Re: [Qemu-devel] [PATCH v11 09/20] tcg: Add generic vector helpers with a scalar operand

["Alex Bennée" <alex.bennee@linaro.org>]

Richard Henderson <richard.henderson@linaro.org> writes:

> Use dup to convert a non-constant scalar to a third vector.
>
> Add addition, multiplication, and logical operations with an immediate.
> Add addition, subtraction, multiplication, and logical operations with
> a non-constant scalar.  Allow for the front-end to build operations in
> which the scalar operand comes first.
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>

> ---
>  accel/tcg/tcg-runtime.h      |  19 +++
>  tcg/tcg-op-gvec.h            |  59 ++++++-
>  accel/tcg/tcg-runtime-gvec.c | 180 +++++++++++++++++++++
>  tcg/tcg-op-gvec.c            | 361 ++++++++++++++++++++++++++++++++++++++++++-
>  4 files changed, 617 insertions(+), 2 deletions(-)
>
> diff --git a/accel/tcg/tcg-runtime.h b/accel/tcg/tcg-runtime.h
> index f224a975e8..2536959a18 100644
> --- a/accel/tcg/tcg-runtime.h
> +++ b/accel/tcg/tcg-runtime.h
> @@ -147,16 +147,31 @@ DEF_HELPER_FLAGS_4(gvec_add16, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
>  DEF_HELPER_FLAGS_4(gvec_add32, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
>  DEF_HELPER_FLAGS_4(gvec_add64, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
>
> +DEF_HELPER_FLAGS_4(gvec_adds8, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
> +DEF_HELPER_FLAGS_4(gvec_adds16, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
> +DEF_HELPER_FLAGS_4(gvec_adds32, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
> +DEF_HELPER_FLAGS_4(gvec_adds64, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
> +
>  DEF_HELPER_FLAGS_4(gvec_sub8, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
>  DEF_HELPER_FLAGS_4(gvec_sub16, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
>  DEF_HELPER_FLAGS_4(gvec_sub32, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
>  DEF_HELPER_FLAGS_4(gvec_sub64, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
>
> +DEF_HELPER_FLAGS_4(gvec_subs8, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
> +DEF_HELPER_FLAGS_4(gvec_subs16, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
> +DEF_HELPER_FLAGS_4(gvec_subs32, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
> +DEF_HELPER_FLAGS_4(gvec_subs64, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
> +
>  DEF_HELPER_FLAGS_4(gvec_mul8, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
>  DEF_HELPER_FLAGS_4(gvec_mul16, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
>  DEF_HELPER_FLAGS_4(gvec_mul32, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
>  DEF_HELPER_FLAGS_4(gvec_mul64, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
>
> +DEF_HELPER_FLAGS_4(gvec_muls8, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
> +DEF_HELPER_FLAGS_4(gvec_muls16, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
> +DEF_HELPER_FLAGS_4(gvec_muls32, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
> +DEF_HELPER_FLAGS_4(gvec_muls64, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
> +
>  DEF_HELPER_FLAGS_4(gvec_ssadd8, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
>  DEF_HELPER_FLAGS_4(gvec_ssadd16, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
>  DEF_HELPER_FLAGS_4(gvec_ssadd32, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
> @@ -189,6 +204,10 @@ DEF_HELPER_FLAGS_4(gvec_xor, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
>  DEF_HELPER_FLAGS_4(gvec_andc, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
>  DEF_HELPER_FLAGS_4(gvec_orc, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
>
> +DEF_HELPER_FLAGS_4(gvec_ands, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
> +DEF_HELPER_FLAGS_4(gvec_xors, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
> +DEF_HELPER_FLAGS_4(gvec_ors, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
> +
>  DEF_HELPER_FLAGS_3(gvec_shl8i, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
>  DEF_HELPER_FLAGS_3(gvec_shl16i, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
>  DEF_HELPER_FLAGS_3(gvec_shl32i, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
> diff --git a/tcg/tcg-op-gvec.h b/tcg/tcg-op-gvec.h
> index 03ced440c2..ff43a29a0b 100644
> --- a/tcg/tcg-op-gvec.h
> +++ b/tcg/tcg-op-gvec.h
> @@ -35,6 +35,12 @@ void tcg_gen_gvec_2_ool(uint32_t dofs, uint32_t aofs,
>                          uint32_t oprsz, uint32_t maxsz, int32_t data,
>                          gen_helper_gvec_2 *fn);
>
> +/* Similarly, passing an extra data value.  */
> +typedef void gen_helper_gvec_2i(TCGv_ptr, TCGv_ptr, TCGv_i64, TCGv_i32);
> +void tcg_gen_gvec_2i_ool(uint32_t dofs, uint32_t aofs, TCGv_i64 c,
> +                         uint32_t oprsz, uint32_t maxsz, int32_t data,
> +                         gen_helper_gvec_2i *fn);
> +
>  /* Similarly, passing an extra pointer (e.g. env or float_status).  */
>  typedef void gen_helper_gvec_2_ptr(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32);
>  void tcg_gen_gvec_2_ptr(uint32_t dofs, uint32_t aofs,
> @@ -102,8 +108,10 @@ typedef struct {
>      void (*fni4)(TCGv_i32, TCGv_i32, int32_t);
>      /* Expand inline with a host vector type.  */
>      void (*fniv)(unsigned, TCGv_vec, TCGv_vec, int64_t);
> -    /* Expand out-of-line helper w/descriptor.  */
> +    /* Expand out-of-line helper w/descriptor, data in descriptor.  */
>      gen_helper_gvec_2 *fno;
> +    /* Expand out-of-line helper w/descriptor, data as argument.  */
> +    gen_helper_gvec_2i *fnoi;
>      /* The opcode, if any, to which this corresponds.  */
>      TCGOpcode opc;
>      /* The vector element size, if applicable.  */
> @@ -114,6 +122,27 @@ typedef struct {
>      bool load_dest;
>  } GVecGen2i;
>
> +typedef struct {
> +    /* Expand inline as a 64-bit or 32-bit integer.
