@@ -458,3 +458,6 @@ DEF_HELPER_FLAGS_3(mve_sqrshrl, TCG_CALL_NO_RWG, i64, env, i64, i32)
DEF_HELPER_FLAGS_3(mve_uqrshll, TCG_CALL_NO_RWG, i64, env, i64, i32)
DEF_HELPER_FLAGS_3(mve_sqrshrl48, TCG_CALL_NO_RWG, i64, env, i64, i32)
DEF_HELPER_FLAGS_3(mve_uqrshll48, TCG_CALL_NO_RWG, i64, env, i64, i32)
+
+DEF_HELPER_FLAGS_3(mve_uqshl, TCG_CALL_NO_RWG, i32, env, i32, i32)
+DEF_HELPER_FLAGS_3(mve_sqshl, TCG_CALL_NO_RWG, i32, env, i32, i32)
@@ -466,6 +466,7 @@ typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr);
typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp);
typedef void WideShiftImmFn(TCGv_i64, TCGv_i64, int64_t shift);
typedef void WideShiftFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i32);
+typedef void ShiftImmFn(TCGv_i32, TCGv_i32, int32_t shift);
/**
* arm_tbflags_from_tb:
@@ -50,6 +50,7 @@
&mve_shl_ri rdalo rdahi shim
&mve_shl_rr rdalo rdahi rm
+&mve_sh_ri rda shim
# rdahi: bits [3:1] from insn, bit 0 is 1
# rdalo: bits [3:1] from insn, bit 0 is 0
@@ -71,6 +72,8 @@
&mve_shl_ri shim=%imm5_12_6 rdalo=%rdalo_17 rdahi=%rdahi_9
@mve_shl_rr ....... .... . ... . rm:4 ... . .. .. .... \
&mve_shl_rr rdalo=%rdalo_17 rdahi=%rdahi_9
+@mve_sh_ri ....... .... . rda:4 . ... ... . .. .. .... \
+ &mve_sh_ri shim=%imm5_12_6
{
TST_xrri 1110101 0000 1 .... 0 ... 1111 .... .... @S_xrr_shi
@@ -101,6 +104,11 @@ BIC_rrri 1110101 0001 . .... 0 ... .... .... .... @s_rrr_shi
UQRSHLL48_rr 1110101 0010 1 ... 1 .... ... 1 1000 1101 @mve_shl_rr
SQRSHRL48_rr 1110101 0010 1 ... 1 .... ... 1 1010 1101 @mve_shl_rr
+ UQSHL_ri 1110101 0010 1 .... 0 ... 1111 .. 00 1111 @mve_sh_ri
+ URSHR_ri 1110101 0010 1 .... 0 ... 1111 .. 01 1111 @mve_sh_ri
+ SRSHR_ri 1110101 0010 1 .... 0 ... 1111 .. 10 1111 @mve_sh_ri
+ SQSHL_ri 1110101 0010 1 .... 0 ... 1111 .. 11 1111 @mve_sh_ri
+
MOV_rxri 1110101 0010 . 1111 0 ... .... .... .... @s_rxr_shi
ORR_rrri 1110101 0010 . .... 0 ... .... .... .... @s_rrr_shi
@@ -1628,3 +1628,13 @@ uint64_t HELPER(mve_uqrshll48)(CPUARMState *env, uint64_t n, uint32_t shift)
{
return do_uqrshl48_d(n, (int8_t)shift, true, &env->QF);
}
+
+uint32_t HELPER(mve_uqshl)(CPUARMState *env, uint32_t n, uint32_t shift)
+{
+ return do_uqrshl_bhs(n, (int8_t)shift, 32, false, &env->QF);
+}
+
+uint32_t HELPER(mve_sqshl)(CPUARMState *env, uint32_t n, uint32_t shift)
+{
+ return do_sqrshl_bhs(n, (int8_t)shift, 32, false, &env->QF);
+}
@@ -3220,8 +3220,14 @@ static void gen_srshr16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
static void gen_srshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh)
{
- TCGv_i32 t = tcg_temp_new_i32();
+ TCGv_i32 t;
