Utilize the condition in the movcond more; this allows some of
the setcond that were feeding into movcond to be removed.
Do not write into source1 and source2.  Re-name "condN" to "tempN"
and use the temporaries for more than holding conditions.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/riscv/translate.c | 160 ++++++++++++++++++++-------------------
 1 file changed, 84 insertions(+), 76 deletions(-)

diff --git a/target/riscv/translate.c b/target/riscv/translate.c
index 20a55c92fb..147b9c2f68 100644
--- a/target/riscv/translate.c
+++ b/target/riscv/translate.c
@@ -213,106 +213,114 @@ static void gen_mulhsu(TCGv ret, TCGv arg1, TCGv arg2)
 
 static void gen_div(TCGv ret, TCGv source1, TCGv source2)
 {
-    TCGv cond1, cond2, zeroreg, resultopt1;
+    TCGv temp1, temp2, zero, one, mone, min;
+
+    temp1 = tcg_temp_new();
+    temp2 = tcg_temp_new();
+    zero = tcg_constant_tl(0);
+    one = tcg_constant_tl(1);
+    mone = tcg_constant_tl(-1);
+    min = tcg_constant_tl(1ull << (TARGET_LONG_BITS - 1));
+
     /*
-     * Handle by altering args to tcg_gen_div to produce req'd results:
-     * For overflow: want source1 in source1 and 1 in source2
-     * For div by zero: want -1 in source1 and 1 in source2 -> -1 result
+     * If overflow, set temp2 to 1, else source2.
+     * This produces the required result of min.
      */
-    cond1 = tcg_temp_new();
-    cond2 = tcg_temp_new();
-    zeroreg = tcg_constant_tl(0);
-    resultopt1 = tcg_temp_new();
+    tcg_gen_setcond_tl(TCG_COND_EQ, temp1, source1, min);
+    tcg_gen_setcond_tl(TCG_COND_EQ, temp2, source2, mone);
+    tcg_gen_and_tl(temp1, temp1, temp2);
+    tcg_gen_movcond_tl(TCG_COND_NE, temp2, temp1, zero, one, source2);
 
-    tcg_gen_movi_tl(resultopt1, (target_ulong)-1);
-    tcg_gen_setcondi_tl(TCG_COND_EQ, cond2, source2, (target_ulong)(~0L));
-    tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source1,
-                        ((target_ulong)1) << (TARGET_LONG_BITS - 1));
-    tcg_gen_and_tl(cond1, cond1, cond2); /* cond1 = overflow */
-    tcg_gen_setcondi_tl(TCG_COND_EQ, cond2, source2, 0); /* cond2 = div 0 */
-    /* if div by zero, set source1 to -1, otherwise don't change */
-    tcg_gen_movcond_tl(TCG_COND_EQ, source1, cond2, zeroreg, source1,
-            resultopt1);
-    /* if overflow or div by zero, set source2 to 1, else don't change */
-    tcg_gen_or_tl(cond1, cond1, cond2);
-    tcg_gen_movi_tl(resultopt1, (target_ulong)1);
-    tcg_gen_movcond_tl(TCG_COND_EQ, source2, cond1, zeroreg, source2,
-            resultopt1);
-    tcg_gen_div_tl(ret, source1, source2);
+    /*
+     * If div by zero, set temp1 to -1 and temp2 to 1 to
+     * produce the required result of -1.
+     */
+    tcg_gen_movcond_tl(TCG_COND_EQ, temp1, source2, zero, mone, source1);
+    tcg_gen_movcond_tl(TCG_COND_EQ, temp2, source2, zero, one, temp2);
 
-    tcg_temp_free(cond1);
-    tcg_temp_free(cond2);
-    tcg_temp_free(resultopt1);
+    tcg_gen_div_tl(ret, temp1, temp2);
+
+    tcg_temp_free(temp1);
+    tcg_temp_free(temp2);
 }
 
 static void gen_divu(TCGv ret, TCGv source1, TCGv source2)
 {
-    TCGv cond1, zeroreg, resultopt1;
-    cond1 = tcg_temp_new();
+    TCGv temp1, temp2, zero, one, max;
 