> +       Only one of these will be non-NULL.  */
> +    void (*fni8)(TCGv_i64, TCGv_i64, TCGv_i64);
> +    void (*fni4)(TCGv_i32, TCGv_i32, TCGv_i32);
> +    /* Expand inline with a host vector type.  */
> +    void (*fniv)(unsigned, TCGv_vec, TCGv_vec, TCGv_vec);
> +    /* Expand out-of-line helper w/descriptor.  */
> +    gen_helper_gvec_2i *fno;
> +    /* The opcode, if any, to which this corresponds.  */
> +    TCGOpcode opc;
> +    /* The data argument to the out-of-line helper.  */
> +    uint32_t data;
> +    /* The vector element size, if applicable.  */
> +    uint8_t vece;
> +    /* Prefer i64 to v64.  */
> +    bool prefer_i64;
> +    /* Load scalar as 1st source operand.  */
> +    bool scalar_first;
> +} GVecGen2s;
> +
>  typedef struct {
>      /* Expand inline as a 64-bit or 32-bit integer.
>         Only one of these will be non-NULL.  */
> @@ -158,6 +187,8 @@ void tcg_gen_gvec_2(uint32_t dofs, uint32_t aofs,
>                      uint32_t oprsz, uint32_t maxsz, const GVecGen2 *);
>  void tcg_gen_gvec_2i(uint32_t dofs, uint32_t aofs, uint32_t oprsz,
>                       uint32_t maxsz, int64_t c, const GVecGen2i *);
> +void tcg_gen_gvec_2s(uint32_t dofs, uint32_t aofs, uint32_t oprsz,
> +                     uint32_t maxsz, TCGv_i64 c, const GVecGen2s *);
>  void tcg_gen_gvec_3(uint32_t dofs, uint32_t aofs, uint32_t bofs,
>                      uint32_t oprsz, uint32_t maxsz, const GVecGen3 *);
>  void tcg_gen_gvec_4(uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t cofs,
> @@ -179,6 +210,18 @@ void tcg_gen_gvec_sub(unsigned vece, uint32_t dofs, uint32_t aofs,
>  void tcg_gen_gvec_mul(unsigned vece, uint32_t dofs, uint32_t aofs,
>                        uint32_t bofs, uint32_t oprsz, uint32_t maxsz);
>
> +void tcg_gen_gvec_addi(unsigned vece, uint32_t dofs, uint32_t aofs,
> +                       int64_t c, uint32_t oprsz, uint32_t maxsz);
> +void tcg_gen_gvec_muli(unsigned vece, uint32_t dofs, uint32_t aofs,
> +                       int64_t c, uint32_t oprsz, uint32_t maxsz);
> +
> +void tcg_gen_gvec_adds(unsigned vece, uint32_t dofs, uint32_t aofs,
> +                       TCGv_i64 c, uint32_t oprsz, uint32_t maxsz);
> +void tcg_gen_gvec_subs(unsigned vece, uint32_t dofs, uint32_t aofs,
> +                       TCGv_i64 c, uint32_t oprsz, uint32_t maxsz);
> +void tcg_gen_gvec_muls(unsigned vece, uint32_t dofs, uint32_t aofs,
> +                       TCGv_i64 c, uint32_t oprsz, uint32_t maxsz);
> +
>  /* Saturated arithmetic.  */
>  void tcg_gen_gvec_ssadd(unsigned vece, uint32_t dofs, uint32_t aofs,
>                          uint32_t bofs, uint32_t oprsz, uint32_t maxsz);
> @@ -200,6 +243,20 @@ void tcg_gen_gvec_andc(unsigned vece, uint32_t dofs, uint32_t aofs,
>  void tcg_gen_gvec_orc(unsigned vece, uint32_t dofs, uint32_t aofs,
>                        uint32_t bofs, uint32_t oprsz, uint32_t maxsz);
>
> +void tcg_gen_gvec_andi(unsigned vece, uint32_t dofs, uint32_t aofs,
> +                       int64_t c, uint32_t oprsz, uint32_t maxsz);
> +void tcg_gen_gvec_xori(unsigned vece, uint32_t dofs, uint32_t aofs,
> +                       int64_t c, uint32_t oprsz, uint32_t maxsz);
> +void tcg_gen_gvec_ori(unsigned vece, uint32_t dofs, uint32_t aofs,
> +                      int64_t c, uint32_t oprsz, uint32_t maxsz);
> +
> +void tcg_gen_gvec_ands(unsigned vece, uint32_t dofs, uint32_t aofs,
> +                       TCGv_i64 c, uint32_t oprsz, uint32_t maxsz);
> +void tcg_gen_gvec_xors(unsigned vece, uint32_t dofs, uint32_t aofs,
> +                       TCGv_i64 c, uint32_t oprsz, uint32_t maxsz);
