LGTM, thanks :)
On Thu, Jun 1, 2023 at 3:20 PM juzhe.zh...@rivai.ai
<juzhe.zh...@rivai.ai> wrote:
>
> LGTM.
>
> We are waiting for FP16 vector to start floating-point auto-vectorizations
>
> Thanks so much.
>
>
> juzhe.zh...@rivai.ai
>
> From: pan2.li
> Date: 2023-06-01 15:17
> To: gcc-patches
> CC: juzhe.zhong; kito.cheng; pan2.li; yanzhang.wang
> Subject: [PATCH] RISC-V: Introduce vfloat16m{f}*_t and their machine mode.
> From: Pan Li <pan2...@intel.com>
>
> This patch would like to introduce the built-in type vfloat16m{f}*_t, as
> well as their machine mode VNx*HF. They depend on architecture zvfhmin
> or zvfh.
>
> When givn the zvfhmin or zvfh, the macro TARGET_VECTOR_ELEN_FP_16 will
> be true.
>
> The underlying PATCH will implement the zvfhmin extension based on this.
>
> Signed-off-by: Pan Li <pan2...@intel.com>
>
> gcc/ChangeLog:
>
> * common/config/riscv/riscv-common.cc: Add FP_16 mask to zvfhmin
> and zvfh.
> * config/riscv/genrvv-type-indexer.cc (valid_type): Allow FP16.
> (main): Disable FP16 tuple.
> * config/riscv/riscv-opts.h (MASK_VECTOR_ELEN_FP_16): New macro.
> (TARGET_VECTOR_ELEN_FP_16): Ditto.
> * config/riscv/riscv-vector-builtins.cc (check_required_extensions):
> Add FP16.
> * config/riscv/riscv-vector-builtins.def (vfloat16mf4_t): New type.
> (vfloat16mf2_t): Ditto.
> (vfloat16m1_t): Ditto.
> (vfloat16m2_t): Ditto.
> (vfloat16m4_t): Ditto.
> (vfloat16m8_t): Ditto.
> * config/riscv/riscv-vector-builtins.h (RVV_REQUIRE_ELEN_FP_16):
> New macro.
> * config/riscv/riscv-vector-switch.def (ENTRY): Allow FP16
> machine mode based on TARGET_VECTOR_ELEN_FP_16.
> ---
> gcc/common/config/riscv/riscv-common.cc | 2 ++
> gcc/config/riscv/genrvv-type-indexer.cc | 7 +++++--
> gcc/config/riscv/riscv-opts.h | 4 ++++
> gcc/config/riscv/riscv-vector-builtins.cc | 2 ++
> gcc/config/riscv/riscv-vector-builtins.def | 20 +++++++++++++++++++
> gcc/config/riscv/riscv-vector-builtins.h | 1 +
> gcc/config/riscv/riscv-vector-switch.def | 23 ++++++++++++++--------
> 7 files changed, 49 insertions(+), 10 deletions(-)
>
> diff --git a/gcc/common/config/riscv/riscv-common.cc
> b/gcc/common/config/riscv/riscv-common.cc
> index e6ed3df9ea6..3247d526c0a 100644
> --- a/gcc/common/config/riscv/riscv-common.cc
> +++ b/gcc/common/config/riscv/riscv-common.cc
> @@ -1248,6 +1248,8 @@ static const riscv_ext_flag_table_t
> riscv_ext_flag_table[] =
> {"zve64x", &gcc_options::x_riscv_vector_elen_flags, MASK_VECTOR_ELEN_64},
> {"zve64f", &gcc_options::x_riscv_vector_elen_flags,
> MASK_VECTOR_ELEN_FP_32},
> {"zve64d", &gcc_options::x_riscv_vector_elen_flags,
> MASK_VECTOR_ELEN_FP_64},
> + {"zvfhmin", &gcc_options::x_riscv_vector_elen_flags,
> MASK_VECTOR_ELEN_FP_16},
> + {"zvfh", &gcc_options::x_riscv_vector_elen_flags,
> MASK_VECTOR_ELEN_FP_16},
> {"zvl32b", &gcc_options::x_riscv_zvl_flags, MASK_ZVL32B},
> {"zvl64b", &gcc_options::x_riscv_zvl_flags, MASK_ZVL64B},
> diff --git a/gcc/config/riscv/genrvv-type-indexer.cc
> b/gcc/config/riscv/genrvv-type-indexer.cc
> index 18e1b375396..8fc93ceaab4 100644
> --- a/gcc/config/riscv/genrvv-type-indexer.cc
> +++ b/gcc/config/riscv/genrvv-type-indexer.cc
> @@ -54,7 +54,7 @@ valid_type (unsigned sew, int lmul_log2, bool float_p)
> case 8:
> return lmul_log2 >= -3 && !float_p;
> case 16:
> - return lmul_log2 >= -2 && !float_p;
> + return lmul_log2 >= -2;
> case 32:
> return lmul_log2 >= -1;
> case 64:
> @@ -73,6 +73,9 @@ valid_type (unsigned sew, int lmul_log2, unsigned nf, bool
> float_p)
> if (nf > 8 || nf < 1)
> return false;
> + if (sew == 16 && nf != 1 && float_p) // Disable FP16 tuple in temporarily.
