@@ -327,6 +327,16 @@ DEF_HELPER_3(neon_qrshl_s32, i32, env, i32, i32)
DEF_HELPER_3(neon_qrshl_u64, i64, env, i64, i64)
DEF_HELPER_3(neon_qrshl_s64, i64, env, i64, i64)
+DEF_HELPER_FLAGS_4(gvec_srshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_srshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_srshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_srshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_urshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_urshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_urshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_urshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
DEF_HELPER_2(neon_add_u8, i32, i32, i32)
DEF_HELPER_2(neon_add_u16, i32, i32, i32)
DEF_HELPER_2(neon_sub_u8, i32, i32, i32)
@@ -459,6 +459,10 @@ void gen_gvec_sshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz);
void gen_gvec_ushl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz);
+void gen_gvec_srshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz);
+void gen_gvec_urshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz);
void gen_cmtst_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b);
void gen_ushl_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b);
@@ -117,14 +117,8 @@ VSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 0 .... @3same_rev
VQSHL_U64_3s 1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev
VQSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_rev
}
-{
- VRSHL_S64_3s 1111 001 0 0 . .. .... .... 0101 . . . 0 .... @3same_64_rev
- VRSHL_S_3s 1111 001 0 0 . .. .... .... 0101 . . . 0 .... @3same_rev
-}
-{
- VRSHL_U64_3s 1111 001 1 0 . .. .... .... 0101 . . . 0 .... @3same_64_rev
- VRSHL_U_3s 1111 001 1 0 . .. .... .... 0101 . . . 0 .... @3same_rev
-}
+VRSHL_S_3s 1111 001 0 0 . .. .... .... 0101 . . . 0 .... @3same_rev
+VRSHL_U_3s 1111 001 1 0 . .. .... .... 0101 . . . 0 .... @3same_rev
{
VQRSHL_S64_3s 1111 001 0 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev
VQRSHL_S_3s 1111 001 0 0 . .. .... .... 0101 . . . 1 .... @3same_rev
@@ -1217,6 +1217,28 @@ void gen_gvec_sshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
}
+void gen_gvec_srshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+ static gen_helper_gvec_3 * const fns[] = {
+ gen_helper_gvec_srshl_b, gen_helper_gvec_srshl_h,
+ gen_helper_gvec_srshl_s, gen_helper_gvec_srshl_d,
+ };
+ tcg_debug_assert(vece <= MO_64);
+ tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, 0, fns[vece]);
+}
+
+void gen_gvec_urshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+ static gen_helper_gvec_3 * const fns[] = {
+ gen_helper_gvec_urshl_b, gen_helper_gvec_urshl_h,
+ gen_helper_gvec_urshl_s, gen_helper_gvec_urshl_d,
+ };
+ tcg_debug_assert(vece <= MO_64);
+ tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, 0, fns[vece]);
+}
+
void gen_uqadd_bhs(TCGv_i64 res, TCGv_i64 qc, TCGv_i64 a, TCGv_i64 b, MemOp esz)
{
uint64_t max = MAKE_64BIT_MASK(0, 8 << esz);
@@ -6,10 +6,11 @@
*
* This code is licensed under the GNU GPL v2.
*/
-#include "qemu/osdep.h"
+#include "qemu/osdep.h"
#include "cpu.h"
#include "exec/helper-proto.h"
+#include "tcg/tcg-gvec-desc.h"
#include "fpu/softfloat.h"
#include "vec_internal.h"
@@ -117,6 +118,17 @@ NEON_VOP_BODY(vtype, n)
uint32_t HELPER(glue(neon_,name))(CPUARMState *env, uint32_t arg1, uint32_t arg2) \
NEON_VOP_BODY(vtype, n)
+#define NEON_GVEC_VOP2(name, vtype) \
+void HELPER(name)(void *vd, void *vn, void *vm, uint32_t desc) \
+{ \
+ intptr_t i, opr_sz = simd_oprsz(desc); \
+ vtype *d = vd, *n = vn, *m = vm; \
+ for (i = 0; i < opr_sz / sizeof(vtype); i++) { \
+ NEON_FN(d[i], n[i], m[i]); \
+ } \
+ clear_tail(d, opr_sz, simd_maxsz(desc)); \
+}
+
/* Pairwise operations. */
/* For 32-bit elements each segment only contains a single element, so
the elementwise and pairwise operations are the same. */