> +void tcg_gen_gvec_ors(unsigned vece, uint32_t dofs, uint32_t aofs,
> +                      TCGv_i64 c, uint32_t oprsz, uint32_t maxsz);
> +
>  void tcg_gen_gvec_dup_mem(unsigned vece, uint32_t dofs, uint32_t aofs,
>                            uint32_t s, uint32_t m);
>  void tcg_gen_gvec_dup_i32(unsigned vece, uint32_t dofs, uint32_t s,
> diff --git a/accel/tcg/tcg-runtime-gvec.c b/accel/tcg/tcg-runtime-gvec.c
> index e6f99babcd..8bf8d63912 100644
> --- a/accel/tcg/tcg-runtime-gvec.c
> +++ b/accel/tcg/tcg-runtime-gvec.c
> @@ -122,6 +122,54 @@ void HELPER(gvec_add64)(void *d, void *a, void *b, uint32_t desc)
>      clear_high(d, oprsz, desc);
>  }
>
> +void HELPER(gvec_adds8)(void *d, void *a, uint64_t b, uint32_t desc)
> +{
> +    intptr_t oprsz = simd_oprsz(desc);
> +    vec8 vecb = (vec8)DUP16(b);
> +    intptr_t i;
> +
> +    for (i = 0; i < oprsz; i += sizeof(vec8)) {
> +        *(vec8 *)(d + i) = *(vec8 *)(a + i) + vecb;
> +    }
> +    clear_high(d, oprsz, desc);
> +}
> +
> +void HELPER(gvec_adds16)(void *d, void *a, uint64_t b, uint32_t desc)
> +{
> +    intptr_t oprsz = simd_oprsz(desc);
> +    vec16 vecb = (vec16)DUP8(b);
> +    intptr_t i;
> +
> +    for (i = 0; i < oprsz; i += sizeof(vec16)) {
> +        *(vec16 *)(d + i) = *(vec16 *)(a + i) + vecb;
> +    }
> +    clear_high(d, oprsz, desc);
> +}
> +
> +void HELPER(gvec_adds32)(void *d, void *a, uint64_t b, uint32_t desc)
> +{
> +    intptr_t oprsz = simd_oprsz(desc);
> +    vec32 vecb = (vec32)DUP4(b);
> +    intptr_t i;
> +
> +    for (i = 0; i < oprsz; i += sizeof(vec32)) {
> +        *(vec32 *)(d + i) = *(vec32 *)(a + i) + vecb;
> +    }
> +    clear_high(d, oprsz, desc);
> +}
> +
> +void HELPER(gvec_adds64)(void *d, void *a, uint64_t b, uint32_t desc)
> +{
> +    intptr_t oprsz = simd_oprsz(desc);
> +    vec64 vecb = (vec64)DUP2(b);
> +    intptr_t i;
> +
> +    for (i = 0; i < oprsz; i += sizeof(vec64)) {
> +        *(vec64 *)(d + i) = *(vec64 *)(a + i) + vecb;
> +    }
> +    clear_high(d, oprsz, desc);
> +}
> +
>  void HELPER(gvec_sub8)(void *d, void *a, void *b, uint32_t desc)
>  {
>      intptr_t oprsz = simd_oprsz(desc);
> @@ -166,6 +214,54 @@ void HELPER(gvec_sub64)(void *d, void *a, void *b, uint32_t desc)
>      clear_high(d, oprsz, desc);
>  }
>
> +void HELPER(gvec_subs8)(void *d, void *a, uint64_t b, uint32_t desc)
> +{
> +    intptr_t oprsz = simd_oprsz(desc);
> +    vec8 vecb = (vec8)DUP16(b);
> +    intptr_t i;
> +
> +    for (i = 0; i < oprsz; i += sizeof(vec8)) {
> +        *(vec8 *)(d + i) = *(vec8 *)(a + i) - vecb;
> +    }
> +    clear_high(d, oprsz, desc);
> +}
> +
> +void HELPER(gvec_subs16)(void *d, void *a, uint64_t b, uint32_t desc)
> +{
> +    intptr_t oprsz = simd_oprsz(desc);
> +    vec16 vecb = (vec16)DUP8(b);
> +    intptr_t i;
> +
> +    for (i = 0; i < oprsz; i += sizeof(vec16)) {
> +        *(vec16 *)(d + i) = *(vec16 *)(a + i) - vecb;
> +    }
> +    clear_high(d, oprsz, desc);
> +}
> +
> +void HELPER(gvec_subs32)(void *d, void *a, uint64_t b, uint32_t desc)
> +{
> +    intptr_t oprsz = simd_oprsz(desc);
> +    vec32 vecb = (vec32)DUP4(b);
> +    intptr_t i;
> +
> +    for (i = 0; i < oprsz; i += sizeof(vec32)) {
> +        *(vec32 *)(d + i) = *(vec32 *)(a + i) - vecb;
> +    }
> +    clear_high(d, oprsz, desc);
> +}
> +
> +void HELPER(gvec_subs64)(void *d, void *a, uint64_t b, uint32_t desc)
> +{
> +    intptr_t oprsz = simd_oprsz(desc);
> +    vec64 vecb = (vec64)DUP2(b);
> +    intptr_t i;
> +
> +    for (i = 0; i < oprsz; i += sizeof(vec64)) {
> +        *(vec64 *)(d + i) = *(vec64 *)(a + i) - vecb;
