diff mbox series

[17/31] target/arm: Implement SVE2 bitwise shift left long

Message ID 20200326230838.31112-18-richard.henderson@linaro.org
State New
Headers show
Series target/arm: SVE2, part 1 | expand

Commit Message

Richard Henderson March 26, 2020, 11:08 p.m. UTC
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

---
 target/arm/helper-sve.h    |  8 +++++++
 target/arm/sve.decode      |  8 +++++++
 target/arm/sve_helper.c    | 34 ++++++++++++++++++++++++++
 target/arm/translate-sve.c | 49 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 99 insertions(+)

-- 
2.20.1
diff mbox series

Patch

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 943839e2dc..9c0c41ba80 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2372,3 +2372,11 @@  DEF_HELPER_FLAGS_4(sve2_umull_zzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_4(sve2_pmull_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve2_pmull_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sve2_sshll_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_sshll_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_sshll_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sve2_ushll_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_ushll_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_ushll_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 440cff4597..36ef9de563 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1207,3 +1207,11 @@  SMULLB_zzz      01000101 .. 0 ..... 011 100 ..... .....  @rd_rn_rm
 SMULLT_zzz      01000101 .. 0 ..... 011 101 ..... .....  @rd_rn_rm
 UMULLB_zzz      01000101 .. 0 ..... 011 110 ..... .....  @rd_rn_rm
 UMULLT_zzz      01000101 .. 0 ..... 011 111 ..... .....  @rd_rn_rm
+
+## SVE2 bitwise shift left long
+
+# Note bit23 == 0 is handled by esz > 0 in do_sve2_shll_tb.
+SSHLLB          01000101 .. 0 ..... 1010 00 ..... .....  @rd_rn_tszimm_shl
+SSHLLT          01000101 .. 0 ..... 1010 01 ..... .....  @rd_rn_tszimm_shl
+USHLLB          01000101 .. 0 ..... 1010 10 ..... .....  @rd_rn_tszimm_shl
+USHLLT          01000101 .. 0 ..... 1010 11 ..... .....  @rd_rn_tszimm_shl
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 130697f3d9..e0a701c446 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -625,6 +625,8 @@  DO_ZPZZ(sve2_sqrshl_zpzz_h, int16_t, H1_2, do_sqrshl_h)
 DO_ZPZZ(sve2_sqrshl_zpzz_s, int32_t, H1_4, do_sqrshl_s)
 DO_ZPZZ_D(sve2_sqrshl_zpzz_d, int64_t, do_sqrshl_d)
 
+#undef do_sqrshl_d
+
 #define do_uqrshl_b(n, m) \
    ({ uint32_t discard; do_uqrshl_bhs(n, m, 8, true, &discard); })
 #define do_uqrshl_h(n, m) \
@@ -639,6 +641,8 @@  DO_ZPZZ(sve2_uqrshl_zpzz_h, uint16_t, H1_2, do_uqrshl_h)
 DO_ZPZZ(sve2_uqrshl_zpzz_s, uint32_t, H1_4, do_uqrshl_s)
 DO_ZPZZ_D(sve2_uqrshl_zpzz_d, uint64_t, do_uqrshl_d)
 
+#undef do_uqrshl_d
+
 #define DO_HADD_BHS(n, m)  (((int64_t)n + m) >> 1)
 #define DO_HADD_D(n, m)    ((n >> 1) + (m >> 1) + (n & m & 1))
 
@@ -1192,6 +1196,36 @@  DO_ZZZ_WTB(sve2_usubw_d, uint64_t, uint32_t, DO_SUB)
 
