diff --git a/qemu/tcg/aarch64/tcg-target-opc.h b/qemu/tcg/aarch64/tcg-target-opc.h index 4816a6c3..59e1d3f7 100644 --- a/qemu/tcg/aarch64/tcg-target-opc.h +++ b/qemu/tcg/aarch64/tcg-target-opc.h @@ -1,3 +1,5 @@ /* Target-specific opcodes for host vector expansion. These will be emitted by tcg_expand_vec_op. For those familiar with GCC internals, consider these to be UNSPEC with names. */ + +DEF(aa64_sshl_vec, 1, 2, 0, IMPLVEC) diff --git a/qemu/tcg/aarch64/tcg-target.h b/qemu/tcg/aarch64/tcg-target.h index ce2bb1f9..f5640a22 100644 --- a/qemu/tcg/aarch64/tcg-target.h +++ b/qemu/tcg/aarch64/tcg-target.h @@ -134,7 +134,7 @@ typedef enum { #define TCG_TARGET_HAS_neg_vec 1 #define TCG_TARGET_HAS_shi_vec 1 #define TCG_TARGET_HAS_shs_vec 0 -#define TCG_TARGET_HAS_shv_vec 0 +#define TCG_TARGET_HAS_shv_vec 1 #define TCG_TARGET_HAS_cmp_vec 1 #define TCG_TARGET_HAS_mul_vec 1 #define TCG_TARGET_HAS_sat_vec 1 diff --git a/qemu/tcg/aarch64/tcg-target.inc.c b/qemu/tcg/aarch64/tcg-target.inc.c index 02122b3c..376a34f7 100644 --- a/qemu/tcg/aarch64/tcg-target.inc.c +++ b/qemu/tcg/aarch64/tcg-target.inc.c @@ -533,12 +533,14 @@ typedef enum { I3616_CMEQ = 0x2e208c00, I3616_SMAX = 0x0e206400, I3616_SMIN = 0x0e206c00, + I3616_SSHL = 0x0e204400, I3616_SQADD = 0x0e200c00, I3616_SQSUB = 0x0e202c00, I3616_UMAX = 0x2e206400, I3616_UMIN = 0x2e206c00, I3616_UQADD = 0x2e200c00, I3616_UQSUB = 0x2e202c00, + I3616_USHL = 0x2e204400, /* AdvSIMD two-reg misc. */ I3617_CMGT0 = 0x0e208800, @@ -2239,6 +2241,12 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc, case INDEX_op_sari_vec: tcg_out_insn(s, 3614, SSHR, is_q, a0, a1, (16 << vece) - a2); break; + case INDEX_op_shlv_vec: + tcg_out_insn(s, 3616, USHL, is_q, vece, a0, a1, a2); + break; + case INDEX_op_aa64_sshl_vec: + tcg_out_insn(s, 3616, SSHL, is_q, vece, a0, a1, a2); + break; case INDEX_op_cmp_vec: { TCGCond cond = args[3]; @@ -2306,7 +2314,11 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece) case INDEX_op_smin_vec: case INDEX_op_umax_vec: case INDEX_op_umin_vec: + case INDEX_op_shlv_vec: return 1; + case INDEX_op_shrv_vec: + case INDEX_op_sarv_vec: + return -1; case INDEX_op_mul_vec: return vece < MO_64; @@ -2315,9 +2327,35 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece) } } -void tcg_expand_vec_op(TCGOpcode opc, TCGType type, unsigned vece, +void tcg_expand_vec_op(TCGContext *s, TCGOpcode opc, TCGType type, unsigned vece, TCGArg a0, ...) { + va_list va; + TCGv_vec v0, v1, v2, t1; + + va_start(va, a0); + v0 = temp_tcgv_vec(s, arg_temp(a0)); + v1 = temp_tcgv_vec(s, arg_temp(va_arg(va, TCGArg))); + v2 = temp_tcgv_vec(s, arg_temp(va_arg(va, TCGArg))); + + switch (opc) { + case INDEX_op_shrv_vec: + case INDEX_op_sarv_vec: + /* Right shifts are negative left shifts for AArch64. */ + t1 = tcg_temp_new_vec(s, type); + tcg_gen_neg_vec(s, vece, t1, v2); + opc = (opc == INDEX_op_shrv_vec + ? INDEX_op_shlv_vec : INDEX_op_aa64_sshl_vec); + vec_gen_3(s, opc, type, vece, tcgv_vec_arg(s, v0), + tcgv_vec_arg(s, v1), tcgv_vec_arg(s, t1)); + tcg_temp_free_vec(s, t1); + break; + + default: + g_assert_not_reached(); + } + + va_end(va); } static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode op) @@ -2499,6 +2537,10 @@ static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode op) case INDEX_op_smin_vec: case INDEX_op_umax_vec: case INDEX_op_umin_vec: + case INDEX_op_shlv_vec: + case INDEX_op_shrv_vec: + case INDEX_op_sarv_vec: + case INDEX_op_aa64_sshl_vec: return &w_w_w; case INDEX_op_not_vec: case INDEX_op_neg_vec: