@@ -2261,7 +2261,9 @@ const struct powerpc_opcode powerpc_opcodes[] = {
{ "vmsumshs", VXA(4, 41), VXA_MASK, PPCVEC, { VD, VA, VB, VC } },
{ "vmsumubm", VXA(4, 36), VXA_MASK, PPCVEC, { VD, VA, VB, VC } },
{ "vmsumuhm", VXA(4, 38), VXA_MASK, PPCVEC, { VD, VA, VB, VC } },
+{ "vmsumudm", VXA(4, 35), VXA_MASK, PPCVEC, { VD, VA, VB, VC } },
{ "vmsumuhs", VXA(4, 39), VXA_MASK, PPCVEC, { VD, VA, VB, VC } },
+{ "vmsumcud", VXA(4, 23), VXA_MASK, PPCVEC, { VD, VA, VB, VC } },
{ "vmulesb", VX(4, 776), VX_MASK, PPCVEC, { VD, VA, VB } },
{ "vmulesh", VX(4, 840), VX_MASK, PPCVEC, { VD, VA, VB } },
{ "vmuleub", VX(4, 520), VX_MASK, PPCVEC, { VD, VA, VB } },
@@ -81,6 +81,8 @@ void muls64(uint64_t *phigh, uint64_t *plow, int64_t a, int64_t b);
void mulu64(uint64_t *phigh, uint64_t *plow, uint64_t a, uint64_t b);
int divu128(uint64_t *plow, uint64_t *phigh, uint64_t divisor);
int divs128(int64_t *plow, int64_t *phigh, int64_t divisor);
+void addu128(uint64_t ah, uint64_t al, uint64_t bh, uint64_t bl,
+ uint64_t *rh, uint64_t *rl, uint64_t *ca);
static inline uint64_t muldiv64(uint64_t a, uint32_t b, uint32_t c)
{
@@ -263,10 +263,12 @@ DEF_HELPER_3(vpkpx, void, avr, avr, avr)
DEF_HELPER_5(vmhaddshs, void, env, avr, avr, avr, avr)
DEF_HELPER_5(vmhraddshs, void, env, avr, avr, avr, avr)
DEF_HELPER_5(vmsumuhm, void, env, avr, avr, avr, avr)
+DEF_HELPER_5(vmsumudm, void, env, avr, avr, avr, avr)
DEF_HELPER_5(vmsumuhs, void, env, avr, avr, avr, avr)
DEF_HELPER_5(vmsumshm, void, env, avr, avr, avr, avr)
DEF_HELPER_5(vmsumshs, void, env, avr, avr, avr, avr)
-DEF_HELPER_4(vmladduhm, void, avr, avr, avr, avr)
+DEF_HELPER_5(vmsumcud, void, env, avr, avr, avr, avr)
+DEF_HELPER_5(vmladduhm, void, env, avr, avr, avr, avr)
DEF_HELPER_FLAGS_2(mtvscr, TCG_CALL_NO_RWG, void, env, i32)
DEF_HELPER_FLAGS_1(mfvscr, TCG_CALL_NO_RWG, i32, env)
DEF_HELPER_3(lvebx, void, env, avr, tl)
@@ -926,7 +926,8 @@ void helper_vmhraddshs(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a,
}
}
-void helper_vmladduhm(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c)
+void helper_vmladduhm(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a,
+ ppc_avr_t *b, ppc_avr_t *c)
{
int i;
@@ -1064,6 +1065,50 @@ void helper_vmsumuhs(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a,
}
}
+static void vmsumcudm(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b,
+ ppc_avr_t *c, bool ca)
+{
+#ifdef CONFIG_INT128
+ __uint128_t prod[2];
+ int i;
+
+ for (i = 0; i < 2; i++) {
+ prod[i] = (__uint128_t)(a->VsrD(i)) * (__uint128_t)(b->VsrD(i));
+ }
+ if (ca)
+ r->u128 = (~prod[0] < prod[1]) + (~c->u128 < (prod[0] + prod[1]));
+ else
+ r->u128 = prod[0] + prod[1] + c->u128;
+#else
+ uint64_t ah64, al64, bh64, bl64, ch64, cl64, rh64, rl64, th64, tl64, ca1, ca2;
+
+ ch64 = c->VsrD(0);
+ cl64 = c->VsrD(1);
+ mulu64(&al64, &ah64, a->VsrD(0), b->VsrD(0));
+ mulu64(&bl64, &bh64, a->VsrD(1), b->VsrD(1));
+ addu128(ah64, al64, bh64, bl64, &rh64, &rl64, &ca1);
+ addu128(rh64, rl64, ch64, cl64, &th64, &tl64, &ca2);
+ if (ca) {
+ r->VsrD(0) = 0;
+ r->VsrD(1) = ca1 + ca2;
+ } else {
+ r->VsrD(0) = th64;
+ r->VsrD(1) = tl64;
+ }
+#endif
+}
+
+void helper_vmsumudm(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a,
+ ppc_avr_t *b, ppc_avr_t *c)
+{
+ vmsumcudm(r, a, b, c, 0);
+}
+void helper_vmsumcud(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a,
+ ppc_avr_t *b, ppc_avr_t *c)
+{
+ vmsumcudm(r, a, b, c, 1);
+}
+