@@ -263,11 +275,23 @@ NEON_VOP(shl_s16, neon_s16, 2)
#define NEON_FN(dest, src1, src2) \
(dest = do_sqrshl_bhs(src1, (int8_t)src2, 8, true, NULL))
NEON_VOP(rshl_s8, neon_s8, 4)
+NEON_GVEC_VOP2(gvec_srshl_b, int8_t)
#undef NEON_FN
#define NEON_FN(dest, src1, src2) \
(dest = do_sqrshl_bhs(src1, (int8_t)src2, 16, true, NULL))
NEON_VOP(rshl_s16, neon_s16, 2)
+NEON_GVEC_VOP2(gvec_srshl_h, int16_t)
+#undef NEON_FN
+
+#define NEON_FN(dest, src1, src2) \
+ (dest = do_sqrshl_bhs(src1, (int8_t)src2, 32, true, NULL))
+NEON_GVEC_VOP2(gvec_srshl_s, int32_t)
+#undef NEON_FN
+
+#define NEON_FN(dest, src1, src2) \
+ (dest = do_sqrshl_d(src1, (int8_t)src2, true, NULL))
+NEON_GVEC_VOP2(gvec_srshl_d, int64_t)
#undef NEON_FN
uint32_t HELPER(neon_rshl_s32)(uint32_t val, uint32_t shift)
@@ -283,11 +307,23 @@ uint64_t HELPER(neon_rshl_s64)(uint64_t val, uint64_t shift)
#define NEON_FN(dest, src1, src2) \
(dest = do_uqrshl_bhs(src1, (int8_t)src2, 8, true, NULL))
NEON_VOP(rshl_u8, neon_u8, 4)
+NEON_GVEC_VOP2(gvec_urshl_b, uint8_t)
#undef NEON_FN
#define NEON_FN(dest, src1, src2) \
(dest = do_uqrshl_bhs(src1, (int8_t)src2, 16, true, NULL))
NEON_VOP(rshl_u16, neon_u16, 2)
+NEON_GVEC_VOP2(gvec_urshl_h, uint16_t)
+#undef NEON_FN
+
+#define NEON_FN(dest, src1, src2) \
+ (dest = do_uqrshl_bhs(src1, (int8_t)src2, 32, true, NULL))
+NEON_GVEC_VOP2(gvec_urshl_s, int32_t)
+#undef NEON_FN
+
+#define NEON_FN(dest, src1, src2) \
+ (dest = do_uqrshl_d(src1, (int8_t)src2, true, NULL))
+NEON_GVEC_VOP2(gvec_urshl_d, int64_t)
#undef NEON_FN
uint32_t HELPER(neon_rshl_u32)(uint32_t val, uint32_t shift)
@@ -10931,6 +10931,13 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
}
switch (opcode) {
+ case 0x0a: /* SRSHL, URSHL */
+ if (u) {
+ gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_urshl, size);
+ } else {
+ gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_srshl, size);
+ }
+ return;
case 0x0c: /* SMAX, UMAX */
if (u) {
gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umax, size);
@@ -11081,16 +11088,6 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
genenvfn = fns[size][u];
break;
}
- case 0xa: /* SRSHL, URSHL */
- {
- static NeonGenTwoOpFn * const fns[3][2] = {
- { gen_helper_neon_rshl_s8, gen_helper_neon_rshl_u8 },
- { gen_helper_neon_rshl_s16, gen_helper_neon_rshl_u16 },
- { gen_helper_neon_rshl_s32, gen_helper_neon_rshl_u32 },
- };
- genfn = fns[size][u];
- break;
- }
case 0xb: /* SQRSHL, UQRSHL */
{
static NeonGenTwoOpEnvFn * const fns[3][2] = {
@@ -794,6 +794,8 @@ DO_3SAME(VQADD_S, gen_gvec_sqadd_qc)
DO_3SAME(VQADD_U, gen_gvec_uqadd_qc)
DO_3SAME(VQSUB_S, gen_gvec_sqsub_qc)
DO_3SAME(VQSUB_U, gen_gvec_uqsub_qc)
+DO_3SAME(VRSHL_S, gen_gvec_srshl)
+DO_3SAME(VRSHL_U, gen_gvec_urshl)
/* These insns are all gvec_bitsel but with the inputs in various orders. */
#define DO_3SAME_BITSEL(INSN, O1, O2, O3) \
@@ -929,8 +931,6 @@ DO_SHA2(SHA256SU1, gen_helper_crypto_sha256su1)
} \
DO_3SAME_64(INSN, gen_##INSN##_elt)
-DO_3SAME_64(VRSHL_S64, gen_helper_neon_rshl_s64)
-DO_3SAME_64(VRSHL_U64, gen_helper_neon_rshl_u64)
DO_3SAME_64_ENV(VQSHL_S64, gen_helper_neon_qshl_s64)
DO_3SAME_64_ENV(VQSHL_U64, gen_helper_neon_qshl_u64)
DO_3SAME_64_ENV(VQRSHL_S64, gen_helper_neon_qrshl_s64)
@@ -999,8 +999,6 @@ DO_3SAME_32(VHSUB_S, hsub_s)
DO_3SAME_32(VHSUB_U, hsub_u)
DO_3SAME_32(VRHADD_S, rhadd_s)
DO_3SAME_32(VRHADD_U, rhadd_u)
-DO_3SAME_32(VRSHL_S, rshl_s)
-DO_3SAME_32(VRSHL_U, rshl_u)
DO_3SAME_32_ENV(VQSHL_S, qshl_s)
DO_3SAME_32_ENV(VQSHL_U, qshl_u)
Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper.h | 10 +++++++++ target/arm/tcg/translate.h | 4 ++++ target/arm/tcg/neon-dp.decode | 10 ++------- target/arm/tcg/gengvec.c | 22 +++++++++++++++++++ target/arm/tcg/neon_helper.c | 38 ++++++++++++++++++++++++++++++++- target/arm/tcg/translate-a64.c | 17 ++++++--------- target/arm/tcg/translate-neon.c | 6 ++---- 7 files changed, 84 insertions(+), 23 deletions(-)