMM_L(0) = F(32, d->ZMM_S(0), s->ZMM_S(0)); \
- } \
- \
- void helper_ ## name ## pd(CPUX86State *env, Reg *d, Reg *s) \
- { \
- d->ZMM_Q(0) = F(64, d->ZMM_D(0), s->ZMM_D(0)); \
- d->ZMM_Q(1) = F(64, d->ZMM_D(1), s->ZMM_D(1)); \
+ Reg *v = d; \
+ int i; \
+ for (i = 0; i < 2 << SHIFT; i++) { \
+ d->ZMM_L(i) = C(F(32, v->ZMM_S(i), s->ZMM_S(i))) ? -1 : 0; \
+ } \
} \
\
- void helper_ ## name ## sd(CPUX86State *env, Reg *d, Reg *s) \
+ void glue(helper_ ## name ## pd, SUFFIX)(CPUX86State *env, \
+ Reg *d, Reg *s) \
{ \
- d->ZMM_Q(0) = F(64, d->ZMM_D(0), s->ZMM_D(0)); \
- }
-
-#define FPU_CMPEQ(size, a, b) \
- (float ## size ## _eq_quiet(a, b, &env->sse_status) ? -1 : 0)
-#define FPU_CMPLT(size, a, b) \
- (float ## size ## _lt(a, b, &env->sse_status) ? -1 : 0)
-#define FPU_CMPLE(size, a, b) \
- (float ## size ## _le(a, b, &env->sse_status) ? -1 : 0)
-#define FPU_CMPUNORD(size, a, b) \
- (float ## size ## _unordered_quiet(a, b, &env->sse_status) ? -1 : 0)
-#define FPU_CMPNEQ(size, a, b) \
- (float ## size ## _eq_quiet(a, b, &env->sse_status) ? 0 : -1)
-#define FPU_CMPNLT(size, a, b) \
- (float ## size ## _lt(a, b, &env->sse_status) ? 0 : -1)
-#define FPU_CMPNLE(size, a, b) \
- (float ## size ## _le(a, b, &env->sse_status) ? 0 : -1)
-#define FPU_CMPORD(size, a, b) \
- (float ## size ## _unordered_quiet(a, b, &env->sse_status) ? 0 : -1)
-
-SSE_HELPER_CMP(cmpeq, FPU_CMPEQ)
-SSE_HELPER_CMP(cmplt, FPU_CMPLT)
-SSE_HELPER_CMP(cmple, FPU_CMPLE)
-SSE_HELPER_CMP(cmpunord, FPU_CMPUNORD)
-SSE_HELPER_CMP(cmpneq, FPU_CMPNEQ)
-SSE_HELPER_CMP(cmpnlt, FPU_CMPNLT)
-SSE_HELPER_CMP(cmpnle, FPU_CMPNLE)
-SSE_HELPER_CMP(cmpord, FPU_CMPORD)
+ Reg *v = d; \
+ int i; \
+ for (i = 0; i < 1 << SHIFT; i++) { \
+ d->ZMM_Q(i) = C(F(64, v->ZMM_D(i), s->ZMM_D(i))) ? -1 : 0; \
+ } \
+ }
+
+#if SHIFT == 1
+#define SSE_HELPER_CMP(name, F, C) \
+ SSE_HELPER_CMP_P(name, F, C) \
+ void helper_ ## name ## ss(CPUX86State *env, Reg *d, Reg *s) \
+ { \
+ Reg *v = d; \
+ d->ZMM_L(0) = C(F(32, v->ZMM_S(0), s->ZMM_S(0))) ? -1 : 0; \
+ } \
+ \
+ void helper_ ## name ## sd(CPUX86State *env, Reg *d, Reg *s) \
+ { \
+ Reg *v = d; \
+ d->ZMM_Q(0) = C(F(64, v->ZMM_D(0), s->ZMM_D(0))) ? -1 : 0; \
+ }
+
+#define FPU_EQ(x) (x == float_relation_equal)
+#define FPU_LT(x) (x == float_relation_less)
+#define FPU_LE(x) (x <= float_relation_equal)
+#define FPU_UNORD(x) (x == float_relation_unordered)
+
+#define FPU_CMPQ(size, a, b) \
+ float ## size ## _compare_quiet(a, b, &env->sse_status)
+#define FPU_CMPS(size, a, b) \
+ float ## size ## _compare(a, b, &env->sse_status)
+
+#else
+#define SSE_HELPER_CMP(name, F, C) SSE_HELPER_CMP_P(name, F, C)
+#endif
+SSE_HELPER_CMP(cmpeq, FPU_CMPQ, FPU_EQ)
+SSE_HELPER_CMP(cmplt, FPU_CMPS, FPU_LT)
+SSE_HELPER_CMP(cmple, FPU_CMPS, FPU_LE)
+SSE_HELPER_CMP(cmpunord, FPU_CMPQ, FPU_UNORD)
+SSE_HELPER_CMP(cmpneq, FPU_CMPQ, !FPU_EQ)
+SSE_HELPER_CMP(cmpnlt, FPU_CMPS, !FPU_LT)
+SSE_HELPER_CMP(cmpnle, FPU_CMPS, !FPU_LE)
+SSE_HELPER_CMP(cmpord, FPU_CMPQ, !FPU_UNORD)
+
+#undef SSE_HELPER_CMP
+
+#if SHIFT == 1
static const int comis_eflags[4] = {CC_C, CC_Z, 0, CC_Z | CC_P | CC_C};
void helper_ucomiss(CPUX86State *env, Reg *d, Reg *s)
@@ -1098,25 +1128,30 @@ void helper_comisd(CPUX86State *env, Reg *d, Reg *s)
ret = float64_compare(d0, d1, &env->sse_status);
CC_SRC = comis_eflags[ret + 1];
}
+#endif
-uint32_t helper_movmskps(CPUX86State *env, Reg *s)
+uint32_t glue(helper_movmskps, SUFFIX)(CPUX86State *env, Reg *s)
{
- int b0, b1, b2, b3;
+ uint32_t mask;
+ int i;
- b0 = s->ZMM_L(0) >> 31;
- b1 = s->ZMM_L(1) >> 31;
- b2 = s->ZMM_L(2) >> 31;
- b3 = s->ZMM_L(3) >> 31;
- return b0 | (b1 << 1) | (b2 << 2) | (b3 << 3);
+ mask = 0;
+ for (i = 0; i < 2 << SHIFT; i++) {
+ mask |= (s->ZMM_L(i) >> (31 - i)) & (1 << i);
+ }
+ return mask;
}
-uint32_t helper_movmskpd(CPUX86State *env, Reg *s)
+uint32_t glue(helper_movmskpd, SUFFIX)(CPUX86State *env, Reg *s)
{
- int b0, b1;
+ uint32_t mask;
+ int i;
- b0 = s->ZMM_L(1) >> 31;
- b1 = s->ZMM_L(3) >> 31;
- return b0 | (b1 << 1);
+ mask = 0;
+ for (i = 0; i < 1 << SHIFT; i++) {
+ mask |= (s->ZMM_Q(i) >> (63 - i)) & (1 << i);
+ }
+ return mask;
}
#endif
@@ -1124,179 +1159,150 @@ uint32_t helper_movmskpd(CPUX86State *env, Reg *s)
uint32_t glue(helper_pmovmskb, SUFFIX)(CPUX86State *env, Reg *s)
{
uint32_t val;
+ int i;
val = 0;
- val |= (s->B(0) >> 7);
- val |= (s->B(1) >> 6) & 0x02;
- val |= (s->B(2) >> 5) & 0x04;
- val |= (s->B(3) >> 4) & 0x08;
- val |= (s->B(4) >> 3) & 0x10;
- val |= (s->B(5) >> 2) & 0x20;
- val |= (s->B(6) >> 1) & 0x40;
- val |= (s->B(7)) & 0x80;
-#if SHIFT == 1
- val |= (s->B(8) << 1) & 0x0100;
- val |= (s->B(9) << 2) & 0x0200;
- val |= (s->B(10) << 3) & 0x0400;
- val |= (s->B(11) << 4) & 0x0800;
- val |= (s->B(12) << 5) & 0x1000;
- val |= (s->B(13) << 6) & 0x2000;
- val |= (s->B(14) << 7) & 0x4000;
- val |= (s->B(15) << 8) & 0x8000;
-#endif
+ for (i = 0; i < (1 << SHIFT); i++) {
+ uint8_t byte = 0;
+ byte |= (s->B(8 * i + 0) >> 7);
+ byte |= (s->B(8 * i + 1) >> 6) & 0x02;