#define VMUL_DO_EVN(name, mul_element, mul_access, prod_access, cast) \
void helper_v##name(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) \
{ \
@@ -7281,7 +7281,6 @@ GEN_HANDLER(lvsl, 0x1f, 0x06, 0x00, 0x00000001, PPC_ALTIVEC),
GEN_HANDLER(lvsr, 0x1f, 0x06, 0x01, 0x00000001, PPC_ALTIVEC),
GEN_HANDLER(mfvscr, 0x04, 0x2, 0x18, 0x001ff800, PPC_ALTIVEC),
GEN_HANDLER(mtvscr, 0x04, 0x2, 0x19, 0x03ff0000, PPC_ALTIVEC),
-GEN_HANDLER(vmladduhm, 0x04, 0x11, 0xFF, 0x00000000, PPC_ALTIVEC),
#if defined(TARGET_PPC64)
GEN_HANDLER_E(maddhd_maddhdu, 0x04, 0x18, 0xFF, 0x00000000, PPC_NONE,
PPC2_ISA300),
@@ -1248,6 +1248,25 @@ static void gen_vsldoi(DisasContext *ctx)
tcg_temp_free_i32(sh);
}
+#define GEN_VAFORM(name, opc2) \
+static void glue(gen_, name)(DisasContext *ctx) \
+{ \
+ TCGv_ptr ra, rb, rc, rd; \
+ if (unlikely(!ctx->altivec_enabled)) { \
+ gen_exception(ctx, POWERPC_EXCP_VPU); \
+ return; \
+ } \
+ ra = gen_avr_ptr(rA(ctx->opcode)); \
+ rb = gen_avr_ptr(rB(ctx->opcode)); \
+ rc = gen_avr_ptr(rC(ctx->opcode)); \
+ rd = gen_avr_ptr(rD(ctx->opcode)); \
+ gen_helper_##name(cpu_env, rd, ra, rb, rc); \
+ tcg_temp_free_ptr(ra); \
+ tcg_temp_free_ptr(rb); \
+ tcg_temp_free_ptr(rc); \
+ tcg_temp_free_ptr(rd); \
+}
+
#define GEN_VAFORM_PAIRED(name0, name1, opc2) \
static void glue(gen_, name0##_##name1)(DisasContext *ctx) \
{ \
@@ -1272,24 +1291,8 @@ static void glue(gen_, name0##_##name1)(DisasContext *ctx) \
}
GEN_VAFORM_PAIRED(vmhaddshs, vmhraddshs, 16)
-
-static void gen_vmladduhm(DisasContext *ctx)
-{
- TCGv_ptr ra, rb, rc, rd;
- if (unlikely(!ctx->altivec_enabled)) {
- gen_exception(ctx, POWERPC_EXCP_VPU);
- return;
- }
- ra = gen_avr_ptr(rA(ctx->opcode));
- rb = gen_avr_ptr(rB(ctx->opcode));
- rc = gen_avr_ptr(rC(ctx->opcode));
- rd = gen_avr_ptr(rD(ctx->opcode));
- gen_helper_vmladduhm(rd, ra, rb, rc);
- tcg_temp_free_ptr(ra);
- tcg_temp_free_ptr(rb);
- tcg_temp_free_ptr(rc);
- tcg_temp_free_ptr(rd);
-}
+GEN_VAFORM(vmsumcud, 11)
+GEN_VAFORM_PAIRED(vmladduhm, vmsumudm, 17)
static void gen_vpermr(DisasContext *ctx)
{
@@ -276,6 +276,8 @@ GEN_VAFORM_PAIRED(vmsumuhm, vmsumuhs, 19),
GEN_VAFORM_PAIRED(vmsumshm, vmsumshs, 20),
GEN_VAFORM_PAIRED(vsel, vperm, 21),
GEN_VAFORM_PAIRED(vmaddfp, vnmsubfp, 23),
+GEN_HANDLER(vmsumcud, 0x4, 11, 0xFF, 0x00000000, PPC_ALTIVEC),
+GEN_VAFORM_PAIRED(vmladduhm, vmsumudm, 17),
GEN_VXFORM_DUAL(vclzb, vpopcntb, 1, 28, PPC_NONE, PPC2_ALTIVEC_207),
GEN_VXFORM_DUAL(vclzh, vpopcnth, 1, 29, PPC_NONE, PPC2_ALTIVEC_207),
@@ -159,6 +159,19 @@ int divs128(int64_t *plow, int64_t *phigh, int64_t divisor)
return overflow;
}
+
+void addu128(uint64_t ah, uint64_t al, uint64_t bh, uint64_t bl,
+ uint64_t *rh, uint64_t *rl, uint64_t *ca)
+{
+ uint64_t lo = al + bl;
+ uint64_t hi = ah + bh + (~al < bl);
+ uint64_t hi_t = ah + bh;
+ uint64_t carry = (~ah < bh) + (~hi_t < (~al < bl));
+
+ *rl = lo;
+ *rh = hi;
+ *ca = carry;
+}
#endif
/**
vmsumudm (Power ISA 3.0) - Vector Multiply-Sum Unsigned Doubleword Modulo VA-form. vmsumcud (Power ISA 3.1) - Vector Multiply-Sum & write Carry-out Unsigned Doubleword VA-form. Signed-off-by: Lijun Pan <ljp@linux.ibm.com> --- disas/ppc.c | 2 ++ include/qemu/host-utils.h | 2 ++ target/ppc/helper.h | 4 ++- target/ppc/int_helper.c | 47 ++++++++++++++++++++++++++++- target/ppc/translate.c | 1 - target/ppc/translate/vmx-impl.inc.c | 39 +++++++++++++----------- target/ppc/translate/vmx-ops.inc.c | 2 ++ util/host-utils.c | 13 ++++++++ 8 files changed, 89 insertions(+), 21 deletions(-)