Patchwork [v5,13/19] tcg-arm: Cleanup multiply subroutines

login
register
mail settings
Submitter Richard Henderson
Date March 31, 2013, 10:34 p.m.
Message ID <1364769305-3687-14-git-send-email-rth@twiddle.net>
Download mbox | patch
Permalink /patch/232641/
State New
Headers show

Comments

Richard Henderson - March 31, 2013, 10:34 p.m.
Make the code more readable by only having one copy of the magic
numbers, swapping registers as needed prior to that.  Speed the
compiler by not applying the rd == rn avoidance for v6 or later.

Signed-off-by: Richard Henderson <rth@twiddle.net>
---
 tcg/arm/tcg-target.c | 85 +++++++++++++++++++++++++++-------------------------
 1 file changed, 45 insertions(+), 40 deletions(-)
Aurelien Jarno - April 22, 2013, 9:07 a.m.
On Sun, Mar 31, 2013 at 03:34:59PM -0700, Richard Henderson wrote:
> Make the code more readable by only having one copy of the magic
> numbers, swapping registers as needed prior to that.  Speed the
> compiler by not applying the rd == rn avoidance for v6 or later.
> 
> Signed-off-by: Richard Henderson <rth@twiddle.net>
> ---
>  tcg/arm/tcg-target.c | 85 +++++++++++++++++++++++++++-------------------------
>  1 file changed, 45 insertions(+), 40 deletions(-)
> 
> diff --git a/tcg/arm/tcg-target.c b/tcg/arm/tcg-target.c
> index 6e1a4b5..24a2354 100644
> --- a/tcg/arm/tcg-target.c
> +++ b/tcg/arm/tcg-target.c
> @@ -542,55 +542,60 @@ static void tcg_out_dat_rIN(TCGContext *s, int cond, int opc, int opneg,
>      }
>  }
>  
> -static inline void tcg_out_mul32(TCGContext *s,
> -                int cond, int rd, int rs, int rm)
> -{
> -    if (rd != rm)
> -        tcg_out32(s, (cond << 28) | (rd << 16) | (0 << 12) |
> -                        (rs << 8) | 0x90 | rm);
> -    else if (rd != rs)
> -        tcg_out32(s, (cond << 28) | (rd << 16) | (0 << 12) |
> -                        (rm << 8) | 0x90 | rs);
> -    else {
> -        tcg_out32(s, (cond << 28) | (TCG_REG_TMP << 16) | (0 << 12) |
> -                        (rs << 8) | 0x90 | rm);
> -        tcg_out_dat_reg(s, cond, ARITH_MOV,
> -                        rd, 0, TCG_REG_TMP, SHIFT_IMM_LSL(0));
> +static inline void tcg_out_mul32(TCGContext *s, int cond, TCGReg rd,
> +                                 TCGReg rn, TCGReg rm)
> +{
> +    /* if ArchVersion() < 6 && d == n then UNPREDICTABLE;  */
> +    if (!use_armv6_instructions && rd == rn) {
> +        if (rd == rm) {
> +            /* rd == rn == rm; copy an input to tmp first.  */
> +            tcg_out_mov_reg(s, cond, TCG_REG_TMP, rn);
> +            rm = rn = TCG_REG_TMP;
> +        } else {
> +            rn = rm;
> +            rm = rd;
> +        }
>      }
> +    /* mul */
> +    tcg_out32(s, (cond << 28) | 0x90 | (rd << 16) | (rm << 8) | rn);
>  }
>  
> -static inline void tcg_out_umull32(TCGContext *s,
> -                int cond, int rd0, int rd1, int rs, int rm)
> +static inline void tcg_out_umull32(TCGContext *s, int cond, TCGReg rd0,
> +                                   TCGReg rd1, TCGReg rn, TCGReg rm)
>  {
> -    if (rd0 != rm && rd1 != rm)
> -        tcg_out32(s, (cond << 28) | 0x800090 |
> -                        (rd1 << 16) | (rd0 << 12) | (rs << 8) | rm);
> -    else if (rd0 != rs && rd1 != rs)
> -        tcg_out32(s, (cond << 28) | 0x800090 |
> -                        (rd1 << 16) | (rd0 << 12) | (rm << 8) | rs);
> -    else {
> -        tcg_out_dat_reg(s, cond, ARITH_MOV,
> -                        TCG_REG_TMP, 0, rm, SHIFT_IMM_LSL(0));
> -        tcg_out32(s, (cond << 28) | 0x800090 | TCG_REG_TMP |
> -                        (rd1 << 16) | (rd0 << 12) | (rs << 8));
> +    /* if ArchVersion() < 6 && (dHi == n || dLo == n) then UNPREDICTABLE;  */
> +    if (!use_armv6_instructions && (rd0 == rn || rd1 == rn)) {
> +        if (rd0 == rm || rd1 == rm) {
> +            tcg_out_mov_reg(s, cond, TCG_REG_TMP, rn);
> +            rn = TCG_REG_TMP;
> +        } else {
> +            TCGReg t = rn;
> +            rn = rm;
> +            rm = t;
> +        }
>      }
> +    /* umull */
> +    tcg_out32(s, (cond << 28) | 0x00800090 |
> +              (rd1 << 16) | (rd0 << 12) | (rm << 8) | rn);
>  }
>  
> -static inline void tcg_out_smull32(TCGContext *s,
> -                int cond, int rd0, int rd1, int rs, int rm)
> +static inline void tcg_out_smull32(TCGContext *s, int cond, TCGReg rd0,
> +                                   TCGReg rd1, TCGReg rn, TCGReg rm)
>  {
> -    if (rd0 != rm && rd1 != rm)
> -        tcg_out32(s, (cond << 28) | 0xc00090 |
> -                        (rd1 << 16) | (rd0 << 12) | (rs << 8) | rm);
> -    else if (rd0 != rs && rd1 != rs)
> -        tcg_out32(s, (cond << 28) | 0xc00090 |
> -                        (rd1 << 16) | (rd0 << 12) | (rm << 8) | rs);
> -    else {
> -        tcg_out_dat_reg(s, cond, ARITH_MOV,
> -                        TCG_REG_TMP, 0, rm, SHIFT_IMM_LSL(0));
> -        tcg_out32(s, (cond << 28) | 0xc00090 | TCG_REG_TMP |
> -                        (rd1 << 16) | (rd0 << 12) | (rs << 8));
> +    /* if ArchVersion() < 6 && (dHi == n || dLo == n) then UNPREDICTABLE;  */
> +    if (!use_armv6_instructions && (rd0 == rn || rd1 == rn)) {
> +        if (rd0 == rm || rd1 == rm) {
> +            tcg_out_mov_reg(s, cond, TCG_REG_TMP, rn);
> +            rn = TCG_REG_TMP;
> +        } else {
> +            TCGReg t = rn;
> +            rn = rm;
> +            rm = t;
> +        }
>      }
> +    /* smull */
> +    tcg_out32(s, (cond << 28) | 0x00c00090 |
> +              (rd1 << 16) | (rd0 << 12) | (rm << 8) | rn);
>  }
>  
>  static inline void tcg_out_sdiv(TCGContext *s, int cond, int rd, int rn, int rm)

