From: Juzhe-Zhong <juzhe.zh...@rivai.ai> gcc/ChangeLog:
* config/riscv/riscv-modes.def (FLOAT_MODE): Add chunk 128 support. (VECTOR_BOOL_MODE): Ditto. (ADJUST_NUNITS): Ditto. (ADJUST_ALIGNMENT): Ditto. (ADJUST_BYTESIZE): Ditto. (ADJUST_PRECISION): Ditto. (RVV_MODES): Ditto. (VECTOR_MODE_WITH_PREFIX): Ditto. * config/riscv/riscv-v.cc (ENTRY): Ditto. (get_vlmul): Ditto. (get_ratio): Ditto. * config/riscv/riscv-vector-builtins.cc (DEF_RVV_TYPE): Ditto. * config/riscv/riscv-vector-builtins.def (DEF_RVV_TYPE): Ditto. (vbool64_t): Ditto. (vbool32_t): Ditto. (vbool16_t): Ditto. (vbool8_t): Ditto. (vbool4_t): Ditto. (vbool2_t): Ditto. (vbool1_t): Ditto. (vint8mf8_t): Ditto. (vuint8mf8_t): Ditto. (vint8mf4_t): Ditto. (vuint8mf4_t): Ditto. (vint8mf2_t): Ditto. (vuint8mf2_t): Ditto. (vint8m1_t): Ditto. (vuint8m1_t): Ditto. (vint8m2_t): Ditto. (vuint8m2_t): Ditto. (vint8m4_t): Ditto. (vuint8m4_t): Ditto. (vint8m8_t): Ditto. (vuint8m8_t): Ditto. (vint16mf4_t): Ditto. (vuint16mf4_t): Ditto. (vint16mf2_t): Ditto. (vuint16mf2_t): Ditto. (vint16m1_t): Ditto. (vuint16m1_t): Ditto. (vint16m2_t): Ditto. (vuint16m2_t): Ditto. (vint16m4_t): Ditto. (vuint16m4_t): Ditto. (vint16m8_t): Ditto. (vuint16m8_t): Ditto. (vint32mf2_t): Ditto. (vuint32mf2_t): Ditto. (vint32m1_t): Ditto. (vuint32m1_t): Ditto. (vint32m2_t): Ditto. (vuint32m2_t): Ditto. (vint32m4_t): Ditto. (vuint32m4_t): Ditto. (vint32m8_t): Ditto. (vuint32m8_t): Ditto. (vint64m1_t): Ditto. (vuint64m1_t): Ditto. (vint64m2_t): Ditto. (vuint64m2_t): Ditto. (vint64m4_t): Ditto. (vuint64m4_t): Ditto. (vint64m8_t): Ditto. (vuint64m8_t): Ditto. (vfloat32mf2_t): Ditto. (vfloat32m1_t): Ditto. (vfloat32m2_t): Ditto. (vfloat32m4_t): Ditto. (vfloat32m8_t): Ditto. (vfloat64m1_t): Ditto. (vfloat64m2_t): Ditto. (vfloat64m4_t): Ditto. (vfloat64m8_t): Ditto. * config/riscv/riscv-vector-switch.def (ENTRY): Ditto. * config/riscv/riscv.cc (riscv_legitimize_poly_move): Ditto. (riscv_convert_vector_bits): Ditto. * config/riscv/riscv.md: * config/riscv/vector-iterators.md: * config/riscv/vector.md (@pred_indexed_<order>store<VNX32_QH:mode><VNX32_QHI:mode>): Ditto. (@pred_indexed_<order>store<VNX32_QHS:mode><VNX32_QHSI:mode>): Ditto. (@pred_indexed_<order>store<VNX64_Q:mode><VNX64_Q:mode>): Ditto. (@pred_indexed_<order>store<VNX64_QH:mode><VNX64_QHI:mode>): Ditto. (@pred_indexed_<order>store<VNX128_Q:mode><VNX128_Q:mode>): Ditto. (@pred_reduc_<reduc><mode><vlmul1_zve64>): Ditto. (@pred_widen_reduc_plus<v_su><mode><vwlmul1_zve64>): Ditto. (@pred_reduc_plus<order><mode><vlmul1_zve64>): Ditto. (@pred_widen_reduc_plus<order><mode><vwlmul1_zve64>): Ditto. gcc/testsuite/ChangeLog: * gcc.target/riscv/rvv/base/pr108185-4.c: Adapt testcase. * gcc.target/riscv/rvv/base/spill-1.c: Ditto. * gcc.target/riscv/rvv/base/spill-11.c: Ditto. * gcc.target/riscv/rvv/base/spill-2.c: Ditto. * gcc.target/riscv/rvv/base/spill-3.c: Ditto. * gcc.target/riscv/rvv/base/spill-5.c: Ditto. * gcc.target/riscv/rvv/base/spill-9.c: Ditto. --- gcc/config/riscv/riscv-modes.def | 89 +-- gcc/config/riscv/riscv-v.cc | 17 +- gcc/config/riscv/riscv-vector-builtins.cc | 11 +- gcc/config/riscv/riscv-vector-builtins.def | 172 +++--- gcc/config/riscv/riscv-vector-switch.def | 105 ++-- gcc/config/riscv/riscv.cc | 12 +- gcc/config/riscv/riscv.md | 14 +- gcc/config/riscv/vector-iterators.md | 571 +++++++++++------- gcc/config/riscv/vector.md | 233 +++++-- .../gcc.target/riscv/rvv/base/pr108185-4.c | 2 +- .../gcc.target/riscv/rvv/base/spill-1.c | 2 +- .../gcc.target/riscv/rvv/base/spill-11.c | 2 +- .../gcc.target/riscv/rvv/base/spill-2.c | 2 +- .../gcc.target/riscv/rvv/base/spill-3.c | 2 +- .../gcc.target/riscv/rvv/base/spill-5.c | 2 +- .../gcc.target/riscv/rvv/base/spill-9.c | 2 +- 16 files changed, 783 insertions(+), 455 deletions(-) diff --git a/gcc/config/riscv/riscv-modes.def b/gcc/config/riscv/riscv-modes.def index 4cf7cf8b1c6..b1669609eec 100644 --- a/gcc/config/riscv/riscv-modes.def +++ b/gcc/config/riscv/riscv-modes.def @@ -27,15 +27,16 @@ FLOAT_MODE (TF, 16, ieee_quad_format); /* Encode the ratio of SEW/LMUL into the mask types. There are the following * mask types. */ -/* | Mode | MIN_VLEN = 32 | MIN_VLEN = 64 | - | | SEW/LMUL | SEW/LMUL | - | VNx1BI | 32 | 64 | - | VNx2BI | 16 | 32 | - | VNx4BI | 8 | 16 | - | VNx8BI | 4 | 8 | - | VNx16BI | 2 | 4 | - | VNx32BI | 1 | 2 | - | VNx64BI | N/A | 1 | */ +/* | Mode | MIN_VLEN = 32 | MIN_VLEN = 64 | MIN_VLEN = 128 | + | | SEW/LMUL | SEW/LMUL | SEW/LMUL | + | VNx1BI | 32 | 64 | 128 | + | VNx2BI | 16 | 32 | 64 | + | VNx4BI | 8 | 16 | 32 | + | VNx8BI | 4 | 8 | 16 | + | VNx16BI | 2 | 4 | 8 | + | VNx32BI | 1 | 2 | 4 | + | VNx64BI | N/A | 1 | 2 | + | VNx128BI | N/A | N/A | 1 | */ /* For RVV modes, each boolean value occupies 1-bit. 4th argument is specify the minmial possible size of the vector mode, @@ -47,6 +48,7 @@ VECTOR_BOOL_MODE (VNx8BI, 8, BI, 1); VECTOR_BOOL_MODE (VNx16BI, 16, BI, 2); VECTOR_BOOL_MODE (VNx32BI, 32, BI, 4); VECTOR_BOOL_MODE (VNx64BI, 64, BI, 8); +VECTOR_BOOL_MODE (VNx128BI, 128, BI, 16); ADJUST_NUNITS (VNx1BI, riscv_v_adjust_nunits (VNx1BImode, 1)); ADJUST_NUNITS (VNx2BI, riscv_v_adjust_nunits (VNx2BImode, 2)); @@ -55,6 +57,7 @@ ADJUST_NUNITS (VNx8BI, riscv_v_adjust_nunits (VNx8BImode, 8)); ADJUST_NUNITS (VNx16BI, riscv_v_adjust_nunits (VNx16BImode, 16)); ADJUST_NUNITS (VNx32BI, riscv_v_adjust_nunits (VNx32BImode, 32)); ADJUST_NUNITS (VNx64BI, riscv_v_adjust_nunits (VNx64BImode, 64)); +ADJUST_NUNITS (VNx128BI, riscv_v_adjust_nunits (VNx128BImode, 128)); ADJUST_ALIGNMENT (VNx1BI, 1); ADJUST_ALIGNMENT (VNx2BI, 1); @@ -63,6 +66,7 @@ ADJUST_ALIGNMENT (VNx8BI, 1); ADJUST_ALIGNMENT (VNx16BI, 1); ADJUST_ALIGNMENT (VNx32BI, 1); ADJUST_ALIGNMENT (VNx64BI, 1); +ADJUST_ALIGNMENT (VNx128BI, 1); ADJUST_BYTESIZE (VNx1BI, riscv_v_adjust_bytesize (VNx1BImode, 1)); ADJUST_BYTESIZE (VNx2BI, riscv_v_adjust_bytesize (VNx2BImode, 1)); @@ -71,6 +75,7 @@ ADJUST_BYTESIZE (VNx8BI, riscv_v_adjust_bytesize (VNx8BImode, 1)); ADJUST_BYTESIZE (VNx16BI, riscv_v_adjust_bytesize (VNx16BImode, 2)); ADJUST_BYTESIZE (VNx32BI, riscv_v_adjust_bytesize (VNx32BImode, 4)); ADJUST_BYTESIZE (VNx64BI, riscv_v_adjust_bytesize (VNx64BImode, 8)); +ADJUST_BYTESIZE (VNx128BI, riscv_v_adjust_bytesize (VNx128BImode, 16)); ADJUST_PRECISION (VNx1BI, riscv_v_adjust_precision (VNx1BImode, 1)); ADJUST_PRECISION (VNx2BI, riscv_v_adjust_precision (VNx2BImode, 2)); @@ -79,38 +84,47 @@ ADJUST_PRECISION (VNx8BI, riscv_v_adjust_precision (VNx8BImode, 8)); ADJUST_PRECISION (VNx16BI, riscv_v_adjust_precision (VNx16BImode, 16)); ADJUST_PRECISION (VNx32BI, riscv_v_adjust_precision (VNx32BImode, 32)); ADJUST_PRECISION (VNx64BI, riscv_v_adjust_precision (VNx64BImode, 64)); +ADJUST_PRECISION (VNx128BI, riscv_v_adjust_precision (VNx128BImode, 128)); /* - | Mode | MIN_VLEN=32 | MIN_VLEN=32 | MIN_VLEN=64 | MIN_VLEN=64 | - | | LMUL | SEW/LMUL | LMUL | SEW/LMUL | - | VNx1QI | MF4 | 32 | MF8 | 64 | - | VNx2QI | MF2 | 16 | MF4 | 32 | - | VNx4QI | M1 | 8 | MF2 | 16 | - | VNx8QI | M2 | 4 | M1 | 8 | - | VNx16QI | M4 | 2 | M2 | 4 | - | VNx32QI | M8 | 1 | M4 | 2 | - | VNx64QI | N/A | N/A | M8 | 1 | - | VNx1(HI|HF) | MF2 | 32 | MF4 | 64 | - | VNx2(HI|HF) | M1 | 16 | MF2 | 32 | - | VNx4(HI|HF) | M2 | 8 | M1 | 16 | - | VNx8(HI|HF) | M4 | 4 | M2 | 8 | - | VNx16(HI|HF)| M8 | 2 | M4 | 4 | - | VNx32(HI|HF)| N/A | N/A | M8 | 2 | - | VNx1(SI|SF) | M1 | 32 | MF2 | 64 | - | VNx2(SI|SF) | M2 | 16 | M1 | 32 | - | VNx4(SI|SF) | M4 | 8 | M2 | 16 | - | VNx8(SI|SF) | M8 | 4 | M4 | 8 | - | VNx16(SI|SF)| N/A | N/A | M8 | 4 | - | VNx1(DI|DF) | N/A | N/A | M1 | 64 | - | VNx2(DI|DF) | N/A | N/A | M2 | 32 | - | VNx4(DI|DF) | N/A | N/A | M4 | 16 | - | VNx8(DI|DF) | N/A | N/A | M8 | 8 | + | Mode | MIN_VLEN=32 | MIN_VLEN=32 | MIN_VLEN=64 | MIN_VLEN=64 | MIN_VLEN=128 | MIN_VLEN=128 | + | | LMUL | SEW/LMUL | LMUL | SEW/LMUL | LMUL | SEW/LMUL | + | VNx1QI | MF4 | 32 | MF8 | 64 | N/A | N/A | + | VNx2QI | MF2 | 16 | MF4 | 32 | MF8 | 64 | + | VNx4QI | M1 | 8 | MF2 | 16 | MF4 | 32 | + | VNx8QI | M2 | 4 | M1 | 8 | MF2 | 16 | + | VNx16QI | M4 | 2 | M2 | 4 | M1 | 8 | + | VNx32QI | M8 | 1 | M4 | 2 | M2 | 4 | + | VNx64QI | N/A | N/A | M8 | 1 | M4 | 2 | + | VNx128QI | N/A | N/A | N/A | N/A | M8 | 1 | + | VNx1(HI|HF) | MF2 | 32 | MF4 | 64 | N/A | N/A | + | VNx2(HI|HF) | M1 | 16 | MF2 | 32 | MF4 | 64 | + | VNx4(HI|HF) | M2 | 8 | M1 | 16 | MF2 | 32 | + | VNx8(HI|HF) | M4 | 4 | M2 | 8 | M1 | 16 | + | VNx16(HI|HF)| M8 | 2 | M4 | 4 | M2 | 8 | + | VNx32(HI|HF)| N/A | N/A | M8 | 2 | M4 | 4 | + | VNx64(HI|HF)| N/A | N/A | N/A | N/A | M8 | 2 | + | VNx1(SI|SF) | M1 | 32 | MF2 | 64 | MF2 | 64 | + | VNx2(SI|SF) | M2 | 16 | M1 | 32 | M1 | 32 | + | VNx4(SI|SF) | M4 | 8 | M2 | 16 | M2 | 16 | + | VNx8(SI|SF) | M8 | 4 | M4 | 8 | M4 | 8 | + | VNx16(SI|SF)| N/A | N/A | M8 | 4 | M8 | 4 | + | VNx1(DI|DF) | N/A | N/A | M1 | 64 | N/A | N/A | + | VNx2(DI|DF) | N/A | N/A | M2 | 32 | M1 | 64 | + | VNx4(DI|DF) | N/A | N/A | M4 | 16 | M2 | 32 | + | VNx8(DI|DF) | N/A | N/A | M8 | 8 | M4 | 16 | + | VNx16(DI|DF)| N/A | N/A | N/A | N/A | M8 | 8 | */ /* Define RVV modes whose sizes are multiples of 64-bit chunks. */ #define RVV_MODES(NVECS, VB, VH, VS, VD) \ - VECTOR_MODES_WITH_PREFIX (VNx, INT, 8 * NVECS, 0); \ - VECTOR_MODES_WITH_PREFIX (VNx, FLOAT, 8 * NVECS, 0); \ + VECTOR_MODE_WITH_PREFIX (VNx, INT, QI, 8 * NVECS, 0); \ + VECTOR_MODE_WITH_PREFIX (VNx, INT, HI, 4 * NVECS, 0); \ + VECTOR_MODE_WITH_PREFIX (VNx, FLOAT, HF, 4 * NVECS, 0); \ + VECTOR_MODE_WITH_PREFIX (VNx, INT, SI, 2 * NVECS, 0); \ + VECTOR_MODE_WITH_PREFIX (VNx, FLOAT, SF, 2 * NVECS, 0); \ + VECTOR_MODE_WITH_PREFIX (VNx, INT, DI, NVECS, 0); \ + VECTOR_MODE_WITH_PREFIX (VNx, FLOAT, DF, NVECS, 0); \ \ ADJUST_NUNITS (VB##QI, riscv_v_adjust_nunits (VB##QI##mode, NVECS * 8)); \ ADJUST_NUNITS (VH##HI, riscv_v_adjust_nunits (VH##HI##mode, NVECS * 4)); \ @@ -128,14 +142,11 @@ ADJUST_PRECISION (VNx64BI, riscv_v_adjust_precision (VNx64BImode, 64)); ADJUST_ALIGNMENT (VS##SF, 4); \ ADJUST_ALIGNMENT (VD##DF, 8); -/* 'VECTOR_MODES_WITH_PREFIX' does not allow ncomponents < 2. - So we use 'VECTOR_MODE_WITH_PREFIX' to define VNx1DImode and VNx1DFmode. */ -VECTOR_MODE_WITH_PREFIX (VNx, INT, DI, 1, 0); -VECTOR_MODE_WITH_PREFIX (VNx, FLOAT, DF, 1, 0); RVV_MODES (1, VNx8, VNx4, VNx2, VNx1) RVV_MODES (2, VNx16, VNx8, VNx4, VNx2) RVV_MODES (4, VNx32, VNx16, VNx8, VNx4) RVV_MODES (8, VNx64, VNx32, VNx16, VNx8) +RVV_MODES (16, VNx128, VNx64, VNx32, VNx16) VECTOR_MODES_WITH_PREFIX (VNx, INT, 4, 0); VECTOR_MODES_WITH_PREFIX (VNx, FLOAT, 4, 0); diff --git a/gcc/config/riscv/riscv-v.cc b/gcc/config/riscv/riscv-v.cc index 392f5d02e17..99c414cc910 100644 --- a/gcc/config/riscv/riscv-v.cc +++ b/gcc/config/riscv/riscv-v.cc @@ -340,14 +340,19 @@ struct mode_vtype_group uint8_t ratio_for_min_vlen32[NUM_MACHINE_MODES]; enum vlmul_type vlmul_for_min_vlen64[NUM_MACHINE_MODES]; uint8_t ratio_for_min_vlen64[NUM_MACHINE_MODES]; + enum vlmul_type vlmul_for_for_vlen128[NUM_MACHINE_MODES]; + uint8_t ratio_for_for_vlen128[NUM_MACHINE_MODES]; mode_vtype_group () { #define ENTRY(MODE, REQUIREMENT, VLMUL_FOR_MIN_VLEN32, RATIO_FOR_MIN_VLEN32, \ - VLMUL_FOR_MIN_VLEN64, RATIO_FOR_MIN_VLEN64) \ + VLMUL_FOR_MIN_VLEN64, RATIO_FOR_MIN_VLEN64, \ + VLMUL_FOR_FOR_VLEN128, RATIO_FOR_FOR_VLEN128) \ vlmul_for_min_vlen32[MODE##mode] = VLMUL_FOR_MIN_VLEN32; \ ratio_for_min_vlen32[MODE##mode] = RATIO_FOR_MIN_VLEN32; \ vlmul_for_min_vlen64[MODE##mode] = VLMUL_FOR_MIN_VLEN64; \ - ratio_for_min_vlen64[MODE##mode] = RATIO_FOR_MIN_VLEN64; + ratio_for_min_vlen64[MODE##mode] = RATIO_FOR_MIN_VLEN64; \ + vlmul_for_for_vlen128[MODE##mode] = VLMUL_FOR_FOR_VLEN128; \ + ratio_for_for_vlen128[MODE##mode] = RATIO_FOR_FOR_VLEN128; #include "riscv-vector-switch.def" } }; @@ -358,7 +363,9 @@ static mode_vtype_group mode_vtype_infos; enum vlmul_type get_vlmul (machine_mode mode) { - if (TARGET_MIN_VLEN == 32) + if (TARGET_MIN_VLEN >= 128) + return mode_vtype_infos.vlmul_for_for_vlen128[mode]; + else if (TARGET_MIN_VLEN == 32) return mode_vtype_infos.vlmul_for_min_vlen32[mode]; else return mode_vtype_infos.vlmul_for_min_vlen64[mode]; @@ -368,7 +375,9 @@ get_vlmul (machine_mode mode) unsigned int get_ratio (machine_mode mode) { - if (TARGET_MIN_VLEN == 32) + if (TARGET_MIN_VLEN >= 128) + return mode_vtype_infos.ratio_for_for_vlen128[mode]; + else if (TARGET_MIN_VLEN == 32) return mode_vtype_infos.ratio_for_min_vlen32[mode]; else return mode_vtype_infos.ratio_for_min_vlen64[mode]; diff --git a/gcc/config/riscv/riscv-vector-builtins.cc b/gcc/config/riscv/riscv-vector-builtins.cc index 01cea23d3e6..434bd8e157b 100644 --- a/gcc/config/riscv/riscv-vector-builtins.cc +++ b/gcc/config/riscv/riscv-vector-builtins.cc @@ -107,7 +107,8 @@ const char *const operand_suffixes[NUM_OP_TYPES] = { /* Static information about type suffix for each RVV type. */ const rvv_builtin_suffixes type_suffixes[NUM_VECTOR_TYPES + 1] = { -#define DEF_RVV_TYPE(NAME, NCHARS, ABI_NAME, SCALAR_TYPE, VECTOR_MODE, \ +#define DEF_RVV_TYPE(NAME, NCHARS, ABI_NAME, SCALAR_TYPE, \ + VECTOR_MODE_MIN_VLEN_128, VECTOR_MODE_MIN_VLEN_64, \ VECTOR_MODE_MIN_VLEN_32, VECTOR_SUFFIX, SCALAR_SUFFIX, \ VSETVL_SUFFIX) \ {#VECTOR_SUFFIX, #SCALAR_SUFFIX, #VSETVL_SUFFIX}, @@ -2350,10 +2351,12 @@ register_builtin_types () tree int64_type_node = get_typenode_from_name (INT64_TYPE); machine_mode mode; -#define DEF_RVV_TYPE(NAME, NCHARS, ABI_NAME, SCALAR_TYPE, VECTOR_MODE, \ +#define DEF_RVV_TYPE(NAME, NCHARS, ABI_NAME, SCALAR_TYPE, \ + VECTOR_MODE_MIN_VLEN_128, VECTOR_MODE_MIN_VLEN_64, \ VECTOR_MODE_MIN_VLEN_32, ARGS...) \ - mode = TARGET_MIN_VLEN > 32 ? VECTOR_MODE##mode \ - : VECTOR_MODE_MIN_VLEN_32##mode; \ + mode = TARGET_MIN_VLEN >= 128 ? VECTOR_MODE_MIN_VLEN_128##mode \ + : TARGET_MIN_VLEN >= 64 ? VECTOR_MODE_MIN_VLEN_64##mode \ + : VECTOR_MODE_MIN_VLEN_32##mode; \ register_builtin_type (VECTOR_TYPE_##NAME, SCALAR_TYPE##_type_node, mode); #include "riscv-vector-builtins.def" } diff --git a/gcc/config/riscv/riscv-vector-builtins.def b/gcc/config/riscv/riscv-vector-builtins.def index 563ad355342..64c09b5d8cb 100644 --- a/gcc/config/riscv/riscv-vector-builtins.def +++ b/gcc/config/riscv/riscv-vector-builtins.def @@ -42,7 +42,8 @@ along with GCC; see the file COPYING3. If not see */ #ifndef DEF_RVV_TYPE -#define DEF_RVV_TYPE(NAME, NCHARS, ABI_NAME, SCALAR_TYPE, VECTOR_MODE, \ +#define DEF_RVV_TYPE(NAME, NCHARS, ABI_NAME, SCALAR_TYPE, \ + VECTOR_MODE_MIN_VLEN_128, VECTOR_MODE_MIN_VLEN_64, \ VECTOR_MODE_MIN_VLEN_32, VECTOR_SUFFIX, SCALAR_SUFFIX, \ VSETVL_SUFFIX) #endif @@ -79,212 +80,247 @@ along with GCC; see the file COPYING3. If not see #endif /* SEW/LMUL = 64: - Only enable when TARGET_MIN_VLEN > 32 and machine mode = VNx1BImode. */ -DEF_RVV_TYPE (vbool64_t, 14, __rvv_bool64_t, boolean, VNx1BI, VOID, _b64, , ) + Only enable when TARGET_MIN_VLEN > 32. + Machine mode = VNx1BImode when TARGET_MIN_VLEN < 128. + Machine mode = VNx2BImode when TARGET_MIN_VLEN >= 128. */ +DEF_RVV_TYPE (vbool64_t, 14, __rvv_bool64_t, boolean, VNx2BI, VNx1BI, VOID, _b64, , ) /* SEW/LMUL = 32: Machine mode = VNx2BImode when TARGET_MIN_VLEN > 32. Machine mode = VNx1BImode when TARGET_MIN_VLEN = 32. */ -DEF_RVV_TYPE (vbool32_t, 14, __rvv_bool32_t, boolean, VNx2BI, VNx1BI, _b32, , ) +DEF_RVV_TYPE (vbool32_t, 14, __rvv_bool32_t, boolean, VNx4BI, VNx2BI, VNx1BI, _b32, , ) /* SEW/LMUL = 16: + Machine mode = VNx8BImode when TARGET_MIN_VLEN >= 128. Machine mode = VNx2BImode when TARGET_MIN_VLEN = 32. Machine mode = VNx4BImode when TARGET_MIN_VLEN > 32. */ -DEF_RVV_TYPE (vbool16_t, 14, __rvv_bool16_t, boolean, VNx4BI, VNx2BI, _b16, , ) +DEF_RVV_TYPE (vbool16_t, 14, __rvv_bool16_t, boolean, VNx8BI, VNx4BI, VNx2BI, _b16, , ) /* SEW/LMUL = 8: + Machine mode = VNx16BImode when TARGET_MIN_VLEN >= 128. Machine mode = VNx8BImode when TARGET_MIN_VLEN > 32. Machine mode = VNx4BImode when TARGET_MIN_VLEN = 32. */ -DEF_RVV_TYPE (vbool8_t, 13, __rvv_bool8_t, boolean, VNx8BI, VNx4BI, _b8, , ) +DEF_RVV_TYPE (vbool8_t, 13, __rvv_bool8_t, boolean, VNx16BI, VNx8BI, VNx4BI, _b8, , ) /* SEW/LMUL = 4: + Machine mode = VNx32BImode when TARGET_MIN_VLEN >= 128. Machine mode = VNx16BImode when TARGET_MIN_VLEN > 32. Machine mode = VNx8BImode when TARGET_MIN_VLEN = 32. */ -DEF_RVV_TYPE (vbool4_t, 13, __rvv_bool4_t, boolean, VNx16BI, VNx8BI, _b4, , ) +DEF_RVV_TYPE (vbool4_t, 13, __rvv_bool4_t, boolean, VNx32BI, VNx16BI, VNx8BI, _b4, , ) /* SEW/LMUL = 2: + Machine mode = VNx64BImode when TARGET_MIN_VLEN >= 128. Machine mode = VNx32BImode when TARGET_MIN_VLEN > 32. Machine mode = VNx16BImode when TARGET_MIN_VLEN = 32. */ -DEF_RVV_TYPE (vbool2_t, 13, __rvv_bool2_t, boolean, VNx32BI, VNx16BI, _b2, , ) +DEF_RVV_TYPE (vbool2_t, 13, __rvv_bool2_t, boolean, VNx64BI, VNx32BI, VNx16BI, _b2, , ) /* SEW/LMUL = 1: + Machine mode = VNx128BImode when TARGET_MIN_VLEN >= 128. Machine mode = VNx64BImode when TARGET_MIN_VLEN > 32. Machine mode = VNx32BImode when TARGET_MIN_VLEN = 32. */ -DEF_RVV_TYPE (vbool1_t, 13, __rvv_bool1_t, boolean, VNx64BI, VNx32BI, _b1, , ) +DEF_RVV_TYPE (vbool1_t, 13, __rvv_bool1_t, boolean, VNx128BI, VNx64BI, VNx32BI, _b1, , ) /* LMUL = 1/8: - Only enble when TARGET_MIN_VLEN > 32 and machine mode = VNx1QImode. */ -DEF_RVV_TYPE (vint8mf8_t, 15, __rvv_int8mf8_t, int8, VNx1QI, VOID, _i8mf8, _i8, + Only enble when TARGET_MIN_VLEN > 32. + Machine mode = VNx1QImode when TARGET_MIN_VLEN < 128. + Machine mode = VNx2QImode when TARGET_MIN_VLEN >= 128. */ +DEF_RVV_TYPE (vint8mf8_t, 15, __rvv_int8mf8_t, int8, VNx2QI, VNx1QI, VOID, _i8mf8, _i8, _e8mf8) -DEF_RVV_TYPE (vuint8mf8_t, 16, __rvv_uint8mf8_t, uint8, VNx1QI, VOID, _u8mf8, +DEF_RVV_TYPE (vuint8mf8_t, 16, __rvv_uint8mf8_t, uint8, VNx2QI, VNx1QI, VOID, _u8mf8, _u8, _e8mf8) /* LMUL = 1/4: + Machine mode = VNx4QImode when TARGET_MIN_VLEN >= 128. Machine mode = VNx2QImode when TARGET_MIN_VLEN > 32. Machine mode = VNx1QImode when TARGET_MIN_VLEN = 32. */ -DEF_RVV_TYPE (vint8mf4_t, 15, __rvv_int8mf4_t, int8, VNx2QI, VNx1QI, _i8mf4, +DEF_RVV_TYPE (vint8mf4_t, 15, __rvv_int8mf4_t, int8, VNx4QI, VNx2QI, VNx1QI, _i8mf4, _i8, _e8mf4) -DEF_RVV_TYPE (vuint8mf4_t, 16, __rvv_uint8mf4_t, uint8, VNx2QI, VNx1QI, _u8mf4, +DEF_RVV_TYPE (vuint8mf4_t, 16, __rvv_uint8mf4_t, uint8, VNx4QI, VNx2QI, VNx1QI, _u8mf4, _u8, _e8mf4) /* LMUL = 1/2: + Machine mode = VNx8QImode when TARGET_MIN_VLEN >= 128. Machine mode = VNx4QImode when TARGET_MIN_VLEN > 32. Machine mode = VNx2QImode when TARGET_MIN_VLEN = 32. */ -DEF_RVV_TYPE (vint8mf2_t, 15, __rvv_int8mf2_t, int8, VNx4QI, VNx2QI, _i8mf2, +DEF_RVV_TYPE (vint8mf2_t, 15, __rvv_int8mf2_t, int8, VNx8QI, VNx4QI, VNx2QI, _i8mf2, _i8, _e8mf2) -DEF_RVV_TYPE (vuint8mf2_t, 16, __rvv_uint8mf2_t, uint8, VNx4QI, VNx2QI, _u8mf2, +DEF_RVV_TYPE (vuint8mf2_t, 16, __rvv_uint8mf2_t, uint8, VNx8QI, VNx4QI, VNx2QI, _u8mf2, _u8, _e8mf2) /* LMUL = 1: + Machine mode = VNx16QImode when TARGET_MIN_VLEN >= 128. Machine mode = VNx8QImode when TARGET_MIN_VLEN > 32. Machine mode = VNx4QImode when TARGET_MIN_VLEN = 32. */ -DEF_RVV_TYPE (vint8m1_t, 14, __rvv_int8m1_t, int8, VNx8QI, VNx4QI, _i8m1, _i8, +DEF_RVV_TYPE (vint8m1_t, 14, __rvv_int8m1_t, int8, VNx16QI, VNx8QI, VNx4QI, _i8m1, _i8, _e8m1) -DEF_RVV_TYPE (vuint8m1_t, 15, __rvv_uint8m1_t, uint8, VNx8QI, VNx4QI, _u8m1, +DEF_RVV_TYPE (vuint8m1_t, 15, __rvv_uint8m1_t, uint8, VNx16QI, VNx8QI, VNx4QI, _u8m1, _u8, _e8m1) /* LMUL = 2: + Machine mode = VNx32QImode when TARGET_MIN_VLEN >= 128. Machine mode = VNx16QImode when TARGET_MIN_VLEN > 32. Machine mode = VNx8QImode when TARGET_MIN_VLEN = 32. */ -DEF_RVV_TYPE (vint8m2_t, 14, __rvv_int8m2_t, int8, VNx16QI, VNx8QI, _i8m2, _i8, +DEF_RVV_TYPE (vint8m2_t, 14, __rvv_int8m2_t, int8, VNx32QI, VNx16QI, VNx8QI, _i8m2, _i8, _e8m2) -DEF_RVV_TYPE (vuint8m2_t, 15, __rvv_uint8m2_t, uint8, VNx16QI, VNx8QI, _u8m2, +DEF_RVV_TYPE (vuint8m2_t, 15, __rvv_uint8m2_t, uint8, VNx32QI, VNx16QI, VNx8QI, _u8m2, _u8, _e8m2) /* LMUL = 4: + Machine mode = VNx64QImode when TARGET_MIN_VLEN >= 128. Machine mode = VNx32QImode when TARGET_MIN_VLEN > 32. Machine mode = VNx16QImode when TARGET_MIN_VLEN = 32. */ -DEF_RVV_TYPE (vint8m4_t, 14, __rvv_int8m4_t, int8, VNx32QI, VNx16QI, _i8m4, _i8, +DEF_RVV_TYPE (vint8m4_t, 14, __rvv_int8m4_t, int8, VNx64QI, VNx32QI, VNx16QI, _i8m4, _i8, _e8m4) -DEF_RVV_TYPE (vuint8m4_t, 15, __rvv_uint8m4_t, uint8, VNx32QI, VNx16QI, _u8m4, +DEF_RVV_TYPE (vuint8m4_t, 15, __rvv_uint8m4_t, uint8, VNx64QI, VNx32QI, VNx16QI, _u8m4, _u8, _e8m4) /* LMUL = 8: + Machine mode = VNx128QImode when TARGET_MIN_VLEN >= 128. Machine mode = VNx64QImode when TARGET_MIN_VLEN > 32. Machine mode = VNx32QImode when TARGET_MIN_VLEN = 32. */ -DEF_RVV_TYPE (vint8m8_t, 14, __rvv_int8m8_t, int8, VNx64QI, VNx32QI, _i8m8, _i8, +DEF_RVV_TYPE (vint8m8_t, 14, __rvv_int8m8_t, int8, VNx128QI, VNx64QI, VNx32QI, _i8m8, _i8, _e8m8) -DEF_RVV_TYPE (vuint8m8_t, 15, __rvv_uint8m8_t, uint8, VNx64QI, VNx32QI, _u8m8, +DEF_RVV_TYPE (vuint8m8_t, 15, __rvv_uint8m8_t, uint8, VNx128QI, VNx64QI, VNx32QI, _u8m8, _u8, _e8m8) /* LMUL = 1/4: - Only enble when TARGET_MIN_VLEN > 32 and machine mode = VNx1HImode. */ -DEF_RVV_TYPE (vint16mf4_t, 16, __rvv_int16mf4_t, int16, VNx1HI, VOID, _i16mf4, + Only enble when TARGET_MIN_VLEN > 32. + Machine mode = VNx1HImode when TARGET_MIN_VLEN < 128. + Machine mode = VNx2HImode when TARGET_MIN_VLEN >= 128. */ +DEF_RVV_TYPE (vint16mf4_t, 16, __rvv_int16mf4_t, int16, VNx2HI, VNx1HI, VOID, _i16mf4, _i16, _e16mf4) -DEF_RVV_TYPE (vuint16mf4_t, 17, __rvv_uint16mf4_t, uint16, VNx1HI, VOID, +DEF_RVV_TYPE (vuint16mf4_t, 17, __rvv_uint16mf4_t, uint16, VNx2HI, VNx1HI, VOID, _u16mf4, _u16, _e16mf4) /* LMUL = 1/2: + Machine mode = VNx4HImode when TARGET_MIN_VLEN >= 128. Machine mode = VNx2HImode when TARGET_MIN_VLEN > 32. Machine mode = VNx1HImode when TARGET_MIN_VLEN = 32. */ -DEF_RVV_TYPE (vint16mf2_t, 16, __rvv_int16mf2_t, int16, VNx2HI, VNx1HI, _i16mf2, +DEF_RVV_TYPE (vint16mf2_t, 16, __rvv_int16mf2_t, int16, VNx4HI, VNx2HI, VNx1HI, _i16mf2, _i16, _e16mf2) -DEF_RVV_TYPE (vuint16mf2_t, 17, __rvv_uint16mf2_t, uint16, VNx2HI, VNx1HI, +DEF_RVV_TYPE (vuint16mf2_t, 17, __rvv_uint16mf2_t, uint16, VNx4HI, VNx2HI, VNx1HI, _u16mf2, _u16, _e16mf2) /* LMUL = 1: + Machine mode = VNx8HImode when TARGET_MIN_VLEN >= 128. Machine mode = VNx4HImode when TARGET_MIN_VLEN > 32. Machine mode = VNx2HImode when TARGET_MIN_VLEN = 32. */ -DEF_RVV_TYPE (vint16m1_t, 15, __rvv_int16m1_t, int16, VNx4HI, VNx2HI, _i16m1, +DEF_RVV_TYPE (vint16m1_t, 15, __rvv_int16m1_t, int16, VNx8HI, VNx4HI, VNx2HI, _i16m1, _i16, _e16m1) -DEF_RVV_TYPE (vuint16m1_t, 16, __rvv_uint16m1_t, uint16, VNx4HI, VNx2HI, _u16m1, +DEF_RVV_TYPE (vuint16m1_t, 16, __rvv_uint16m1_t, uint16, VNx8HI, VNx4HI, VNx2HI, _u16m1, _u16, _e16m1) /* LMUL = 2: + Machine mode = VNx16HImode when TARGET_MIN_VLEN >= 128. Machine mode = VNx8HImode when TARGET_MIN_VLEN > 32. Machine mode = VNx4HImode when TARGET_MIN_VLEN = 32. */ -DEF_RVV_TYPE (vint16m2_t, 15, __rvv_int16m2_t, int16, VNx8HI, VNx4HI, _i16m2, +DEF_RVV_TYPE (vint16m2_t, 15, __rvv_int16m2_t, int16, VNx16HI, VNx8HI, VNx4HI, _i16m2, _i16, _e16m2) -DEF_RVV_TYPE (vuint16m2_t, 16, __rvv_uint16m2_t, uint16, VNx8HI, VNx4HI, _u16m2, +DEF_RVV_TYPE (vuint16m2_t, 16, __rvv_uint16m2_t, uint16, VNx16HI, VNx8HI, VNx4HI, _u16m2, _u16, _e16m2) /* LMUL = 4: + Machine mode = VNx32HImode when TARGET_MIN_VLEN >= 128. Machine mode = VNx16HImode when TARGET_MIN_VLEN > 32. Machine mode = VNx8HImode when TARGET_MIN_VLEN = 32. */ -DEF_RVV_TYPE (vint16m4_t, 15, __rvv_int16m4_t, int16, VNx16HI, VNx8HI, _i16m4, +DEF_RVV_TYPE (vint16m4_t, 15, __rvv_int16m4_t, int16, VNx32HI, VNx16HI, VNx8HI, _i16m4, _i16, _e16m4) -DEF_RVV_TYPE (vuint16m4_t, 16, __rvv_uint16m4_t, uint16, VNx16HI, VNx8HI, +DEF_RVV_TYPE (vuint16m4_t, 16, __rvv_uint16m4_t, uint16, VNx32HI, VNx16HI, VNx8HI, _u16m4, _u16, _e16m4) /* LMUL = 8: + Machine mode = VNx64HImode when TARGET_MIN_VLEN >= 128. Machine mode = VNx32HImode when TARGET_MIN_VLEN > 32. Machine mode = VNx16HImode when TARGET_MIN_VLEN = 32. */ -DEF_RVV_TYPE (vint16m8_t, 15, __rvv_int16m8_t, int16, VNx32HI, VNx16HI, _i16m8, +DEF_RVV_TYPE (vint16m8_t, 15, __rvv_int16m8_t, int16, VNx64HI, VNx32HI, VNx16HI, _i16m8, _i16, _e16m8) -DEF_RVV_TYPE (vuint16m8_t, 16, __rvv_uint16m8_t, uint16, VNx32HI, VNx16HI, +DEF_RVV_TYPE (vuint16m8_t, 16, __rvv_uint16m8_t, uint16, VNx64HI, VNx32HI, VNx16HI, _u16m8, _u16, _e16m8) /* LMUL = 1/2: - Only enble when TARGET_MIN_VLEN > 32 and machine mode = VNx1SImode. */ -DEF_RVV_TYPE (vint32mf2_t, 16, __rvv_int32mf2_t, int32, VNx1SI, VOID, _i32mf2, + Only enble when TARGET_MIN_VLEN > 32. + Machine mode = VNx1SImode when TARGET_MIN_VLEN < 128. + Machine mode = VNx2SImode when TARGET_MIN_VLEN >= 128. */ +DEF_RVV_TYPE (vint32mf2_t, 16, __rvv_int32mf2_t, int32, VNx2SI, VNx1SI, VOID, _i32mf2, _i32, _e32mf2) -DEF_RVV_TYPE (vuint32mf2_t, 17, __rvv_uint32mf2_t, uint32, VNx1SI, VOID, +DEF_RVV_TYPE (vuint32mf2_t, 17, __rvv_uint32mf2_t, uint32, VNx2SI, VNx1SI, VOID, _u32mf2, _u32, _e32mf2) /* LMUL = 1: + Machine mode = VNx4SImode when TARGET_MIN_VLEN >= 128. Machine mode = VNx2SImode when TARGET_MIN_VLEN > 32. Machine mode = VNx1SImode when TARGET_MIN_VLEN = 32. */ -DEF_RVV_TYPE (vint32m1_t, 15, __rvv_int32m1_t, int32, VNx2SI, VNx1SI, _i32m1, +DEF_RVV_TYPE (vint32m1_t, 15, __rvv_int32m1_t, int32, VNx4SI, VNx2SI, VNx1SI, _i32m1, _i32, _e32m1) -DEF_RVV_TYPE (vuint32m1_t, 16, __rvv_uint32m1_t, uint32, VNx2SI, VNx1SI, _u32m1, +DEF_RVV_TYPE (vuint32m1_t, 16, __rvv_uint32m1_t, uint32, VNx4SI, VNx2SI, VNx1SI, _u32m1, _u32, _e32m1) /* LMUL = 2: + Machine mode = VNx8SImode when TARGET_MIN_VLEN >= 128. Machine mode = VNx4SImode when TARGET_MIN_VLEN > 32. Machine mode = VNx2SImode when TARGET_MIN_VLEN = 32. */ -DEF_RVV_TYPE (vint32m2_t, 15, __rvv_int32m2_t, int32, VNx4SI, VNx2SI, _i32m2, +DEF_RVV_TYPE (vint32m2_t, 15, __rvv_int32m2_t, int32, VNx8SI, VNx4SI, VNx2SI, _i32m2, _i32, _e32m2) -DEF_RVV_TYPE (vuint32m2_t, 16, __rvv_uint32m2_t, uint32, VNx4SI, VNx2SI, _u32m2, +DEF_RVV_TYPE (vuint32m2_t, 16, __rvv_uint32m2_t, uint32, VNx8SI, VNx4SI, VNx2SI, _u32m2, _u32, _e32m2) /* LMUL = 4: + Machine mode = VNx16SImode when TARGET_MIN_VLEN >= 128. Machine mode = VNx8SImode when TARGET_MIN_VLEN > 32. Machine mode = VNx4SImode when TARGET_MIN_VLEN = 32. */ -DEF_RVV_TYPE (vint32m4_t, 15, __rvv_int32m4_t, int32, VNx8SI, VNx4SI, _i32m4, +DEF_RVV_TYPE (vint32m4_t, 15, __rvv_int32m4_t, int32, VNx16SI, VNx8SI, VNx4SI, _i32m4, _i32, _e32m4) -DEF_RVV_TYPE (vuint32m4_t, 16, __rvv_uint32m4_t, uint32, VNx8SI, VNx4SI, _u32m4, +DEF_RVV_TYPE (vuint32m4_t, 16, __rvv_uint32m4_t, uint32, VNx16SI, VNx8SI, VNx4SI, _u32m4, _u32, _e32m4) /* LMUL = 8: + Machine mode = VNx32SImode when TARGET_MIN_VLEN >= 128. Machine mode = VNx16SImode when TARGET_MIN_VLEN > 32. Machine mode = VNx8SImode when TARGET_MIN_VLEN = 32. */ -DEF_RVV_TYPE (vint32m8_t, 15, __rvv_int32m8_t, int32, VNx16SI, VNx8SI, _i32m8, +DEF_RVV_TYPE (vint32m8_t, 15, __rvv_int32m8_t, int32, VNx32SI, VNx16SI, VNx8SI, _i32m8, _i32, _e32m8) -DEF_RVV_TYPE (vuint32m8_t, 16, __rvv_uint32m8_t, uint32, VNx16SI, VNx8SI, +DEF_RVV_TYPE (vuint32m8_t, 16, __rvv_uint32m8_t, uint32, VNx32SI, VNx16SI, VNx8SI, _u32m8, _u32, _e32m8) /* SEW = 64: - Enable when TARGET_MIN_VLEN > 32. */ -DEF_RVV_TYPE (vint64m1_t, 15, __rvv_int64m1_t, int64, VNx1DI, VOID, _i64m1, + Disable when !TARGET_VECTOR_ELEN_64. */ +DEF_RVV_TYPE (vint64m1_t, 15, __rvv_int64m1_t, int64, VNx2DI, VNx1DI, VOID, _i64m1, _i64, _e64m1) -DEF_RVV_TYPE (vuint64m1_t, 