+ byte |= (s->B(8 * i + 2) >> 5) & 0x04;
+ byte |= (s->B(8 * i + 3) >> 4) & 0x08;
+ byte |= (s->B(8 * i + 4) >> 3) & 0x10;
+ byte |= (s->B(8 * i + 5) >> 2) & 0x20;
+ byte |= (s->B(8 * i + 6) >> 1) & 0x40;
+ byte |= (s->B(8 * i + 7)) & 0x80;
+ val |= byte << (8 * i);
+ }
return val;
}
-void glue(helper_packsswb, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
-{
- Reg r;
-
- r.B(0) = satsb((int16_t)d->W(0));
- r.B(1) = satsb((int16_t)d->W(1));
- r.B(2) = satsb((int16_t)d->W(2));
- r.B(3) = satsb((int16_t)d->W(3));
-#if SHIFT == 1
- r.B(4) = satsb((int16_t)d->W(4));
- r.B(5) = satsb((int16_t)d->W(5));
- r.B(6) = satsb((int16_t)d->W(6));
- r.B(7) = satsb((int16_t)d->W(7));
-#endif
- r.B((4 << SHIFT) + 0) = satsb((int16_t)s->W(0));
- r.B((4 << SHIFT) + 1) = satsb((int16_t)s->W(1));
- r.B((4 << SHIFT) + 2) = satsb((int16_t)s->W(2));
- r.B((4 << SHIFT) + 3) = satsb((int16_t)s->W(3));
-#if SHIFT == 1
- r.B(12) = satsb((int16_t)s->W(4));
- r.B(13) = satsb((int16_t)s->W(5));
- r.B(14) = satsb((int16_t)s->W(6));
- r.B(15) = satsb((int16_t)s->W(7));
-#endif
- MOVE(*d, r);
-}
-
-void glue(helper_packuswb, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
-{
- Reg r;
-
- r.B(0) = satub((int16_t)d->W(0));
- r.B(1) = satub((int16_t)d->W(1));
- r.B(2) = satub((int16_t)d->W(2));
- r.B(3) = satub((int16_t)d->W(3));
-#if SHIFT == 1
- r.B(4) = satub((int16_t)d->W(4));
- r.B(5) = satub((int16_t)d->W(5));
- r.B(6) = satub((int16_t)d->W(6));
- r.B(7) = satub((int16_t)d->W(7));
-#endif
- r.B((4 << SHIFT) + 0) = satub((int16_t)s->W(0));
- r.B((4 << SHIFT) + 1) = satub((int16_t)s->W(1));
- r.B((4 << SHIFT) + 2) = satub((int16_t)s->W(2));
- r.B((4 << SHIFT) + 3) = satub((int16_t)s->W(3));
-#if SHIFT == 1
- r.B(12) = satub((int16_t)s->W(4));
- r.B(13) = satub((int16_t)s->W(5));
- r.B(14) = satub((int16_t)s->W(6));
- r.B(15) = satub((int16_t)s->W(7));
-#endif
- MOVE(*d, r);
-}
+#define PACK_HELPER_B(name, F) \
+void glue(helper_pack ## name, SUFFIX)(CPUX86State *env, \
+ Reg *d, Reg *s) \
+{ \
+ Reg *v = d; \
+ uint8_t r[PACK_WIDTH * 2]; \
+ int j, k; \
+ for (j = 0; j < 4 << SHIFT; j += PACK_WIDTH) { \
+ for (k = 0; k < PACK_WIDTH; k++) { \
+ r[k] = F((int16_t)v->W(j + k)); \
+ } \
+ for (k = 0; k < PACK_WIDTH; k++) { \
+ r[PACK_WIDTH + k] = F((int16_t)s->W(j + k)); \
+ } \
+ for (k = 0; k < PACK_WIDTH * 2; k++) { \
+ d->B(2 * j + k) = r[k]; \
+ } \
+ } \
+}
+
+PACK_HELPER_B(sswb, satsb)
+PACK_HELPER_B(uswb, satub)
void glue(helper_packssdw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
{
- Reg r;
+ Reg *v = d;
+ uint16_t r[PACK_WIDTH];
+ int j, k;
- r.W(0) = satsw(d->L(0));
- r.W(1) = satsw(d->L(1));
-#if SHIFT == 1
- r.W(2) = satsw(d->L(2));
- r.W(3) = satsw(d->L(3));
-#endif
- r.W((2 << SHIFT) + 0) = satsw(s->L(0));
- r.W((2 << SHIFT) + 1) = satsw(s->L(1));
-#if SHIFT == 1
- r.W(6) = satsw(s->L(2));
- r.W(7) = satsw(s->L(3));
-#endif
- MOVE(*d, r);
+ for (j = 0; j < 2 << SHIFT; j += PACK_WIDTH / 2) {
+ for (k = 0; k < PACK_WIDTH / 2; k++) {
+ r[k] = satsw(v->L(j + k));
+ }
+ for (k = 0; k < PACK_WIDTH / 2; k++) {
+ r[PACK_WIDTH / 2 + k] = satsw(s->L(j + k));
+ }
+ for (k = 0; k < PACK_WIDTH; k++) {
+ d->W(2 * j + k) = r[k];
+ }
+ }
}
#define UNPCK_OP(base_name, base) \
\
void glue(helper_punpck ## base_name ## bw, SUFFIX)(CPUX86State *env,\
- Reg *d, Reg *s) \
+ Reg *d, Reg *s) \
{ \
- Reg r; \
+ Reg *v = d; \
+ uint8_t r[PACK_WIDTH * 2]; \
+ int j, i; \
\
- r.B(0) = d->B((base << (SHIFT + 2)) + 0); \
- r.B(1) = s->B((base << (SHIFT + 2)) + 0); \
- r.B(2) = d->B((base << (SHIFT + 2)) + 1); \
- r.B(3) = s->B((base << (SHIFT + 2)) + 1); \
- r.B(4) = d->B((base << (SHIFT + 2)) + 2); \
- r.B(5) = s->B((base << (SHIFT + 2)) + 2); \
- r.B(6) = d->B((base << (SHIFT + 2)) + 3); \
- r.B(7) = s->B((base << (SHIFT + 2)) + 3); \
- XMM_ONLY( \
- r.B(8) = d->B((base << (SHIFT + 2)) + 4); \
- r.B(9) = s->B((base << (SHIFT + 2)) + 4); \
- r.B(10) = d->B((base << (SHIFT + 2)) + 5); \
- r.B(11) = s->B((base << (SHIFT + 2)) + 5); \
- r.B(12) = d->B((base << (SHIFT + 2)) + 6); \
- r.B(13) = s->B((base << (SHIFT + 2)) + 6); \
- r.B(14) = d->B((base << (SHIFT + 2)) + 7); \
- r.B(15) = s->B((base << (SHIFT + 2)) + 7); \
- ) \
- MOVE(*d, r); \
+ for (j = 0; j < 8 << SHIFT; ) { \
+ int k = j + base * PACK_WIDTH; \
+ for (i = 0; i < PACK_WIDTH; i++) { \
+ r[2 * i] = v->B(k + i); \
+ r[2 * i + 1] = s->B(k + i); \
+ } \
+ for (i = 0; i < PACK_WIDTH * 2; i++, j++) { \
+ d->B(j) = r[i]; \
+ } \
+ } \
} \
\
void glue(helper_punpck ## base_name ## wd, SUFFIX)(CPUX86State *env,\
- Reg *d, Reg *s) \
+ Reg *d, Reg *s) \
{ \
- Reg r; \
+ Reg *v = d; \
+ uint16_t r[PACK_WIDTH]; \
+ int j, i; \
\
- r.W(0) = d->W((base << (SHIFT + 1)) + 0); \
- r.W(1) = s->W((base << (SHIFT + 1)) + 0); \
- r.W(2) = d->W((base << (SHIFT + 1)) + 1); \
- r.W(3) = s->W((base << (SHIFT + 1)) + 1); \
- XMM_ONLY( \
- r.W(4) = d->W((base << (SHIFT + 1)) + 2); \
- r.W(5) = s->W((base << (SHIFT + 1)) + 2); \
- r.W(6) = d->W((base << (SHIFT + 1)) + 3); \
