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

2018-02-06 Thread Alex Bennée 

Richard Henderson  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 

Reviewed-by: Alex Bennée 

> ---
>  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

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

2018-01-25 Thread Richard Henderson 
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 
---
 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;