Reviewed-by: Aurelien Jarno <aurelien@aurel32.net>

Patch

diff --git a/tcg/arm/tcg-target.c b/tcg/arm/tcg-target.c
index 6e1a4b5..24a2354 100644
--- a/tcg/arm/tcg-target.c
+++ b/tcg/arm/tcg-target.c
@@ -542,55 +542,60 @@  static void tcg_out_dat_rIN(TCGContext *s, int cond, int opc, int opneg,
     }
 }
 
-static inline void tcg_out_mul32(TCGContext *s,
-                int cond, int rd, int rs, int rm)
-{
-    if (rd != rm)
-        tcg_out32(s, (cond << 28) | (rd << 16) | (0 << 12) |
-                        (rs << 8) | 0x90 | rm);
-    else if (rd != rs)
-        tcg_out32(s, (cond << 28) | (rd << 16) | (0 << 12) |
-                        (rm << 8) | 0x90 | rs);
-    else {
-        tcg_out32(s, (cond << 28) | (TCG_REG_TMP << 16) | (0 << 12) |
-                        (rs << 8) | 0x90 | rm);
-        tcg_out_dat_reg(s, cond, ARITH_MOV,
-                        rd, 0, TCG_REG_TMP, SHIFT_IMM_LSL(0));
+static inline void tcg_out_mul32(TCGContext *s, int cond, TCGReg rd,
+                                 TCGReg rn, TCGReg rm)
+{
+    /* if ArchVersion() < 6 && d == n then UNPREDICTABLE;  */
+    if (!use_armv6_instructions && rd == rn) {
+        if (rd == rm) {
+            /* rd == rn == rm; copy an input to tmp first.  */
+            tcg_out_mov_reg(s, cond, TCG_REG_TMP, rn);
+            rm = rn = TCG_REG_TMP;
+        } else {
+            rn = rm;
+            rm = rd;
+        }
     }
+    /* mul */
+    tcg_out32(s, (cond << 28) | 0x90 | (rd << 16) | (rm << 8) | rn);
 }
 