> +    }
> +    clear_high(d, oprsz, desc);
> +}
> +
>  void HELPER(gvec_mul8)(void *d, void *a, void *b, uint32_t desc)
>  {
>      intptr_t oprsz = simd_oprsz(desc);
> @@ -210,6 +306,54 @@ void HELPER(gvec_mul64)(void *d, void *a, void *b, uint32_t desc)
>      clear_high(d, oprsz, desc);
>  }
>
> +void HELPER(gvec_muls8)(void *d, void *a, uint64_t b, uint32_t desc)
> +{
> +    intptr_t oprsz = simd_oprsz(desc);
> +    vec8 vecb = (vec8)DUP16(b);
> +    intptr_t i;
> +
> +    for (i = 0; i < oprsz; i += sizeof(vec8)) {
> +        *(vec8 *)(d + i) = *(vec8 *)(a + i) * vecb;
> +    }
> +    clear_high(d, oprsz, desc);
> +}
> +
> +void HELPER(gvec_muls16)(void *d, void *a, uint64_t b, uint32_t desc)
> +{
> +    intptr_t oprsz = simd_oprsz(desc);
> +    vec16 vecb = (vec16)DUP8(b);
> +    intptr_t i;
> +
> +    for (i = 0; i < oprsz; i += sizeof(vec16)) {
> +        *(vec16 *)(d + i) = *(vec16 *)(a + i) * vecb;
> +    }
> +    clear_high(d, oprsz, desc);
> +}
> +
> +void HELPER(gvec_muls32)(void *d, void *a, uint64_t b, uint32_t desc)
> +{
> +    intptr_t oprsz = simd_oprsz(desc);
> +    vec32 vecb = (vec32)DUP4(b);
> +    intptr_t i;
> +
> +    for (i = 0; i < oprsz; i += sizeof(vec32)) {
> +        *(vec32 *)(d + i) = *(vec32 *)(a + i) * vecb;
> +    }
> +    clear_high(d, oprsz, desc);
> +}
> +
> +void HELPER(gvec_muls64)(void *d, void *a, uint64_t b, uint32_t desc)
> +{
> +    intptr_t oprsz = simd_oprsz(desc);
> +    vec64 vecb = (vec64)DUP2(b);
> +    intptr_t i;
> +
> +    for (i = 0; i < oprsz; i += sizeof(vec64)) {
> +        *(vec64 *)(d + i) = *(vec64 *)(a + i) * vecb;
> +    }
> +    clear_high(d, oprsz, desc);
> +}
> +
>  void HELPER(gvec_neg8)(void *d, void *a, uint32_t desc)
>  {
>      intptr_t oprsz = simd_oprsz(desc);
> @@ -368,6 +512,42 @@ void HELPER(gvec_orc)(void *d, void *a, void *b, uint32_t desc)
>      clear_high(d, oprsz, desc);
>  }
>
> +void HELPER(gvec_ands)(void *d, void *a, uint64_t b, uint32_t desc)
> +{
> +    intptr_t oprsz = simd_oprsz(desc);
> +    vec64 vecb = (vec64)DUP2(b);
> +    intptr_t i;
> +
> +    for (i = 0; i < oprsz; i += sizeof(vec64)) {
> +        *(vec64 *)(d + i) = *(vec64 *)(a + i) & vecb;
> +    }
> +    clear_high(d, oprsz, desc);
> +}
> +
> +void HELPER(gvec_xors)(void *d, void *a, uint64_t b, uint32_t desc)
> +{
> +    intptr_t oprsz = simd_oprsz(desc);
> +    vec64 vecb = (vec64)DUP2(b);
> +    intptr_t i;
> +
> +    for (i = 0; i < oprsz; i += sizeof(vec64)) {
> +        *(vec64 *)(d + i) = *(vec64 *)(a + i) ^ vecb;
> +    }
> +    clear_high(d, oprsz, desc);
> +}
> +
> +void HELPER(gvec_ors)(void *d, void *a, uint64_t b, uint32_t desc)
> +{
> +    intptr_t oprsz = simd_oprsz(desc);
> +    vec64 vecb = (vec64)DUP2(b);
> +    intptr_t i;
> +
> +    for (i = 0; i < oprsz; i += sizeof(vec64)) {
> +        *(vec64 *)(d + i) = *(vec64 *)(a + i) | vecb;
> +    }
> +    clear_high(d, oprsz, desc);
> +}
> +
>  void HELPER(gvec_shl8i)(void *d, void *a, uint32_t desc)
>  {
>      intptr_t oprsz = simd_oprsz(desc);
> diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c
> index f621422646..082698f87f 100644
> --- a/tcg/tcg-op-gvec.c
> +++ b/tcg/tcg-op-gvec.c
> @@ -103,6 +103,28 @@ void tcg_gen_gvec_2_ool(uint32_t dofs, uint32_t aofs,
>      tcg_temp_free_i32(desc);
>  }
>
> +/* Generate a call to a gvec-style helper with two vector operands
> +   and one scalar operand.  */
> +void tcg_gen_gvec_2i_ool(uint32_t dofs, uint32_t aofs, TCGv_i64 c,
> +                         uint32_t oprsz, uint32_t maxsz, int32_t data,
> +                         gen_helper_gvec_2i *fn)
