tcg: Implement gvec support for rotate by scalar

No host backend support yet, but the interfaces for rotls
are in place.  Only implement left-rotate for now, as the
only known use of vector rotate by scalar is s390x, so any
right-rotate would be unused and untestable.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

10 files changed, 37 insertions, 0 deletions

diff --git a/include/tcg/tcg-op-gvec.h b/include/tcg/tcg-op-gvec.h
index 2d768f1..c69a7de 100644
--- a/include/tcg/tcg-op-gvec.h
+++ b/include/tcg/tcg-op-gvec.h
@@ -345,6 +345,8 @@ void tcg_gen_gvec_shrs(unsigned vece, uint32_t dofs, uint32_t aofs,
                        TCGv_i32 shift, uint32_t oprsz, uint32_t maxsz);
 void tcg_gen_gvec_sars(unsigned vece, uint32_t dofs, uint32_t aofs,
                        TCGv_i32 shift, uint32_t oprsz, uint32_t maxsz);
+void tcg_gen_gvec_rotls(unsigned vece, uint32_t dofs, uint32_t aofs,
+                        TCGv_i32 shift, uint32_t oprsz, uint32_t maxsz);
 
 /*
  * Perform vector shift by vector element, modulo the element size.
diff --git a/include/tcg/tcg-op.h b/include/tcg/tcg-op.h
index 5523ee7..5abf17f 100644
--- a/include/tcg/tcg-op.h
+++ b/include/tcg/tcg-op.h
@@ -1005,6 +1005,7 @@ void tcg_gen_rotri_vec(unsigned vece, TCGv_vec r, TCGv_vec a, int64_t i);
 void tcg_gen_shls_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_i32 s);
 void tcg_gen_shrs_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_i32 s);
 void tcg_gen_sars_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_i32 s);
+void tcg_gen_rotls_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_i32 s);
 
 void tcg_gen_shlv_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec s);
 void tcg_gen_shrv_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec s);
diff --git a/include/tcg/tcg-opc.h b/include/tcg/tcg-opc.h
index 69f98d6..e3929b8 100644
--- a/include/tcg/tcg-opc.h
+++ b/include/tcg/tcg-opc.h
@@ -253,6 +253,7 @@ DEF(rotli_vec, 1, 1, 1, IMPLVEC | IMPL(TCG_TARGET_HAS_roti_vec))
 DEF(shls_vec, 1, 2, 0, IMPLVEC | IMPL(TCG_TARGET_HAS_shs_vec))
 DEF(shrs_vec, 1, 2, 0, IMPLVEC | IMPL(TCG_TARGET_HAS_shs_vec))
 DEF(sars_vec, 1, 2, 0, IMPLVEC | IMPL(TCG_TARGET_HAS_shs_vec))
+DEF(rotls_vec, 1, 2, 0, IMPLVEC | IMPL(TCG_TARGET_HAS_rots_vec))
 