16, __rvv_uint64m1_t, uint64, VNx1DI, VOID, _u64m1, +DEF_RVV_TYPE (vuint64m1_t, 16, __rvv_uint64m1_t, uint64, VNx2DI, VNx1DI, VOID, _u64m1, _u64, _e64m1) -DEF_RVV_TYPE (vint64m2_t, 15, __rvv_int64m2_t, int64, VNx2DI, VOID, _i64m2, +DEF_RVV_TYPE (vint64m2_t, 15, __rvv_int64m2_t, int64, VNx4DI, VNx2DI, VOID, _i64m2, _i64, _e64m2) -DEF_RVV_TYPE (vuint64m2_t, 16, __rvv_uint64m2_t, uint64, VNx2DI, VOID, _u64m2, +DEF_RVV_TYPE (vuint64m2_t, 16, __rvv_uint64m2_t, uint64, VNx4DI, VNx2DI, VOID, _u64m2, _u64, _e64m2) -DEF_RVV_TYPE (vint64m4_t, 15, __rvv_int64m4_t, int64, VNx4DI, VOID, _i64m4, +DEF_RVV_TYPE (vint64m4_t, 15, __rvv_int64m4_t, int64, VNx8DI, VNx4DI, VOID, _i64m4, _i64, _e64m4) -DEF_RVV_TYPE (vuint64m4_t, 16, __rvv_uint64m4_t, uint64, VNx4DI, VOID, _u64m4, +DEF_RVV_TYPE (vuint64m4_t, 16, __rvv_uint64m4_t, uint64, VNx8DI, VNx4DI, VOID, _u64m4, _u64, _e64m4) -DEF_RVV_TYPE (vint64m8_t, 15, __rvv_int64m8_t, int64, VNx8DI, VOID, _i64m8, +DEF_RVV_TYPE (vint64m8_t, 15, __rvv_int64m8_t, int64, VNx16DI, VNx8DI, VOID, _i64m8, _i64, _e64m8) -DEF_RVV_TYPE (vuint64m8_t, 16, __rvv_uint64m8_t, uint64, VNx8DI, VOID, _u64m8, +DEF_RVV_TYPE (vuint64m8_t, 16, __rvv_uint64m8_t, uint64, VNx16DI, VNx8DI, VOID, _u64m8, _u64, _e64m8) +/* Disable all when !TARGET_VECTOR_ELEN_FP_32. */ /* LMUL = 1/2: - Only enble when TARGET_MIN_VLEN > 32 and machine mode = VNx1SFmode. */ -DEF_RVV_TYPE (vfloat32mf2_t, 18, __rvv_float32mf2_t, float, VNx1SF, VOID, + Only enble when TARGET_MIN_VLEN > 32. + Machine mode = VNx1SFmode when TARGET_MIN_VLEN < 128. + Machine mode = VNx2SFmode when TARGET_MIN_VLEN >= 128. */ +DEF_RVV_TYPE (vfloat32mf2_t, 18, __rvv_float32mf2_t, float, VNx2SF, VNx1SF, VOID, _f32mf2, _f32, _e32mf2) /* LMUL = 1: + Machine mode = VNx4SFmode when TARGET_MIN_VLEN >= 128. Machine mode = VNx2SFmode when TARGET_MIN_VLEN > 32. Machine mode = VNx1SFmode when TARGET_MIN_VLEN = 32. */ -DEF_RVV_TYPE (vfloat32m1_t, 17, __rvv_float32m1_t, float, VNx2SF, VNx1SF, +DEF_RVV_TYPE (vfloat32m1_t, 17, __rvv_float32m1_t, float, VNx4SF, VNx2SF, VNx1SF, _f32m1, _f32, _e32m1) /* LMUL = 2: + Machine mode = VNx8SFmode when TARGET_MIN_VLEN >= 128. Machine mode = VNx4SFmode when TARGET_MIN_VLEN > 32. Machine mode = VNx2SFmode when TARGET_MIN_VLEN = 32. */ -DEF_RVV_TYPE (vfloat32m2_t, 17, __rvv_float32m2_t, float, VNx4SF, VNx2SF, +DEF_RVV_TYPE (vfloat32m2_t, 17, __rvv_float32m2_t, float, VNx8SF, VNx4SF, VNx2SF, _f32m2, _f32, _e32m2) /* LMUL = 4: + Machine mode = VNx16SFmode when TARGET_MIN_VLEN >= 128. Machine mode = VNx8SFmode when TARGET_MIN_VLEN > 32. Machine mode = VNx4SFmode when TARGET_MIN_VLEN = 32. */ -DEF_RVV_TYPE (vfloat32m4_t, 17, __rvv_float32m4_t, float, VNx8SF, VNx4SF, +DEF_RVV_TYPE (vfloat32m4_t, 17, __rvv_float32m4_t, float, VNx16SF, VNx8SF, VNx4SF, _f32m4, _f32, _e32m4) /* LMUL = 8: + Machine mode = VNx32SFmode when TARGET_MIN_VLEN >= 128. Machine mode = VNx16SFmode when TARGET_MIN_VLEN > 32. Machine mode = VNx8SFmode when TARGET_MIN_VLEN = 32. */ -DEF_RVV_TYPE (vfloat32m8_t, 17, __rvv_float32m8_t, float, VNx16SF, VNx8SF, +DEF_RVV_TYPE (vfloat32m8_t, 17, __rvv_float32m8_t, float, VNx32SF, VNx16SF, VNx8SF, _f32m8, _f32, _e32m8) /* SEW = 64: - Enable when TARGET_VECTOR_FP64. */ -DEF_RVV_TYPE (vfloat64m1_t, 17, __rvv_float64m1_t, double, VNx1DF, VOID, _f64m1, + Disable when !TARGET_VECTOR_ELEN_FP_64. */ +DEF_RVV_TYPE (vfloat64m1_t, 17, __rvv_float64m1_t, double, VNx2DF, VNx1DF, VOID, _f64m1, _f64, _e64m1) -DEF_RVV_TYPE (vfloat64m2_t, 17, __rvv_float64m2_t, double, VNx2DF, VOID, _f64m2, +DEF_RVV_TYPE (vfloat64m2_t, 17, __rvv_float64m2_t, double, VNx4DF, VNx2DF, VOID, _f64m2, _f64, _e64m2) -DEF_RVV_TYPE (vfloat64m4_t, 17, __rvv_float64m4_t, double, VNx4DF, VOID, _f64m4, +DEF_RVV_TYPE (vfloat64m4_t, 17, __rvv_float64m4_t, double, VNx8DF, VNx4DF, VOID, _f64m4, _f64, _e64m4) -DEF_RVV_TYPE (vfloat64m8_t, 17, __rvv_float64m8_t, double, VNx8DF, VOID, _f64m8, +DEF_RVV_TYPE (vfloat64m8_t, 17, __rvv_float64m8_t, double, VNx16DF, VNx8DF, VOID, _f64m8, _f64, _e64m8) DEF_RVV_OP_TYPE (vv) diff --git a/gcc/config/riscv/riscv-vector-switch.def b/gcc/config/riscv/riscv-vector-switch.def index 3b944547b49..8aae22d3259 100644 --- a/gcc/config/riscv/riscv-vector-switch.def +++ b/gcc/config/riscv/riscv-vector-switch.def @@ -81,69 +81,80 @@ TODO: FP16 vector needs support of 'zvfh', we don't support it yet. */ For example: 'MODE' = VNx64BImode needs TARGET_MIN_VLEN > 32. */ #ifndef ENTRY #define ENTRY(MODE, REQUIREMENT, VLMUL_FOR_MIN_VLEN32, RATIO_FOR_MIN_VLEN32, \ - VLMUL_FOR_MIN_VLEN64, RATIO_FOR_MIN_VLEN64) + VLMUL_FOR_MIN_VLEN64, RATIO_FOR_MIN_VLEN64, \ + VLMUL_FOR_MIN_VLEN128, RATIO_FOR_MIN_VLEN128) #endif /* Mask modes. Disable VNx64BImode when TARGET_MIN_VLEN == 32. */ -ENTRY (VNx64BI, TARGET_MIN_VLEN > 32, LMUL_RESERVED, 0, LMUL_8, 1) -ENTRY (VNx32BI, true, LMUL_8, 1, LMUL_4, 2) -ENTRY (VNx16BI, true, LMUL_4, 2, LMUL_2, 4) -ENTRY (VNx8BI, true, LMUL_2, 4, LMUL_1, 8) -ENTRY (VNx4BI, true, LMUL_1, 8, LMUL_F2, 16) -ENTRY (VNx2BI, true, LMUL_F2, 16, LMUL_F4, 32) -ENTRY (VNx1BI, true, LMUL_F4, 32, LMUL_F8, 64) +ENTRY (VNx128BI, TARGET_MIN_VLEN >= 128, LMUL_RESERVED, 0, LMUL_RESERVED, 0, LMUL_8, 1) +ENTRY (VNx64BI, TARGET_MIN_VLEN > 32, LMUL_RESERVED, 0, LMUL_8, 1, LMUL_4, 2) +ENTRY (VNx32BI, true, LMUL_8, 1, LMUL_4, 2, LMUL_2, 4) +ENTRY (VNx16BI, true, LMUL_4, 2, LMUL_2, 4, LMUL_1, 8) +ENTRY (VNx8BI, true, LMUL_2, 4, LMUL_1, 8, LMUL_F2, 16) +ENTRY (VNx4BI, true, LMUL_1, 8, LMUL_F2, 16, LMUL_F4, 32) +ENTRY (VNx2BI, true, LMUL_F2, 16, LMUL_F4, 32, LMUL_F8, 64) +ENTRY (VNx1BI, TARGET_MIN_VLEN < 128, LMUL_F4, 32, LMUL_F8, 64, LMUL_RESERVED, 0) /* SEW = 8. Disable VNx64QImode when TARGET_MIN_VLEN == 32. */ -ENTRY (VNx64QI, TARGET_MIN_VLEN > 32, LMUL_RESERVED, 0, LMUL_8, 1) -ENTRY (VNx32QI, true, LMUL_8, 1, LMUL_4, 2) -ENTRY (VNx16QI, true, LMUL_4, 2, LMUL_2, 4) -ENTRY (VNx8QI, true, LMUL_2, 4, LMUL_1, 8) -ENTRY (VNx4QI, true, LMUL_1, 8, LMUL_F2, 16) -ENTRY (VNx2QI, true, LMUL_F2, 16, LMUL_F4, 32) -ENTRY (VNx1QI, true, LMUL_F4, 32, LMUL_F8, 64) +ENTRY (VNx128QI, TARGET_MIN_VLEN >= 128, LMUL_RESERVED, 0, LMUL_RESERVED, 0, LMUL_8, 1) +ENTRY (VNx64QI, TARGET_MIN_VLEN > 32, LMUL_RESERVED, 0, LMUL_8, 1, LMUL_4, 2) +ENTRY (VNx32QI, true, LMUL_8, 1, LMUL_4, 2, LMUL_2, 4) +ENTRY (VNx16QI, true, LMUL_4, 2, LMUL_2, 4, LMUL_1, 8) +ENTRY (VNx8QI, true, LMUL_2, 4, LMUL_1, 8, LMUL_F2, 16) +ENTRY (VNx4QI, true, LMUL_1, 8, LMUL_F2, 16, LMUL_F4, 32) +ENTRY (VNx2QI, true, LMUL_F2, 16, LMUL_F4, 32, LMUL_F8, 64) +ENTRY (VNx1QI, TARGET_MIN_VLEN < 128, LMUL_F4, 32, LMUL_F8, 64, LMUL_RESERVED, 0) /* SEW = 16. Disable VNx32HImode when TARGET_MIN_VLEN == 32. */ -ENTRY (VNx32HI, TARGET_MIN_VLEN > 32, LMUL_RESERVED, 0, LMUL_8, 2) -ENTRY (VNx16HI, true, LMUL_8, 2, LMUL_4, 4) -ENTRY (VNx8HI, true, LMUL_4, 4, LMUL_2, 8) -ENTRY (VNx4HI, true, LMUL_2, 8, LMUL_1, 16) -ENTRY (VNx2HI, true, LMUL_1, 16, LMUL_F2, 32) -ENTRY (VNx1HI, true, LMUL_F2, 32, LMUL_F4, 64) +ENTRY (VNx64HI, TARGET_MIN_VLEN >= 128, LMUL_RESERVED, 0, LMUL_RESERVED, 0, LMUL_8, 2) +ENTRY (VNx32HI, TARGET_MIN_VLEN > 32, LMUL_RESERVED, 0, LMUL_8, 2, LMUL_4, 4) +ENTRY (VNx16HI, true, LMUL_8, 2, LMUL_4, 4, LMUL_2, 8) +ENTRY (VNx8HI, true, LMUL_4, 4, LMUL_2, 8, LMUL_1, 16) +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 (VNx32HF, false, LMUL_RESERVED, 0, LMUL_8, 2) -ENTRY (VNx16HF, false, LMUL_8, 2, LMUL_4, 4) -ENTRY (VNx8HF, false, LMUL_4, 4, LMUL_2, 8) -ENTRY (VNx4HF, false, LMUL_2, 8, LMUL_1, 16) -ENTRY (VNx2HF, false, LMUL_1, 16, LMUL_F2, 32) -ENTRY (VNx1HF, false, LMUL_F2, 32, LMUL_F4, 64) +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 = 32. Disable VNx16SImode when TARGET_MIN_VLEN == 32. For single-precision floating-point, we need TARGET_VECTOR_ELEN_FP_32 to be true. */ -ENTRY (VNx16SI, TARGET_MIN_VLEN > 32, LMUL_RESERVED, 0, LMUL_8, 4) -ENTRY (VNx8SI, true, LMUL_8, 4, LMUL_4, 8) -ENTRY (VNx4SI, true, LMUL_4, 8, LMUL_2, 16) -ENTRY (VNx2SI, true, LMUL_2, 16, LMUL_1, 32) -ENTRY (VNx1SI, true, LMUL_1, 32, LMUL_F2, 64) - -ENTRY (VNx16SF, TARGET_VECTOR_ELEN_FP_32, LMUL_RESERVED, 0, LMUL_8, 4) -ENTRY (VNx8SF, TARGET_VECTOR_ELEN_FP_32, LMUL_8, 4, LMUL_4, 8) -ENTRY (VNx4SF, TARGET_VECTOR_ELEN_FP_32, LMUL_4, 8, LMUL_2, 16) -ENTRY (VNx2SF, TARGET_VECTOR_ELEN_FP_32, LMUL_2, 16, LMUL_1, 32) -ENTRY (VNx1SF, TARGET_VECTOR_ELEN_FP_32, LMUL_1, 32, LMUL_F2, 64) +ENTRY (VNx32SI, TARGET_MIN_VLEN >= 128, LMUL_RESERVED, 0, LMUL_RESERVED, 0, LMUL_8, 4) +ENTRY (VNx16SI, TARGET_MIN_VLEN > 32, LMUL_RESERVED, 0, LMUL_8, 4, LMUL_4, 8) +ENTRY (VNx8SI, true, LMUL_8, 4, LMUL_4, 8, LMUL_2, 16) +ENTRY (VNx4SI, true, LMUL_4, 8, LMUL_2, 16, LMUL_1, 32) +ENTRY (VNx2SI, true, LMUL_2, 16, LMUL_1, 32, LMUL_F2, 64) +ENTRY (VNx1SI, TARGET_MIN_VLEN < 128, LMUL_1, 32, LMUL_F2, 64, LMUL_RESERVED, 0) + +ENTRY (VNx32SF, TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN >= 128, LMUL_RESERVED, 0, LMUL_RESERVED, 0, LMUL_8, 4) +ENTRY (VNx16SF, TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32, LMUL_RESERVED, 0, + LMUL_8, 4, LMUL_4, 8) +ENTRY (VNx8SF, TARGET_VECTOR_ELEN_FP_32, LMUL_8, 4, LMUL_4, 8, LMUL_2, 16) +ENTRY (VNx4SF, TARGET_VECTOR_ELEN_FP_32, LMUL_4, 8, LMUL_2, 16, LMUL_1, 32) +ENTRY (VNx2SF, TARGET_VECTOR_ELEN_FP_32, LMUL_2, 16, LMUL_1, 32, LMUL_F2, 64) +ENTRY (VNx1SF, TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN < 128, LMUL_1, 32, LMUL_F2, 64, LMUL_RESERVED, 0) /* SEW = 64. Enable when TARGET_VECTOR_ELEN_64 is true. For double-precision floating-point, we need TARGET_VECTOR_ELEN_FP_64 to be true. */ -ENTRY (VNx8DI, TARGET_VECTOR_ELEN_64, LMUL_RESERVED, 0, LMUL_8, 8) -ENTRY (VNx4DI, TARGET_VECTOR_ELEN_64, LMUL_RESERVED, 0, LMUL_4, 16) -ENTRY (VNx2DI, TARGET_VECTOR_ELEN_64, LMUL_RESERVED, 0, LMUL_2, 32) -ENTRY (VNx1DI, TARGET_VECTOR_ELEN_64, LMUL_RESERVED, 0, LMUL_1, 64) - -ENTRY (VNx8DF, TARGET_VECTOR_ELEN_FP_64, LMUL_RESERVED, 0, LMUL_8, 8) -ENTRY (VNx4DF, TARGET_VECTOR_ELEN_FP_64, LMUL_RESERVED, 0, LMUL_4, 16) -ENTRY (VNx2DF, TARGET_VECTOR_ELEN_FP_64, LMUL_RESERVED, 0, LMUL_2, 32) -ENTRY (VNx1DF, TARGET_VECTOR_ELEN_FP_64, LMUL_RESERVED, 0, LMUL_1, 64) +ENTRY (VNx16DI, TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 128, LMUL_RESERVED, 0, LMUL_RESERVED, 0, LMUL_8, 8) +ENTRY (VNx8DI, TARGET_VECTOR_ELEN_64, LMUL_RESERVED, 0, LMUL_8, 8, LMUL_4, 16) +ENTRY (VNx4DI, TARGET_VECTOR_ELEN_64, LMUL_RESERVED, 0, LMUL_4, 16, LMUL_2, 32) +ENTRY (VNx2DI, TARGET_VECTOR_ELEN_64, LMUL_RESERVED, 0, LMUL_2, 32, LMUL_1, 64) +ENTRY (VNx1DI, TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN < 128, LMUL_RESERVED, 0, LMUL_1, 64, LMUL_RESERVED, 0) + +ENTRY (VNx16DF, TARGET_VECTOR_ELEN_FP_64 && TARGET_MIN_VLEN >= 128, LMUL_RESERVED, 0, LMUL_RESERVED, 0, LMUL_8, 8) +ENTRY (VNx8DF, TARGET_VECTOR_ELEN_FP_64 && TARGET_MIN_VLEN > 32, LMUL_RESERVED, 0, + LMUL_8, 8, LMUL_4, 16) +ENTRY (VNx4DF, TARGET_VECTOR_ELEN_FP_64, LMUL_RESERVED, 0, LMUL_4, 16, LMUL_2, 32) +ENTRY (VNx2DF, TARGET_VECTOR_ELEN_FP_64, LMUL_RESERVED, 0, LMUL_2, 32, LMUL_1, 64) +ENTRY (VNx1DF, TARGET_VECTOR_ELEN_FP_64 && TARGET_MIN_VLEN < 128, LMUL_RESERVED, 0, LMUL_1, 64, LMUL_RESERVED, 0) #undef ENTRY diff --git a/gcc/config/riscv/riscv.cc b/gcc/config/riscv/riscv.cc index dc47434fac4..a0b32a247b6 100644 --- a/gcc/config/riscv/riscv.cc +++ b/gcc/config/riscv/riscv.cc @@ -1974,6 +1974,8 @@ riscv_legitimize_poly_move (machine_mode mode, rtx dest, rtx tmp, rtx src) div_factor = 4; else if ((factor % (vlenb / 8)) == 0) div_factor = 8; + else if ((factor % (vlenb / 16)) == 0) + div_factor = 16; else gcc_unreachable (); @@ -6181,7 +6183,15 @@ riscv_init_machine_status (void) static poly_uint16 riscv_convert_vector_bits (void) { - if (TARGET_MIN_VLEN > 32) + if (TARGET_MIN_VLEN >= 128) + { + /* We have Full 'V' extension for application processors. It's specified + by -march=rv64gcv/rv32gcv, The 'V' extension depends upon the Zvl128b + and Zve64d extensions. Thus the number of bytes in a vector is 16 + 16 + * x1 which is riscv_vector_chunks * 16 = poly_int (16, 16). */ + riscv_bytes_per_vector_chunk = 16; + } + else if (TARGET_MIN_VLEN > 32) { /* When targetting minimum VLEN > 32, we should use 64-bit chunk size. Otherwise we can not include SEW = 64bits. diff --git a/gcc/config/riscv/riscv.md b/gcc/config/riscv/riscv.md index bc384d9aedf..1fb29da8a0b 100644 --- a/gcc/config/riscv/riscv.md +++ b/gcc/config/riscv/riscv.md @@ -163,13 +163,13 @@ ;; Main data type used by the insn (define_attr "mode" "unknown,none,QI,HI,SI,DI,TI,HF,SF,DF,TF, - VNx1BI,VNx2BI,VNx4BI,VNx8BI,VNx16BI,VNx32BI,VNx64BI, - VNx1QI,VNx2QI,VNx4QI,VNx8QI,VNx16QI,VNx32QI,VNx64QI, - VNx1HI,VNx2HI,VNx4HI,VNx8HI,VNx16HI,VNx32HI, - VNx1SI,VNx2SI,VNx4SI,VNx8SI,VNx16SI, - VNx1DI,VNx2DI,VNx4DI,VNx8DI, - VNx1SF,VNx2SF,VNx4SF,VNx8SF,VNx16SF, - VNx1DF,VNx2DF,VNx4DF,VNx8DF" + VNx1BI,VNx2BI,VNx4BI,VNx8BI,VNx16BI,VNx32BI,VNx64BI,VNx128BI, + VNx1QI,VNx2QI,VNx4QI,VNx8QI,VNx16QI,VNx32QI,VNx64QI,VNx128QI, + VNx1HI,VNx2HI,VNx4HI,VNx8HI,VNx16HI,VNx32HI,VNx64HI, + VNx1SI,VNx2SI,VNx4SI,VNx8SI,VNx16SI,VNx32SI, + VNx1DI,VNx2DI,VNx4DI,VNx8DI,VNx16DI, + VNx1SF,VNx2SF,VNx4SF,VNx8SF,VNx16SF,VNx32SF, + VNx1DF,VNx2DF,VNx4DF,VNx8DF,VNx16DF" (const_string "unknown")) ;; True if the main data type is twice the size of a word. diff --git a/gcc/config/riscv/vector-iterators.md b/gcc/config/riscv/vector-iterators.md index 70ad85b661b..3c6575208be 100644 --- a/gcc/config/riscv/vector-iterators.md +++ b/gcc/config/riscv/vector-iterators.md @@ -83,157 +83,181 @@ ]) (define_mode_iterator V [ - VNx1QI VNx2QI VNx4QI VNx8QI VNx16QI VNx32QI (VNx64QI "TARGET_MIN_VLEN > 32") - VNx1HI VNx2HI VNx4HI VNx8HI VNx16HI (VNx32HI "TARGET_MIN_VLEN > 32") - VNx1SI VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN > 32") - (VNx1DI "TARGET_VECTOR_ELEN_64") (VNx2DI "TARGET_VECTOR_ELEN_64") - (VNx4DI "TARGET_VECTOR_ELEN_64") (VNx8DI "TARGET_VECTOR_ELEN_64") - (VNx1SF "TARGET_VECTOR_ELEN_FP_32") + (VNx1QI "TARGET_MIN_VLEN < 128") VNx2QI VNx4QI VNx8QI VNx16QI VNx32QI (VNx64QI "TARGET_MIN_VLEN > 32") (VNx128QI "TARGET_MIN_VLEN >= 128") + (VNx1HI "TARGET_MIN_VLEN < 128") VNx2HI VNx4HI VNx8HI VNx16HI (VNx32HI "TARGET_MIN_VLEN > 32") (VNx64HI "TARGET_MIN_VLEN >= 128") + (VNx1SI "TARGET_MIN_VLEN < 128") VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN > 32") (VNx32SI "TARGET_MIN_VLEN >= 128") + (VNx1DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN < 128") (VNx2DI "TARGET_VECTOR_ELEN_64") + (VNx4DI "TARGET_VECTOR_ELEN_64") (VNx8DI "TARGET_VECTOR_ELEN_64") (VNx16DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 128") + (VNx1SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN < 128") (VNx2SF "TARGET_VECTOR_ELEN_FP_32") (VNx4SF "TARGET_VECTOR_ELEN_FP_32") (VNx8SF "TARGET_VECTOR_ELEN_FP_32") (VNx16SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32") - (VNx1DF "TARGET_VECTOR_ELEN_FP_64") + (VNx32SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN >= 128") + (VNx1DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_MIN_VLEN < 128") (VNx2DF "TARGET_VECTOR_ELEN_FP_64") (VNx4DF "TARGET_VECTOR_ELEN_FP_64") (VNx8DF "TARGET_VECTOR_ELEN_FP_64") + (VNx16DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_MIN_VLEN >= 128") ]) (define_mode_iterator VEEWEXT2 [ - VNx1HI VNx2HI VNx4HI VNx8HI VNx16HI (VNx32HI "TARGET_MIN_VLEN > 32") - VNx1SI VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN > 32") - (VNx1DI "TARGET_VECTOR_ELEN_64") (VNx2DI "TARGET_VECTOR_ELEN_64") - (VNx4DI "TARGET_VECTOR_ELEN_64") (VNx8DI "TARGET_VECTOR_ELEN_64") - (VNx1SF "TARGET_VECTOR_ELEN_FP_32") + (VNx1HI "TARGET_MIN_VLEN < 128") VNx2HI VNx4HI VNx8HI VNx16HI (VNx32HI "TARGET_MIN_VLEN > 32") (VNx64HI "TARGET_MIN_VLEN >= 128") + (VNx1SI "TARGET_MIN_VLEN < 128") VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN > 32") (VNx32SI "TARGET_MIN_VLEN >= 128") + (VNx1DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN < 128") (VNx2DI "TARGET_VECTOR_ELEN_64") + (VNx4DI "TARGET_VECTOR_ELEN_64") (VNx8DI "TARGET_VECTOR_ELEN_64") (VNx16DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 128") + (VNx1SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN < 128") (VNx2SF "TARGET_VECTOR_ELEN_FP_32") (VNx4SF "TARGET_VECTOR_ELEN_FP_32") (VNx8SF "TARGET_VECTOR_ELEN_FP_32") (VNx16SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32") - (VNx1DF "TARGET_VECTOR_ELEN_FP_64") + (VNx32SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN >= 128") + (VNx1DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_MIN_VLEN < 128") (VNx2DF "TARGET_VECTOR_ELEN_FP_64") (VNx4DF "TARGET_VECTOR_ELEN_FP_64") (VNx8DF "TARGET_VECTOR_ELEN_FP_64") + (VNx16DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_MIN_VLEN >= 128") ]) (define_mode_iterator VEEWEXT4 [ - VNx1SI VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN > 32") - (VNx1DI "TARGET_VECTOR_ELEN_64") (VNx2DI "TARGET_VECTOR_ELEN_64") - (VNx4DI "TARGET_VECTOR_ELEN_64") (VNx8DI "TARGET_VECTOR_ELEN_64") - (VNx1SF "TARGET_VECTOR_ELEN_FP_32") + (VNx1SI "TARGET_MIN_VLEN < 128") VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN > 32") (VNx32SI "TARGET_MIN_VLEN >= 128") + (VNx1DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN < 128") (VNx2DI "TARGET_VECTOR_ELEN_64") + (VNx4DI "TARGET_VECTOR_ELEN_64") (VNx8DI "TARGET_VECTOR_ELEN_64") (VNx16DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 128") + (VNx1SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN < 128") (VNx2SF "TARGET_VECTOR_ELEN_FP_32") (VNx4SF "TARGET_VECTOR_ELEN_FP_32") (VNx8SF "TARGET_VECTOR_ELEN_FP_32") (VNx16SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32") - (VNx1DF "TARGET_VECTOR_ELEN_FP_64") + (VNx32SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN >= 128") + (VNx1DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_MIN_VLEN < 128") (VNx2DF "TARGET_VECTOR_ELEN_FP_64") (VNx4DF "TARGET_VECTOR_ELEN_FP_64") (VNx8DF "TARGET_VECTOR_ELEN_FP_64") + (VNx16DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_MIN_VLEN >= 128") ]) (define_mode_iterator VEEWEXT8 [ (VNx1DI "TARGET_VECTOR_ELEN_64") (VNx2DI "TARGET_VECTOR_ELEN_64") - (VNx4DI "TARGET_VECTOR_ELEN_64") (VNx8DI "TARGET_VECTOR_ELEN_64") - (VNx1DF "TARGET_VECTOR_ELEN_FP_64") + (VNx4DI "TARGET_VECTOR_ELEN_64") (VNx8DI "TARGET_VECTOR_ELEN_64") (VNx16DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 128") + (VNx1DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_MIN_VLEN < 128") (VNx2DF "TARGET_VECTOR_ELEN_FP_64") (VNx4DF "TARGET_VECTOR_ELEN_FP_64") (VNx8DF "TARGET_VECTOR_ELEN_FP_64") + (VNx16DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_MIN_VLEN >= 128") ]) (define_mode_iterator VEEWTRUNC2 [ - VNx1QI VNx2QI VNx4QI VNx8QI VNx16QI VNx32QI - VNx1HI VNx2HI VNx4HI VNx8HI VNx16HI - VNx1SI VNx2SI VNx4SI VNx8SI - (VNx1SF "TARGET_VECTOR_ELEN_FP_32") + (VNx1QI "TARGET_MIN_VLEN < 128") VNx2QI VNx4QI VNx8QI VNx16QI VNx32QI (VNx64QI "TARGET_MIN_VLEN >= 128") + (VNx1HI "TARGET_MIN_VLEN < 128") VNx2HI VNx4HI VNx8HI VNx16HI (VNx32HI "TARGET_MIN_VLEN >= 128") + (VNx1SI "TARGET_MIN_VLEN < 128") VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN >= 128") + (VNx1SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN < 128") (VNx2SF "TARGET_VECTOR_ELEN_FP_32") (VNx4SF "TARGET_VECTOR_ELEN_FP_32") (VNx8SF "TARGET_VECTOR_ELEN_FP_32") + (VNx16SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN >= 128") ]) (define_mode_iterator VEEWTRUNC4 [ - VNx1QI VNx2QI VNx4QI VNx8QI VNx16QI - VNx1HI VNx2HI VNx4HI VNx8HI + (VNx1QI "TARGET_MIN_VLEN < 128") VNx2QI VNx4QI VNx8QI VNx16QI (VNx32QI "TARGET_MIN_VLEN >= 128") + (VNx1HI "TARGET_MIN_VLEN < 128") VNx2HI VNx4HI VNx8HI (VNx16HI "TARGET_MIN_VLEN >= 128") ]) (define_mode_iterator VEEWTRUNC8 [ - VNx1QI VNx2QI VNx4QI VNx8QI + (VNx1QI "TARGET_MIN_VLEN < 128") VNx2QI VNx4QI VNx8QI (VNx16QI "TARGET_MIN_VLEN >= 128") ]) (define_mode_iterator VLMULEXT2 [ - VNx1QI VNx2QI VNx4QI VNx8QI VNx16QI VNx32QI - VNx1HI VNx2HI VNx4HI VNx8HI VNx16HI - VNx1SI VNx2SI VNx4SI VNx8SI - (VNx1DI "TARGET_VECTOR_ELEN_64") (VNx2DI "TARGET_VECTOR_ELEN_64") - (VNx4DI "TARGET_VECTOR_ELEN_64") - (VNx1SF "TARGET_VECTOR_ELEN_FP_32") + (VNx1QI "TARGET_MIN_VLEN < 128") VNx2QI VNx4QI VNx8QI VNx16QI VNx32QI (VNx64QI "TARGET_MIN_VLEN >= 128") + (VNx1HI "TARGET_MIN_VLEN < 128") VNx2HI VNx4HI VNx8HI VNx16HI (VNx32HI "TARGET_MIN_VLEN >= 128") + (VNx1SI "TARGET_MIN_VLEN < 128") VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN >= 128") + (VNx1DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN < 128") (VNx2DI "TARGET_VECTOR_ELEN_64") + (VNx4DI "TARGET_VECTOR_ELEN_64") (VNx8DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 128") + (VNx1SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN < 128") (VNx2SF "TARGET_VECTOR_ELEN_FP_32") (VNx4SF "TARGET_VECTOR_ELEN_FP_32") (VNx8SF "TARGET_VECTOR_ELEN_FP_32") + (VNx16SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN >= 128") (VNx1DF "TARGET_VECTOR_ELEN_FP_64") (VNx2DF "TARGET_VECTOR_ELEN_FP_64") (VNx4DF "TARGET_VECTOR_ELEN_FP_64") + (VNx8DF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN >= 128") ]) (define_mode_iterator VLMULEXT4 [ - VNx1QI VNx2QI VNx4QI VNx8QI VNx16QI - VNx1HI VNx2HI VNx4HI VNx8HI - VNx1SI VNx2SI VNx4SI - (VNx1DI "TARGET_VECTOR_ELEN_64") (VNx2DI "TARGET_VECTOR_ELEN_64") - (VNx1SF "TARGET_VECTOR_ELEN_FP_32") + (VNx1QI "TARGET_MIN_VLEN < 128") VNx2QI VNx4QI VNx8QI VNx16QI (VNx32QI "TARGET_MIN_VLEN >= 128") + (VNx1HI "TARGET_MIN_VLEN < 128") VNx2HI VNx4HI VNx8HI (VNx16HI "TARGET_MIN_VLEN >= 128") + (VNx1SI "TARGET_MIN_VLEN < 128") VNx2SI VNx4SI (VNx8SI "TARGET_MIN_VLEN >= 128") + (VNx1DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN < 128") (VNx2DI "TARGET_VECTOR_ELEN_64") + (VNx1SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN < 128") (VNx2SF "TARGET_VECTOR_ELEN_FP_32") (VNx4SF "TARGET_VECTOR_ELEN_FP_32") - (VNx1DF "TARGET_VECTOR_ELEN_FP_64") + (VNx8SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN >= 128") + (VNx1DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_MIN_VLEN < 128") (VNx2DF "TARGET_VECTOR_ELEN_FP_64") + (VNx4DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_MIN_VLEN >= 128") ]) (define_mode_iterator VLMULEXT8 [ - VNx1QI VNx2QI VNx4QI VNx8QI - VNx1HI VNx2HI VNx4HI - VNx1SI VNx2SI - (VNx1DI "TARGET_VECTOR_ELEN_64") - (VNx1SF "TARGET_VECTOR_ELEN_FP_32") + (VNx1QI "TARGET_MIN_VLEN < 128") VNx2QI VNx4QI VNx8QI (VNx16QI "TARGET_MIN_VLEN >= 128") + (VNx1HI "TARGET_MIN_VLEN < 128") VNx2HI VNx4HI (VNx8HI "TARGET_MIN_VLEN >= 128") + (VNx1SI "TARGET_MIN_VLEN < 128") VNx2SI (VNx4SI "TARGET_MIN_VLEN >= 128") + (VNx1DI "TARGET_VECTOR_ELEN_64") (VNx2DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 128") + (VNx1SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN < 128") (VNx2SF "TARGET_VECTOR_ELEN_FP_32") + (VNx4SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN >= 128") (VNx1DF "TARGET_VECTOR_ELEN_FP_64") + (VNx2DF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN >= 128") ]) (define_mode_iterator VLMULEXT16 [ - VNx1QI VNx2QI VNx4QI - VNx1HI VNx2HI - VNx1SI - (VNx1SF "TARGET_VECTOR_ELEN_FP_32") + (VNx1QI "TARGET_MIN_VLEN < 128") VNx2QI VNx4QI (VNx8QI "TARGET_MIN_VLEN >= 128") + (VNx1HI "TARGET_MIN_VLEN < 128") VNx2HI (VNx4HI "TARGET_MIN_VLEN >= 128") + (VNx1SI "TARGET_MIN_VLEN < 128") (VNx2SI "TARGET_MIN_VLEN >= 128") + (VNx1SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN < 128") + (VNx2SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN >= 128") ]) (define_mode_iterator VLMULEXT32 [ - VNx1QI VNx2QI - VNx1HI + (VNx1QI "TARGET_MIN_VLEN < 128") VNx2QI (VNx4QI "TARGET_MIN_VLEN >= 128") + (VNx1HI "TARGET_MIN_VLEN < 128") ]) (define_mode_iterator VLMULEXT64 [ - VNx1QI + (VNx1QI "TARGET_MIN_VLEN < 128") (VNx2QI "TARGET_MIN_VLEN >= 128") ]) (define_mode_iterator VEI16 [ - VNx1QI VNx2QI VNx4QI VNx8QI VNx16QI VNx32QI - VNx1HI VNx2HI VNx4HI VNx8HI VNx16HI (VNx32HI "TARGET_MIN_VLEN > 32") - VNx1SI VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN > 32") - (VNx1DI "TARGET_VECTOR_ELEN_64") (VNx2DI "TARGET_VECTOR_ELEN_64") - (VNx4DI "TARGET_VECTOR_ELEN_64") (VNx8DI "TARGET_VECTOR_ELEN_64") - (VNx1SF "TARGET_VECTOR_ELEN_FP_32") + (VNx1QI "TARGET_MIN_VLEN < 128") VNx2QI VNx4QI VNx8QI VNx16QI VNx32QI (VNx64QI "TARGET_MIN_VLEN >= 128") + (VNx1HI "TARGET_MIN_VLEN < 128") VNx2HI VNx4HI VNx8HI VNx16HI (VNx32HI "TARGET_MIN_VLEN > 32") (VNx64HI "TARGET_MIN_VLEN >= 128") + (VNx1SI "TARGET_MIN_VLEN < 128") VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN > 32") (VNx32SI "TARGET_MIN_VLEN >= 128") + (VNx1DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN < 128") (VNx2DI "TARGET_VECTOR_ELEN_64") + (VNx4DI "TARGET_VECTOR_ELEN_64") (VNx8DI "TARGET_VECTOR_ELEN_64") (VNx16DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 128") + (VNx1SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN < 128") (VNx2SF "TARGET_VECTOR_ELEN_FP_32") (VNx4SF "TARGET_VECTOR_ELEN_FP_32") (VNx8SF "TARGET_VECTOR_ELEN_FP_32") (VNx16SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32") - (VNx1DF "TARGET_VECTOR_ELEN_FP_64") + (VNx32SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN >= 128") + (VNx1DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_MIN_VLEN < 128") (VNx2DF "TARGET_VECTOR_ELEN_FP_64") (VNx4DF "TARGET_VECTOR_ELEN_FP_64") (VNx8DF "TARGET_VECTOR_ELEN_FP_64") + (VNx16DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_MIN_VLEN >= 128") ]) (define_mode_iterator VI [ - VNx1QI VNx2QI VNx4QI VNx8QI VNx16QI VNx32QI (VNx64QI "TARGET_MIN_VLEN > 32") - VNx1HI VNx2HI VNx4HI VNx8HI VNx16HI (VNx32HI "TARGET_MIN_VLEN > 32") - VNx1SI VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN > 32") - (VNx1DI "TARGET_VECTOR_ELEN_64") (VNx2DI "TARGET_VECTOR_ELEN_64") - (VNx4DI "TARGET_VECTOR_ELEN_64") (VNx8DI "TARGET_VECTOR_ELEN_64") + (VNx1QI "TARGET_MIN_VLEN < 128") VNx2QI VNx4QI VNx8QI VNx16QI VNx32QI (VNx64QI "TARGET_MIN_VLEN > 32") (VNx128QI "TARGET_MIN_VLEN >= 128") + (VNx1HI "TARGET_MIN_VLEN < 128") VNx2HI VNx4HI VNx8HI VNx16HI (VNx32HI "TARGET_MIN_VLEN > 32") (VNx64HI "TARGET_MIN_VLEN >= 128") + (VNx1SI "TARGET_MIN_VLEN < 128") VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN > 32") (VNx32SI "TARGET_MIN_VLEN >= 128") + (VNx1DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN < 128") (VNx2DI "TARGET_VECTOR_ELEN_64") + (VNx4DI "TARGET_VECTOR_ELEN_64") (VNx8DI "TARGET_VECTOR_ELEN_64") (VNx16DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 128") +]) + +(define_mode_iterator VI_ZVE64 [ + VNx1QI VNx2QI VNx4QI VNx8QI VNx16QI VNx32QI VNx64QI + VNx1HI VNx2HI VNx4HI VNx8HI VNx16HI VNx32HI + VNx1SI VNx2SI VNx4SI VNx8SI VNx16SI + VNx1DI VNx2DI VNx4DI VNx8DI ]) (define_mode_iterator VI_ZVE32 [ @@ -243,9 +267,15 @@ ]) (define_mode_iterator VWI [ - VNx1QI VNx2QI VNx4QI VNx8QI VNx16QI VNx32QI (VNx64QI "TARGET_MIN_VLEN > 32") - VNx1HI VNx2HI VNx4HI VNx8HI VNx16HI (VNx32HI "TARGET_MIN_VLEN > 32") - VNx1SI VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN > 32") + (VNx1QI "TARGET_MIN_VLEN < 128") VNx2QI VNx4QI VNx8QI VNx16QI VNx32QI (VNx64QI "TARGET_MIN_VLEN > 32") (VNx128QI "TARGET_MIN_VLEN >= 128") + (VNx1HI "TARGET_MIN_VLEN < 128") VNx2HI VNx4HI VNx8HI VNx16HI (VNx32HI "TARGET_MIN_VLEN > 32") (VNx64HI "TARGET_MIN_VLEN >= 128") + (VNx1SI "TARGET_MIN_VLEN < 128") VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN > 32") (VNx32SI "TARGET_MIN_VLEN >= 128") +]) + +(define_mode_iterator VWI_ZVE64 [ + VNx1QI VNx2QI VNx4QI VNx8QI VNx16QI VNx32QI VNx64QI + VNx1HI VNx2HI VNx4HI VNx8HI VNx16HI VNx32HI + VNx1SI VNx2SI VNx4SI VNx8SI VNx16SI ]) (define_mode_iterator