- r.W(7) = s->W((base << (SHIFT + 1)) + 3); \
- ) \
- MOVE(*d, r); \
+ for (j = 0; j < 4 << SHIFT; ) { \
+ int k = j + base * PACK_WIDTH / 2; \
+ for (i = 0; i < PACK_WIDTH / 2; i++) { \
+ r[2 * i] = v->W(k + i); \
+ r[2 * i + 1] = s->W(k + i); \
+ } \
+ for (i = 0; i < PACK_WIDTH; i++, j++) { \
+ d->W(j) = r[i]; \
+ } \
+ } \
} \
\
void glue(helper_punpck ## base_name ## dq, SUFFIX)(CPUX86State *env,\
- Reg *d, Reg *s) \
+ Reg *d, Reg *s) \
{ \
- Reg r; \
+ Reg *v = d; \
+ uint32_t r[PACK_WIDTH / 2]; \
+ int j, i; \
\
- r.L(0) = d->L((base << SHIFT) + 0); \
- r.L(1) = s->L((base << SHIFT) + 0); \
- XMM_ONLY( \
- r.L(2) = d->L((base << SHIFT) + 1); \
- r.L(3) = s->L((base << SHIFT) + 1); \
- ) \
- MOVE(*d, r); \
+ for (j = 0; j < 2 << SHIFT; ) { \
+ int k = j + base * PACK_WIDTH / 4; \
+ for (i = 0; i < PACK_WIDTH / 4; i++) { \
+ r[2 * i] = v->L(k + i); \
+ r[2 * i + 1] = s->L(k + i); \
+ } \
+ for (i = 0; i < PACK_WIDTH / 2; i++, j++) { \
+ d->L(j) = r[i]; \
+ } \
+ } \
} \
\
XMM_ONLY( \
- void glue(helper_punpck ## base_name ## qdq, SUFFIX)(CPUX86State \
- *env, \
- Reg *d, \
- Reg *s) \
+ void glue(helper_punpck ## base_name ## qdq, SUFFIX)( \
+ CPUX86State *env, Reg *d, Reg *s) \
{ \
- Reg r; \
+ Reg *v = d; \
+ uint64_t r[2]; \
+ int i; \
\
- r.Q(0) = d->Q(base); \
- r.Q(1) = s->Q(base); \
- MOVE(*d, r); \
+ for (i = 0; i < 1 << SHIFT; i += 2) { \
+ r[0] = v->Q(base + i); \
+ r[1] = s->Q(base + i); \
+ d->Q(i) = r[0]; \
+ d->Q(i + 1) = r[1]; \
+ } \
} \
)
UNPCK_OP(l, 0)
UNPCK_OP(h, 1)
+#undef PACK_WIDTH
+#undef PACK_HELPER_B
+#undef UNPCK_OP
+
+
/* 3DNow! float ops */
#if SHIFT == 0
void helper_pi2fd(CPUX86State *env, MMXReg *d, MMXReg *s)
@@ -1327,11 +1333,11 @@ void helper_pf2iw(CPUX86State *env, MMXReg *d, MMXReg *s)
void helper_pfacc(CPUX86State *env, MMXReg *d, MMXReg *s)
{
- MMXReg r;
+ float32 r;
- r.MMX_S(0) = float32_add(d->MMX_S(0), d->MMX_S(1), &env->mmx_status);
- r.MMX_S(1) = float32_add(s->MMX_S(0), s->MMX_S(1), &env->mmx_status);
- MOVE(*d, r);
+ r = float32_add(d->MMX_S(0), d->MMX_S(1), &env->mmx_status);
+ d->MMX_S(1) = float32_add(s->MMX_S(0), s->MMX_S(1), &env->mmx_status);
+ d->MMX_S(0) = r;
}
void helper_pfadd(CPUX86State *env, MMXReg *d, MMXReg *s)
@@ -1392,20 +1398,20 @@ void helper_pfmul(CPUX86State *env, MMXReg *d, MMXReg *s)
void helper_pfnacc(CPUX86State *env, MMXReg *d, MMXReg *s)
{
- MMXReg r;
+ float32 r;
- r.MMX_S(0) = float32_sub(d->MMX_S(0), d->MMX_S(1), &env->mmx_status);
- r.MMX_S(1) = float32_sub(s->MMX_S(0), s->MMX_S(1), &env->mmx_status);
- MOVE(*d, r);
+ r = float32_sub(d->MMX_S(0), d->MMX_S(1), &env->mmx_status);
+ d->MMX_S(1) = float32_sub(s->MMX_S(0), s->MMX_S(1), &env->mmx_status);
+ d->MMX_S(0) = r;
}
void helper_pfpnacc(CPUX86State *env, MMXReg *d, MMXReg *s)
{
- MMXReg r;
+ float32 r;
- r.MMX_S(0) = float32_sub(d->MMX_S(0), d->MMX_S(1), &env->mmx_status);
- r.MMX_S(1) = float32_add(s->MMX_S(0), s->MMX_S(1), &env->mmx_status);
- MOVE(*d, r);
+ r = float32_sub(d->MMX_S(0), d->MMX_S(1), &env->mmx_status);
+ d->MMX_S(1) = float32_add(s->MMX_S(0), s->MMX_S(1), &env->mmx_status);
+ d->MMX_S(0) = r;
}
void helper_pfrcp(CPUX86State *env, MMXReg *d, MMXReg *s)
@@ -1438,132 +1444,105 @@ void helper_pfsubr(CPUX86State *env, MMXReg *d, MMXReg *s)
void helper_pswapd(CPUX86State *env, MMXReg *d, MMXReg *s)
{
- MMXReg r;
+ uint32_t r;
- r.MMX_L(0) = s->MMX_L(1);
- r.MMX_L(1) = s->MMX_L(0);
- MOVE(*d, r);
+ r = s->MMX_L(0);
+ d->MMX_L(0) = s->MMX_L(1);
+ d->MMX_L(1) = r;
}
#endif
/* SSSE3 op helpers */
void glue(helper_pshufb, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
{
+ Reg *v = d;
int i;
- Reg r;
+#if SHIFT == 0
+ uint8_t r[8];
- for (i = 0; i < (8 << SHIFT); i++) {
- r.B(i) = (s->B(i) & 0x80) ? 0 : (d->B(s->B(i) & ((8 << SHIFT) - 1)));
+ for (i = 0; i < 8; i++) {
+ r[i] = (s->B(i) & 0x80) ? 0 : (v->B(s->B(i) & 7));
}
+ for (i = 0; i < 8; i++) {
+ d->B(i) = r[i];
+ }
+#else
+ uint8_t r[8 << SHIFT];
- MOVE(*d, r);
-}
-
-void glue(helper_phaddw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
-{
-
- Reg r;
-
- r.W(0) = (int16_t)d->W(0) + (int16_t)d->W(1);
- r.W(1) = (int16_t)d->W(2) + (int16_t)d->W(3);
- XMM_ONLY(r.W(2) = (int16_t)d->W(4) + (int16_t)d->W(5));
- XMM_ONLY(r.W(3) = (int16_t)d->W(6) + (int16_t)d->W(7));
- r.W((2 << SHIFT) + 0) = (int16_t)s->W(0) + (int16_t)s->W(1);
- r.W((2 << SHIFT) + 1) = (int16_t)s->W(2) + (int16_t)s->W(3);
- XMM_ONLY(r.W(6) = (int16_t)s->W(4) + (int16_t)s->W(5));
- XMM_ONLY(r.W(7) = (int16_t)s->W(6) + (int16_t)s->W(7));
-
- MOVE(*d, r);
-}
-
-void glue(helper_phaddd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
-{
- Reg r;
-
- r.L(0) = (int32_t)d->L(0) + (int32_t)d->L(1);
- XMM_ONLY(r.L(1) = (int32_t)d->L(2) + (int32_t)d->L(3));
- r.L((1 << SHIFT) + 0) = (int32_t)s->L(0) + (int32_t)s->L(1);
- XMM_ONLY(r.L(3) = (int32_t)s->L(2) + (int32_t)s->L(3));
-
- MOVE(*d, r);
-}
-
-void glue(helper_phaddsw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
-{
- Reg r;