> + return false;
> +
> switch (lmul_log2)
> {
> case 1:
> @@ -342,7 +345,7 @@ main (int argc, const char **argv)
> fprintf (fp, ")\n");
> }
> // Build for vfloat
> - for (unsigned sew : {32, 64})
> + for (unsigned sew : {16, 32, 64})
> for (int lmul_log2 : {-3, -2, -1, 0, 1, 2, 3})
> for (unsigned nf : {1, 2, 3, 4, 5, 6, 7, 8})
> {
> diff --git a/gcc/config/riscv/riscv-opts.h b/gcc/config/riscv/riscv-opts.h
> index 5f387d0e393..208a557b8ff 100644
> --- a/gcc/config/riscv/riscv-opts.h
> +++ b/gcc/config/riscv/riscv-opts.h
> @@ -154,6 +154,8 @@ enum riscv_entity
> #define MASK_VECTOR_ELEN_64 (1 << 1)
> #define MASK_VECTOR_ELEN_FP_32 (1 << 2)
> #define MASK_VECTOR_ELEN_FP_64 (1 << 3)
> +/* Align the bit index to riscv-vector-builtins.h. */
> +#define MASK_VECTOR_ELEN_FP_16 (1 << 6)
> #define TARGET_VECTOR_ELEN_32 \
> ((riscv_vector_elen_flags & MASK_VECTOR_ELEN_32) != 0)
> @@ -163,6 +165,8 @@ enum riscv_entity
> ((riscv_vector_elen_flags & MASK_VECTOR_ELEN_FP_32) != 0)
> #define TARGET_VECTOR_ELEN_FP_64 \
> ((riscv_vector_elen_flags & MASK_VECTOR_ELEN_FP_64) != 0)
> +#define TARGET_VECTOR_ELEN_FP_16 \
> + ((riscv_vector_elen_flags & MASK_VECTOR_ELEN_FP_16) != 0)
> #define MASK_ZVL32B (1 << 0)
> #define MASK_ZVL64B (1 << 1)
> diff --git a/gcc/config/riscv/riscv-vector-builtins.cc
> b/gcc/config/riscv/riscv-vector-builtins.cc
> index 9fea70709fd..43bf6d8f262 100644
> --- a/gcc/config/riscv/riscv-vector-builtins.cc
> +++ b/gcc/config/riscv/riscv-vector-builtins.cc
> @@ -2944,6 +2944,8 @@ check_required_extensions (const function_instance
> &instance)
> uint64_t riscv_isa_flags = 0;
> + if (TARGET_VECTOR_ELEN_FP_16)
> + riscv_isa_flags |= RVV_REQUIRE_ELEN_FP_16;
> if (TARGET_VECTOR_ELEN_FP_32)
> riscv_isa_flags |= RVV_REQUIRE_ELEN_FP_32;
> if (TARGET_VECTOR_ELEN_FP_64)
> diff --git a/gcc/config/riscv/riscv-vector-builtins.def
> b/gcc/config/riscv/riscv-vector-builtins.def
> index 61346e53d7b..149835f36ac 100644
> --- a/gcc/config/riscv/riscv-vector-builtins.def
> +++ b/gcc/config/riscv/riscv-vector-builtins.def
> @@ -490,6 +490,26 @@ DEF_RVV_TYPE (vint64m8_t, 15, __rvv_int64m8_t, int64,
> VNx16DI, VNx8DI, VOID, _i6
> DEF_RVV_TYPE (vuint64m8_t, 16, __rvv_uint64m8_t, uint64, VNx16DI, VNx8DI,
> VOID, _u64m8,
> _u64, _e64m8)
> +/* Enabled if TARGET_VECTOR_ELEN_FP_16 && 9TARGET_ZVFH or TARGET_ZVFHMIN).
> */
> +/* LMUL = 1/4. */
> +DEF_RVV_TYPE (vfloat16mf4_t, 18, __rvv_float16mf4_t, float16, VNx2HF,
> VNx1HF, VOID,
> + _f16mf4, _f16, _e16mf4)
> +/* LMUL = 1/2. */
> +DEF_RVV_TYPE (vfloat16mf2_t, 18, __rvv_float16mf2_t, float16, VNx4HF,
> VNx2HF, VNx1HF,
> + _f16mf2, _f16, _e16mf2)
> +/* LMUL = 1. */
> +DEF_RVV_TYPE (vfloat16m1_t, 17, __rvv_float16m1_t, float16, VNx8HF, VNx4HF,
> VNx2HF,
> + _f16m1, _f16, _e16m1)
> +/* LMUL = 2. */
> +DEF_RVV_TYPE (vfloat16m2_t, 17, __rvv_float16m2_t, float16, VNx16HF, VNx8HF,
> VNx4HF,
> + _f16m2, _f16, _e16m2)
> +/* LMUL = 4. */
> +DEF_RVV_TYPE (vfloat16m4_t, 17, __rvv_float16m4_t, float16, VNx32HF,
> VNx16HF, VNx8HF,
> + _f16m4, _f16, _e16m4)
> +/* LMUL = 8. */
> +DEF_RVV_TYPE (vfloat16m8_t, 16, __rvv_float16m8_t, float16, VNx64HF,
> VNx32HF, VNx16HF,
> + _f16m8, _f16, _e16m8)
> +
> /* Disable all when !TARGET_VECTOR_ELEN_FP_32. */
> /* LMUL = 1/2:
> Only enble when TARGET_MIN_VLEN > 32.