VWI_ZVE32 [ @@ -254,15 +284,22 @@ ]) (define_mode_iterator VF [ - (VNx1SF "TARGET_VECTOR_ELEN_FP_32") + (VNx1SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN < 128") (VNx2SF "TARGET_VECTOR_ELEN_FP_32") (VNx4SF "TARGET_VECTOR_ELEN_FP_32") (VNx8SF "TARGET_VECTOR_ELEN_FP_32") (VNx16SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32") - (VNx1DF "TARGET_VECTOR_ELEN_FP_64") + (VNx32SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN >= 128") + (VNx1DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_MIN_VLEN < 128") (VNx2DF "TARGET_VECTOR_ELEN_FP_64") (VNx4DF "TARGET_VECTOR_ELEN_FP_64") (VNx8DF "TARGET_VECTOR_ELEN_FP_64") + (VNx16DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_MIN_VLEN >= 128") +]) + +(define_mode_iterator VF_ZVE64 [ + VNx1SF VNx2SF VNx4SF VNx8SF VNx16SF + VNx1DF VNx2DF VNx4DF VNx8DF ]) (define_mode_iterator VF_ZVE32 [ @@ -273,38 +310,40 @@ ]) (define_mode_iterator VWF [ - VNx1SF VNx2SF VNx4SF VNx8SF (VNx16SF "TARGET_MIN_VLEN > 32") + (VNx1SF "TARGET_MIN_VLEN < 128") VNx2SF VNx4SF VNx8SF (VNx16SF "TARGET_MIN_VLEN > 32") (VNx32SF "TARGET_MIN_VLEN >= 128") +]) + +(define_mode_iterator VWF_ZVE64 [ + VNx1SF VNx2SF VNx4SF VNx8SF VNx16SF ]) (define_mode_iterator VFULLI [ - VNx1QI VNx2QI VNx4QI VNx8QI VNx16QI VNx32QI (VNx64QI "TARGET_MIN_VLEN > 32") - VNx1HI VNx2HI VNx4HI VNx8HI VNx16HI (VNx32HI "TARGET_MIN_VLEN > 32") - VNx1SI VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN > 32") - (VNx1DI "TARGET_FULL_V") (VNx2DI "TARGET_FULL_V") - (VNx4DI "TARGET_FULL_V") (VNx8DI "TARGET_FULL_V") + (VNx1QI "!TARGET_FULL_V") VNx2QI VNx4QI VNx8QI VNx16QI VNx32QI (VNx64QI "TARGET_MIN_VLEN > 32") (VNx128QI "TARGET_FULL_V") + (VNx1HI "!TARGET_FULL_V") VNx2HI VNx4HI VNx8HI VNx16HI (VNx32HI "TARGET_MIN_VLEN > 32") (VNx64HI "TARGET_FULL_V") + (VNx1SI "!TARGET_FULL_V") VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN > 32") (VNx32SI "TARGET_FULL_V") + (VNx2DI "TARGET_FULL_V") (VNx4DI "TARGET_FULL_V") (VNx8DI "TARGET_FULL_V") (VNx16DI "TARGET_FULL_V") ]) (define_mode_iterator VI_QHS [ - VNx1QI VNx2QI VNx4QI VNx8QI VNx16QI VNx32QI (VNx64QI "TARGET_MIN_VLEN > 32") - VNx1HI VNx2HI VNx4HI VNx8HI VNx16HI (VNx32HI "TARGET_MIN_VLEN > 32") - VNx1SI VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN > 32") + (VNx1QI "TARGET_MIN_VLEN < 128") VNx2QI VNx4QI VNx8QI VNx16QI VNx32QI (VNx64QI "TARGET_MIN_VLEN > 32") (VNx128QI "TARGET_MIN_VLEN >= 128") + (VNx1HI "TARGET_MIN_VLEN < 128") VNx2HI VNx4HI VNx8HI VNx16HI (VNx32HI "TARGET_MIN_VLEN > 32") (VNx64HI "TARGET_MIN_VLEN >= 128") + (VNx1SI "TARGET_MIN_VLEN < 128") VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN > 32") (VNx32SI "TARGET_MIN_VLEN >= 128") ]) (define_mode_iterator VI_D [ - (VNx1DI "TARGET_VECTOR_ELEN_64") (VNx2DI "TARGET_VECTOR_ELEN_64") - (VNx4DI "TARGET_VECTOR_ELEN_64") (VNx8DI "TARGET_VECTOR_ELEN_64") + (VNx1DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN < 128") (VNx2DI "TARGET_VECTOR_ELEN_64") + (VNx4DI "TARGET_VECTOR_ELEN_64") (VNx8DI "TARGET_VECTOR_ELEN_64") (VNx16DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 128") ]) (define_mode_iterator VFULLI_D [ - (VNx1DI "TARGET_FULL_V") (VNx2DI "TARGET_FULL_V") - (VNx4DI "TARGET_FULL_V") (VNx8DI "TARGET_FULL_V") + (VNx2DI "TARGET_FULL_V") (VNx4DI "TARGET_FULL_V") (VNx8DI "TARGET_FULL_V") (VNx16DI "TARGET_FULL_V") ]) (define_mode_iterator VNX1_QHSD [ - VNx1QI VNx1HI VNx1SI - (VNx1DI "TARGET_VECTOR_ELEN_64") - (VNx1SF "TARGET_VECTOR_ELEN_FP_32") - (VNx1DF "TARGET_VECTOR_ELEN_FP_64") + (VNx1QI "TARGET_MIN_VLEN < 128") (VNx1HI "TARGET_MIN_VLEN < 128") (VNx1SI "TARGET_MIN_VLEN < 128") + (VNx1DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN < 128") + (VNx1SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN < 128") + (VNx1DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_MIN_VLEN < 128") ]) (define_mode_iterator VNX2_QHSD [ @@ -331,18 +370,24 @@ (define_mode_iterator VNX16_QHS [ VNx16QI VNx16HI (VNx16SI "TARGET_MIN_VLEN > 32") (VNx16SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32") + (VNx16DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 128") (VNx16DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_MIN_VLEN >= 128") ]) -(define_mode_iterator VNX32_QH [ - VNx32QI (VNx32HI "TARGET_MIN_VLEN > 32") +(define_mode_iterator VNX32_QHS [ + VNx32QI (VNx32HI "TARGET_MIN_VLEN > 32") (VNx32SI "TARGET_MIN_VLEN >= 128") (VNx32SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN >= 128") ]) -(define_mode_iterator VNX64_Q [ +(define_mode_iterator VNX64_QH [ (VNx64QI "TARGET_MIN_VLEN > 32") + (VNx64HI "TARGET_MIN_VLEN >= 128") +]) + +(define_mode_iterator VNX128_Q [ + (VNx128QI "TARGET_MIN_VLEN >= 128") ]) (define_mode_iterator VNX1_QHSDI [ - VNx1QI VNx1HI VNx1SI + (VNx1QI "TARGET_MIN_VLEN < 128") (VNx1HI "TARGET_MIN_VLEN < 128") (VNx1SI "TARGET_MIN_VLEN < 128") (VNx1DI "TARGET_64BIT && TARGET_MIN_VLEN > 32") ]) @@ -362,298 +407,325 @@ ]) (define_mode_iterator VNX16_QHSI [ - VNx16QI VNx16HI (VNx16SI "TARGET_MIN_VLEN > 32") + VNx16QI VNx16HI (VNx16SI "TARGET_MIN_VLEN > 32") (VNx16DI "TARGET_MIN_VLEN >= 128") ]) -(define_mode_iterator VNX32_QHI [ - VNx32QI (VNx32HI "TARGET_MIN_VLEN > 32") +(define_mode_iterator VNX32_QHSI [ + VNx32QI (VNx32HI "TARGET_MIN_VLEN > 32") (VNx32SI "TARGET_MIN_VLEN >= 128") +]) + +(define_mode_iterator VNX64_QHI [ + VNx64QI (VNx64HI "TARGET_MIN_VLEN >= 128") ]) (define_mode_iterator V_WHOLE [ - (VNx4QI "TARGET_MIN_VLEN == 32") VNx8QI VNx16QI VNx32QI (VNx64QI "TARGET_MIN_VLEN > 32") - (VNx2HI "TARGET_MIN_VLEN == 32") VNx4HI VNx8HI VNx16HI (VNx32HI "TARGET_MIN_VLEN > 32") - (VNx1SI "TARGET_MIN_VLEN == 32") VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN > 32") - (VNx1DI "TARGET_VECTOR_ELEN_64") (VNx2DI "TARGET_VECTOR_ELEN_64") - (VNx4DI "TARGET_VECTOR_ELEN_64") (VNx8DI "TARGET_VECTOR_ELEN_64") + (VNx4QI "TARGET_MIN_VLEN == 32") VNx8QI VNx16QI VNx32QI (VNx64QI "TARGET_MIN_VLEN > 32") (VNx128QI "TARGET_MIN_VLEN >= 128") + (VNx2HI "TARGET_MIN_VLEN == 32") VNx4HI VNx8HI VNx16HI (VNx32HI "TARGET_MIN_VLEN > 32") (VNx64HI "TARGET_MIN_VLEN >= 128") + (VNx1SI "TARGET_MIN_VLEN == 32") VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN > 32") (VNx32SI "TARGET_MIN_VLEN >= 128") + (VNx1DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN < 128") (VNx2DI "TARGET_VECTOR_ELEN_64") + (VNx4DI "TARGET_VECTOR_ELEN_64") (VNx8DI "TARGET_VECTOR_ELEN_64") (VNx16DI "TARGET_MIN_VLEN >= 128") (VNx1SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN == 32") (VNx2SF "TARGET_VECTOR_ELEN_FP_32") (VNx4SF "TARGET_VECTOR_ELEN_FP_32") (VNx8SF "TARGET_VECTOR_ELEN_FP_32") (VNx16SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32") - (VNx1DF "TARGET_VECTOR_ELEN_FP_64") + (VNx32SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN >= 128") + (VNx1DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_MIN_VLEN < 128") (VNx2DF "TARGET_VECTOR_ELEN_FP_64") (VNx4DF "TARGET_VECTOR_ELEN_FP_64") (VNx8DF "TARGET_VECTOR_ELEN_FP_64") + (VNx16DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_MIN_VLEN >= 128") ]) (define_mode_iterator V_FRACT [ - VNx1QI VNx2QI (VNx4QI "TARGET_MIN_VLEN > 32") - VNx1HI (VNx2HI "TARGET_MIN_VLEN > 32") - (VNx1SI "TARGET_MIN_VLEN > 32") + (VNx1QI "TARGET_MIN_VLEN < 128") VNx2QI (VNx4QI "TARGET_MIN_VLEN > 32") (VNx8QI "TARGET_MIN_VLEN >= 128") + (VNx1HI "TARGET_MIN_VLEN < 128") (VNx2HI "TARGET_MIN_VLEN > 32") (VNx4HI "TARGET_MIN_VLEN >= 128") + (VNx1SI "TARGET_MIN_VLEN > 32 && TARGET_MIN_VLEN < 128") (VNx2SI "TARGET_MIN_VLEN >= 128") (VNx1SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32") + (VNx2SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN >= 128") ]) (define_mode_iterator VB [ - VNx1BI VNx2BI VNx4BI VNx8BI VNx16BI VNx32BI - (VNx64BI "TARGET_MIN_VLEN > 32") + (VNx1BI "TARGET_MIN_VLEN < 128") VNx2BI VNx4BI VNx8BI VNx16BI VNx32BI + (VNx64BI "TARGET_MIN_VLEN > 32") (VNx128BI "TARGET_MIN_VLEN >= 128") ]) (define_mode_iterator VWEXTI [ - VNx1HI VNx2HI VNx4HI VNx8HI VNx16HI (VNx32HI "TARGET_MIN_VLEN > 32") - VNx1SI VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN > 32") - (VNx1DI "TARGET_VECTOR_ELEN_64") (VNx2DI "TARGET_VECTOR_ELEN_64") + (VNx1HI "TARGET_MIN_VLEN < 128") VNx2HI VNx4HI VNx8HI VNx16HI (VNx32HI "TARGET_MIN_VLEN > 32") (VNx64HI "TARGET_MIN_VLEN >= 128") + (VNx1SI "TARGET_MIN_VLEN < 128") VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN > 32") (VNx32SI "TARGET_MIN_VLEN >= 128") + (VNx1DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN < 128") (VNx2DI "TARGET_VECTOR_ELEN_64") (VNx4DI "TARGET_VECTOR_ELEN_64") (VNx8DI "TARGET_VECTOR_ELEN_64") + (VNx16DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 128") ]) (define_mode_iterator VWEXTF [ - (VNx1DF "TARGET_VECTOR_ELEN_FP_64") + (VNx1DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_MIN_VLEN < 128") (VNx2DF "TARGET_VECTOR_ELEN_FP_64") (VNx4DF "TARGET_VECTOR_ELEN_FP_64") (VNx8DF "TARGET_VECTOR_ELEN_FP_64") + (VNx16DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_MIN_VLEN >= 128") ]) (define_mode_iterator VWCONVERTI [ - (VNx1DI "TARGET_VECTOR_ELEN_64 && TARGET_VECTOR_ELEN_FP_32") + (VNx1DI "TARGET_VECTOR_ELEN_64 && TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN < 128") (VNx2DI "TARGET_VECTOR_ELEN_64 && TARGET_VECTOR_ELEN_FP_32") (VNx4DI "TARGET_VECTOR_ELEN_64 && TARGET_VECTOR_ELEN_FP_32") (VNx8DI "TARGET_VECTOR_ELEN_64 && TARGET_VECTOR_ELEN_FP_32") + (VNx16DI "TARGET_VECTOR_ELEN_64 && TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN >= 128") ]) (define_mode_iterator VQEXTI [ - VNx1SI VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN > 32") - (VNx1DI "TARGET_VECTOR_ELEN_64") (VNx2DI "TARGET_VECTOR_ELEN_64") + (VNx1SI "TARGET_MIN_VLEN < 128") VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN > 32") (VNx32SI "TARGET_MIN_VLEN >= 128") + (VNx1DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN < 128") (VNx2DI "TARGET_VECTOR_ELEN_64") (VNx4DI "TARGET_VECTOR_ELEN_64") (VNx8DI "TARGET_VECTOR_ELEN_64") + (VNx16DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 128") ]) (define_mode_iterator VOEXTI [ - (VNx1DI "TARGET_VECTOR_ELEN_64") (VNx2DI "TARGET_VECTOR_ELEN_64") + (VNx1DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN < 128") (VNx2DI "TARGET_VECTOR_ELEN_64") (VNx4DI "TARGET_VECTOR_ELEN_64") (VNx8DI "TARGET_VECTOR_ELEN_64") + (VNx16DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 128") ]) (define_mode_attr VLMULX2 [ - (VNx1QI "VNx2QI") (VNx2QI "VNx4QI") (VNx4QI "VNx8QI") (VNx8QI "VNx16QI") (VNx16QI "VNx32QI") (VNx32QI "VNx64QI") - (VNx1HI "VNx2HI") (VNx2HI "VNx4HI") (VNx4HI "VNx8HI") (VNx8HI "VNx16HI") (VNx16HI "VNx32HI") - (VNx1SI "VNx2SI") (VNx2SI "VNx4SI") (VNx4SI "VNx8SI") (VNx8SI "VNx16SI") - (VNx1DI "VNx2DI") (VNx2DI "VNx4DI") (VNx4DI "VNx8DI") - (VNx1SF "VNx2SF") (VNx2SF "VNx4SF") (VNx4SF "VNx8SF") (VNx8SF "VNx16SF") - (VNx1DF "VNx2DF") (VNx2DF "VNx4DF") (VNx4DF "VNx8DF") + (VNx1QI "VNx2QI") (VNx2QI "VNx4QI") (VNx4QI "VNx8QI") (VNx8QI "VNx16QI") (VNx16QI "VNx32QI") (VNx32QI "VNx64QI") (VNx64QI "VNx128QI") + (VNx1HI "VNx2HI") (VNx2HI "VNx4HI") (VNx4HI "VNx8HI") (VNx8HI "VNx16HI") (VNx16HI "VNx32HI") (VNx32HI "VNx64HI") + (VNx1SI "VNx2SI") (VNx2SI "VNx4SI") (VNx4SI "VNx8SI") (VNx8SI "VNx16SI") (VNx16SI "VNx32SI") + (VNx1DI "VNx2DI") (VNx2DI "VNx4DI") (VNx4DI "VNx8DI") (VNx8DI "VNx16DI") + (VNx1SF "VNx2SF") (VNx2SF "VNx4SF") (VNx4SF "VNx8SF") (VNx8SF "VNx16SF") (VNx16SF "VNx32SF") + (VNx1DF "VNx2DF") (VNx2DF "VNx4DF") (VNx4DF "VNx8DF") (VNx8DF "VNx16DF") ]) (define_mode_attr VLMULX4 [ - (VNx1QI "VNx4QI") (VNx2QI "VNx8QI") (VNx4QI "VNx16QI") (VNx8QI "VNx32QI") (VNx16QI "VNx64QI") - (VNx1HI "VNx4HI") (VNx2HI "VNx8HI") (VNx4HI "VNx16HI") (VNx8HI "VNx32HI") - (VNx1SI "VNx4SI") (VNx2SI "VNx8SI") (VNx4SI "VNx16SI") - (VNx1DI "VNx4DI") (VNx2DI "VNx8DI") - (VNx1SF "VNx4SF") (VNx2SF "VNx8SF") (VNx4SF "VNx16SF") - (VNx1DF "VNx4DF") (VNx2DF "VNx8DF") + (VNx1QI "VNx4QI") (VNx2QI "VNx8QI") (VNx4QI "VNx16QI") (VNx8QI "VNx32QI") (VNx16QI "VNx64QI") (VNx32QI "VNx128QI") + (VNx1HI "VNx4HI") (VNx2HI "VNx8HI") (VNx4HI "VNx16HI") (VNx8HI "VNx32HI") (VNx16HI "VNx64HI") + (VNx1SI "VNx4SI") (VNx2SI "VNx8SI") (VNx4SI "VNx16SI") (VNx8SI "VNx32SI") + (VNx1DI "VNx4DI") (VNx2DI "VNx8DI") (VNx4DI "VNx16DI") + (VNx1SF "VNx4SF") (VNx2SF "VNx8SF") (VNx4SF "VNx16SF") (VNx8SF "VNx32SF") + (VNx1DF "VNx4DF") (VNx2DF "VNx8DF") (VNx4DF "VNx16DF") ]) (define_mode_attr VLMULX8 [ - (VNx1QI "VNx8QI") (VNx2QI "VNx16QI") (VNx4QI "VNx32QI") (VNx8QI "VNx64QI") - (VNx1HI "VNx8HI") (VNx2HI "VNx16HI") (VNx4HI "VNx32HI") - (VNx1SI "VNx8SI") (VNx2SI "VNx16SI") - (VNx1DI "VNx8DI") - (VNx1SF "VNx8SF") (VNx2SF "VNx16SF") - (VNx1DF "VNx8DF") + (VNx1QI "VNx8QI") (VNx2QI "VNx16QI") (VNx4QI "VNx32QI") (VNx8QI "VNx64QI") (VNx16QI "VNx128QI") + (VNx1HI "VNx8HI") (VNx2HI "VNx16HI") (VNx4HI "VNx32HI") (VNx8HI "VNx64HI") + (VNx1SI "VNx8SI") (VNx2SI "VNx16SI") (VNx4SI "VNx32SI") + (VNx1DI "VNx8DI") (VNx2DI "VNx16DI") + (VNx1SF "VNx8SF") (VNx2SF "VNx16SF") (VNx4SF "VNx32SF") + (VNx1DF "VNx8DF") (VNx2DF "VNx16DF") ]) (define_mode_attr VLMULX16 [ - (VNx1QI "VNx16QI") (VNx2QI "VNx32QI") (VNx4QI "VNx64QI") - (VNx1HI "VNx16HI") (VNx2HI "VNx32HI") - (VNx1SI "VNx16SI") - (VNx1SF "VNx16SF") + (VNx1QI "VNx16QI") (VNx2QI "VNx32QI") (VNx4QI "VNx64QI") (VNx8QI "VNx128QI") + (VNx1HI "VNx16HI") (VNx2HI "VNx32HI") (VNx4HI "VNx64HI") + (VNx1SI "VNx16SI") (VNx2SI "VNx32SI") + (VNx1SF "VNx16SF") (VNx2SF "VNx32SF") ]) (define_mode_attr VLMULX32 [ - (VNx1QI "VNx32QI") (VNx2QI "VNx64QI") - (VNx1HI "VNx32HI") + (VNx1QI "VNx32QI") (VNx2QI "VNx64QI") (VNx4QI "VNx128QI") + (VNx1HI "VNx32HI") (VNx2HI "VNx64HI") ]) (define_mode_attr VLMULX64 [ - (VNx1QI "VNx64QI") + (VNx1QI "VNx64QI") (VNx2QI "VNx128QI") ]) (define_mode_attr VINDEX [ (VNx1QI "VNx1QI") (VNx2QI "VNx2QI") (VNx4QI "VNx4QI") (VNx8QI "VNx8QI") - (VNx16QI "VNx16QI") (VNx32QI "VNx32QI") (VNx64QI "VNx64QI") + (VNx16QI "VNx16QI") (VNx32QI "VNx32QI") (VNx64QI "VNx64QI") (VNx128QI "VNx128QI") (VNx1HI "VNx1HI") (VNx2HI "VNx2HI") (VNx4HI "VNx4HI") (VNx8HI "VNx8HI") - (VNx16HI "VNx16HI") (VNx32HI "VNx32HI") + (VNx16HI "VNx16HI") (VNx32HI "VNx32HI") (VNx64HI "VNx64HI") (VNx1SI "VNx1SI") (VNx2SI "VNx2SI") (VNx4SI "VNx4SI") (VNx8SI "VNx8SI") - (VNx16SI "VNx16SI") - (VNx1DI "VNx1DI") (VNx2DI "VNx2DI") (VNx4DI "VNx4DI") (VNx8DI "VNx8DI") + (VNx16SI "VNx16SI") (VNx32SI "VNx32SI") + (VNx1DI "VNx1DI") (VNx2DI "VNx2DI") (VNx4DI "VNx4DI") (VNx8DI "VNx8DI") (VNx16DI "VNx16DI") (VNx1SF "VNx1SI") (VNx2SF "VNx2SI") (VNx4SF "VNx4SI") (VNx8SF "VNx8SI") - (VNx16SF "VNx16SI") - (VNx1DF "VNx1DI") (VNx2DF "VNx2DI") (VNx4DF "VNx4DI") (VNx8DF "VNx8DI") + (VNx16SF "VNx16SI") (VNx32SF "VNx32SI") + (VNx1DF "VNx1DI") (VNx2DF "VNx2DI") (VNx4DF "VNx4DI") (VNx8DF "VNx8DI") (VNx16DF "VNx16DI") ]) (define_mode_attr VINDEXEI16 [ (VNx1QI "VNx1HI") (VNx2QI "VNx2HI") (VNx4QI "VNx4HI") (VNx8QI "VNx8HI") - (VNx16QI "VNx16HI") (VNx32QI "VNx32HI") + (VNx16QI "VNx16HI") (VNx32QI "VNx32HI") (VNx64QI "VNx64HI") (VNx1HI "VNx1HI") (VNx2HI "VNx2HI") (VNx4HI "VNx4HI") (VNx8HI "VNx8HI") - (VNx16HI "VNx16HI") (VNx32HI "VNx32HI") + (VNx16HI "VNx16HI") (VNx32HI "VNx32HI") (VNx64HI "VNx64HI") (VNx1SI "VNx1HI") (VNx2SI "VNx2HI") (VNx4SI "VNx4HI") (VNx8SI "VNx8HI") - (VNx16SI "VNx16HI") - (VNx1DI "VNx1HI") (VNx2DI "VNx2HI") (VNx4DI "VNx4HI") (VNx8DI "VNx8HI") + (VNx16SI "VNx16HI") (VNx32SI "VNx32HI") + (VNx1DI "VNx1HI") (VNx2DI "VNx2HI") (VNx4DI "VNx4HI") (VNx8DI "VNx8HI") (VNx16DI "VNx16HI") (VNx1SF "VNx1HI") (VNx2SF "VNx2HI") (VNx4SF "VNx4HI") (VNx8SF "VNx8HI") - (VNx16SF "VNx16HI") - (VNx1DF "VNx1HI") (VNx2DF "VNx2HI") (VNx4DF "VNx4HI") (VNx8DF "VNx8HI") + (VNx16SF "VNx16HI") (VNx32SF "VNx32HI") + (VNx1DF "VNx1HI") (VNx2DF "VNx2HI") (VNx4DF "VNx4HI") (VNx8DF "VNx8HI") (VNx16DF "VNx16HI") ]) (define_mode_attr VM [ - (VNx1QI "VNx1BI") (VNx2QI "VNx2BI") (VNx4QI "VNx4BI") (VNx8QI "VNx8BI") (VNx16QI "VNx16BI") (VNx32QI "VNx32BI") (VNx64QI "VNx64BI") - (VNx1HI "VNx1BI") (VNx2HI "VNx2BI") (VNx4HI "VNx4BI") (VNx8HI "VNx8BI") (VNx16HI "VNx16BI") (VNx32HI "VNx32BI") - (VNx1SI "VNx1BI") (VNx2SI "VNx2BI") (VNx4SI "VNx4BI") (VNx8SI "VNx8BI") (VNx16SI "VNx16BI") - (VNx1DI "VNx1BI") (VNx2DI "VNx2BI") (VNx4DI "VNx4BI") (VNx8DI "VNx8BI") - (VNx1SF "VNx1BI") (VNx2SF "VNx2BI") (VNx4SF "VNx4BI") (VNx8SF "VNx8BI") (VNx16SF "VNx16BI") - (VNx1DF "VNx1BI") (VNx2DF "VNx2BI") (VNx4DF "VNx4BI") (VNx8DF "VNx8BI") + (VNx1QI "VNx1BI") (VNx2QI "VNx2BI") (VNx4QI "VNx4BI") (VNx8QI "VNx8BI") (VNx16QI "VNx16BI") (VNx32QI "VNx32BI") (VNx64QI "VNx64BI") (VNx128QI "VNx128BI") + (VNx1HI "VNx1BI") (VNx2HI "VNx2BI") (VNx4HI "VNx4BI") (VNx8HI "VNx8BI") (VNx16HI "VNx16BI") (VNx32HI "VNx32BI") (VNx64HI "VNx64BI") + (VNx1SI "VNx1BI") (VNx2SI "VNx2BI") (VNx4SI "VNx4BI") (VNx8SI "VNx8BI") (VNx16SI "VNx16BI") (VNx32SI "VNx32BI") + (VNx1DI "VNx1BI") (VNx2DI "VNx2BI") (VNx4DI "VNx4BI") (VNx8DI "VNx8BI") (VNx16DI "VNx16BI") + (VNx1SF "VNx1BI") (VNx2SF "VNx2BI") (VNx4SF "VNx4BI") (VNx8SF "VNx8BI") (VNx16SF "VNx16BI") (VNx32SF "VNx32BI") + (VNx1DF "VNx1BI") (VNx2DF "VNx2BI") (VNx4DF "VNx4BI") (VNx8DF "VNx8BI") (VNx16DF "VNx16BI") ]) (define_mode_attr vm [ - (VNx1QI "vnx1bi") (VNx2QI "vnx2bi") (VNx4QI "vnx4bi") (VNx8QI "vnx8bi") (VNx16QI "vnx16bi") (VNx32QI "vnx32bi") (VNx64QI "vnx64bi") - (VNx1HI "vnx1bi") (VNx2HI "vnx2bi") (VNx4HI "vnx4bi") (VNx8HI "vnx8bi") (VNx16HI "vnx16bi") (VNx32HI "vnx32bi") - (VNx1SI "vnx1bi") (VNx2SI "vnx2bi") (VNx4SI "vnx4bi") (VNx8SI "vnx8bi") (VNx16SI "vnx16bi") - (VNx1DI "vnx1bi") (VNx2DI "vnx2bi") (VNx4DI "vnx4bi") (VNx8DI "vnx8bi") - (VNx1SF "vnx1bi") (VNx2SF "vnx2bi") (VNx4SF "vnx4bi") (VNx8SF "vnx8bi") (VNx16SF "vnx16bi") - (VNx1DF "vnx1bi") (VNx2DF "vnx2bi") (VNx4DF "vnx4bi") (VNx8DF "vnx8bi") + (VNx1QI "vnx1bi") (VNx2QI "vnx2bi") (VNx4QI "vnx4bi") (VNx8QI "vnx8bi") (VNx16QI "vnx16bi") (VNx32QI "vnx32bi") (VNx64QI "vnx64bi") (VNx128QI "vnx128bi") + (VNx1HI "vnx1bi") (VNx2HI "vnx2bi") (VNx4HI "vnx4bi") (VNx8HI "vnx8bi") (VNx16HI "vnx16bi") (VNx32HI "vnx32bi") (VNx64HI "vnx64bi") + (VNx1SI "vnx1bi") (VNx2SI "vnx2bi") (VNx4SI "vnx4bi") (VNx8SI "vnx8bi") (VNx16SI "vnx16bi") (VNx32SI "vnx32bi") + (VNx1DI "vnx1bi") (VNx2DI "vnx2bi") (VNx4DI "vnx4bi") (VNx8DI "vnx8bi") (VNx16DI "vnx16bi") + (VNx1SF "vnx1bi") (VNx2SF "vnx2bi") (VNx4SF "vnx4bi") (VNx8SF "vnx8bi") (VNx16SF "vnx16bi") (VNx32SF "vnx32bi") + (VNx1DF "vnx1bi") (VNx2DF "vnx2bi") (VNx4DF "vnx4bi") (VNx8DF "vnx8bi") (VNx16DF "vnx16bi") ]) (define_mode_attr VEL [ - (VNx1QI "QI") (VNx2QI "QI") (VNx4QI "QI") (VNx8QI "QI") (VNx16QI "QI") (VNx32QI "QI") (VNx64QI "QI") - (VNx1HI "HI") (VNx2HI "HI") (VNx4HI "HI") (VNx8HI "HI") (VNx16HI "HI") (VNx32HI "HI") - (VNx1SI "SI") (VNx2SI "SI") (VNx4SI "SI") (VNx8SI "SI") (VNx16SI "SI") - (VNx1DI "DI") (VNx2DI "DI") (VNx4DI "DI") (VNx8DI "DI") - (VNx1SF "SF") (VNx2SF "SF") (VNx4SF "SF") (VNx8SF "SF") (VNx16SF "SF") - (VNx1DF "DF") (VNx2DF "DF") (VNx4DF "DF") (VNx8DF "DF") + (VNx1QI "QI") (VNx2QI "QI") (VNx4QI "QI") (VNx8QI "QI") (VNx16QI "QI") (VNx32QI "QI") (VNx64QI "QI") (VNx128QI "QI") + (VNx1HI "HI") (VNx2HI "HI") (VNx4HI "HI") (VNx8HI "HI") (VNx16HI "HI") (VNx32HI "HI") (VNx64HI "HI") + (VNx1SI "SI") (VNx2SI "SI") (VNx4SI "SI") (VNx8SI "SI") (VNx16SI "SI") (VNx32SI "SI") + (VNx1DI "DI") (VNx2DI "DI") (VNx4DI "DI") (VNx8DI "DI") (VNx16DI "DI") + (VNx1SF "SF") (VNx2SF "SF") (VNx4SF "SF") (VNx8SF "SF") (VNx16SF "SF") (VNx32SF "SF") + (VNx1DF "DF") (VNx2DF "DF") (VNx4DF "DF") (VNx8DF "DF") (VNx16DF "DF") ]) (define_mode_attr VSUBEL [ - (VNx1HI "QI") (VNx2HI "QI") (VNx4HI "QI") (VNx8HI "QI") (VNx16HI "QI") (VNx32HI "QI") - (VNx1SI "HI") (VNx2SI "HI") (VNx4SI "HI") (VNx8SI "HI") (VNx16SI "HI") - (VNx1DI "SI") (VNx2DI "SI") (VNx4DI "SI") (VNx8DI "SI") - (VNx1SF "HF") (VNx2SF "HF") (VNx4SF "HF") (VNx8SF "HF") (VNx16SF "HF") - (VNx1DF "SF") (VNx2DF "SF") (VNx4DF "SF") (VNx8DF "SF") + (VNx1HI "QI") (VNx2HI "QI") (VNx4HI "QI") (VNx8HI "QI") (VNx16HI "QI") (VNx32HI "QI") (VNx64HI "QI") + (VNx1SI "HI") (VNx2SI "HI") (VNx4SI "HI") (VNx8SI "HI") (VNx16SI "HI") (VNx32SI "HI") + (VNx1DI "SI") (VNx2DI "SI") (VNx4DI "SI") (VNx8DI "SI") (VNx16DI "SI") + (VNx1SF "HF") (VNx2SF "HF") (VNx4SF "HF") (VNx8SF "HF") (VNx16SF "HF") (VNx32SF "HF") + (VNx1DF "SF") (VNx2DF "SF") (VNx4DF "SF") (VNx8DF "SF") (VNx16DF "SF") ]) (define_mode_attr sew [ - (VNx1QI "8") (VNx2QI "8") (VNx4QI "8") (VNx8QI "8") (VNx16QI "8") (VNx32QI "8") (VNx64QI "8") - (VNx1HI "16") (VNx2HI "16") (VNx4HI "16") (VNx8HI "16") (VNx16HI "16") (VNx32HI "16") - (VNx1SI "32") (VNx2SI "32") (VNx4SI "32") (VNx8SI "32") (VNx16SI "32") - (VNx1DI "64") (VNx2DI "64") (VNx4DI "64") (VNx8DI "64") - (VNx1SF "32") (VNx2SF "32") (VNx4SF "32") (VNx8SF "32") (VNx16SF "32") - (VNx1DF "64") (VNx2DF "64") (VNx4DF "64") (VNx8DF "64") + (VNx1QI "8") (VNx2QI "8") (VNx4QI "8") (VNx8QI "8") (VNx16QI "8") (VNx32QI "8") (VNx64QI "8") (VNx128QI "8") + (VNx1HI "16") (VNx2HI "16") (VNx4HI "16") (VNx8HI "16") (VNx16HI "16") (VNx32HI "16") (VNx64HI "16") + (VNx1SI "32") (VNx2SI "32") (VNx4SI "32") (VNx8SI "32") (VNx16SI "32") (VNx32SI "32") + (VNx1DI "64") (VNx2DI "64") (VNx4DI "64") (VNx8DI "64") (VNx16DI "64") + (VNx1SF "32") (VNx2SF "32") (VNx4SF "32") (VNx8SF "32") (VNx16SF "32") (VNx32SF "32") + (VNx1DF "64") (VNx2DF "64") (VNx4DF "64") (VNx8DF "64") (VNx16DF "64") ]) (define_mode_attr double_trunc_sew [ - (VNx1HI "8") (VNx2HI "8") (VNx4HI "8") (VNx8HI "8") (VNx16HI "8") (VNx32HI "8") - (VNx1SI "16") (VNx2SI "16") (VNx4SI "16") (VNx8SI "16") (VNx16SI "16") - (VNx1DI "32") (VNx2DI "32") (VNx4DI "32") (VNx8DI "32") - (VNx1SF "16") (VNx2SF "16") (VNx4SF "16") (VNx8SF "16") (VNx16SF "16") - (VNx1DF "32") (VNx2DF "32") (VNx4DF "32") (VNx8DF "32") + (VNx1HI "8") (VNx2HI "8") (VNx4HI "8") (VNx8HI "8") (VNx16HI "8") (VNx32HI "8") (VNx64HI "8") + (VNx1SI "16") (VNx2SI "16") (VNx4SI "16") (VNx8SI "16") (VNx16SI "16") (VNx32SI "16") + (VNx1DI "32") (VNx2DI "32") (VNx4DI "32") (VNx8DI "32") (VNx16DI "32") + (VNx1SF "16") (VNx2SF "16") (VNx4SF "16") (VNx8SF "16") (VNx16SF "16") (VNx32SF "16") + (VNx1DF "32") (VNx2DF "32") (VNx4DF "32") (VNx8DF "32") (VNx16DF "32") ]) (define_mode_attr quad_trunc_sew [ - (VNx1SI "8") (VNx2SI "8") (VNx4SI "8") (VNx8SI "8") (VNx16SI "8") - (VNx1DI "16") (VNx2DI "16") (VNx4DI "16") (VNx8DI "16") - (VNx1SF "8") (VNx2SF "8") (VNx4SF "8") (VNx8SF "8") (VNx16SF "8") - (VNx1DF "16") (VNx2DF "16") (VNx4DF "16") (VNx8DF "16") + (VNx1SI "8") (VNx2SI "8") (VNx4SI "8") (VNx8SI "8") (VNx16SI "8") (VNx32SI "8") + (VNx1DI "16") (VNx2DI "16") (VNx4DI "16") (VNx8DI "16") (VNx16DI "16") + (VNx1SF "8") (VNx2SF "8") (VNx4SF "8") (VNx8SF "8") (VNx16SF "8") (VNx32SF "8") + (VNx1DF "16") (VNx2DF "16") (VNx4DF "16") (VNx8DF "16") (VNx16DF "16") ]) (define_mode_attr oct_trunc_sew [ - (VNx1DI "8") (VNx2DI "8") (VNx4DI "8") (VNx8DI "8") - (VNx1DF "8") (VNx2DF "8") (VNx4DF "8") (VNx8DF "8") + (VNx1DI "8") (VNx2DI "8") (VNx4DI "8") (VNx8DI "8") (VNx16DI "8") + (VNx1DF "8") (VNx2DF "8") (VNx4DF "8") (VNx8DF "8") (VNx16DF "8") ]) (define_mode_attr double_ext_sew [ - (VNx1QI "16") (VNx2QI "16") (VNx4QI "16") (VNx8QI "16") (VNx16QI "16") (VNx32QI "16") - (VNx1HI "32") (VNx2HI "32") (VNx4HI "32") (VNx8HI "32") (VNx16HI "32") - (VNx1SI "64") (VNx2SI "64") (VNx4SI "64") (VNx8SI "64") - (VNx1SF "64") (VNx2SF "64") (VNx4SF "64") (VNx8SF "64") + (VNx1QI "16") (VNx2QI "16") (VNx4QI "16") (VNx8QI "16") (VNx16QI "16") (VNx32QI "16") (VNx64QI "16") + (VNx1HI "32") (VNx2HI "32") (VNx4HI "32") (VNx8HI "32") (VNx16HI "32") (VNx32HI "32") + (VNx1SI "64") (VNx2SI "64") (VNx4SI "64") (VNx8SI "64") (VNx16SI "64") + (VNx1SF "64") (VNx2SF "64") (VNx4SF "64") (VNx8SF "64") (VNx16SF "64") ]) (define_mode_attr quad_ext_sew [ - (VNx1QI "32") (VNx2QI "32") (VNx4QI "32") (VNx8QI "32") (VNx16QI "32") - (VNx1HI "64") (VNx2HI "64") (VNx4HI "64") (VNx8HI "64") + (VNx1QI "32") (VNx2QI "32") (VNx4QI "32") (VNx8QI "32") (VNx16QI "32") (VNx32QI "32") + (VNx1HI "64") (VNx2HI "64") (VNx4HI "64") (VNx8HI "64") (VNx16HI "64") ]) (define_mode_attr oct_ext_sew [ - (VNx1QI "64") (VNx2QI "64") (VNx4QI "64") (VNx8QI "64") + (VNx1QI "64") (VNx2QI "64") (VNx4QI "64") (VNx8QI "64") (VNx16QI "64") ]) (define_mode_attr V_DOUBLE_TRUNC [ (VNx1HI "VNx1QI") (VNx2HI "VNx2QI") (VNx4HI "VNx4QI") (VNx8HI "VNx8QI") - (VNx16HI "VNx16QI") (VNx32HI "VNx32QI") + (VNx16HI "VNx16QI") (VNx32HI "VNx32QI") (VNx64HI "VNx64QI") (VNx1SI "VNx1HI") (VNx2SI "VNx2HI") (VNx4SI "VNx4HI") (VNx8SI "VNx8HI") - (VNx16SI "VNx16HI") - (VNx1DI "VNx1SI") (VNx2DI "VNx2SI") (VNx4DI "VNx4SI") (VNx8DI "VNx8SI") - (VNx1DF "VNx1SF") (VNx2DF "VNx2SF") (VNx4DF "VNx4SF") (VNx8DF "VNx8SF") + (VNx16SI "VNx16HI") (VNx32SI "VNx32HI") + (VNx1DI "VNx1SI") (VNx2DI "VNx2SI") (VNx4DI "VNx4SI") (VNx8DI "VNx8SI") (VNx16DI "VNx16SI") + (VNx1DF "VNx1SF") (VNx2DF "VNx2SF") (VNx4DF "VNx4SF") (VNx8DF "VNx8SF") (VNx16DF "VNx16SF") ]) (define_mode_attr V_QUAD_TRUNC [ (VNx1SI "VNx1QI") (VNx2SI "VNx2QI") (VNx4SI "VNx4QI") (VNx8SI "VNx8QI") - (VNx16SI "VNx16QI") + (VNx16SI "VNx16QI") (VNx32SI "VNx32QI") (VNx1DI "VNx1HI") (VNx2DI "VNx2HI") - (VNx4DI "VNx4HI") (VNx8DI "VNx8HI") + (VNx4DI "VNx4HI") (VNx8DI "VNx8HI") (VNx16DI "VNx16HI") ]) (define_mode_attr V_OCT_TRUNC [ - (VNx1DI "VNx1QI") (VNx2DI "VNx2QI") (VNx4DI "VNx4QI") (VNx8DI "VNx8QI") + (VNx1DI "VNx1QI") (VNx2DI "VNx2QI") (VNx4DI "VNx4QI") (VNx8DI "VNx8QI") (VNx16DI "VNx16QI") ]) (define_mode_attr VINDEX_DOUBLE_TRUNC [ (VNx1HI "VNx1QI") (VNx2HI "VNx2QI") (VNx4HI "VNx4QI") (VNx8HI "VNx8QI") - (VNx16HI "VNx16QI") (VNx32HI "VNx32QI") + (VNx16HI "VNx16QI") (VNx32HI "VNx32QI") (VNx64HI "VNx64QI") (VNx1SI "VNx1HI") (VNx2SI "VNx2HI") (VNx4SI "VNx4HI") (VNx8SI "VNx8HI") - (VNx16SI "VNx16HI") + (VNx16SI "VNx16HI") (VNx32SI "VNx32HI") (VNx1SF "VNx1HI") (VNx2SF "VNx2HI") (VNx4SF "VNx4HI") (VNx8SF "VNx8HI") - (VNx16SF "VNx16HI") - (VNx1DI "VNx1SI") (VNx2DI "VNx2SI") (VNx4DI "VNx4SI") (VNx8DI "VNx8SI") - (VNx1DF "VNx1SI") (VNx2DF "VNx2SI") (VNx4DF "VNx4SI") (VNx8DF "VNx8SI") + (VNx16SF "VNx16HI") (VNx32SF "VNx32HI") + (VNx1DI "VNx1SI") (VNx2DI "VNx2SI") (VNx4DI "VNx4SI") (VNx8DI "VNx8SI") (VNx16DI "VNx16SI") + (VNx1DF "VNx1SI") (VNx2DF "VNx2SI") (VNx4DF "VNx4SI") (VNx8DF "VNx8SI") (VNx16DF "VNx16SI") ]) (define_mode_attr VINDEX_QUAD_TRUNC [ (VNx1SI "VNx1QI") (VNx2SI "VNx2QI") (VNx4SI "VNx4QI") (VNx8SI "VNx8QI") - (VNx16SI "VNx16QI") + (VNx16SI "VNx16QI") (VNx32SI "VNx32QI") (VNx1DI "VNx1HI") (VNx2DI "VNx2HI") - (VNx4DI "VNx4HI") (VNx8DI "VNx8HI") + (VNx4DI "VNx4HI") (VNx8DI "VNx8HI") (VNx16DI "VNx16HI") (VNx1SF "VNx1QI") (VNx2SF "VNx2QI") (VNx4SF "VNx4QI") (VNx8SF "VNx8QI") - (VNx16SF "VNx16QI") + (VNx16SF "VNx16QI") (VNx32SF "VNx32QI") (VNx1DF "VNx1HI") (VNx2DF "VNx2HI") - (VNx4DF "VNx4HI") (VNx8DF "VNx8HI") + (VNx4DF "VNx4HI") (VNx8DF "VNx8HI") (VNx16DF "VNx16HI") ]) (define_mode_attr VINDEX_OCT_TRUNC [ - (VNx1DI "VNx1QI") (VNx2DI "VNx2QI") (VNx4DI "VNx4QI") (VNx8DI "VNx8QI") - (VNx1DF "VNx1QI") (VNx2DF "VNx2QI") (VNx4DF "VNx4QI") (VNx8DF "VNx8QI") + (VNx1DI "VNx1QI") (VNx2DI "VNx2QI") (VNx4DI "VNx4QI") (VNx8DI "VNx8QI") (VNx16DI "VNx16QI") + (VNx1DF "VNx1QI") (VNx2DF "VNx2QI") (VNx4DF "VNx4QI") (VNx8DF "VNx8QI") (VNx16DF "VNx16QI") ]) (define_mode_attr VINDEX_DOUBLE_EXT [ - (VNx1QI "VNx1HI") (VNx2QI "VNx2HI") (VNx4QI "VNx4HI") (VNx8QI "VNx8HI") (VNx16QI "VNx16HI") (VNx32QI "VNx32HI") - (VNx1HI "VNx1SI") (VNx2HI "VNx2SI") (VNx4HI "VNx4SI") (VNx8HI "VNx8SI") (VNx16HI "VNx16SI") - (VNx1SI "VNx1DI") (VNx2SI "VNx2DI") (VNx4SI "VNx4DI") (VNx8SI "VNx8DI") - (VNx1SF "VNx1DI") (VNx2SF "VNx2DI") (VNx4SF "VNx4DI") (VNx8SF "VNx8DI") + (VNx1QI "VNx1HI") (VNx2QI "VNx2HI") (VNx4QI "VNx4HI") (VNx8QI "VNx8HI") (VNx16QI "VNx16HI") (VNx32QI "VNx32HI") (VNx64QI "VNx64HI") + (VNx1HI "VNx1SI") (VNx2HI "VNx2SI") (VNx4HI "VNx4SI") (VNx8HI "VNx8SI") (VNx16HI "VNx16SI") (VNx32HI "VNx32SI") + (VNx1SI "VNx1DI") (VNx2SI "VNx2DI") (VNx4SI "VNx4DI") (VNx8SI "VNx8DI") (VNx16SI "VNx16DI") + (VNx1SF "VNx1DI") (VNx2SF "VNx2DI") (VNx4SF "VNx4DI") (VNx8SF "VNx8DI") (VNx16SF "VNx16DI") ]) (define_mode_attr VINDEX_QUAD_EXT [ - (VNx1QI "VNx1SI") (VNx2QI "VNx2SI") (VNx4QI "VNx4SI") (VNx8QI "VNx8SI") (VNx16QI "VNx16SI") - (VNx1HI "VNx1DI") (VNx2HI "VNx2DI") (VNx4HI "VNx4DI") (VNx8HI "VNx8DI") + (VNx1QI "VNx1SI") (VNx2QI "VNx2SI") (VNx4QI "VNx4SI") (VNx8QI "VNx8SI") (VNx16QI "VNx16SI") (VNx32QI "VNx32SI") + (VNx1HI "VNx1DI") (VNx2HI "VNx2DI") (VNx4HI "VNx4DI") (VNx8HI "VNx8DI") (VNx16HI "VNx16DI") ]) (define_mode_attr VINDEX_OCT_EXT [ - (VNx1QI "VNx1DI") (VNx2QI "VNx2DI") (VNx4QI "VNx4DI") (VNx8QI "VNx8DI") + (VNx1QI "VNx1DI") (VNx2QI "VNx2DI") (VNx4QI "VNx4DI") (VNx8QI "VNx8DI") (VNx16QI "VNx16DI") ]) (define_mode_attr VCONVERT [ - (VNx1SF "VNx1SI") (VNx2SF "VNx2SI") (VNx4SF "VNx4SI") (VNx8SF "VNx8SI") (VNx16SF "VNx16SI") - (VNx1DF "VNx1DI") (VNx2DF "VNx2DI") (VNx4DF "VNx4DI") (VNx8DF "VNx8DI") + (VNx1SF "VNx1SI") (VNx2SF "VNx2SI") (VNx4SF "VNx4SI") (VNx8SF "VNx8SI") (VNx16SF "VNx16SI") (VNx32SF "VNx32SI") + (VNx1DF "VNx1DI") (VNx2DF "VNx2DI") (VNx4DF "VNx4DI") (VNx8DF "VNx8DI") (VNx16DF "VNx16DI") ]) (define_mode_attr VNCONVERT [ - (VNx1SF "VNx1HI") (VNx2SF "VNx2HI") (VNx4SF "VNx4HI") (VNx8SF "VNx8HI") (VNx16SF "VNx16HI") - (VNx1DI "VNx1SF") (VNx2DI "VNx2SF") (VNx4DI "VNx4SF") (VNx8DI "VNx8SF") - (VNx1DF "VNx1SI") (VNx2DF "VNx2SI") (VNx4DF "VNx4SI") (VNx8DF "VNx8SI") + (VNx1SF "VNx1HI") (VNx2SF "VNx2HI") (VNx4SF "VNx4HI") (VNx8SF "VNx8HI") (VNx16SF "VNx16HI") (VNx32SF "VNx32HI") + (VNx1DI "VNx1SF") (VNx2DI "VNx2SF") (VNx4DI "VNx4SF") (VNx8DI "VNx8SF") (VNx16DI "VNx16SF") + (VNx1DF "VNx1SI") (VNx2DF "VNx2SI") (VNx4DF "VNx4SI") (VNx8DF "VNx8SI") (VNx16DF "VNx16SI") ]) (define_mode_attr VLMUL1 [ + (VNx1QI "VNx16QI") (VNx2QI "VNx16QI") (VNx4QI "VNx16QI") + (VNx8QI "VNx16QI") (VNx16QI "VNx16QI") (VNx32QI "VNx16QI") (VNx64QI "VNx16QI") (VNx128QI "VNx16QI") + (VNx1HI "VNx8HI") (VNx2HI "VNx8HI") (VNx4HI "VNx8HI") + (VNx8HI "VNx8HI") (VNx16HI "VNx8HI") (VNx32HI "VNx8HI") (VNx64HI "VNx8HI") + (VNx1SI "VNx4SI") (VNx2SI "VNx4SI") (VNx4SI "VNx4SI") + (VNx8SI "VNx4SI") (VNx16SI "VNx4SI") (VNx32SI "VNx4SI") + (VNx1DI "VNx2DI") (VNx2DI "VNx2DI") + (VNx4DI "VNx2DI") (VNx8DI "VNx2DI") (VNx16DI "VNx2DI") + (VNx1SF "VNx4SF") (VNx2SF "VNx4SF") + (VNx4SF "VNx4SF") (VNx8SF "VNx4SF") (VNx16SF "VNx4SF") (VNx32SF "VNx4SF") + (VNx1DF "VNx2DF") (VNx2DF "VNx2DF") + (VNx4DF "VNx2DF") (VNx8DF "VNx2DF") (VNx16DF "VNx2DF") +]) + +(define_mode_attr VLMUL1_ZVE64 [ (VNx1QI "VNx8QI") (VNx2QI "VNx8QI") (VNx4QI "VNx8QI") (VNx8QI "VNx8QI") (VNx16QI "VNx8QI") (VNx32QI "VNx8QI") (VNx64QI "VNx8QI") (VNx1HI "VNx4HI") (VNx2HI "VNx4HI") (VNx4HI "VNx4HI") @@ -680,6 +752,17 @@ ]) (define_mode_attr VWLMUL1 [ + (VNx1QI "VNx8HI") (VNx2QI "VNx8HI") (VNx4QI "VNx8HI") + (VNx8QI "VNx8HI") (VNx16QI "VNx8HI") (VNx32QI "VNx8HI") (VNx64QI "VNx8HI") (VNx128QI "VNx8HI") + (VNx1HI "VNx4SI") (VNx2HI "VNx4SI") (VNx4HI "VNx4SI") + (VNx8HI "VNx4SI") (VNx16HI "VNx4SI") (VNx32HI "VNx4SI") (VNx64HI "VNx4SI") + (VNx1SI "VNx2DI") (VNx2SI "VNx2DI") (VNx4SI "VNx2DI") + (VNx8SI "VNx2DI") (VNx16SI "VNx2DI") (VNx32SI "VNx2DI") + (VNx1SF "VNx2DF") (VNx2SF "VNx2DF") + (VNx4SF "VNx2DF") (VNx8SF "VNx2DF") (VNx16SF "VNx2DF") (VNx32SF "VNx2DF") +]) + +(define_mode_attr VWLMUL1_ZVE64 [ (VNx1QI "VNx4HI") (VNx2QI "VNx4HI") (VNx4QI "VNx4HI") (VNx8QI "VNx4HI") (VNx16QI "VNx4HI") (VNx32QI "VNx4HI") (VNx64QI "VNx4HI") (VNx1HI "VNx2SI") (VNx2HI "VNx2SI") (VNx4HI "VNx2SI") @@ -698,6 +781,21 @@ ]) (define_mode_attr vlmul1 [ + (VNx1QI "vnx16qi") (VNx2QI "vnx16qi") (VNx4QI "vnx16qi") + (VNx8QI "vnx16qi") (VNx16QI "vnx16qi") (VNx32QI "vnx16qi") (VNx64QI "vnx16qi") (VNx128QI "vnx16qi") + (VNx1HI "vnx8hi") (VNx2HI "vnx8hi") (VNx4HI "vnx8hi") + (VNx8HI "vnx8hi") (VNx16HI "vnx8hi") (VNx32HI "vnx8hi") (VNx64HI "vnx8hi") + (VNx1SI "vnx4si") (VNx2SI "vnx4si") (VNx4SI "vnx4si") + (VNx8SI "vnx4si") (VNx16SI "vnx4si") (VNx32SI "vnx4si") + (VNx1DI "vnx2di") (VNx2DI "vnx2di") + (VNx4DI "vnx2di") (VNx8DI "vnx2di") (VNx16DI "vnx2di") + (VNx1SF "vnx4sf") (VNx2SF "vnx4sf") + (VNx4SF "vnx4sf") (VNx8SF "vnx4sf") (VNx16SF "vnx4sf") (VNx32SF "vnx4sf") + (VNx1DF "vnx2df") (VNx2DF "vnx2df") + (VNx4DF "vnx2df") (VNx8DF "vnx2df") (VNx16DF "vnx2df") +]) + +(define_mode_attr vlmul1_zve64 [ (VNx1QI "vnx8qi") (VNx2QI "vnx8qi") (VNx4QI "vnx8qi") (VNx8QI "vnx8qi") (VNx16QI "vnx8qi") (VNx32QI "vnx8qi") (VNx64QI "vnx8qi") (VNx1HI "vnx4hi") (VNx2HI "vnx4hi") (VNx4HI "vnx4hi") @@ -724,12 +822,23 @@ ]) (define_mode_attr vwlmul1 [ + (VNx1QI "vnx8hi") (VNx2QI "vnx8hi") (VNx4QI "vnx8hi") + (VNx8QI "vnx8hi") (VNx16QI "vnx8hi") (VNx32QI "vnx8hi") (VNx64QI "vnx8hi") (VNx128QI "vnx8hi") + (VNx1HI "vnx4si") (VNx2HI "vnx4si") (VNx4HI "vnx4si") + (VNx8HI "vnx4si") (VNx16HI "vnx4si") (VNx32HI "vnx4si") (VNx64HI "vnx4si") + (VNx1SI "vnx2di") (VNx2SI "vnx2di") (VNx4SI "vnx2di") + (VNx8SI "vnx2di") (VNx16SI "vnx2di") (VNx32SI "vnx2di") + (VNx1SF "vnx2df") (VNx2SF "vnx2df") + (VNx4SF "vnx2df") (VNx8SF "vnx2df") (VNx16SF "vnx2df") (VNx32SF "vnx2df") +]) + +(define_mode_attr vwlmul1_zve64 [ (VNx1QI "vnx4hi") (VNx2QI "vnx4hi") (VNx4QI "vnx4hi") (VNx8QI "vnx4hi") (VNx16QI "vnx4hi") (VNx32QI "vnx4hi") (VNx64QI "vnx4hi") (VNx1HI "vnx2si") (VNx2HI "vnx2si") (VNx4HI "vnx2si") - (VNx8HI "vnx2si") (VNx16HI "vnx2si") (VNx32HI "vnx2si") - (VNx1SI "vnx2di") (VNx2SI "vnx2di") (VNx4SI "vnx2di") - (VNx8SI "vnx2di") (VNx16SI "vnx2di") + (VNx8HI "vnx2si") (VNx16HI "vnx2si") (VNx32HI "vnx2SI") + (VNx1SI "vnx1di") (VNx2SI "vnx1di") (VNx4SI "vnx1di") + (VNx8SI "vnx1di") (VNx16SI "vnx1di") (VNx1SF "vnx1df") (VNx2SF "vnx1df") (VNx4SF "vnx1df") (VNx8SF "vnx1df") (VNx16SF "vnx1df") ]) @@ -738,17 +847,17 @@ (VNx1QI "vnx2hi") (VNx2QI "vnx2hi") (VNx4QI "vnx2hi") (VNx8QI "vnx2hi") (VNx16QI "vnx2hi") (VNx32QI "vnx2hi") (VNx1HI "vnx1si") (VNx2HI "vnx1si") (VNx4HI "vnx1si") - (VNx8HI "vnx1si") (VNx16HI "vnx1si") + (VNx8HI "vnx1si") (VNx16HI "vnx1SI") ]) (define_mode_attr VDEMOTE [ (VNx1DI "VNx2SI") (VNx2DI "VNx4SI") - (VNx4DI "VNx8SI") (VNx8DI "VNx16SI") + (VNx4DI "VNx8SI") (VNx8DI "VNx16SI") (VNx16DI "VNx32SI") ]) (define_mode_attr VMDEMOTE [ (VNx1DI "VNx2BI") (VNx2DI "VNx4BI") - (VNx4DI "VNx8BI") (VNx8DI "VNx16BI") + (VNx4DI "VNx8BI") (VNx8DI "VNx16BI") (VNx16DI "VNx32BI") ]) (define_int_iterator WREDUC [UNSPEC_WREDUC_SUM UNSPEC_WREDUC_USUM]) diff --git a/gcc/config/riscv/vector.md b/gcc/config/riscv/vector.md index 0ecca98f20c..0fda11ed67d 100644 --- a/gcc/config/riscv/vector.md +++ b/gcc/config/riscv/vector.md @@ -82,15 +82,16 @@ ;; is no field for ratio in the vsetvl instruction encoding. (define_attr "sew" "" (cond [(eq_attr "mode" "VNx1QI,VNx2QI,VNx4QI,VNx8QI,VNx16QI,VNx32QI,VNx64QI,\ - VNx1BI,VNx2BI,VNx4BI,VNx8BI,VNx16BI,VNx32BI,VNx64BI") + VNx1BI,VNx2BI,VNx4BI,VNx8BI,VNx16BI,VNx32BI,VNx64BI,\ + VNx128QI,VNx128BI") (const_int 8) - (eq_attr "mode" "VNx1HI,VNx2HI,VNx4HI,VNx8HI,VNx16HI,VNx32HI") + (eq_attr "mode" "VNx1HI,VNx2HI,VNx4HI,VNx8HI,VNx16HI,VNx32HI,VNx64HI") (const_int 16) - (eq_attr "mode" "VNx1SI,VNx2SI,VNx4SI,VNx8SI,VNx16SI,\ - VNx1SF,VNx2SF,VNx4SF,VNx8SF,VNx16SF") + (eq_attr "mode" "VNx1SI,VNx2SI,VNx4SI,VNx8SI,VNx16SI,VNx32SI,\ + VNx1SF,VNx2SF,VNx4SF,VNx8SF,VNx16SF,VNx32SF") (const_int 32) - (eq_attr "mode" "VNx1DI,VNx2DI,VNx4DI,VNx8DI,\ - VNx1DF,VNx2DF,VNx4DF,VNx8DF") + (eq_attr "mode" "VNx1DI,VNx2DI,VNx4DI,VNx8DI,VNx16DI,\ + VNx1DF,VNx2DF,VNx4DF,VNx8DF,VNx16DF") (const_int 64)] (const_int INVALID_ATTRIBUTE))) @@ -110,6 +111,8 @@ (symbol_ref "riscv_vector::get_vlmul(E_VNx32QImode)") (eq_attr "mode" "VNx64QI,VNx64BI") (symbol_ref "riscv_vector::get_vlmul(E_VNx64QImode)") + (eq_attr "mode" "VNx128QI,VNx128BI") + (symbol_ref "riscv_vector::get_vlmul(E_VNx128QImode)") (eq_attr "mode" "VNx1HI") (symbol_ref "riscv_vector::get_vlmul(E_VNx1HImode)") (eq_attr "mode" "VNx2HI") @@ -122,6 +125,8 @@ (symbol_ref "riscv_vector::get_vlmul(E_VNx16HImode)") (eq_attr "mode" "VNx32HI") (symbol_ref "riscv_vector::get_vlmul(E_VNx32HImode)") + (eq_attr "mode" "VNx64HI") + (symbol_ref "riscv_vector::get_vlmul(E_VNx64HImode)") (eq_attr "mode" "VNx1SI,VNx1SF") (symbol_ref "riscv_vector::get_vlmul(E_VNx1SImode)") (eq_attr "mode" "VNx2SI,VNx2SF") @@ -132,6 +137,8 @@ (symbol_ref "riscv_vector::get_vlmul(E_VNx8SImode)") (eq_attr "mode" "VNx16SI,VNx16SF") (symbol_ref "riscv_vector::get_vlmul(E_VNx16SImode)") + (eq_attr "mode" "VNx32SI,VNx32SF") + (symbol_ref "riscv_vector::get_vlmul(E_VNx32SImode)") (eq_attr "mode" "VNx1DI,VNx1DF") (symbol_ref "riscv_vector::get_vlmul(E_VNx1DImode)") (eq_attr "mode" "VNx2DI,VNx2DF") @@ -139,7 +146,9 @@ (eq_attr "mode" "VNx4DI,VNx4DF") (symbol_ref "riscv_vector::get_vlmul(E_VNx4DImode)") (eq_attr "mode" "VNx8DI,VNx8DF") - (symbol_ref "riscv_vector::get_vlmul(E_VNx8DImode)")] + (symbol_ref "riscv_vector::get_vlmul(E_VNx8DImode)") + (eq_attr "mode" "VNx16DI,VNx16DF") + (symbol_ref "riscv_vector::get_vlmul(E_VNx16DImode)")] (const_int INVALID_ATTRIBUTE))) ;; It is valid for instruction that require sew/lmul ratio. @@ -173,6 +182,8 @@ (symbol_ref "riscv_vector::get_ratio(E_VNx32QImode)") (eq_attr "mode" "VNx64QI,VNx64BI") (symbol_ref "riscv_vector::get_ratio(E_VNx64QImode)") + (eq_attr "mode" "VNx128QI,VNx128BI") + (symbol_ref "riscv_vector::get_ratio(E_VNx128QImode)") (eq_attr "mode" "VNx1HI") (symbol_ref "riscv_vector::get_ratio(E_VNx1HImode)") (eq_attr "mode" "VNx2HI") @@ -185,6 +196,8 @@ (symbol_ref "riscv_vector::get_ratio(E_VNx16HImode)") (eq_attr "mode" "VNx32HI") (symbol_ref "riscv_vector::get_ratio(E_VNx32HImode)") + (eq_attr "mode" "VNx64HI") + (symbol_ref "riscv_vector::get_ratio(E_VNx64HImode)") (eq_attr "mode" "VNx1SI,VNx1SF") (symbol_ref "riscv_vector::get_ratio(E_VNx1SImode)") (eq_attr "mode" "VNx2SI,VNx2SF") @@ -195,6 +208,8 @@ (symbol_ref "riscv_vector::get_ratio(E_VNx8SImode)") (eq_attr "mode" "VNx16SI,VNx16SF") (symbol_ref "riscv_vector::get_ratio(E_VNx16SImode)") + (eq_attr "mode" "VNx32SI,VNx32SF") + (symbol_ref "riscv_vector::get_ratio(E_VNx32SImode)") (eq_attr "mode" "VNx1DI,VNx1DF") (symbol_ref "riscv_vector::get_ratio(E_VNx1DImode)") (eq_attr "mode" "VNx2DI,VNx2DF") @@ -202,7 +217,9 @@ (eq_attr "mode" "VNx4DI,VNx4DF") (symbol_ref "riscv_vector::get_ratio(E_VNx4DImode)") (eq_attr "mode" "VNx8DI,VNx8DF") - (symbol_ref "riscv_vector::get_ratio(E_VNx8DImode)")] + (symbol_ref "riscv_vector::get_ratio(E_VNx8DImode)") + (eq_attr "mode" "VNx16DI,VNx16DF") + (symbol_ref "riscv_vector::get_ratio(E_VNx16DImode)")] (const_int INVALID_ATTRIBUTE))) ;; The index of operand[] to get the merge op. @@ -1633,7 +1650,7 @@ [(set_attr "type" "vst<order>x") (set_attr "mode" "<VNX16_QHS:MODE>")]) -(define_insn "@pred_indexed_<order>store<VNX32_QH:mode><VNX32_QHI:mode>" +(define_insn "@pred_indexed_<order>store<VNX32_QHS:mode><VNX32_QHSI:mode>" [(set (mem:BLK (scratch)) (unspec:BLK [(unspec:<VM> @@ -1643,14 +1660,14 @@ (reg:SI VL_REGNUM) (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) (match_operand 1 "pmode_register_operand" " r") - (match_operand:VNX32_QHI 2 "register_operand" " vr") - (match_operand:VNX32_QH 3 "register_operand" " vr")] ORDER))] + (match_operand:VNX32_QHSI 2 "register_operand" " vr") + (match_operand:VNX32_QHS 3 "register_operand" " vr")] ORDER))] "TARGET_VECTOR" - "vs<order>xei<VNX32_QHI:sew>.v\t%3,(%1),%2%p0" + "vs<order>xei<VNX32_QHSI:sew>.v\t%3,(%1),%2%p0" [(set_attr "type" "vst<order>x") - (set_attr "mode" "<VNX32_QH:MODE>")]) + (set_attr "mode" "<VNX32_QHS:MODE>")]) -(define_insn "@pred_indexed_<order>store<VNX64_Q:mode><VNX64_Q:mode>" +(define_insn "@pred_indexed_<order>store<VNX64_QH:mode><VNX64_QHI:mode>" [(set (mem:BLK (scratch)) (unspec:BLK [(unspec:<VM> @@ -1660,12 +1677,29 @@ (reg:SI VL_REGNUM) (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) (match_operand 1 "pmode_register_operand" " r") - (match_operand:VNX64_Q 2 "register_operand" " vr") - (match_operand:VNX64_Q 3 "register_operand" " vr")] ORDER))] + (match_operand:VNX64_QHI 2 "register_operand" " vr") + (match_operand:VNX64_QH 3 "register_operand" " vr")] ORDER))] "TARGET_VECTOR" - "vs<order>xei<VNX64_Q:sew>.v\t%3,(%1),%2%p0" + "vs<order>xei<VNX64_QHI:sew>.v\t%3,(%1),%2%p0" [(set_attr "type" "vst<order>x") - (set_attr "mode" "<VNX64_Q:MODE>")]) + (set_attr "mode" "<VNX64_QH:MODE>")]) + +(define_insn "@pred_indexed_<order>store<VNX128_Q:mode><VNX128_Q:mode>" + [(set (mem:BLK (scratch)) + (unspec:BLK + [(unspec:<VM> + [(match_operand:<VM> 0 "vector_mask_operand" "vmWc1") + (match_operand 4 "vector_length_operand" " rK") + (match_operand 5 "const_int_operand" " i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (match_operand 1 "pmode_register_operand" " r") + (match_operand:VNX128_Q 2 "register_operand" " vr") + (match_operand:VNX128_Q 3 "register_operand" " vr")] ORDER))] + "TARGET_VECTOR" + "vs<order>xei<VNX128_Q:sew>.v\t%3,(%1),%2%p0" + [(set_attr "type" "vst<order>x") + (set_attr "mode" "<VNX128_Q:MODE>")]) ;; ------------------------------------------------------------------------------- ;; ---- Predicated integer binary operations @@ -6746,23 +6780,45 @@ ;; For example, The LMUL = 1 corresponding mode of VNx16QImode is VNx4QImode ;; for -march=rv*zve32* wheras VNx8QImode for -march=rv*zve64* (define_insn "@pred_reduc_<reduc><mode><vlmul1>" - [(set (match_operand:<VLMUL1> 0 "register_operand" "=vd, vd, vr, vr") + [(set (match_operand:<VLMUL1> 0 "register_operand" "=vr, vr") (unspec:<VLMUL1> [(unspec:<VM> - [(match_operand:<VM> 1 "vector_mask_operand" " vm, vm,Wc1,Wc1") - (match_operand 5 "vector_length_operand" " rK, rK, rK, rK") - (match_operand 6 "const_int_operand" " i, i, i, i") - (match_operand 7 "const_int_operand" " i, i, i, i") + [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1") + (match_operand 5 "vector_length_operand" " rK, rK") + (match_operand 6 "const_int_operand" " i, i") + (match_operand 7 "const_int_operand" " i, i") (reg:SI VL_REGNUM) (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) (any_reduc:VI (vec_duplicate:VI (vec_select:<VEL> - (match_operand:<VLMUL1> 4 "register_operand" " vr, vr, vr, vr") + (match_operand:<VLMUL1> 4 "register_operand" " vr, vr") (parallel [(const_int 0)]))) - (match_operand:VI 3 "register_operand" " vr, vr, vr, vr")) - (match_operand:<VLMUL1> 2 "vector_merge_operand" " vu, 0, vu, 0")] UNSPEC_REDUC))] - "TARGET_VECTOR && TARGET_MIN_VLEN > 32" + (match_operand:VI 3 "register_operand" " vr, vr")) + (match_operand:<VLMUL1> 2 "vector_merge_operand" " vu, 0")] UNSPEC_REDUC))] + "TARGET_VECTOR && TARGET_MIN_VLEN >= 128" + "vred<reduc>.vs\t%0,%3,%4%p1" + [(set_attr "type" "vired") + (set_attr "mode" "<MODE>")]) + +(define_insn "@pred_reduc_<reduc><mode><vlmul1_zve64>" + [(set (match_operand:<VLMUL1_ZVE64> 0 "register_operand" "=vr, vr") + (unspec:<VLMUL1_ZVE64> + [(unspec:<VM> + [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1") + (match_operand 5 "vector_length_operand" " rK, rK") + (match_operand 6 "const_int_operand" " i, i") + (match_operand 7 "const_int_operand" " i, i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (any_reduc:VI_ZVE64 + (vec_duplicate:VI_ZVE64 + (vec_select:<VEL> + (match_operand:<VLMUL1_ZVE64> 4 "register_operand" " vr, vr") + (parallel [(const_int 0)]))) + (match_operand:VI_ZVE64 3 "register_operand" " vr, vr")) + (match_operand:<VLMUL1_ZVE64> 2 "vector_merge_operand" " vu, 0")] UNSPEC_REDUC))] + "TARGET_VECTOR && TARGET_MIN_VLEN == 64" "vred<reduc>.vs\t%0,%3,%4%p1" [(set_attr "type" "vired") (set_attr "mode" "<MODE>")]) @@ -6802,11 +6858,30 @@ (match_operand:VWI 3 "register_operand" " vr, vr") (match_operand:<VWLMUL1> 4 "register_operand" " vr, vr") (match_operand:<VWLMUL1> 2 "vector_merge_operand" " vu, 0")] WREDUC))] - "TARGET_VECTOR && TARGET_MIN_VLEN > 32" + "TARGET_VECTOR && TARGET_MIN_VLEN >= 128" "vwredsum<v_su>.vs\t%0,%3,%4%p1" [(set_attr "type" "viwred") (set_attr "mode" "<MODE>")]) +(define_insn "@pred_widen_reduc_plus<v_su><mode><vwlmul1_zve64>" + [(set (match_operand:<VWLMUL1_ZVE64> 0 "register_operand" "=&vr, &vr") + (unspec:<VWLMUL1_ZVE64> + [(unspec:<VM> + [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1") + (match_operand 5 "vector_length_operand" " rK, rK") + (match_operand 6 "const_int_operand" " i, i") + (match_operand 7 "const_int_operand" " i, i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (match_operand:VWI_ZVE64 3 "register_operand" " vr, vr") + (match_operand:<VWLMUL1_ZVE64> 4 "register_operand" " vr, vr") + (match_operand:<VWLMUL1_ZVE64> 2 "vector_merge_operand" " vu, 0")] WREDUC))] + "TARGET_VECTOR && TARGET_MIN_VLEN == 64" + "vwredsum<v_su>.vs\t%0,%3,%4%p1" + [(set_attr "type" "viwred") + (set_attr "mode" "<MODE>")]) + + (define_insn "@pred_widen_reduc_plus<v_su><mode><vwlmul1_zve32>" [(set (match_operand:<VWLMUL1_ZVE32> 0 "register_operand" "=&vr, &vr") (unspec:<VWLMUL1_ZVE32> @@ -6826,23 +6901,45 @@ (set_attr "mode" "<MODE>")]) (define_insn "@pred_reduc_<reduc><mode><vlmul1>" - [(set (match_operand:<VLMUL1> 0 "register_operand" "=vd, vd, vr, vr") + [(set (match_operand:<VLMUL1> 0 "register_operand" "=vr, vr") (unspec:<VLMUL1> [(unspec:<VM> - [(match_operand:<VM> 1 "vector_mask_operand" " vm, vm,Wc1,Wc1") - (match_operand 5 "vector_length_operand" " rK, rK, rK, rK") - (match_operand 6 "const_int_operand" " i, i, i, i") - (match_operand 7 "const_int_operand" " i, i, i, i") + [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1") + (match_operand 5 "vector_length_operand" " rK, rK") + (match_operand 6 "const_int_operand" " i, i") + (match_operand 7 "const_int_operand" " i, i") (reg:SI VL_REGNUM) (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) (any_freduc:VF (vec_duplicate:VF (vec_select:<VEL> - (match_operand:<VLMUL1> 4 "register_operand" " vr, vr, vr, vr") + (match_operand:<VLMUL1> 4 "register_operand" " vr, vr") + (parallel [(const_int 0)]))) + (match_operand:VF 3 "register_operand" " vr, vr")) + (match_operand:<VLMUL1> 2 "vector_merge_operand" " vu, 0")] UNSPEC_REDUC))] + "TARGET_VECTOR && TARGET_MIN_VLEN >= 128" + "vfred<reduc>.vs\t%0,%3,%4%p1" + [(set_attr "type" "vfredu") + (set_attr "mode" "<MODE>")]) + +(define_insn "@pred_reduc_<reduc><mode><vlmul1_zve64>" + [(set (match_operand:<VLMUL1_ZVE64> 0 "register_operand" "=vr, vr") + (unspec:<VLMUL1_ZVE64> + [(unspec:<VM> + [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1") + (match_operand 5 "vector_length_operand" " rK, rK") + (match_operand 6 "const_int_operand" " i, i") + (match_operand 7 "const_int_operand" " i, i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (any_freduc:VF_ZVE64 + (vec_duplicate:VF_ZVE64 + (vec_select:<VEL> + (match_operand:<VLMUL1_ZVE64> 4 "register_operand" " vr, vr") (parallel [(const_int 0)]))) - (match_operand:VF 3 "register_operand" " vr, vr, vr, vr")) - (match_operand:<VLMUL1> 2 "vector_merge_operand" " vu, 0, vu, 0")] UNSPEC_REDUC))] - "TARGET_VECTOR && TARGET_MIN_VLEN > 32" + (match_operand:VF_ZVE64 3 "register_operand" " vr, vr")) + (match_operand:<VLMUL1_ZVE64> 2 "vector_merge_operand" " vu, 0")] UNSPEC_REDUC))] + "TARGET_VECTOR && TARGET_MIN_VLEN == 64" "vfred<reduc>.vs\t%0,%3,%4%p1" [(set_attr "type" "vfredu") (set_attr "mode" "<MODE>")]) @@ -6870,24 +6967,47 @@ (set_attr "mode" "<MODE>")]) (define_insn "@pred_reduc_plus<order><mode><vlmul1>" - [(set (match_operand:<VLMUL1> 0 "register_operand" "=vd, vd, vr, vr") + [(set (match_operand:<VLMUL1> 0 "register_operand" "=vr, vr") (unspec:<VLMUL1> [(unspec:<VLMUL1> [(unspec:<VM> - [(match_operand:<VM> 1 "vector_mask_operand" " vm, vm,Wc1,Wc1") - (match_operand 5 "vector_length_operand" " rK, rK, rK, rK") - (match_operand 6 "const_int_operand" " i, i, i, i") - (match_operand 7 "const_int_operand" " i, i, i, i") + [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1") + (match_operand 5 "vector_length_operand" " rK, rK") + (match_operand 6 "const_int_operand" " i, i") + (match_operand 7 "const_int_operand" " i, i") (reg:SI VL_REGNUM) (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) (plus:VF (vec_duplicate:VF (vec_select:<VEL> - (match_operand:<VLMUL1> 4 "register_operand" " vr, vr, vr, vr") + (match_operand:<VLMUL1> 4 "register_operand" " vr, vr") (parallel [(const_int 0)]))) - (match_operand:VF 3 "register_operand" " vr, vr, vr, vr")) - (match_operand:<VLMUL1> 2 "vector_merge_operand" " vu, 0, vu, 0")] UNSPEC_REDUC)] ORDER))] - "TARGET_VECTOR && TARGET_MIN_VLEN > 32" + (match_operand:VF 3 "register_operand" " vr, vr")) + (match_operand:<VLMUL1> 2 "vector_merge_operand" " vu, 0")] UNSPEC_REDUC)] ORDER))] + "TARGET_VECTOR && TARGET_MIN_VLEN >= 128" + "vfred<order>sum.vs\t%0,%3,%4%p1" + [(set_attr "type" "vfred<order>") + (set_attr "mode" "<MODE>")]) + +(define_insn "@pred_reduc_plus<order><mode><vlmul1_zve64>" + [(set (match_operand:<VLMUL1_ZVE64> 0 "register_operand" "=vr, vr") + (unspec:<VLMUL1_ZVE64> + [(unspec:<VLMUL1_ZVE64> + [(unspec:<VM> + [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1") + (match_operand 5 "vector_length_operand" " rK, rK") + (match_operand 6 "const_int_operand" " i, i") + (match_operand 7 "const_int_operand" " i, i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (plus:VF_ZVE64 + (vec_duplicate:VF_ZVE64 + (vec_select:<VEL> + (match_operand:<VLMUL1_ZVE64> 4 "register_operand" " vr, vr") + (parallel [(const_int 0)]))) + (match_operand:VF_ZVE64 3 "register_operand" " vr, vr")) + (match_operand:<VLMUL1_ZVE64> 2 "vector_merge_operand" " vu, 0")] UNSPEC_REDUC)] ORDER))] + "TARGET_VECTOR && TARGET_MIN_VLEN == 64" "vfred<order>sum.vs\t%0,%3,%4%p1" [(set_attr "type" "vfred<order>") (set_attr "mode" "<MODE>")]) @@ -6929,7 +7049,26 @@ (match_operand:VWF 3 "register_operand" " vr, vr") (match_operand:<VWLMUL1> 4 "register_operand" " vr, vr") (match_operand:<VWLMUL1> 2 "vector_merge_operand" " vu, 0")] UNSPEC_WREDUC_SUM)] ORDER))] - "TARGET_VECTOR && TARGET_MIN_VLEN > 32" + "TARGET_VECTOR && TARGET_MIN_VLEN >= 128" + "vfwred<order>sum.vs\t%0,%3,%4%p1" + [(set_attr "type" "vfwred<order>") + (set_attr "mode" "<MODE>")]) + +(define_insn "@pred_widen_reduc_plus<order><mode><vwlmul1_zve64>" + [(set (match_operand:<VWLMUL1_ZVE64> 0 "register_operand" "=&vr, &vr") + (unspec:<VWLMUL1_ZVE64> + [(unspec:<VWLMUL1_ZVE64> + [(unspec:<VM> + [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1") + (match_operand 5 "vector_length_operand" " rK, rK") + (match_operand 6 "const_int_operand" " i, i") + (match_operand 7 "const_int_operand" " i, i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (match_operand:VWF_ZVE64 3 "register_operand" " vr, vr") + (match_operand:<VWLMUL1_ZVE64> 4 "register_operand" " vr, vr") + (match_operand:<VWLMUL1_ZVE64> 2 "vector_merge_operand" " vu, 0")] UNSPEC_WREDUC_SUM)] ORDER))] + "TARGET_VECTOR && TARGET_MIN_VLEN == 64" "vfwred<order>sum.vs\t%0,%3,%4%p1" [(set_attr "type" "vfwred<order>") (set_attr "mode" "<MODE>")]) diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr108185-4.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr108185-4.c index ea3c360d756..6e4d1cb1e44 100644 --- a/gcc/testsuite/gcc.target/riscv/rvv/base/pr108185-4.c +++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr108185-4.c @@ -1,5 +1,5 @@ /* { dg-do compile } */ -/* { dg-options "-march=rv64gcv -mabi=lp64 -O3" } */ +/* { dg-options "-march=rv64gc_zve64d -mabi=lp64 -O3" } */ #include "riscv_vector.h" diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/spill-1.c b/gcc/testsuite/gcc.target/riscv/rvv/base/spill-1.c index 2f2d85807ec..3b11e5562d4 100644 --- a/gcc/testsuite/gcc.target/riscv/rvv/base/spill-1.c +++ b/gcc/testsuite/gcc.target/riscv/rvv/base/spill-1.c @@ -1,5 +1,5 @@ /* { dg-do compile } */ -/* { dg-options "-march=rv32gcv -mabi=ilp32 -mpreferred-stack-boundary=3 -O3 -fno-schedule-insns -fno-schedule-insns2" } */ +/* { dg-options "-march=rv32gc_zve64d -mabi=ilp32 -mpreferred-stack-boundary=3 -O3 -fno-schedule-insns -fno-schedule-insns2" } */ /* { dg-final { check-function-bodies "**" "" } } */ #include "riscv_vector.h" diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/spill-11.c b/gcc/testsuite/gcc.target/riscv/rvv/base/spill-11.c index f5223491665..aa2e5e75330 100644 --- a/gcc/testsuite/gcc.target/riscv/rvv/base/spill-11.c +++ b/gcc/testsuite/gcc.target/riscv/rvv/base/spill-11.c @@ -1,5 +1,5 @@ /* { dg-do compile } */ -/* { dg-options "-msave-restore -march=rv32gcv -mabi=ilp32 -msave-restore -fno-schedule-insns -fno-schedule-insns2 -O3" } */ +/* { dg-options "-msave-restore -march=rv32gc_zve64d -mabi=ilp32 -msave-restore -fno-schedule-insns -fno-schedule-insns2 -O3" } */ /* { dg-final { check-function-bodies "**" "" } } */ #include "riscv_vector.h" diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/spill-2.c b/gcc/testsuite/gcc.target/riscv/rvv/base/spill-2.c index 4bcaf4dce79..567aa56d982 100644 --- a/gcc/testsuite/gcc.target/riscv/rvv/base/spill-2.c +++ b/gcc/testsuite/gcc.target/riscv/rvv/base/spill-2.c @@ -1,5 +1,5 @@ /* { dg-do compile } */ -/* { dg-options "-march=rv32gcv -mabi=ilp32 -mpreferred-stack-boundary=3 -O3 -fno-schedule-insns -fno-schedule-insns2" } */ +/* { dg-options "-march=rv32gc_zve64d -mabi=ilp32 -mpreferred-stack-boundary=3 -O3 -fno-schedule-insns -fno-schedule-insns2" } */ /* { dg-final { check-function-bodies "**" "" } } */ #include "riscv_vector.h" diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/spill-3.c b/gcc/testsuite/gcc.target/riscv/rvv/base/spill-3.c index 82d685e029d..2c1213b0f78 100644 --- a/gcc/testsuite/gcc.target/riscv/rvv/base/spill-3.c +++ b/gcc/testsuite/gcc.target/riscv/rvv/base/spill-3.c @@ -1,5 +1,5 @@ /* { dg-do compile } */ -/* { dg-options "-march=rv32gcv -mabi=ilp32 -mpreferred-stack-boundary=3 -O3 -fno-schedule-insns -fno-schedule-insns2" } */ +/* { dg-options "-march=rv32gc_zve64d -mabi=ilp32 -mpreferred-stack-boundary=3 -O3 -fno-schedule-insns -fno-schedule-insns2" } */ /* { dg-final { check-function-bodies "**" "" } } */ #include "riscv_vector.h" diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/spill-5.c b/gcc/testsuite/gcc.target/riscv/rvv/base/spill-5.c index 5b3f75f3552..a6874067e76 100644 --- a/gcc/testsuite/gcc.target/riscv/rvv/base/spill-5.c +++ b/gcc/testsuite/gcc.target/riscv/rvv/base/spill-5.c @@ -1,5 +1,5 @@ /* { dg-do compile } */ -/* { dg-options "-march=rv32gcv -mabi=ilp32 -mpreferred-stack-boundary=3 -O3 -fno-schedule-insns -fno-schedule-insns2" } */ +/* { dg-options "-march=rv32gc_zve64d -mabi=ilp32 -mpreferred-stack-boundary=3 -O3 -fno-schedule-insns -fno-schedule-insns2" } */ /* { dg-final { check-function-bodies "**" "" } } */ #include "riscv_vector.h" diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/spill-9.c b/gcc/testsuite/gcc.target/riscv/rvv/base/spill-9.c index 7111113d393..ec673575b4b 100644 --- a/gcc/testsuite/gcc.target/riscv/rvv/base/spill-9.c +++ b/gcc/testsuite/gcc.target/riscv/rvv/base/spill-9.c @@ -1,5 +1,5 @@ /* { dg-do compile } */ -/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-schedule-insns -fno-schedule-insns2 -O3" } */ +/* { dg-options "-march=rv32gc_zve64d -mabi=ilp32 -fno-schedule-insns -fno-schedule-insns2 -O3" } */ /* { dg-final { check-function-bodies "**" "" } } */ #include "riscv_vector.h" -- 2.36.1