[PATCH v3 02/44] target/arm: Implement widening/narrowing MVE VLDR/VSTR insns

[Peter Maydell <peter.maydell@linaro.org>]

Implement the variants of MVE VLDR (encodings T1, T2) which perform
"widening" loads where bytes or halfwords are loaded from memory and
zero or sign-extended into halfword or word length vector elements,
and the narrowing MVE VSTR (encodings T1, T2) where bytes or
halfwords are stored from halfword or word elements.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
v2->v3 changes: pass MSIZE, so we advance the address by
the right amount in these widening/narrowing versions.
---
 target/arm/helper-mve.h    | 10 ++++++++++
 target/arm/mve.decode      | 25 +++++++++++++++++++++++--
 target/arm/mve_helper.c    | 11 +++++++++++
 target/arm/translate-mve.c | 14 ++++++++++++++
 4 files changed, 58 insertions(+), 2 deletions(-)

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index 9e3b0b09afd..e47d4164ae7 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -22,3 +22,13 @@ DEF_HELPER_FLAGS_3(mve_vldrw, TCG_CALL_NO_WG, void, env, ptr, i32)
 DEF_HELPER_FLAGS_3(mve_vstrb, TCG_CALL_NO_WG, void, env, ptr, i32)
 DEF_HELPER_FLAGS_3(mve_vstrh, TCG_CALL_NO_WG, void, env, ptr, i32)
 DEF_HELPER_FLAGS_3(mve_vstrw, TCG_CALL_NO_WG, void, env, ptr, i32)
+
+DEF_HELPER_FLAGS_3(mve_vldrb_sh, TCG_CALL_NO_WG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vldrb_sw, TCG_CALL_NO_WG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vldrb_uh, TCG_CALL_NO_WG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vldrb_uw, TCG_CALL_NO_WG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vldrh_sw, TCG_CALL_NO_WG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vldrh_uw, TCG_CALL_NO_WG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vstrb_h, TCG_CALL_NO_WG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vstrb_w, TCG_CALL_NO_WG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vstrh_w, TCG_CALL_NO_WG, void, env, ptr, i32)
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index 858a161fd7e..3bc5f034531 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -21,12 +21,33 @@
 
 %qd 22:1 13:3
 
-&vldr_vstr rn qd imm p a w size l
+&vldr_vstr rn qd imm p a w size l u
 
-@vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd
+@vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0
+# Note that both Rn and Qd are 3 bits only (no D bit)
+@vldst_wn ... u:1 ... . . . . l:1 . rn:3 qd:3 . ... .. imm:7 &vldr_vstr
 
 # Vector loads and stores
 
+# Widening loads and narrowing stores:
+# for these P=0 W=0 is 'related encoding'; sz=11 is 'related encoding'
+# This means we need to expand out to multiple patterns for P, W, SZ.
+# For stores the U bit must be 0 but we catch that in the trans_ function.
+# The naming scheme here is "VLDSTB_H == in-memory byte load/store to/from
+# signed halfword element in register", etc.
+VLDSTB_H         111 . 110 0 a:1 0 1   . 0 ... ... 0 111 01 ....... @vldst_wn \
+                 p=0 w=1 size=1
+VLDSTB_H         111 . 110 1 a:1 0 w:1 . 0 ... ... 0 111 01 ....... @vldst_wn \
+                 p=1 size=1
+VLDSTB_W         111 . 110 0 a:1 0 1   . 0 ... ... 0 111 10 ....... @vldst_wn \
+                 p=0 w=1 size=2
+VLDSTB_W         111 . 110 1 a:1 0 w:1 . 0 ... ... 0 111 10 ....... @vldst_wn \
+                 p=1 size=2
+VLDSTH_W         111 . 110 0 a:1 0 1   . 1 ... ... 0 111 10 ....... @vldst_wn \
+                 p=0 w=1 size=2
+VLDSTH_W         111 . 110 1 a:1 0 w:1 . 1 ... ... 0 111 10 ....... @vldst_wn \
+                 p=1 size=2
+
 # Non-widening loads/stores (P=0 W=0 is 'related encoding')
 VLDR_VSTR        1110110 0 a:1 . 1   . .... ... 111100 .......   @vldr_vstr \
                  size=0 p=0 w=1
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index 60c61268c7c..3c2b036c9ca 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -168,5 +168,16 @@ DO_VSTR(vstrb, 1, stb, 1, uint8_t)
 DO_VSTR(vstrh, 2, stw, 2, uint16_t)
 DO_VSTR(vstrw, 4, stl, 4, uint32_t)
 
+DO_VLDR(vldrb_sh, 1, ldsb, 2, int16_t)
+DO_VLDR(vldrb_sw, 1, ldsb, 4, int32_t)
+DO_VLDR(vldrb_uh, 1, ldub, 2, uint16_t)
+DO_VLDR(vldrb_uw, 1, ldub, 4, uint32_t)
+DO_VLDR(vldrh_sw, 2, ldsw, 4, int32_t)
+DO_VLDR(vldrh_uw, 2, lduw, 4, uint32_t)
+
+DO_VSTR(vstrb_h, 1, stb, 2, int16_t)
+DO_VSTR(vstrb_w, 1, stb, 4, int32_t)
+DO_VSTR(vstrh_w, 2, stw, 4, int32_t)
+
 #undef DO_VLDR
 #undef DO_VSTR
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index f98bd6d038d..4cabdf7a69b 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -146,3 +146,17 @@ static bool trans_VLDR_VSTR(DisasContext *s, arg_VLDR_VSTR *a)
     };
     return do_ldst(s, a, ldstfns[a->size][a->l]);
 }
+
+#define DO_VLDST_WIDE_NARROW(OP, SLD, ULD, ST)                  \
+    static bool trans_##OP(DisasContext *s, arg_VLDR_VSTR *a)   \
+    {                                                           \
+        static MVEGenLdStFn * const ldstfns[2][2] = {           \
+            { gen_helper_mve_##ST, gen_helper_mve_##SLD },      \
+            { NULL, gen_helper_mve_##ULD },                     \
+        };                                                      \
+        return do_ldst(s, a, ldstfns[a->u][a->l]);              \
+    }
+
+DO_VLDST_WIDE_NARROW(VLDSTB_H, vldrb_sh, vldrb_uh, vstrb_h)
+DO_VLDST_WIDE_NARROW(VLDSTB_W, vldrb_sw, vldrb_uw, vstrb_w)
+DO_VLDST_WIDE_NARROW(VLDSTH_W, vldrh_sw, vldrh_uw, vstrh_w)
-- 
2.20.1