> +{
> +    TCGv_ptr a0, a1;
> +    TCGv_i32 desc = tcg_const_i32(simd_desc(oprsz, maxsz, data));
> +
> +    a0 = tcg_temp_new_ptr();
> +    a1 = tcg_temp_new_ptr();
> +
> +    tcg_gen_addi_ptr(a0, cpu_env, dofs);
> +    tcg_gen_addi_ptr(a1, cpu_env, aofs);
> +
> +    fn(a0, a1, c, desc);
> +
> +    tcg_temp_free_ptr(a0);
> +    tcg_temp_free_ptr(a1);
> +    tcg_temp_free_i32(desc);
> +}
> +
>  /* Generate a call to a gvec-style helper with three vector operands.  */
>  void tcg_gen_gvec_3_ool(uint32_t dofs, uint32_t aofs, uint32_t bofs,
>                          uint32_t oprsz, uint32_t maxsz, int32_t data,
> @@ -554,6 +576,27 @@ static void expand_2i_i32(uint32_t dofs, uint32_t aofs, uint32_t oprsz,
>      tcg_temp_free_i32(t1);
>  }
>
> +static void expand_2s_i32(uint32_t dofs, uint32_t aofs, uint32_t oprsz,
> +                          TCGv_i32 c, bool scalar_first,
> +                          void (*fni)(TCGv_i32, TCGv_i32, TCGv_i32))
> +{
> +    TCGv_i32 t0 = tcg_temp_new_i32();
> +    TCGv_i32 t1 = tcg_temp_new_i32();
> +    uint32_t i;
> +
> +    for (i = 0; i < oprsz; i += 4) {
> +        tcg_gen_ld_i32(t0, cpu_env, aofs + i);
> +        if (scalar_first) {
> +            fni(t1, c, t0);
> +        } else {
> +            fni(t1, t0, c);
> +        }
> +        tcg_gen_st_i32(t1, cpu_env, dofs + i);
> +    }
> +    tcg_temp_free_i32(t0);
> +    tcg_temp_free_i32(t1);
> +}
> +
>  /* Expand OPSZ bytes worth of three-operand operations using i32 elements.  */
>  static void expand_3_i32(uint32_t dofs, uint32_t aofs,
>                           uint32_t bofs, uint32_t oprsz, bool load_dest,
> @@ -637,6 +680,27 @@ static void expand_2i_i64(uint32_t dofs, uint32_t aofs, uint32_t oprsz,
>      tcg_temp_free_i64(t1);
>  }
>
> +static void expand_2s_i64(uint32_t dofs, uint32_t aofs, uint32_t oprsz,
> +                          TCGv_i64 c, bool scalar_first,
> +                          void (*fni)(TCGv_i64, TCGv_i64, TCGv_i64))
> +{
> +    TCGv_i64 t0 = tcg_temp_new_i64();
> +    TCGv_i64 t1 = tcg_temp_new_i64();
> +    uint32_t i;
> +
> +    for (i = 0; i < oprsz; i += 8) {
> +        tcg_gen_ld_i64(t0, cpu_env, aofs + i);
> +        if (scalar_first) {
> +            fni(t1, c, t0);
> +        } else {
> +            fni(t1, t0, c);
> +        }
> +        tcg_gen_st_i64(t1, cpu_env, dofs + i);
> +    }
> +    tcg_temp_free_i64(t0);
> +    tcg_temp_free_i64(t1);
> +}
> +
>  /* Expand OPSZ bytes worth of three-operand operations using i64 elements.  */
>  static void expand_3_i64(uint32_t dofs, uint32_t aofs,
>                           uint32_t bofs, uint32_t oprsz, bool load_dest,
> @@ -724,6 +788,28 @@ static void expand_2i_vec(unsigned vece, uint32_t dofs, uint32_t aofs,
>      tcg_temp_free_vec(t1);
>  }
>
> +static void expand_2s_vec(unsigned vece, uint32_t dofs, uint32_t aofs,
> +                          uint32_t oprsz, uint32_t tysz, TCGType type,
> +                          TCGv_vec c, bool scalar_first,
> +                          void (*fni)(unsigned, TCGv_vec, TCGv_vec, TCGv_vec))
> +{
> +    TCGv_vec t0 = tcg_temp_new_vec(type);
> +    TCGv_vec t1 = tcg_temp_new_vec(type);
> +    uint32_t i;
> +
> +    for (i = 0; i < oprsz; i += tysz) {
> +        tcg_gen_ld_vec(t0, cpu_env, aofs + i);
> +        if (scalar_first) {
> +            fni(vece, t1, c, t0);
> +        } else {
> +            fni(vece, t1, t0, c);
> +        }
> +        tcg_gen_st_vec(t1, cpu_env, dofs + i);
> +    }
> +    tcg_temp_free_vec(t0);
> +    tcg_temp_free_vec(t1);
> +}
> +
>  /* Expand OPSZ bytes worth of three-operand operations using host vectors.  */
>  static void expand_3_vec(unsigned vece, uint32_t dofs, uint32_t aofs,
>                           uint32_t bofs, uint32_t oprsz,
> @@ -827,6 +913,7 @@ void tcg_gen_gvec_2(uint32_t dofs, uint32_t aofs,
>      }
>  }
>
> +/* Expand a vector operation with two vectors and an immediate.  */
>  void tcg_gen_gvec_2i(uint32_t dofs, uint32_t aofs, uint32_t oprsz,
>                       uint32_t maxsz, int64_t c, const GVecGen2i *g)
>  {
> @@ -866,7 +953,13 @@ void tcg_gen_gvec_2i(uint32_t dofs, uint32_t aofs, uint32_t oprsz,
>      } else if (g->fni4 && check_size_impl(oprsz, 4)) {
>          expand_2i_i32(dofs, aofs, oprsz, c, g->load_dest, g->fni4);
>      } else {
> -        tcg_gen_gvec_2_ool(dofs, aofs, oprsz, maxsz, c, g->fno);
> +        if (g->fno) {
> +            tcg_gen_gvec_2_ool(dofs, aofs, oprsz, maxsz, c, g->fno);
> +        } else {
> +            TCGv_i64 tcg_c = tcg_const_i64(c);
> +            tcg_gen_gvec_2i_ool(dofs, aofs, tcg_c, oprsz, maxsz, c, g->fnoi);
> +            tcg_temp_free_i64(tcg_c);
> +        }
>          return;
>      }
>
> @@ -876,6 +969,87 @@ void tcg_gen_gvec_2i(uint32_t dofs, uint32_t aofs, uint32_t oprsz,
>      }
>  }
>
> +/* Expand a vector operation with two vectors and a scalar.  */
> +void tcg_gen_gvec_2s(uint32_t dofs, uint32_t aofs, uint32_t oprsz,
> +                     uint32_t maxsz, TCGv_i64 c, const GVecGen2s *g)
> +{
> +    TCGType type;
> +
> +    check_size_align(oprsz, maxsz, dofs | aofs);
> +    check_overlap_2(dofs, aofs, maxsz);
> +
> +    type = 0;
> +    if (g->fniv) {
> +        if (TCG_TARGET_HAS_v256 && check_size_impl(oprsz, 32)) {
> +            type = TCG_TYPE_V256;
> +        } else if (TCG_TARGET_HAS_v128 && check_size_impl(oprsz, 16)) {
> +            type = TCG_TYPE_V128;
> +        } else if (TCG_TARGET_HAS_v64 && !g->prefer_i64
> +               && check_size_impl(oprsz, 8)) {
> +            type = TCG_TYPE_V64;
> +        }
> +    }
> +    if (type != 0) {
> +        TCGv_vec t_vec = tcg_temp_new_vec(type);
> +
> +        tcg_gen_dup_i64_vec(g->vece, t_vec, c);
> +
> +        /* Recall that ARM SVE allows vector sizes that are not a power of 2.
> +           Expand with successively smaller host vector sizes.  The intent is
> +           that e.g. oprsz == 80 would be expanded with 2x32 + 1x16.  */
> +        switch (type) {
> +        case TCG_TYPE_V256:
> +            {
> +                uint32_t some = QEMU_ALIGN_DOWN(oprsz, 32);
> +                expand_2s_vec(g->vece, dofs, aofs, some, 32, TCG_TYPE_V256,
> +                              t_vec, g->scalar_first, g->fniv);
> +                if (some == oprsz) {
> +                    break;
> +                }
> +                dofs += some;
> +                aofs += some;
> +                oprsz -= some;
> +                maxsz -= some;
> +            }
> +            /* fallthru */
> +
> +        case TCG_TYPE_V128:
> +            expand_2s_vec(g->vece, dofs, aofs, oprsz, 16, TCG_TYPE_V128,
> +                          t_vec, g->scalar_first, g->fniv);
> +            break;
> +
> +        case TCG_TYPE_V64:
> +            expand_2s_vec(g->vece, dofs, aofs, oprsz, 8, TCG_TYPE_V64,
> +                          t_vec, g->scalar_first, g->fniv);
> +            break;
> +
> +        default:
> +            g_assert_not_reached();
> +        }
> +        tcg_temp_free_vec(t_vec);
> +    } else if (g->fni8 && check_size_impl(oprsz, 8)) {
> +        TCGv_i64 t64 = tcg_temp_new_i64();
> +
> +        gen_dup_i64(g->vece, t64, c);
