The vector unmasked unit-stride and whole register load/store
instructions will load/store continuous memory. If the endian of both
the host and guest architecture are the same, then we can group the
element load/store to load/store more data at a time.
Signed-off-by: Max Chou <max.chou@sifive.com>
---
target/riscv/vector_helper.c | 77 +++++++++++++++++++++++++++++-------
1 file changed, 63 insertions(+), 14 deletions(-)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 59009a940ff..654d5e111f3 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -189,6 +189,45 @@ GEN_VEXT_ST_ELEM(ste_h, uint16_t, H2, stw)
GEN_VEXT_ST_ELEM(ste_w, uint32_t, H4, stl)
GEN_VEXT_ST_ELEM(ste_d, uint64_t, H8, stq)
+static inline QEMU_ALWAYS_INLINE void
+vext_continus_ldst_tlb(CPURISCVState *env, vext_ldst_elem_fn_tlb *ldst_tlb,
+ void *vd, uint32_t evl, target_ulong addr,
+ uint32_t reg_start, uintptr_t ra, uint32_t esz,
+ bool is_load)
+{
+ uint32_t i;
+ for (i = env->vstart; i < evl; env->vstart = ++i, addr += esz) {
+ ldst_tlb(env, adjust_addr(env, addr), i, vd, ra);
+ }
+}
+
+static inline QEMU_ALWAYS_INLINE void
+vext_continus_ldst_host(CPURISCVState *env, vext_ldst_elem_fn_host *ldst_host,
+ void *vd, uint32_t evl, uint32_t reg_start, void *host,
+ uint32_t esz, bool is_load)
+{
+#if HOST_BIG_ENDIAN
+ for (; reg_start < evl; reg_start++, host += esz) {
+ ldst_host(vd, reg_start, host);
+ }
+#else
+ if (esz == 1) {
+ uint32_t byte_offset = reg_start * esz;
+ uint32_t size = (evl - reg_start) * esz;
+
+ if (is_load) {
+ memcpy(vd + byte_offset, host, size);
+ } else {
+ memcpy(host, vd + byte_offset, size);
+ }
+ } else {
+ for (; reg_start < evl; reg_start++, host += esz) {
+ ldst_host(vd, reg_start, host);
+ }
+ }
+#endif
+}
+
static void vext_set_tail_elems_1s(target_ulong vl, void *vd,
uint32_t desc, uint32_t nf,
uint32_t esz, uint32_t max_elems)
@@ -297,24 +336,34 @@ vext_page_ldst_us(CPURISCVState *env, void *vd, target_ulong addr,
mmu_index, true, &host, ra);
if (flags == 0) {
- for (i = env->vstart; i < evl; ++i) {
- k = 0;
- while (k < nf) {
- ldst_host(vd, i + k * max_elems, host);
- host += esz;
- k++;
+ if (nf == 1) {
+ vext_continus_ldst_host(env, ldst_host, vd, evl, env->vstart, host,
+ esz, is_load);
+ } else {
+ for (i = env->vstart; i < evl; ++i) {
+ k = 0;
+ while (k < nf) {
+ ldst_host(vd, i + k * max_elems, host);
+ host += esz;
+ k++;
+ }
}
}
env->vstart += elems;
} else {
- /* load bytes from guest memory */
- for (i = env->vstart; i < evl; env->vstart = ++i) {
- k = 0;
- while (k < nf) {
- ldst_tlb(env, adjust_addr(env, addr), i + k * max_elems, vd,
- ra);
- addr += esz;
- k++;
+ if (nf == 1) {
+ vext_continus_ldst_tlb(env, ldst_tlb, vd, evl, addr, env->vstart,
+ ra, esz, is_load);
+ } else {
+ /* load bytes from guest memory */
+ for (i = env->vstart; i < evl; env->vstart = ++i) {
+ k = 0;
+ while (k < nf) {
+ ldst_tlb(env, adjust_addr(env, addr), i + k * max_elems,
+ vd, ra);
+ addr += esz;
+ k++;
+ }
}
}
}
--
2.34.1
On 9/18/24 2:14 PM, Max Chou wrote:
> The vector unmasked unit-stride and whole register load/store
> instructions will load/store continuous memory. If the endian of both
> the host and guest architecture are the same, then we can group the
> element load/store to load/store more data at a time.