-
- r.W(0) = satsw((int16_t)d->W(0) + (int16_t)d->W(1));
- r.W(1) = satsw((int16_t)d->W(2) + (int16_t)d->W(3));
- XMM_ONLY(r.W(2) = satsw((int16_t)d->W(4) + (int16_t)d->W(5)));
- XMM_ONLY(r.W(3) = satsw((int16_t)d->W(6) + (int16_t)d->W(7)));
- r.W((2 << SHIFT) + 0) = satsw((int16_t)s->W(0) + (int16_t)s->W(1));
- r.W((2 << SHIFT) + 1) = satsw((int16_t)s->W(2) + (int16_t)s->W(3));
- XMM_ONLY(r.W(6) = satsw((int16_t)s->W(4) + (int16_t)s->W(5)));
- XMM_ONLY(r.W(7) = satsw((int16_t)s->W(6) + (int16_t)s->W(7)));
-
- MOVE(*d, r);
-}
-
-void glue(helper_pmaddubsw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
-{
- d->W(0) = satsw((int8_t)s->B(0) * (uint8_t)d->B(0) +
- (int8_t)s->B(1) * (uint8_t)d->B(1));
- d->W(1) = satsw((int8_t)s->B(2) * (uint8_t)d->B(2) +
- (int8_t)s->B(3) * (uint8_t)d->B(3));
- d->W(2) = satsw((int8_t)s->B(4) * (uint8_t)d->B(4) +
- (int8_t)s->B(5) * (uint8_t)d->B(5));
- d->W(3) = satsw((int8_t)s->B(6) * (uint8_t)d->B(6) +
- (int8_t)s->B(7) * (uint8_t)d->B(7));
-#if SHIFT == 1
- d->W(4) = satsw((int8_t)s->B(8) * (uint8_t)d->B(8) +
- (int8_t)s->B(9) * (uint8_t)d->B(9));
- d->W(5) = satsw((int8_t)s->B(10) * (uint8_t)d->B(10) +
- (int8_t)s->B(11) * (uint8_t)d->B(11));
- d->W(6) = satsw((int8_t)s->B(12) * (uint8_t)d->B(12) +
- (int8_t)s->B(13) * (uint8_t)d->B(13));
- d->W(7) = satsw((int8_t)s->B(14) * (uint8_t)d->B(14) +
- (int8_t)s->B(15) * (uint8_t)d->B(15));
+ for (i = 0; i < 8 << SHIFT; i++) {
+ int j = i & ~0xf;
+ r[i] = (s->B(i) & 0x80) ? 0 : v->B(j | (s->B(i) & 0xf));
+ }
+ for (i = 0; i < 8 << SHIFT; i++) {
+ d->B(i) = r[i];
+ }
#endif
}
-void glue(helper_phsubw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
-{
- d->W(0) = (int16_t)d->W(0) - (int16_t)d->W(1);
- d->W(1) = (int16_t)d->W(2) - (int16_t)d->W(3);
- XMM_ONLY(d->W(2) = (int16_t)d->W(4) - (int16_t)d->W(5));
- XMM_ONLY(d->W(3) = (int16_t)d->W(6) - (int16_t)d->W(7));
- d->W((2 << SHIFT) + 0) = (int16_t)s->W(0) - (int16_t)s->W(1);
- d->W((2 << SHIFT) + 1) = (int16_t)s->W(2) - (int16_t)s->W(3);
- XMM_ONLY(d->W(6) = (int16_t)s->W(4) - (int16_t)s->W(5));
- XMM_ONLY(d->W(7) = (int16_t)s->W(6) - (int16_t)s->W(7));
-}
+#define SSE_HELPER_HW(name, F) \
+void glue(helper_ ## name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s) \
+{ \
+ Reg *v = d; \
+ uint16_t r[4 << SHIFT]; \
+ int i, j, k; \
+ for (k = 0; k < 4 << SHIFT; k += LANE_WIDTH / 2) { \
+ for (i = j = 0; j < LANE_WIDTH / 2; i++, j += 2) { \
+ r[i + k] = F(v->W(j + k), v->W(j + k + 1)); \
+ } \
+ for (j = 0; j < LANE_WIDTH / 2; i++, j += 2) { \
+ r[i + k] = F(s->W(j + k), s->W(j + k + 1)); \
+ } \
+ } \
+ for (i = 0; i < 4 << SHIFT; i++) { \
+ d->W(i) = r[i]; \
+ } \
+}
+
+#define SSE_HELPER_HL(name, F) \
+void glue(helper_ ## name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s) \
+{ \
+ Reg *v = d; \
+ uint32_t r[2 << SHIFT]; \
+ int i, j, k; \
+ for (k = 0; k < 2 << SHIFT; k += LANE_WIDTH / 4) { \
+ for (i = j = 0; j < LANE_WIDTH / 4; i++, j += 2) { \
+ r[i + k] = F(v->L(j + k), v->L(j + k + 1)); \
+ } \
+ for (j = 0; j < LANE_WIDTH / 4; i++, j += 2) { \
+ r[i + k] = F(s->L(j + k), s->L(j + k + 1)); \
+ } \
+ } \
+ for (i = 0; i < 2 << SHIFT; i++) { \
+ d->L(i) = r[i]; \
+ } \
+}
+
+SSE_HELPER_HW(phaddw, FADD)
+SSE_HELPER_HW(phsubw, FSUB)
+SSE_HELPER_HW(phaddsw, FADDSW)
+SSE_HELPER_HW(phsubsw, FSUBSW)
+SSE_HELPER_HL(phaddd, FADD)
+SSE_HELPER_HL(phsubd, FSUB)
+
+#undef SSE_HELPER_HW
+#undef SSE_HELPER_HL
-void glue(helper_phsubd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
-{
- d->L(0) = (int32_t)d->L(0) - (int32_t)d->L(1);
- XMM_ONLY(d->L(1) = (int32_t)d->L(2) - (int32_t)d->L(3));
- d->L((1 << SHIFT) + 0) = (int32_t)s->L(0) - (int32_t)s->L(1);
- XMM_ONLY(d->L(3) = (int32_t)s->L(2) - (int32_t)s->L(3));
-}
-
-void glue(helper_phsubsw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+void glue(helper_pmaddubsw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
{
- d->W(0) = satsw((int16_t)d->W(0) - (int16_t)d->W(1));
- d->W(1) = satsw((int16_t)d->W(2) - (int16_t)d->W(3));
- XMM_ONLY(d->W(2) = satsw((int16_t)d->W(4) - (int16_t)d->W(5)));
- XMM_ONLY(d->W(3) = satsw((int16_t)d->W(6) - (int16_t)d->W(7)));
- d->W((2 << SHIFT) + 0) = satsw((int16_t)s->W(0) - (int16_t)s->W(1));
- d->W((2 << SHIFT) + 1) = satsw((int16_t)s->W(2) - (int16_t)s->W(3));
- XMM_ONLY(d->W(6) = satsw((int16_t)s->W(4) - (int16_t)s->W(5)));
- XMM_ONLY(d->W(7) = satsw((int16_t)s->W(6) - (int16_t)s->W(7)));
+ Reg *v = d;
+ int i;
+ for (i = 0; i < 4 << SHIFT; i++) {
+ d->W(i) = satsw((int8_t)s->B(i * 2) * (uint8_t)v->B(i * 2) +
+ (int8_t)s->B(i * 2 + 1) * (uint8_t)v->B(i * 2 + 1));
+ }
}
-#define FABSB(_, x) (x > INT8_MAX ? -(int8_t)x : x)
-#define FABSW(_, x) (x > INT16_MAX ? -(int16_t)x : x)
-#define FABSL(_, x) (x > INT32_MAX ? -(int32_t)x : x)
-SSE_HELPER_B(helper_pabsb, FABSB)
-SSE_HELPER_W(helper_pabsw, FABSW)
-SSE_HELPER_L(helper_pabsd, FABSL)
+#define FABSB(x) (x > INT8_MAX ? -(int8_t)x : x)
+#define FABSW(x) (x > INT16_MAX ? -(int16_t)x : x)