+ /* Handle shift by the input size for the benefit of trans_SRSHR_ri */
+ if (sh == 32) {
+ tcg_gen_movi_i32(d, 0);
+ return;
+ }
+ t = tcg_temp_new_i32();
tcg_gen_extract_i32(t, a, sh - 1, 1);
tcg_gen_sari_i32(d, a, sh);
tcg_gen_add_i32(d, d, t);
@@ -3421,8 +3427,14 @@ static void gen_urshr16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
static void gen_urshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh)
{
- TCGv_i32 t = tcg_temp_new_i32();
+ TCGv_i32 t;
+ /* Handle shift by the input size for the benefit of trans_URSHR_ri */
+ if (sh == 32) {
+ tcg_gen_extract_i32(d, a, sh - 1, 1);
+ return;
+ }
+ t = tcg_temp_new_i32();
tcg_gen_extract_i32(t, a, sh - 1, 1);
tcg_gen_shri_i32(d, a, sh);
tcg_gen_add_i32(d, d, t);
@@ -5863,6 +5875,58 @@ static bool trans_SQRSHRL48_rr(DisasContext *s, arg_mve_shl_rr *a)
return do_mve_shl_rr(s, a, gen_helper_mve_sqrshrl48);
}
+static bool do_mve_sh_ri(DisasContext *s, arg_mve_sh_ri *a, ShiftImmFn *fn)
+{
+ if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) {
+ /* Decode falls through to ORR/MOV UNPREDICTABLE handling */
+ return false;
+ }
+ if (!dc_isar_feature(aa32_mve, s) ||
+ !arm_dc_feature(s, ARM_FEATURE_M_MAIN) ||
+ a->rda == 13 || a->rda == 15) {
+ /* These rda cases are UNPREDICTABLE; we choose to UNDEF */
+ unallocated_encoding(s);
+ return true;
+ }
+
+ if (a->shim == 0) {
+ a->shim = 32;
+ }
+ fn(cpu_R[a->rda], cpu_R[a->rda], a->shim);
+
+ return true;
+}
+
+static bool trans_URSHR_ri(DisasContext *s, arg_mve_sh_ri *a)
+{
+ return do_mve_sh_ri(s, a, gen_urshr32_i32);
+}
+
+static bool trans_SRSHR_ri(DisasContext *s, arg_mve_sh_ri *a)
+{
+ return do_mve_sh_ri(s, a, gen_srshr32_i32);
+}
+
+static void gen_mve_sqshl(TCGv_i32 r, TCGv_i32 n, int32_t shift)
+{
+ gen_helper_mve_sqshl(r, cpu_env, n, tcg_constant_i32(shift));
+}
+
+static bool trans_SQSHL_ri(DisasContext *s, arg_mve_sh_ri *a)
+{
+ return do_mve_sh_ri(s, a, gen_mve_sqshl);
+}
+
+static void gen_mve_uqshl(TCGv_i32 r, TCGv_i32 n, int32_t shift)
+{
+ gen_helper_mve_uqshl(r, cpu_env, n, tcg_constant_i32(shift));
+}
+
+static bool trans_UQSHL_ri(DisasContext *s, arg_mve_sh_ri *a)
+{
+ return do_mve_sh_ri(s, a, gen_mve_uqshl);
+}
+
/*
* Multiply and multiply accumulate
*/
Implement the MVE shifts by immediate, which perform shifts on a single general-purpose register. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-mve.h | 3 ++ target/arm/translate.h | 1 + target/arm/t32.decode | 8 +++++ target/arm/mve_helper.c | 10 ++++++ target/arm/translate.c | 68 +++++++++++++++++++++++++++++++++++++++-- 5 files changed, 88 insertions(+), 2 deletions(-)