>
> Signed-off-by: Max Chou <max.chou@sifive.com>
> ---
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
> target/riscv/vector_helper.c | 77 +++++++++++++++++++++++++++++-------
> 1 file changed, 63 insertions(+), 14 deletions(-)
>
> diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
> index 59009a940ff..654d5e111f3 100644
> --- a/target/riscv/vector_helper.c
> +++ b/target/riscv/vector_helper.c
> @@ -189,6 +189,45 @@ GEN_VEXT_ST_ELEM(ste_h, uint16_t, H2, stw)
> GEN_VEXT_ST_ELEM(ste_w, uint32_t, H4, stl)
> GEN_VEXT_ST_ELEM(ste_d, uint64_t, H8, stq)
>
> +static inline QEMU_ALWAYS_INLINE void
> +vext_continus_ldst_tlb(CPURISCVState *env, vext_ldst_elem_fn_tlb *ldst_tlb,
> + void *vd, uint32_t evl, target_ulong addr,
> + uint32_t reg_start, uintptr_t ra, uint32_t esz,
> + bool is_load)
> +{
> + uint32_t i;
> + for (i = env->vstart; i < evl; env->vstart = ++i, addr += esz) {
> + ldst_tlb(env, adjust_addr(env, addr), i, vd, ra);
> + }
> +}
> +
> +static inline QEMU_ALWAYS_INLINE void
> +vext_continus_ldst_host(CPURISCVState *env, vext_ldst_elem_fn_host *ldst_host,
> + void *vd, uint32_t evl, uint32_t reg_start, void *host,
> + uint32_t esz, bool is_load)
> +{
> +#if HOST_BIG_ENDIAN
> + for (; reg_start < evl; reg_start++, host += esz) {
> + ldst_host(vd, reg_start, host);
> + }
> +#else
> + if (esz == 1) {
> + uint32_t byte_offset = reg_start * esz;
> + uint32_t size = (evl - reg_start) * esz;
> +
> + if (is_load) {
> + memcpy(vd + byte_offset, host, size);
> + } else {
> + memcpy(host, vd + byte_offset, size);
> + }
> + } else {
> + for (; reg_start < evl; reg_start++, host += esz) {
> + ldst_host(vd, reg_start, host);
> + }
> + }
> +#endif
> +}
> +
> static void vext_set_tail_elems_1s(target_ulong vl, void *vd,
> uint32_t desc, uint32_t nf,
> uint32_t esz, uint32_t max_elems)
> @@ -297,24 +336,34 @@ vext_page_ldst_us(CPURISCVState *env, void *vd, target_ulong addr,
> mmu_index, true, &host, ra);
>
> if (flags == 0) {
> - for (i = env->vstart; i < evl; ++i) {
> - k = 0;
> - while (k < nf) {
> - ldst_host(vd, i + k * max_elems, host);
> - host += esz;
> - k++;
> + if (nf == 1) {
> + vext_continus_ldst_host(env, ldst_host, vd, evl, env->vstart, host,
> + esz, is_load);
> + } else {
> + for (i = env->vstart; i < evl; ++i) {
> + k = 0;
> + while (k < nf) {
> + ldst_host(vd, i + k * max_elems, host);
> + host += esz;
> + k++;
> + }
> }
> }
> env->vstart += elems;
> } else {
> - /* load bytes from guest memory */
> - for (i = env->vstart; i < evl; env->vstart = ++i) {
> - k = 0;
> - while (k < nf) {
> - ldst_tlb(env, adjust_addr(env, addr), i + k * max_elems, vd,
> - ra);
> - addr += esz;
> - k++;
> + if (nf == 1) {
> + vext_continus_ldst_tlb(env, ldst_tlb, vd, evl, addr, env->vstart,
> + ra, esz, is_load);
> + } else {
> + /* load bytes from guest memory */
> + for (i = env->vstart; i < evl; env->vstart = ++i) {
> + k = 0;
> + while (k < nf) {
> + ldst_tlb(env, adjust_addr(env, addr), i + k * max_elems,
> + vd, ra);
> + addr += esz;
> + k++;
> + }
> }
> }
> }
© 2016 - 2024 Red Hat, Inc.