+#define FABSL(x) (x > INT32_MAX ? -(int32_t)x : x)
+SSE_HELPER_1(helper_pabsb, B, 8 << SHIFT, FABSB)
+SSE_HELPER_1(helper_pabsw, W, 4 << SHIFT, FABSW)
+SSE_HELPER_1(helper_pabsd, L, 2 << SHIFT, FABSL)
#define FMULHRSW(d, s) (((int16_t) d * (int16_t)s + 0x4000) >> 15)
SSE_HELPER_W(helper_pmulhrsw, FMULHRSW)
@@ -1578,147 +1557,117 @@ SSE_HELPER_L(helper_psignd, FSIGNL)
void glue(helper_palignr, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
int32_t shift)
{
- Reg r;
+ Reg *v = d;
+ int i;
/* XXX could be checked during translation */
- if (shift >= (16 << SHIFT)) {
- r.Q(0) = 0;
- XMM_ONLY(r.Q(1) = 0);
+ if (shift >= (SHIFT ? 32 : 16)) {
+ for (i = 0; i < (1 << SHIFT); i++) {
+ d->Q(i) = 0;
+ }
} else {
shift <<= 3;
#define SHR(v, i) (i < 64 && i > -64 ? i > 0 ? v >> (i) : (v << -(i)) : 0)
#if SHIFT == 0
- r.Q(0) = SHR(s->Q(0), shift - 0) |
- SHR(d->Q(0), shift - 64);
+ d->Q(0) = SHR(s->Q(0), shift - 0) |
+ SHR(v->Q(0), shift - 64);
#else
- r.Q(0) = SHR(s->Q(0), shift - 0) |
- SHR(s->Q(1), shift - 64) |
- SHR(d->Q(0), shift - 128) |
- SHR(d->Q(1), shift - 192);
- r.Q(1) = SHR(s->Q(0), shift + 64) |
- SHR(s->Q(1), shift - 0) |
- SHR(d->Q(0), shift - 64) |
- SHR(d->Q(1), shift - 128);
+ for (i = 0; i < (1 << SHIFT); i += 2) {
+ uint64_t r0, r1;
+
+ r0 = SHR(s->Q(i), shift - 0) |
+ SHR(s->Q(i + 1), shift - 64) |
+ SHR(v->Q(i), shift - 128) |
+ SHR(v->Q(i + 1), shift - 192);
+ r1 = SHR(s->Q(i), shift + 64) |
+ SHR(s->Q(i + 1), shift - 0) |
+ SHR(v->Q(i), shift - 64) |
+ SHR(v->Q(i + 1), shift - 128);
+ d->Q(i) = r0;
+ d->Q(i + 1) = r1;
+ }
#endif
#undef SHR
}
-
- MOVE(*d, r);
}
-#define XMM0 (env->xmm_regs[0])
+#if SHIFT >= 1
-#if SHIFT == 1
#define SSE_HELPER_V(name, elem, num, F) \
- void glue(name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s) \
+ void glue(name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s) \
{ \
- d->elem(0) = F(d->elem(0), s->elem(0), XMM0.elem(0)); \
- d->elem(1) = F(d->elem(1), s->elem(1), XMM0.elem(1)); \
- if (num > 2) { \
- d->elem(2) = F(d->elem(2), s->elem(2), XMM0.elem(2)); \
- d->elem(3) = F(d->elem(3), s->elem(3), XMM0.elem(3)); \
- if (num > 4) { \
- d->elem(4) = F(d->elem(4), s->elem(4), XMM0.elem(4)); \
- d->elem(5) = F(d->elem(5), s->elem(5), XMM0.elem(5)); \
- d->elem(6) = F(d->elem(6), s->elem(6), XMM0.elem(6)); \
- d->elem(7) = F(d->elem(7), s->elem(7), XMM0.elem(7)); \
- if (num > 8) { \
- d->elem(8) = F(d->elem(8), s->elem(8), XMM0.elem(8)); \
- d->elem(9) = F(d->elem(9), s->elem(9), XMM0.elem(9)); \
- d->elem(10) = F(d->elem(10), s->elem(10), XMM0.elem(10)); \
- d->elem(11) = F(d->elem(11), s->elem(11), XMM0.elem(11)); \
- d->elem(12) = F(d->elem(12), s->elem(12), XMM0.elem(12)); \
- d->elem(13) = F(d->elem(13), s->elem(13), XMM0.elem(13)); \
- d->elem(14) = F(d->elem(14), s->elem(14), XMM0.elem(14)); \
- d->elem(15) = F(d->elem(15), s->elem(15), XMM0.elem(15)); \
- } \
- } \
+ Reg *v = d; \
+ Reg *m = &env->xmm_regs[0]; \
+ int i; \
+ for (i = 0; i < num; i++) { \
+ d->elem(i) = F(v->elem(i), s->elem(i), m->elem(i)); \
} \
}
#define SSE_HELPER_I(name, elem, num, F) \
- void glue(name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s, uint32_t imm) \
+ void glue(name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s, \
+ uint32_t imm) \
{ \
- d->elem(0) = F(d->elem(0), s->elem(0), ((imm >> 0) & 1)); \
- d->elem(1) = F(d->elem(1), s->elem(1), ((imm >> 1) & 1)); \
- if (num > 2) { \
- d->elem(2) = F(d->elem(2), s->elem(2), ((imm >> 2) & 1)); \
- d->elem(3) = F(d->elem(3), s->elem(3), ((imm >> 3) & 1)); \
- if (num > 4) { \
- d->elem(4) = F(d->elem(4), s->elem(4), ((imm >> 4) & 1)); \
- d->elem(5) = F(d->elem(5), s->elem(5), ((imm >> 5) & 1)); \
- d->elem(6) = F(d->elem(6), s->elem(6), ((imm >> 6) & 1)); \
- d->elem(7) = F(d->elem(7), s->elem(7), ((imm >> 7) & 1)); \
- if (num > 8) { \
- d->elem(8) = F(d->elem(8), s->elem(8), ((imm >> 8) & 1)); \
- d->elem(9) = F(d->elem(9), s->elem(9), ((imm >> 9) & 1)); \
- d->elem(10) = F(d->elem(10), s->elem(10), \
- ((imm >> 10) & 1)); \
- d->elem(11) = F(d->elem(11), s->elem(11), \
- ((imm >> 11) & 1)); \
- d->elem(12) = F(d->elem(12), s->elem(12), \
- ((imm >> 12) & 1)); \
- d->elem(13) = F(d->elem(13), s->elem(13), \
- ((imm >> 13) & 1)); \
- d->elem(14) = F(d->elem(14), s->elem(14), \
- ((imm >> 14) & 1)); \
- d->elem(15) = F(d->elem(15), s->elem(15), \
- ((imm >> 15) & 1)); \
- } \
- } \
+ Reg *v = d; \
+ int i; \
+ for (i = 0; i < num; i++) { \
+ int j = i & 7; \
+ d->elem(i) = F(v->elem(i), s->elem(i), (imm >> j) & 1); \
} \
}
/* SSE4.1 op helpers */
-#define FBLENDVB(d, s, m) ((m & 0x80) ? s : d)
-#define FBLENDVPS(d, s, m) ((m & 0x80000000) ? s : d)
-#define FBLENDVPD(d, s, m) ((m & 0x8000000000000000LL) ? s : d)
-SSE_HELPER_V(helper_pblendvb, B, 16, FBLENDVB)
-SSE_HELPER_V(helper_blendvps, L, 4, FBLENDVPS)
-SSE_HELPER_V(helper_blendvpd, Q, 2, FBLENDVPD)
+#define FBLENDVB(v, s, m) ((m & 0x80) ? s : v)
+#define FBLENDVPS(v, s, m) ((m & 0x80000000) ? s : v)
