@@ -1017,6 +1017,24 @@ DEF_HELPER_FLAGS_6(gvec_bfmlal, TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_6(gvec_bfmlal_idx, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sclamp_b, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sclamp_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sclamp_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sclamp_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_uclamp_b, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_uclamp_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_uclamp_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_uclamp_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
#ifdef TARGET_AARCH64
#include "helper-a64.h"
#include "helper-sve.h"
@@ -7438,3 +7438,105 @@ static bool trans_PSEL(DisasContext *s, arg_psel *a)
tcg_temp_free_ptr(ptr);
return true;
}
+
+static void gen_sclamp_i32(TCGv_i32 d, TCGv_i32 n, TCGv_i32 m, TCGv_i32 a)
+{
+ tcg_gen_smax_i32(d, a, n);
+ tcg_gen_smin_i32(d, d, m);
+}
+
+static void gen_sclamp_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 a)
+{
+ tcg_gen_smax_i64(d, a, n);
+ tcg_gen_smin_i64(d, d, m);
+}
+
+static void gen_sclamp_vec(unsigned vece, TCGv_vec d, TCGv_vec n,
+ TCGv_vec m, TCGv_vec a)
+{
+ tcg_gen_smax_vec(vece, d, a, n);
+ tcg_gen_smin_vec(vece, d, d, m);
+}
+
+static void gen_sclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m,
+ uint32_t a, uint32_t oprsz, uint32_t maxsz)
+{
+ static const TCGOpcode vecop[] = {
+ INDEX_op_smin_vec, INDEX_op_smax_vec, 0
+ };
+ static const GVecGen4 ops[4] = {
+ { .fniv = gen_sclamp_vec,
+ .fno = gen_helper_gvec_sclamp_b,
+ .opt_opc = vecop,
+ .vece = MO_8 },
+ { .fniv = gen_sclamp_vec,
+ .fno = gen_helper_gvec_sclamp_h,
+ .opt_opc = vecop,
+ .vece = MO_16 },
+ { .fni4 = gen_sclamp_i32,
+ .fniv = gen_sclamp_vec,
+ .fno = gen_helper_gvec_sclamp_s,
+ .opt_opc = vecop,
+ .vece = MO_32 },
+ { .fni8 = gen_sclamp_i64,
+ .fniv = gen_sclamp_vec,
+ .fno = gen_helper_gvec_sclamp_d,
+ .opt_opc = vecop,
+ .vece = MO_64,
+ .prefer_i64 = TCG_TARGET_REG_BITS == 64 }
+ };
+ tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &ops[vece]);
+}
+
+TRANS_FEAT(SCLAMP, aa64_sme, gen_gvec_fn_arg_zzzz, gen_sclamp, a)
+
+static void gen_uclamp_i32(TCGv_i32 d, TCGv_i32 n, TCGv_i32 m, TCGv_i32 a)
+{
+ tcg_gen_umax_i32(d, a, n);
+ tcg_gen_umin_i32(d, d, m);
+}
+
+static void gen_uclamp_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 a)
+{
+ tcg_gen_umax_i64(d, a, n);
+ tcg_gen_umin_i64(d, d, m);
+}
+
+static void gen_uclamp_vec(unsigned vece, TCGv_vec d, TCGv_vec n,
+ TCGv_vec m, TCGv_vec a)
+{
+ tcg_gen_umax_vec(vece, d, a, n);
+ tcg_gen_umin_vec(vece, d, d, m);
+}
+
+static void gen_uclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m,
+ uint32_t a, uint32_t oprsz, uint32_t maxsz)
+{
+ static const TCGOpcode vecop[] = {
+ INDEX_op_umin_vec, INDEX_op_umax_vec, 0
+ };
+ static const GVecGen4 ops[4] = {
+ { .fniv = gen_uclamp_vec,
+ .fno = gen_helper_gvec_uclamp_b,
+ .opt_opc = vecop,
+ .vece = MO_8 },
+ { .fniv = gen_uclamp_vec,
+ .fno = gen_helper_gvec_uclamp_h,
+ .opt_opc = vecop,
+ .vece = MO_16 },
+ { .fni4 = gen_uclamp_i32,
+ .fniv = gen_uclamp_vec,
+ .fno = gen_helper_gvec_uclamp_s,
+ .opt_opc = vecop,
+ .vece = MO_32 },
+ { .fni8 = gen_uclamp_i64,
+ .fniv = gen_uclamp_vec,
+ .fno = gen_helper_gvec_uclamp_d,
+ .opt_opc = vecop,
+ .vece = MO_64,
+ .prefer_i64 = TCG_TARGET_REG_BITS == 64 }
+ };
+ tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &ops[vece]);
+}
+
+TRANS_FEAT(UCLAMP, aa64_sme, gen_gvec_fn_arg_zzzz, gen_uclamp, a)
@@ -2690,3 +2690,27 @@ void HELPER(gvec_bfmlal_idx)(void *vd, void *vn, void *vm,
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}
+
+#define DO_CLAMP(NAME, TYPE) \
+void HELPER(NAME)(void *d, void *n, void *m, void *a, uint32_t desc) \
+{ \
+ intptr_t i, opr_sz = simd_oprsz(desc); \
+ for (i = 0; i < opr_sz; i += sizeof(TYPE)) { \
+ TYPE aa = *(TYPE *)(a + i); \
+ TYPE nn = *(TYPE *)(n + i); \
+ TYPE mm = *(TYPE *)(m + i); \
+ TYPE dd = MIN(MAX(aa, nn), mm); \
+ *(TYPE *)(d + i) = dd; \
+ } \
+ clear_tail(d, opr_sz, simd_maxsz(desc)); \
+}
+
+DO_CLAMP(gvec_sclamp_b, int8_t)
+DO_CLAMP(gvec_sclamp_h, int16_t)
+DO_CLAMP(gvec_sclamp_s, int32_t)
+DO_CLAMP(gvec_sclamp_d, int64_t)
+
+DO_CLAMP(gvec_uclamp_b, uint8_t)
+DO_CLAMP(gvec_uclamp_h, uint16_t)
+DO_CLAMP(gvec_uclamp_s, uint32_t)
+DO_CLAMP(gvec_uclamp_d, uint64_t)
@@ -1695,3 +1695,8 @@ PSEL 00100101 .. 1 100 .. 01 .... 0 .... 0 .... \
@psel esz=2 imm=%psel_imm_s
PSEL 00100101 .1 1 000 .. 01 .... 0 .... 0 .... \
@psel esz=3 imm=%psel_imm_d
+
+### SVE clamp
+
+SCLAMP 01000100 .. 0 ..... 110000 ..... ..... @rda_rn_rm
+UCLAMP 01000100 .. 0 ..... 110001 ..... ..... @rda_rn_rm
Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper.h | 18 +++++++ target/arm/translate-sve.c | 102 +++++++++++++++++++++++++++++++++++++ target/arm/vec_helper.c | 24 +++++++++ target/arm/sve.decode | 5 ++ 4 files changed, 149 insertions(+)