[Qemu-devel] [PATCH 11/15] tcg-mips: Use mips64r6 instructions in tcg_out_movi

[Richard Henderson]

The DAHI and DATI instructions can eliminate two insns
off the pre-r6 path.

Signed-off-by: Richard Henderson <address@hidden>
---
 tcg/mips/tcg-target.c | 63 +++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 63 insertions(+)

diff --git a/tcg/mips/tcg-target.c b/tcg/mips/tcg-target.c
index 97f9251..f7f4331 100644
--- a/tcg/mips/tcg-target.c
+++ b/tcg/mips/tcg-target.c
@@ -303,7 +303,9 @@ typedef enum {
     OPC_ORI      = 015 << 26,
     OPC_XORI     = 016 << 26,
     OPC_LUI      = 017 << 26,
+    OPC_AUI      = OPC_LUI,
     OPC_DADDIU   = 031 << 26,
+    OPC_DAUI     = 035 << 26,
     OPC_LB       = 040 << 26,
     OPC_LH       = 041 << 26,
     OPC_LW       = 043 << 26,
@@ -383,6 +385,8 @@ typedef enum {
     OPC_REGIMM   = 001 << 26,
     OPC_BLTZ     = OPC_REGIMM | (000 << 16),
     OPC_BGEZ     = OPC_REGIMM | (001 << 16),
+    OPC_DAHI     = OPC_REGIMM | (006 << 16),
+    OPC_DATI     = OPC_REGIMM | (036 << 16),
 
     OPC_SPECIAL2 = 034 << 26,
     OPC_MUL_R5   = OPC_SPECIAL2 | 002,
@@ -402,6 +406,10 @@ typedef enum {
     OPC_SEB      = OPC_SPECIAL3 | 02040,
     OPC_SEH      = OPC_SPECIAL3 | 03040,
 
+    OPC_PCREL    = 073 << 26,
+    OPC_ADDIUPC  = OPC_PCREL | (0 << 19),
+    OPC_ALUIPC   = OPC_PCREL | (3 << 19) | (7 << 16),
+
     /* MIPS r6 doesn't have JR, JALR should be used instead */
     OPC_JR       = use_mips32r6_instructions ? OPC_JALR : OPC_JR_R5,
 
@@ -448,6 +456,17 @@ static inline void tcg_out_opc_imm(TCGContext *s, MIPSInsn 
opc,
     tcg_out32(s, inst);
 }
 
+static inline void tcg_out_opc_pc19(TCGContext *s, MIPSInsn opc,
+                                    TCGReg rs, TCGArg imm)
+{
+    int32_t inst;
+
+    inst = opc;
+    inst |= (rs & 0x1F) << 21;
+    inst |= (imm & 0x7ffff);
+    tcg_out32(s, inst);
+}
+
 /*
  * Type bitfield
  */
@@ -589,6 +608,50 @@ static void tcg_out_movi(TCGContext *s, TCGType type,
     }
     if (TCG_TARGET_REG_BITS == 32 || arg == (int32_t)arg) {
         tcg_out_opc_imm(s, OPC_LUI, ret, TCG_REG_ZERO, arg >> 16);
+    } else if (use_mips32r6_instructions) {
+        tcg_target_long disp = arg - (intptr_t)s->code_ptr;
+        if (disp == sextract32(disp, 2, 19) * 4) {
+            tcg_out_opc_pc19(s, OPC_ADDIUPC, ret, disp >> 2);
+            return;
+        } else if ((disp & ~(tcg_target_long)0xffff)
+                   == sextract32(disp, 16, 16) * 0x10000) {
+            tcg_out_opc_imm(s, OPC_ALUIPC, ret, 0, disp >> 16);
+        } else {
+            TCGReg in = TCG_REG_ZERO;
+            tcg_target_long tmp = (int16_t)arg;
+
+            /* The R6 manual recommends construction of immediates in
+               order of low to high (ADDI, AUI, DAHI, DATI) in order
+               to simplify hardware recognizing these sequences.  */
+
+            if (tmp) {
+                tcg_out_opc_imm(s, OPC_ADDIU, ret, in, tmp);
+                in = ret;
+            }
+            arg = (arg - tmp) >> 16;
+            tmp = (int16_t)arg;
+
+            /* Note that DAHI and DATI only have one register operand,
+               and are thus we must put a zero low part in place.  Also
+               note that we already eliminated simple 32-bit constants
+               so we know this must happen.  */
+            if (tmp || in != ret) {
+                tcg_out_opc_imm(s, OPC_AUI, ret, in, tmp);
+            }
+            arg = (arg - tmp) >> 16;
+            tmp = (int16_t)arg;
+
+            if (tmp) {
+                tcg_out_opc_imm(s, OPC_DAHI, ret, 0, tmp);
+            }
+            arg = (arg - tmp) >> 16;
+            tcg_debug_assert(arg == (int16_t)arg);
+
+            if (arg) {
+                tcg_out_opc_imm(s, OPC_DATI, ret, 0, arg);
+            }
+            return;
+        }
     } else {
         tcg_out_movi(s, TCG_TYPE_I32, ret, arg >> 31 >> 1);
         if (arg & 0xffff0000ull) {
-- 
2.5.0