+#define FBLENDVPD(v, s, m) ((m & 0x8000000000000000LL) ? s : v)
+SSE_HELPER_V(helper_pblendvb, B, 8 << SHIFT, FBLENDVB)
+SSE_HELPER_V(helper_blendvps, L, 2 << SHIFT, FBLENDVPS)
+SSE_HELPER_V(helper_blendvpd, Q, 1 << SHIFT, FBLENDVPD)
void glue(helper_ptest, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
{
- uint64_t zf = (s->Q(0) & d->Q(0)) | (s->Q(1) & d->Q(1));
- uint64_t cf = (s->Q(0) & ~d->Q(0)) | (s->Q(1) & ~d->Q(1));
+ uint64_t zf = 0, cf = 0;
+ int i;
+ for (i = 0; i < 1 << SHIFT; i++) {
+ zf |= (s->Q(i) & d->Q(i));
+ cf |= (s->Q(i) & ~d->Q(i));
+ }
CC_SRC = (zf ? 0 : CC_Z) | (cf ? 0 : CC_C);
}
-#define SSE_HELPER_F(name, elem, num, F) \
- void glue(name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s) \
- { \
- if (num > 2) { \
- if (num > 4) { \
- d->elem(7) = F(7); \
- d->elem(6) = F(6); \
- d->elem(5) = F(5); \
- d->elem(4) = F(4); \
- } \
- d->elem(3) = F(3); \
- d->elem(2) = F(2); \
- } \
- d->elem(1) = F(1); \
- d->elem(0) = F(0); \
- }
-
-SSE_HELPER_F(helper_pmovsxbw, W, 8, (int8_t) s->B)
-SSE_HELPER_F(helper_pmovsxbd, L, 4, (int8_t) s->B)
-SSE_HELPER_F(helper_pmovsxbq, Q, 2, (int8_t) s->B)
-SSE_HELPER_F(helper_pmovsxwd, L, 4, (int16_t) s->W)
-SSE_HELPER_F(helper_pmovsxwq, Q, 2, (int16_t) s->W)
-SSE_HELPER_F(helper_pmovsxdq, Q, 2, (int32_t) s->L)
-SSE_HELPER_F(helper_pmovzxbw, W, 8, s->B)
-SSE_HELPER_F(helper_pmovzxbd, L, 4, s->B)
-SSE_HELPER_F(helper_pmovzxbq, Q, 2, s->B)
-SSE_HELPER_F(helper_pmovzxwd, L, 4, s->W)
-SSE_HELPER_F(helper_pmovzxwq, Q, 2, s->W)
-SSE_HELPER_F(helper_pmovzxdq, Q, 2, s->L)
+#define SSE_HELPER_F(name, elem, num, F) \
+ void glue(name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s) \
+ { \
+ int n = num; \
+ for (int i = n; --i >= 0; ) { \
+ d->elem(i) = F(i); \
+ } \
+ }
+
+#if SHIFT > 0
+SSE_HELPER_F(helper_pmovsxbw, W, 4 << SHIFT, (int8_t) s->B)
+SSE_HELPER_F(helper_pmovsxbd, L, 2 << SHIFT, (int8_t) s->B)
+SSE_HELPER_F(helper_pmovsxbq, Q, 1 << SHIFT, (int8_t) s->B)
+SSE_HELPER_F(helper_pmovsxwd, L, 2 << SHIFT, (int16_t) s->W)
+SSE_HELPER_F(helper_pmovsxwq, Q, 1 << SHIFT, (int16_t) s->W)
+SSE_HELPER_F(helper_pmovsxdq, Q, 1 << SHIFT, (int32_t) s->L)
+SSE_HELPER_F(helper_pmovzxbw, W, 4 << SHIFT, s->B)
+SSE_HELPER_F(helper_pmovzxbd, L, 2 << SHIFT, s->B)
+SSE_HELPER_F(helper_pmovzxbq, Q, 1 << SHIFT, s->B)
+SSE_HELPER_F(helper_pmovzxwd, L, 2 << SHIFT, s->W)
+SSE_HELPER_F(helper_pmovzxwq, Q, 1 << SHIFT, s->W)
+SSE_HELPER_F(helper_pmovzxdq, Q, 1 << SHIFT, s->L)
+#endif
void glue(helper_pmuldq, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
{
- d->Q(0) = (int64_t)(int32_t) d->L(0) * (int32_t) s->L(0);
- d->Q(1) = (int64_t)(int32_t) d->L(2) * (int32_t) s->L(2);
+ Reg *v = d;
+ int i;
+
+ for (i = 0; i < 1 << SHIFT; i++) {
+ d->Q(i) = (int64_t)(int32_t) v->L(2 * i) * (int32_t) s->L(2 * i);
+ }
}
#define FCMPEQQ(d, s) (d == s ? -1 : 0)
@@ -1726,17 +1675,23 @@ SSE_HELPER_Q(helper_pcmpeqq, FCMPEQQ)
void glue(helper_packusdw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
{
- Reg r;
-
- r.W(0) = satuw((int32_t) d->L(0));
- r.W(1) = satuw((int32_t) d->L(1));
- r.W(2) = satuw((int32_t) d->L(2));
- r.W(3) = satuw((int32_t) d->L(3));
- r.W(4) = satuw((int32_t) s->L(0));
- r.W(5) = satuw((int32_t) s->L(1));
- r.W(6) = satuw((int32_t) s->L(2));
- r.W(7) = satuw((int32_t) s->L(3));
- MOVE(*d, r);
+ Reg *v = d;
+ uint16_t r[8];
+ int i, j, k;
+
+ for (i = 0, j = 0; i <= 2 << SHIFT; i += 8, j += 4) {
+ r[0] = satuw(v->L(j));
+ r[1] = satuw(v->L(j + 1));
+ r[2] = satuw(v->L(j + 2));
+ r[3] = satuw(v->L(j + 3));
+ r[4] = satuw(s->L(j));
+ r[5] = satuw(s->L(j + 1));
+ r[6] = satuw(s->L(j + 2));
+ r[7] = satuw(s->L(j + 3));
+ for (k = 0; k < 8; k++) {
+ d->W(i + k) = r[k];
+ }
+ }
}
#define FMINSB(d, s) MIN((int8_t)d, (int8_t)s)
@@ -1755,6 +1710,7 @@ SSE_HELPER_L(helper_pmaxud, MAX)
#define FMULLD(d, s) ((int32_t)d * (int32_t)s)
SSE_HELPER_L(helper_pmulld, FMULLD)
+#if SHIFT == 1
void glue(helper_phminposuw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
{
int idx = 0;
@@ -1786,12 +1742,14 @@ void glue(helper_phminposuw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
d->L(1) = 0;
d->Q(1) = 0;
}
+#endif
void glue(helper_roundps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
uint32_t mode)
{
uint8_t old_flags = get_float_exception_flags(&env->sse_status);
signed char prev_rounding_mode;
+ int i;
prev_rounding_mode = env->sse_status.float_rounding_mode;
if (!(mode & (1 << 2))) {
@@ -1811,10 +1769,9 @@ void glue(helper_roundps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
}
}
- d->ZMM_S(0) = float32_round_to_int(s->ZMM_S(0), &env->sse_status);
- d->ZMM_S(1) = float32_round_to_int(s->ZMM_S(1), &env->sse_status);
- d->ZMM_S(2) = float32_round_to_int(s->ZMM_S(2), &env->sse_status);
- d->ZMM_S(3) = float32_round_to_int(s->ZMM_S(3), &env->sse_status);
+ for (i = 0; i < 2 << SHIFT; i++) {
+ d->ZMM_S(i) = float32_round_to_int(s->ZMM_S(i), &env->sse_status);
+ }
if (mode & (1 << 3) && !(old_flags & float_flag_inexact)) {