 #undef DO_ZZZ_WTB
 
+#define DO_ZZI_SHLL(NAME, TYPE, TYPEN, OP) \
+void HELPER(NAME)(void *vd, void *vn, uint32_t desc)           \
+{                                                              \
+    intptr_t i, opr_sz = simd_oprsz(desc);                     \
+    int sel = (simd_data(desc) & 1) * sizeof(TYPE);            \
+    int shift = simd_data(desc) >> 1;                          \
+    for (i = 0; i < opr_sz; i += sizeof(TYPE)) {               \
+        TYPE nn = (TYPEN)(*(TYPE *)(vn + i) >> sel);           \
+        *(TYPE *)(vd + i) = OP(nn, shift);                     \
+    }                                                          \
+}
+
+#define DO_SSHLL_H(val, sh)  do_sqrshl_bhs(val, sh, 16, false, NULL)
+#define DO_SSHLL_S(val, sh)  do_sqrshl_bhs(val, sh, 32, false, NULL)
+#define DO_SSHLL_D(val, sh)  do_sqrshl_d(val, sh, false, NULL)
+
+DO_ZZI_SHLL(sve2_sshll_h, int16_t, int8_t, DO_SSHLL_H)
+DO_ZZI_SHLL(sve2_sshll_s, int32_t, int16_t, DO_SSHLL_S)
+DO_ZZI_SHLL(sve2_sshll_d, int64_t, int32_t, DO_SSHLL_D)
+
+#define DO_USHLL_H(val, sh)  do_uqrshl_bhs(val, sh, 16, false, NULL)
+#define DO_USHLL_S(val, sh)  do_uqrshl_bhs(val, sh, 32, false, NULL)
+#define DO_USHLL_D(val, sh)  do_uqrshl_d(val, sh, false, NULL)
+
+DO_ZZI_SHLL(sve2_ushll_h, uint16_t, uint8_t, DO_USHLL_H)
+DO_ZZI_SHLL(sve2_ushll_s, uint32_t, uint16_t, DO_USHLL_S)
+DO_ZZI_SHLL(sve2_ushll_d, uint64_t, uint32_t, DO_USHLL_D)
+
+#undef DO_ZZI_SHLL
+
 /* Two-operand reduction expander, controlled by a predicate.
  * The difference between TYPERED and TYPERET has to do with
  * sign-extension.  E.g. for SMAX, TYPERED must be signed,
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 67416a25ce..9873b83feb 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -6105,3 +6105,52 @@  DO_SVE2_ZZZ_WTB(UADDWB, uaddw, false)
 DO_SVE2_ZZZ_WTB(UADDWT, uaddw, true)
 DO_SVE2_ZZZ_WTB(USUBWB, usubw, false)
 DO_SVE2_ZZZ_WTB(USUBWT, usubw, true)
+
+static bool do_sve2_shll_tb(DisasContext *s, arg_rri_esz *a,
+                            bool sel, bool uns)
+{
+    static gen_helper_gvec_2 * const fns[2][3] = {
+        { gen_helper_sve2_sshll_h,
+          gen_helper_sve2_sshll_s,
+          gen_helper_sve2_sshll_d },
+        { gen_helper_sve2_ushll_h,
+          gen_helper_sve2_ushll_s,
+          gen_helper_sve2_ushll_d },
+    };
+
+    if (a->esz <= 0 || !dc_isar_feature(aa64_sve2, s)) {
+        /*
+         * For < 0, invalid tsz encoding -- see tszimm_esz.
+         * For = 0, not a widening operation; note this implies bit23 = 0.
+         */
+        return false;
+    }
+    if (sve_access_check(s)) {
+        unsigned vsz = vec_full_reg_size(s);
+        tcg_gen_gvec_2_ool(vec_full_reg_offset(s, a->rd),
+                           vec_full_reg_offset(s, a->rn),
+                           vsz, vsz, (a->imm << 1) | sel,
+                           fns[uns][a->esz - 1]);
+    }
+    return true;
+}
+
+static bool trans_SSHLLB(DisasContext *s, arg_rri_esz *a)
+{
+    return do_sve2_shll_tb(s, a, false, false);
+}
+
+static bool trans_SSHLLT(DisasContext *s, arg_rri_esz *a)
+{
+    return do_sve2_shll_tb(s, a, true, false);
+}
+
+static bool trans_USHLLB(DisasContext *s, arg_rri_esz *a)
+{
+    return do_sve2_shll_tb(s, a, false, true);
+}
+
+static bool trans_USHLLT(DisasContext *s, arg_rri_esz *a)
+{
+    return do_sve2_shll_tb(s, a, true, true);
+}