-static inline void tcg_out_umull32(TCGContext *s,
-                int cond, int rd0, int rd1, int rs, int rm)
+static inline void tcg_out_umull32(TCGContext *s, int cond, TCGReg rd0,
+                                   TCGReg rd1, TCGReg rn, TCGReg rm)
 {
-    if (rd0 != rm && rd1 != rm)
-        tcg_out32(s, (cond << 28) | 0x800090 |
-                        (rd1 << 16) | (rd0 << 12) | (rs << 8) | rm);
-    else if (rd0 != rs && rd1 != rs)
-        tcg_out32(s, (cond << 28) | 0x800090 |
-                        (rd1 << 16) | (rd0 << 12) | (rm << 8) | rs);
-    else {
-        tcg_out_dat_reg(s, cond, ARITH_MOV,
-                        TCG_REG_TMP, 0, rm, SHIFT_IMM_LSL(0));
-        tcg_out32(s, (cond << 28) | 0x800090 | TCG_REG_TMP |
-                        (rd1 << 16) | (rd0 << 12) | (rs << 8));
+    /* if ArchVersion() < 6 && (dHi == n || dLo == n) then UNPREDICTABLE;  */
+    if (!use_armv6_instructions && (rd0 == rn || rd1 == rn)) {
+        if (rd0 == rm || rd1 == rm) {
+            tcg_out_mov_reg(s, cond, TCG_REG_TMP, rn);
+            rn = TCG_REG_TMP;
+        } else {
+            TCGReg t = rn;
+            rn = rm;
+            rm = t;
+        }
     }
+    /* umull */
+    tcg_out32(s, (cond << 28) | 0x00800090 |
+              (rd1 << 16) | (rd0 << 12) | (rm << 8) | rn);
 }
 
-static inline void tcg_out_smull32(TCGContext *s,
-                int cond, int rd0, int rd1, int rs, int rm)
+static inline void tcg_out_smull32(TCGContext *s, int cond, TCGReg rd0,
+                                   TCGReg rd1, TCGReg rn, TCGReg rm)
 {
-    if (rd0 != rm && rd1 != rm)
-        tcg_out32(s, (cond << 28) | 0xc00090 |
-                        (rd1 << 16) | (rd0 << 12) | (rs << 8) | rm);
-    else if (rd0 != rs && rd1 != rs)
-        tcg_out32(s, (cond << 28) | 0xc00090 |
-                        (rd1 << 16) | (rd0 << 12) | (rm << 8) | rs);
-    else {
-        tcg_out_dat_reg(s, cond, ARITH_MOV,
-                        TCG_REG_TMP, 0, rm, SHIFT_IMM_LSL(0));
-        tcg_out32(s, (cond << 28) | 0xc00090 | TCG_REG_TMP |
-                        (rd1 << 16) | (rd0 << 12) | (rs << 8));
+    /* if ArchVersion() < 6 && (dHi == n || dLo == n) then UNPREDICTABLE;  */
+    if (!use_armv6_instructions && (rd0 == rn || rd1 == rn)) {
+        if (rd0 == rm || rd1 == rm) {
+            tcg_out_mov_reg(s, cond, TCG_REG_TMP, rn);
+            rn = TCG_REG_TMP;
+        } else {
+            TCGReg t = rn;
+            rn = rm;
+            rm = t;
+        }
     }
+    /* smull */
+    tcg_out32(s, (cond << 28) | 0x00c00090 |
+              (rd1 << 16) | (rd0 << 12) | (rm << 8) | rn);
 }
 
 static inline void tcg_out_sdiv(TCGContext *s, int cond, int rd, int rn, int rm)