diff mbox series

[v3,10/33] target/arm: Convert SRSHL and URSHL (register) to gvec

Message ID 20240528203044.612851-11-richard.henderson@linaro.org
State New
Headers show
Series target/arm: Convert a64 advsimd to decodetree (part 1b) | expand

Commit Message

Richard Henderson May 28, 2024, 8:30 p.m. UTC
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(-)

Comments

Peter Maydell May 30, 2024, 2:12 p.m. UTC | #1
On Tue, 28 May 2024 at 21:33, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>

thanks
-- PMM
diff mbox series

Patch

diff --git a/target/arm/helper.h b/target/arm/helper.h
index a14c040451..25eb7bf5df 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -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)
diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h
index 87439dcc61..ea63ffc47b 100644
--- a/target/arm/tcg/translate.h
+++ b/target/arm/tcg/translate.h
@@ -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);
diff --git a/target/arm/tcg/neon-dp.decode b/target/arm/tcg/neon-dp.decode
index fd3a01bfa0..8525c65c0d 100644
--- a/target/arm/tcg/neon-dp.decode
+++ b/target/arm/tcg/neon-dp.decode
@@ -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
diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c
index 740f3f864e..216a9f81e3 100644
--- a/target/arm/tcg/gengvec.c
+++ b/target/arm/tcg/gengvec.c
@@ -1218,6 +1218,28 @@  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);
diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c
index 0af15e9f6e..516ecc1dcb 100644
--- a/target/arm/tcg/neon_helper.c
+++ b/target/arm/tcg/neon_helper.c
@@ -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)
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 7c7a22985b..7e981f8d01 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -10938,6 +10938,13 @@  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);
@@ -11083,16 +11090,6 @@  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] = {
diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c
index 18b048611b..337488bbf1 100644
--- a/target/arm/tcg/translate-neon.c
+++ b/target/arm/tcg/translate-neon.c
@@ -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)