 DEF(shlv_vec, 1, 2, 0, IMPLVEC | IMPL(TCG_TARGET_HAS_shv_vec))
 DEF(shrv_vec, 1, 2, 0, IMPLVEC | IMPL(TCG_TARGET_HAS_shv_vec))
diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h
index b2cb303..380014e 100644
--- a/include/tcg/tcg.h
+++ b/include/tcg/tcg.h
@@ -183,6 +183,7 @@ typedef uint64_t TCGRegSet;
 #define TCG_TARGET_HAS_andc_vec         0
 #define TCG_TARGET_HAS_orc_vec          0
 #define TCG_TARGET_HAS_roti_vec         0
+#define TCG_TARGET_HAS_rots_vec         0
 #define TCG_TARGET_HAS_rotv_vec         0
 #define TCG_TARGET_HAS_shi_vec          0
 #define TCG_TARGET_HAS_shs_vec          0
diff --git a/tcg/aarch64/tcg-target.h b/tcg/aarch64/tcg-target.h
index a5477bb..9bc2a5e 100644
--- a/tcg/aarch64/tcg-target.h
+++ b/tcg/aarch64/tcg-target.h
@@ -134,6 +134,7 @@ typedef enum {
 #define TCG_TARGET_HAS_neg_vec          1
 #define TCG_TARGET_HAS_abs_vec          1
 #define TCG_TARGET_HAS_roti_vec         0
+#define TCG_TARGET_HAS_rots_vec         0
 #define TCG_TARGET_HAS_rotv_vec         0
 #define TCG_TARGET_HAS_shi_vec          1
 #define TCG_TARGET_HAS_shs_vec          0
diff --git a/tcg/i386/tcg-target.h b/tcg/i386/tcg-target.h
index 4c806c9..99ac1e3 100644
--- a/tcg/i386/tcg-target.h
+++ b/tcg/i386/tcg-target.h
@@ -184,6 +184,7 @@ extern bool have_avx2;
 #define TCG_TARGET_HAS_neg_vec          0
 #define TCG_TARGET_HAS_abs_vec          1
 #define TCG_TARGET_HAS_roti_vec         0
+#define TCG_TARGET_HAS_rots_vec         0
 #define TCG_TARGET_HAS_rotv_vec         0
 #define TCG_TARGET_HAS_shi_vec          1
 #define TCG_TARGET_HAS_shs_vec          1
diff --git a/tcg/ppc/tcg-target.h b/tcg/ppc/tcg-target.h
index 7993422..4a17aeb 100644
--- a/tcg/ppc/tcg-target.h
+++ b/tcg/ppc/tcg-target.h
@@ -162,6 +162,7 @@ extern bool have_vsx;
 #define TCG_TARGET_HAS_neg_vec          have_isa_3_00
 #define TCG_TARGET_HAS_abs_vec          0
 #define TCG_TARGET_HAS_roti_vec         0
+#define TCG_TARGET_HAS_rots_vec         0
 #define TCG_TARGET_HAS_rotv_vec         0
 #define TCG_TARGET_HAS_shi_vec          0
 #define TCG_TARGET_HAS_shs_vec          0
diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c
index 2b71725..3707c0e 100644
--- a/tcg/tcg-op-gvec.c
+++ b/tcg/tcg-op-gvec.c
@@ -2976,6 +2976,28 @@ void tcg_gen_gvec_sars(unsigned vece, uint32_t dofs, uint32_t aofs,
     do_gvec_shifts(vece, dofs, aofs, shift, oprsz, maxsz, &g);
 }
 
+void tcg_gen_gvec_rotls(unsigned vece, uint32_t dofs, uint32_t aofs,
+                        TCGv_i32 shift, uint32_t oprsz, uint32_t maxsz)
+{
+    static const GVecGen2sh g = {
+        .fni4 = tcg_gen_rotl_i32,
+        .fni8 = tcg_gen_rotl_i64,
+        .fniv_s = tcg_gen_rotls_vec,
+        .fniv_v = tcg_gen_rotlv_vec,
+        .fno = {
+            gen_helper_gvec_rotl8i,
+            gen_helper_gvec_rotl16i,
+            gen_helper_gvec_rotl32i,
+            gen_helper_gvec_rotl64i,
+        },
+        .s_list = { INDEX_op_rotls_vec, 0 },
+        .v_list = { INDEX_op_rotlv_vec, 0 },
+    };
+
+    tcg_debug_assert(vece <= MO_64);
+    do_gvec_shifts(vece, dofs, aofs, shift, oprsz, maxsz, &g);
+}
+
 /*
  * Expand D = A << (B % element bits)
  *
diff --git a/tcg/tcg-op-vec.c b/tcg/tcg-op-vec.c
index fb1250f..f784517 100644
--- a/tcg/tcg-op-vec.c
+++ b/tcg/tcg-op-vec.c
@@ -747,6 +747,11 @@ void tcg_gen_sars_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_i32 b)
     do_shifts(vece, r, a, b, INDEX_op_sars_vec);
 }
 
+void tcg_gen_rotls_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_i32 s)
+{
+    do_shifts(vece, r, a, s, INDEX_op_rotls_vec);
+}
+
 void tcg_gen_bitsel_vec(unsigned vece, TCGv_vec r, TCGv_vec a,
                         TCGv_vec b, TCGv_vec c)
 {
diff --git a/tcg/tcg.c b/tcg/tcg.c
index bd6ffab..97558ec 100644
--- a/tcg/tcg.c
+++ b/tcg/tcg.c
@@ -1663,6 +1663,8 @@ bool tcg_op_supported(TCGOpcode op)
         return have_vec && TCG_TARGET_HAS_shv_vec;
     case INDEX_op_rotli_vec:
         return have_vec && TCG_TARGET_HAS_roti_vec;
+    case INDEX_op_rotls_vec:
+        return have_vec && TCG_TARGET_HAS_rots_vec;
     case INDEX_op_rotlv_vec:
     case INDEX_op_rotrv_vec:
         return have_vec && TCG_TARGET_HAS_rotv_vec;