> +        expand_2s_i64(dofs, aofs, oprsz, t64, g->scalar_first, g->fni8);
> +        tcg_temp_free_i64(t64);
> +    } else if (g->fni4 && check_size_impl(oprsz, 4)) {
> +        TCGv_i32 t32 = tcg_temp_new_i32();
> +
> +        tcg_gen_extrl_i64_i32(t32, c);
> +        gen_dup_i32(g->vece, t32, t32);
> +        expand_2s_i32(dofs, aofs, oprsz, t32, g->scalar_first, g->fni4);
> +        tcg_temp_free_i32(t32);
> +    } else {
> +        tcg_gen_gvec_2i_ool(dofs, aofs, c, oprsz, maxsz, 0, g->fno);
> +        return;
> +    }
> +
> +    if (oprsz < maxsz) {
> +        expand_clr(dofs + oprsz, maxsz - oprsz);
> +    }
> +}
> +
>  /* Expand a vector three-operand operation.  */
>  void tcg_gen_gvec_3(uint32_t dofs, uint32_t aofs, uint32_t bofs,
>                      uint32_t oprsz, uint32_t maxsz, const GVecGen3 *g)
> @@ -1200,6 +1374,76 @@ void tcg_gen_gvec_add(unsigned vece, uint32_t dofs, uint32_t aofs,
>      tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g[vece]);
>  }
>
> +void tcg_gen_gvec_adds(unsigned vece, uint32_t dofs, uint32_t aofs,
> +                       TCGv_i64 c, uint32_t oprsz, uint32_t maxsz)
> +{
> +    static const GVecGen2s g[4] = {
> +        { .fni8 = tcg_gen_vec_add8_i64,
> +          .fniv = tcg_gen_add_vec,
> +          .fno = gen_helper_gvec_adds8,
> +          .opc = INDEX_op_add_vec,
> +          .vece = MO_8 },
> +        { .fni8 = tcg_gen_vec_add16_i64,
> +          .fniv = tcg_gen_add_vec,
> +          .fno = gen_helper_gvec_adds16,
> +          .opc = INDEX_op_add_vec,
> +          .vece = MO_16 },
> +        { .fni4 = tcg_gen_add_i32,
> +          .fniv = tcg_gen_add_vec,
> +          .fno = gen_helper_gvec_adds32,
> +          .opc = INDEX_op_add_vec,
> +          .vece = MO_32 },
> +        { .fni8 = tcg_gen_add_i64,
> +          .fniv = tcg_gen_add_vec,
> +          .fno = gen_helper_gvec_adds64,
> +          .opc = INDEX_op_add_vec,
> +          .prefer_i64 = TCG_TARGET_REG_BITS == 64,
> +          .vece = MO_64 },
> +    };
> +
> +    tcg_debug_assert(vece <= MO_64);
> +    tcg_gen_gvec_2s(dofs, aofs, oprsz, maxsz, c, &g[vece]);
> +}
> +
> +void tcg_gen_gvec_addi(unsigned vece, uint32_t dofs, uint32_t aofs,
> +                       int64_t c, uint32_t oprsz, uint32_t maxsz)
> +{
> +    TCGv_i64 tmp = tcg_const_i64(c);
> +    tcg_gen_gvec_adds(vece, dofs, aofs, tmp, oprsz, maxsz);
> +    tcg_temp_free_i64(tmp);
> +}
> +
> +void tcg_gen_gvec_subs(unsigned vece, uint32_t dofs, uint32_t aofs,
> +                       TCGv_i64 c, uint32_t oprsz, uint32_t maxsz)
> +{
> +    static const GVecGen2s g[4] = {
> +        { .fni8 = tcg_gen_vec_sub8_i64,
> +          .fniv = tcg_gen_sub_vec,
> +          .fno = gen_helper_gvec_subs8,
> +          .opc = INDEX_op_sub_vec,
> +          .vece = MO_8 },
> +        { .fni8 = tcg_gen_vec_sub16_i64,
> +          .fniv = tcg_gen_sub_vec,
> +          .fno = gen_helper_gvec_subs16,
> +          .opc = INDEX_op_sub_vec,
> +          .vece = MO_16 },
> +        { .fni4 = tcg_gen_sub_i32,
> +          .fniv = tcg_gen_sub_vec,
> +          .fno = gen_helper_gvec_subs32,
> +          .opc = INDEX_op_sub_vec,
> +          .vece = MO_32 },
> +        { .fni8 = tcg_gen_sub_i64,
> +          .fniv = tcg_gen_sub_vec,
> +          .fno = gen_helper_gvec_subs64,
> +          .opc = INDEX_op_sub_vec,
> +          .prefer_i64 = TCG_TARGET_REG_BITS == 64,
> +          .vece = MO_64 },
> +    };
> +
> +    tcg_debug_assert(vece <= MO_64);
> +    tcg_gen_gvec_2s(dofs, aofs, oprsz, maxsz, c, &g[vece]);
> +}
> +
>  /* Perform a vector subtraction using normal subtraction and a mask.