set_float_exception_flags(get_float_exception_flags(&env->sse_status) &
@@ -1829,6 +1786,7 @@ void glue(helper_roundpd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
{
uint8_t old_flags = get_float_exception_flags(&env->sse_status);
signed char prev_rounding_mode;
+ int i;
prev_rounding_mode = env->sse_status.float_rounding_mode;
if (!(mode & (1 << 2))) {
@@ -1848,8 +1806,9 @@ void glue(helper_roundpd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
}
}
- d->ZMM_D(0) = float64_round_to_int(s->ZMM_D(0), &env->sse_status);
- d->ZMM_D(1) = float64_round_to_int(s->ZMM_D(1), &env->sse_status);
+ for (i = 0; i < 1 << SHIFT; i++) {
+ d->ZMM_D(i) = float64_round_to_int(s->ZMM_D(i), &env->sse_status);
+ }
if (mode & (1 << 3) && !(old_flags & float_flag_inexact)) {
set_float_exception_flags(get_float_exception_flags(&env->sse_status) &
@@ -1859,6 +1818,7 @@ void glue(helper_roundpd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
env->sse_status.float_rounding_mode = prev_rounding_mode;
}
+#if SHIFT == 1
void glue(helper_roundss, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
uint32_t mode)
{
@@ -1926,89 +1886,109 @@ void glue(helper_roundsd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
}
env->sse_status.float_rounding_mode = prev_rounding_mode;
}
+#endif
-#define FBLENDP(d, s, m) (m ? s : d)
-SSE_HELPER_I(helper_blendps, L, 4, FBLENDP)
-SSE_HELPER_I(helper_blendpd, Q, 2, FBLENDP)
-SSE_HELPER_I(helper_pblendw, W, 8, FBLENDP)
+#define FBLENDP(v, s, m) (m ? s : v)
+SSE_HELPER_I(helper_blendps, L, 2 << SHIFT, FBLENDP)
+SSE_HELPER_I(helper_blendpd, Q, 1 << SHIFT, FBLENDP)
+SSE_HELPER_I(helper_pblendw, W, 4 << SHIFT, FBLENDP)
-void glue(helper_dpps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s, uint32_t mask)
+void glue(helper_dpps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
+ uint32_t mask)
{
- float32 iresult = float32_zero;
+ Reg *v = d;
+ float32 prod1, prod2, temp2, temp3, temp4;
+ int i;
- if (mask & (1 << 4)) {
- iresult = float32_add(iresult,
- float32_mul(d->ZMM_S(0), s->ZMM_S(0),
- &env->sse_status),
- &env->sse_status);
- }
- if (mask & (1 << 5)) {
- iresult = float32_add(iresult,
- float32_mul(d->ZMM_S(1), s->ZMM_S(1),
- &env->sse_status),
- &env->sse_status);
- }
- if (mask & (1 << 6)) {
- iresult = float32_add(iresult,
- float32_mul(d->ZMM_S(2), s->ZMM_S(2),
- &env->sse_status),
- &env->sse_status);
- }
- if (mask & (1 << 7)) {
- iresult = float32_add(iresult,
- float32_mul(d->ZMM_S(3), s->ZMM_S(3),
- &env->sse_status),
- &env->sse_status);
+ for (i = 0; i < 2 << SHIFT; i += 4) {
+ /*
+ * We must evaluate (A+B)+(C+D), not ((A+B)+C)+D
+ * to correctly round the intermediate results
+ */
+ if (mask & (1 << 4)) {
+ prod1 = float32_mul(v->ZMM_S(i), s->ZMM_S(i), &env->sse_status);
+ } else {
+ prod1 = float32_zero;
+ }
+ if (mask & (1 << 5)) {
+ prod2 = float32_mul(v->ZMM_S(i+1), s->ZMM_S(i+1), &env->sse_status);
+ } else {
+ prod2 = float32_zero;
+ }
+ temp2 = float32_add(prod1, prod2, &env->sse_status);
+ if (mask & (1 << 6)) {
+ prod1 = float32_mul(v->ZMM_S(i+2), s->ZMM_S(i+2), &env->sse_status);
+ } else {
+ prod1 = float32_zero;
+ }
+ if (mask & (1 << 7)) {
+ prod2 = float32_mul(v->ZMM_S(i+3), s->ZMM_S(i+3), &env->sse_status);
+ } else {
+ prod2 = float32_zero;
+ }
+ temp3 = float32_add(prod1, prod2, &env->sse_status);
+ temp4 = float32_add(temp2, temp3, &env->sse_status);
+
+ d->ZMM_S(i) = (mask & (1 << 0)) ? temp4 : float32_zero;
+ d->ZMM_S(i+1) = (mask & (1 << 1)) ? temp4 : float32_zero;
+ d->ZMM_S(i+2) = (mask & (1 << 2)) ? temp4 : float32_zero;
+ d->ZMM_S(i+3) = (mask & (1 << 3)) ? temp4 : float32_zero;
}
- d->ZMM_S(0) = (mask & (1 << 0)) ? iresult : float32_zero;
- d->ZMM_S(1) = (mask & (1 << 1)) ? iresult : float32_zero;
- d->ZMM_S(2) = (mask & (1 << 2)) ? iresult : float32_zero;
- d->ZMM_S(3) = (mask & (1 << 3)) ? iresult : float32_zero;
}
-void glue(helper_dppd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s, uint32_t mask)
+#if SHIFT == 1
+/* Oddly, there is no ymm version of dppd */
+void glue(helper_dppd, SUFFIX)(CPUX86State *env,
+ Reg *d, Reg *s, uint32_t mask)
{
- float64 iresult = float64_zero;
+ Reg *v = d;
+ float64 prod1, prod2, temp2;
if (mask & (1 << 4)) {
- iresult = float64_add(iresult,
- float64_mul(d->ZMM_D(0), s->ZMM_D(0),
- &env->sse_status),
- &env->sse_status);
+ prod1 = float64_mul(v->ZMM_D(0), s->ZMM_D(0), &env->sse_status);
+ } else {
+ prod1 = float64_zero;
}
if (mask & (1 << 5)) {
- iresult = float64_add(iresult,
- float64_mul(d->ZMM_D(1), s->ZMM_D(1),
- &env->sse_status),
- &env->sse_status);
+ prod2 = float64_mul(v->ZMM_D(1), s->ZMM_D(1), &env->sse_status);
+ } else {
+ prod2 = float64_zero;
}
- d->ZMM_D(0) = (mask & (1 << 0)) ? iresult : float64_zero;
- d->ZMM_D(1) = (mask & (1 << 1)) ? iresult : float64_zero;
+ temp2 = float64_add(prod1, prod2, &env->sse_status);
+ d->ZMM_D(0) = (mask & (1 << 0)) ? temp2 : float64_zero;
+ d->ZMM_D(1) = (mask & (1 << 1)) ? temp2 : float64_zero;