> diff --git a/gcc/config/riscv/riscv-vector-builtins.h
> b/gcc/config/riscv/riscv-vector-builtins.h
> index 5d434579131..b0c3a42d820 100644
> --- a/gcc/config/riscv/riscv-vector-builtins.h
> +++ b/gcc/config/riscv/riscv-vector-builtins.h
> @@ -108,6 +108,7 @@ static const unsigned int CP_WRITE_CSR = 1U << 5;
> #define RVV_REQUIRE_ELEN_FP_64 (1 << 3) /* Require FP ELEN >= 64. */
> #define RVV_REQUIRE_FULL_V (1 << 4) /* Require Full 'V' extension. */
> #define RVV_REQUIRE_MIN_VLEN_64 (1 << 5) /* Require TARGET_MIN_VLEN >= 64. */
> +#define RVV_REQUIRE_ELEN_FP_16 (1 << 6) /* Require FP ELEN >= 32. */
> /* Enumerates the RVV operand types. */
> enum operand_type_index
> diff --git a/gcc/config/riscv/riscv-vector-switch.def
> b/gcc/config/riscv/riscv-vector-switch.def
> index 4b1c32de0a3..52f07709f99 100644
> --- a/gcc/config/riscv/riscv-vector-switch.def
> +++ b/gcc/config/riscv/riscv-vector-switch.def
> @@ -120,14 +120,21 @@ ENTRY (VNx4HI, true, LMUL_2, 8, LMUL_1, 16, LMUL_F2, 32)
> ENTRY (VNx2HI, true, LMUL_1, 16, LMUL_F2, 32, LMUL_F4, 64)
> ENTRY (VNx1HI, TARGET_MIN_VLEN < 128, LMUL_F2, 32, LMUL_F4, 64,
> LMUL_RESERVED, 0)
> -/* TODO:Disable all FP16 vector, enable them when 'zvfh' is supported. */
> -ENTRY (VNx64HF, false, LMUL_RESERVED, 0, LMUL_RESERVED, 0, LMUL_8, 2)
> -ENTRY (VNx32HF, false, LMUL_RESERVED, 0, LMUL_8, 2, LMUL_4, 4)
> -ENTRY (VNx16HF, false, LMUL_8, 2, LMUL_4, 4, LMUL_2, 8)
> -ENTRY (VNx8HF, false, LMUL_4, 4, LMUL_2, 8, LMUL_1, 16)
> -ENTRY (VNx4HF, false, LMUL_2, 8, LMUL_1, 16, LMUL_F2, 32)
> -ENTRY (VNx2HF, false, LMUL_1, 16, LMUL_F2, 32, LMUL_F4, 64)
> -ENTRY (VNx1HF, false, LMUL_F2, 32, LMUL_F4, 64, LMUL_RESERVED, 0)
> +/* SEW = 16 for float point. Enabled when 'zvfh' or 'zvfhmin' is given. */
> +ENTRY (VNx64HF, TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN >= 128, \
> + LMUL_RESERVED, 0, LMUL_RESERVED, 0, LMUL_8, 2)
> +ENTRY (VNx32HF, TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN > 32, \
> + LMUL_RESERVED, 0, LMUL_8, 2, LMUL_4, 4)
> +ENTRY (VNx16HF, TARGET_VECTOR_ELEN_FP_16, \
> + LMUL_8, 2, LMUL_4, 4, LMUL_2, 8)
> +ENTRY (VNx8HF, TARGET_VECTOR_ELEN_FP_16, \
> + LMUL_4, 4, LMUL_2, 8, LMUL_1, 16)
> +ENTRY (VNx4HF, TARGET_VECTOR_ELEN_FP_16, \
> + LMUL_2, 8, LMUL_1, 16, LMUL_F2, 32)
> +ENTRY (VNx2HF, TARGET_VECTOR_ELEN_FP_16, \
> + LMUL_1, 16, LMUL_F2, 32, LMUL_F4, 64)
> +ENTRY (VNx1HF, TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN < 128, \
> + LMUL_F2, 32, LMUL_F4, 64, LMUL_RESERVED, 0)
> /* SEW = 32. Disable VNx16SImode when TARGET_MIN_VLEN == 32.
> For single-precision floating-point, we need TARGET_VECTOR_ELEN_FP_32 to
> be
> --
> 2.34.1
>
>