>     Compare gen_addv_mask above.  */
>  static void gen_subv_mask(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b, TCGv_i64 m)
> @@ -1308,6 +1552,43 @@ void tcg_gen_gvec_mul(unsigned vece, uint32_t dofs, uint32_t aofs,
>      tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g[vece]);
>  }
>
> +void tcg_gen_gvec_muls(unsigned vece, uint32_t dofs, uint32_t aofs,
> +                       TCGv_i64 c, uint32_t oprsz, uint32_t maxsz)
> +{
> +    static const GVecGen2s g[4] = {
> +        { .fniv = tcg_gen_mul_vec,
> +          .fno = gen_helper_gvec_muls8,
> +          .opc = INDEX_op_mul_vec,
> +          .vece = MO_8 },
> +        { .fniv = tcg_gen_mul_vec,
> +          .fno = gen_helper_gvec_muls16,
> +          .opc = INDEX_op_mul_vec,
> +          .vece = MO_16 },
> +        { .fni4 = tcg_gen_mul_i32,
> +          .fniv = tcg_gen_mul_vec,
> +          .fno = gen_helper_gvec_muls32,
> +          .opc = INDEX_op_mul_vec,
> +          .vece = MO_32 },
> +        { .fni8 = tcg_gen_mul_i64,
> +          .fniv = tcg_gen_mul_vec,
> +          .fno = gen_helper_gvec_muls64,
> +          .opc = INDEX_op_mul_vec,
> +          .prefer_i64 = TCG_TARGET_REG_BITS == 64,
> +          .vece = MO_64 },
> +    };
> +
> +    tcg_debug_assert(vece <= MO_64);
> +    tcg_gen_gvec_2s(dofs, aofs, oprsz, maxsz, c, &g[vece]);
> +}
> +
> +void tcg_gen_gvec_muli(unsigned vece, uint32_t dofs, uint32_t aofs,
> +                       int64_t c, uint32_t oprsz, uint32_t maxsz)
> +{
> +    TCGv_i64 tmp = tcg_const_i64(c);
> +    tcg_gen_gvec_muls(vece, dofs, aofs, tmp, oprsz, maxsz);
> +    tcg_temp_free_i64(tmp);
> +}
> +
>  void tcg_gen_gvec_ssadd(unsigned vece, uint32_t dofs, uint32_t aofs,
>                          uint32_t bofs, uint32_t oprsz, uint32_t maxsz)
>  {
> @@ -1540,6 +1821,84 @@ void tcg_gen_gvec_orc(unsigned vece, uint32_t dofs, uint32_t aofs,
>      tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g);
>  }
>
> +static const GVecGen2s gop_ands = {
> +    .fni8 = tcg_gen_and_i64,
> +    .fniv = tcg_gen_and_vec,
> +    .fno = gen_helper_gvec_ands,
> +    .opc = INDEX_op_and_vec,
> +    .prefer_i64 = TCG_TARGET_REG_BITS == 64,
> +    .vece = MO_64
> +};
> +
> +void tcg_gen_gvec_ands(unsigned vece, uint32_t dofs, uint32_t aofs,
> +                       TCGv_i64 c, uint32_t oprsz, uint32_t maxsz)
> +{
> +    TCGv_i64 tmp = tcg_temp_new_i64();
> +    gen_dup_i64(vece, tmp, c);
> +    tcg_gen_gvec_2s(dofs, aofs, oprsz, maxsz, tmp, &gop_ands);
> +    tcg_temp_free_i64(tmp);
> +}
> +
> +void tcg_gen_gvec_andi(unsigned vece, uint32_t dofs, uint32_t aofs,
> +                       int64_t c, uint32_t oprsz, uint32_t maxsz)
> +{
> +    TCGv_i64 tmp = tcg_const_i64(dup_const(vece, c));
> +    tcg_gen_gvec_2s(dofs, aofs, oprsz, maxsz, tmp, &gop_ands);
> +    tcg_temp_free_i64(tmp);
> +}
> +
> +static const GVecGen2s gop_xors = {
> +    .fni8 = tcg_gen_xor_i64,
> +    .fniv = tcg_gen_xor_vec,
> +    .fno = gen_helper_gvec_xors,
> +    .opc = INDEX_op_xor_vec,
> +    .prefer_i64 = TCG_TARGET_REG_BITS == 64,
> +    .vece = MO_64
> +};
> +
> +void tcg_gen_gvec_xors(unsigned vece, uint32_t dofs, uint32_t aofs,
> +                       TCGv_i64 c, uint32_t oprsz, uint32_t maxsz)
> +{
> +    TCGv_i64 tmp = tcg_temp_new_i64();
> +    gen_dup_i64(vece, tmp, c);
> +    tcg_gen_gvec_2s(dofs, aofs, oprsz, maxsz, tmp, &gop_xors);
> +    tcg_temp_free_i64(tmp);
> +}
> +
> +void tcg_gen_gvec_xori(unsigned vece, uint32_t dofs, uint32_t aofs,
> +                       int64_t c, uint32_t oprsz, uint32_t maxsz)
> +{
> +    TCGv_i64 tmp = tcg_const_i64(dup_const(vece, c));
> +    tcg_gen_gvec_2s(dofs, aofs, oprsz, maxsz, tmp, &gop_xors);
> +    tcg_temp_free_i64(tmp);
> +}
> +
> +static const GVecGen2s gop_ors = {
> +    .fni8 = tcg_gen_or_i64,
> +    .fniv = tcg_gen_or_vec,
> +    .fno = gen_helper_gvec_ors,
> +    .opc = INDEX_op_or_vec,
> +    .prefer_i64 = TCG_TARGET_REG_BITS == 64,
> +    .vece = MO_64
> +};
> +
> +void tcg_gen_gvec_ors(unsigned vece, uint32_t dofs, uint32_t aofs,
> +                      TCGv_i64 c, uint32_t oprsz, uint32_t maxsz)
> +{
> +    TCGv_i64 tmp = tcg_temp_new_i64();
> +    gen_dup_i64(vece, tmp, c);
> +    tcg_gen_gvec_2s(dofs, aofs, oprsz, maxsz, tmp, &gop_ors);
> +    tcg_temp_free_i64(tmp);
> +}
> +
> +void tcg_gen_gvec_ori(unsigned vece, uint32_t dofs, uint32_t aofs,
> +                      int64_t c, uint32_t oprsz, uint32_t maxsz)
> +{
> +    TCGv_i64 tmp = tcg_const_i64(dup_const(vece, c));
> +    tcg_gen_gvec_2s(dofs, aofs, oprsz, maxsz, tmp, &gop_ors);
> +    tcg_temp_free_i64(tmp);
> +}
> +
>  void tcg_gen_vec_shl8i_i64(TCGv_i64 d, TCGv_i64 a, int64_t c)
>  {
>      uint64_t mask = dup_const(MO_8, 0xff << c);


--
Alex Bennée