}
+#endif
void glue(helper_mpsadbw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
uint32_t offset)
{
- int s0 = (offset & 3) << 2;
- int d0 = (offset & 4) << 0;
- int i;
- Reg r;
-
- for (i = 0; i < 8; i++, d0++) {
- r.W(i) = 0;
- r.W(i) += abs1(d->B(d0 + 0) - s->B(s0 + 0));
- r.W(i) += abs1(d->B(d0 + 1) - s->B(s0 + 1));
- r.W(i) += abs1(d->B(d0 + 2) - s->B(s0 + 2));
- r.W(i) += abs1(d->B(d0 + 3) - s->B(s0 + 3));
+ Reg *v = d;
+ int i, j;
+ uint16_t r[8];
+
+ for (j = 0; j < 4 << SHIFT; ) {
+ int s0 = (j * 2) + ((offset & 3) << 2);
+ int d0 = (j * 2) + ((offset & 4) << 0);
+ for (i = 0; i < LANE_WIDTH / 2; i++, d0++) {
+ r[i] = 0;
+ r[i] += abs1(v->B(d0 + 0) - s->B(s0 + 0));
+ r[i] += abs1(v->B(d0 + 1) - s->B(s0 + 1));
+ r[i] += abs1(v->B(d0 + 2) - s->B(s0 + 2));
+ r[i] += abs1(v->B(d0 + 3) - s->B(s0 + 3));
+ }
+ for (i = 0; i < LANE_WIDTH / 2; i++, j++) {
+ d->W(j) = r[i];
+ }
+ offset >>= 3;
}
-
- MOVE(*d, r);
}
/* SSE4.2 op helpers */
#define FCMPGTQ(d, s) ((int64_t)d > (int64_t)s ? -1 : 0)
SSE_HELPER_Q(helper_pcmpgtq, FCMPGTQ)
+#if SHIFT == 1
static inline int pcmp_elen(CPUX86State *env, int reg, uint32_t ctrl)
{
target_long val, limit;
@@ -2229,14 +2209,16 @@ target_ulong helper_crc32(uint32_t crc1, target_ulong msg, uint32_t len)
return crc;
}
-void glue(helper_pclmulqdq, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
- uint32_t ctrl)
+#endif
+
+#if SHIFT == 1
+static void clmulq(uint64_t *dest_l, uint64_t *dest_h,
+ uint64_t a, uint64_t b)
{
- uint64_t ah, al, b, resh, resl;
+ uint64_t al, ah, resh, resl;
ah = 0;
- al = d->Q((ctrl & 1) != 0);
- b = s->Q((ctrl & 16) != 0);
+ al = a;
resh = resl = 0;
while (b) {
@@ -2249,8 +2231,23 @@ void glue(helper_pclmulqdq, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
b >>= 1;
}
- d->Q(0) = resl;
- d->Q(1) = resh;
+ *dest_l = resl;
+ *dest_h = resh;
+}
+#endif
+
+void glue(helper_pclmulqdq, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
+ uint32_t ctrl)
+{
+ Reg *v = d;
+ uint64_t a, b;
+ int i;
+
+ for (i = 0; i < 1 << SHIFT; i += 2) {
+ a = v->Q(((ctrl & 1) != 0) + i);
+ b = s->Q(((ctrl & 16) != 0) + i);
+ clmulq(&d->Q(i), &d->Q(i + 1), a, b);
+ }
}
void glue(helper_aesdec, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
@@ -2259,11 +2256,12 @@ void glue(helper_aesdec, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
Reg st = *d;
Reg rk = *s;
- for (i = 0 ; i < 4 ; i++) {
- d->L(i) = rk.L(i) ^ bswap32(AES_Td0[st.B(AES_ishifts[4*i+0])] ^
- AES_Td1[st.B(AES_ishifts[4*i+1])] ^
- AES_Td2[st.B(AES_ishifts[4*i+2])] ^
- AES_Td3[st.B(AES_ishifts[4*i+3])]);
+ for (i = 0 ; i < 2 << SHIFT ; i++) {
+ int j = i & 3;
+ d->L(i) = rk.L(i) ^ bswap32(AES_Td0[st.B(AES_ishifts[4 * j + 0])] ^
+ AES_Td1[st.B(AES_ishifts[4 * j + 1])] ^
+ AES_Td2[st.B(AES_ishifts[4 * j + 2])] ^
+ AES_Td3[st.B(AES_ishifts[4 * j + 3])]);
}
}
@@ -2273,8 +2271,8 @@ void glue(helper_aesdeclast, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
Reg st = *d;
Reg rk = *s;
- for (i = 0; i < 16; i++) {
- d->B(i) = rk.B(i) ^ (AES_isbox[st.B(AES_ishifts[i])]);
+ for (i = 0; i < 8 << SHIFT; i++) {
+ d->B(i) = rk.B(i) ^ (AES_isbox[st.B(AES_ishifts[i & 15] + (i & ~15))]);
}
}
@@ -2284,11 +2282,12 @@ void glue(helper_aesenc, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
Reg st = *d;
Reg rk = *s;
- for (i = 0 ; i < 4 ; i++) {
- d->L(i) = rk.L(i) ^ bswap32(AES_Te0[st.B(AES_shifts[4*i+0])] ^
- AES_Te1[st.B(AES_shifts[4*i+1])] ^
- AES_Te2[st.B(AES_shifts[4*i+2])] ^
- AES_Te3[st.B(AES_shifts[4*i+3])]);
+ for (i = 0 ; i < 2 << SHIFT ; i++) {
+ int j = i & 3;
+ d->L(i) = rk.L(i) ^ bswap32(AES_Te0[st.B(AES_shifts[4 * j + 0])] ^
+ AES_Te1[st.B(AES_shifts[4 * j + 1])] ^
+ AES_Te2[st.B(AES_shifts[4 * j + 2])] ^
+ AES_Te3[st.B(AES_shifts[4 * j + 3])]);
}
}
@@ -2298,22 +2297,22 @@ void glue(helper_aesenclast, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
Reg st = *d;
Reg rk = *s;
- for (i = 0; i < 16; i++) {
- d->B(i) = rk.B(i) ^ (AES_sbox[st.B(AES_shifts[i])]);
+ for (i = 0; i < 8 << SHIFT; i++) {
+ d->B(i) = rk.B(i) ^ (AES_sbox[st.B(AES_shifts[i & 15] + (i & ~15))]);
}
-
}
+#if SHIFT == 1
void glue(helper_aesimc, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
{
int i;
Reg tmp = *s;
for (i = 0 ; i < 4 ; i++) {
- d->L(i) = bswap32(AES_imc[tmp.B(4*i+0)][0] ^
- AES_imc[tmp.B(4*i+1)][1] ^
- AES_imc[tmp.B(4*i+2)][2] ^
- AES_imc[tmp.B(4*i+3)][3]);
+ d->L(i) = bswap32(AES_imc[tmp.B(4 * i + 0)][0] ^
+ AES_imc[tmp.B(4 * i + 1)][1] ^
+ AES_imc[tmp.B(4 * i + 2)][2] ^
+ AES_imc[tmp.B(4 * i + 3)][3]);
}
}
@@ -2331,6 +2330,9 @@ void glue(helper_aeskeygenassist, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
d->L(3) = (d->L(2) << 24 | d->L(2) >> 8) ^ ctrl;
}
#endif
+#endif
+
+#undef SSE_HELPER_S
#undef SHIFT
#undef XMM_ONLY
@@ -2340,4 +2342,3 @@ void glue(helper_aeskeygenassist, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
#undef L
#undef Q
#undef SUFFIX
-#undef SIZE
generated by cgit v1.2.3 (git 2.26.2) at 2024-12-01 04:56:55 +0000