-    zeroreg = tcg_constant_tl(0);
-    resultopt1 = tcg_temp_new();
+    temp1 = tcg_temp_new();
+    temp2 = tcg_temp_new();
+    zero = tcg_constant_tl(0);
+    one = tcg_constant_tl(1);
+    max = tcg_constant_tl(~0);
 
-    tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source2, 0);
-    tcg_gen_movi_tl(resultopt1, (target_ulong)-1);
-    tcg_gen_movcond_tl(TCG_COND_EQ, source1, cond1, zeroreg, source1,
-            resultopt1);
-    tcg_gen_movi_tl(resultopt1, (target_ulong)1);
-    tcg_gen_movcond_tl(TCG_COND_EQ, source2, cond1, zeroreg, source2,
-            resultopt1);
-    tcg_gen_divu_tl(ret, source1, source2);
+    /*
+     * If div by zero, set temp1 to max and temp2 to 1 to
+     * produce the required result of max.
+     */
+    tcg_gen_movcond_tl(TCG_COND_EQ, temp1, source2, zero, max, source1);
+    tcg_gen_movcond_tl(TCG_COND_EQ, temp2, source2, zero, one, source2);
+    tcg_gen_divu_tl(ret, temp1, temp2);
 
-    tcg_temp_free(cond1);
-    tcg_temp_free(resultopt1);
+    tcg_temp_free(temp1);
+    tcg_temp_free(temp2);
 }
 
 static void gen_rem(TCGv ret, TCGv source1, TCGv source2)
 {
-    TCGv cond1, cond2, zeroreg, resultopt1;
+    TCGv temp1, temp2, zero, one, mone, min;
 
-    cond1 = tcg_temp_new();
-    cond2 = tcg_temp_new();
-    zeroreg = tcg_constant_tl(0);
-    resultopt1 = tcg_temp_new();
+    temp1 = tcg_temp_new();
+    temp2 = tcg_temp_new();
+    zero = tcg_constant_tl(0);
+    one = tcg_constant_tl(1);
+    mone = tcg_constant_tl(-1);
+    min = tcg_constant_tl(1ull << (TARGET_LONG_BITS - 1));
 
-    tcg_gen_movi_tl(resultopt1, 1L);
-    tcg_gen_setcondi_tl(TCG_COND_EQ, cond2, source2, (target_ulong)-1);
-    tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source1,
-                        (target_ulong)1 << (TARGET_LONG_BITS - 1));
-    tcg_gen_and_tl(cond2, cond1, cond2); /* cond1 = overflow */
-    tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source2, 0); /* cond2 = div 0 */
-    /* if overflow or div by zero, set source2 to 1, else don't change */
-    tcg_gen_or_tl(cond2, cond1, cond2);
-    tcg_gen_movcond_tl(TCG_COND_EQ, source2, cond2, zeroreg, source2,
-            resultopt1);
-    tcg_gen_rem_tl(resultopt1, source1, source2);
-    /* if div by zero, just return the original dividend */
-    tcg_gen_movcond_tl(TCG_COND_EQ, ret, cond1, zeroreg, resultopt1,
-            source1);
+    /*
+     * If overflow, set temp1 to 0, else source1.
+     * This avoids a possible host trap, and produces the required result of 0.
+     */
+    tcg_gen_setcond_tl(TCG_COND_EQ, temp1, source1, min);
+    tcg_gen_setcond_tl(TCG_COND_EQ, temp2, source2, mone);
+    tcg_gen_and_tl(temp1, temp1, temp2);
+    tcg_gen_movcond_tl(TCG_COND_NE, temp1, temp1, zero, zero, source1);
 
-    tcg_temp_free(cond1);
-    tcg_temp_free(cond2);
-    tcg_temp_free(resultopt1);
+    /*
+     * If div by zero, set temp2 to 1, else source2.
+     * This avoids a possible host trap, but produces an incorrect result.
+     */
+    tcg_gen_movcond_tl(TCG_COND_EQ, temp2, source2, zero, one, source2);
+
+    tcg_gen_rem_tl(temp1, temp1, temp2);
+
+    /* If div by zero, the required result is the original dividend. */
+    tcg_gen_movcond_tl(TCG_COND_EQ, ret, source2, zero, source1, temp1);
+
+    tcg_temp_free(temp1);
+    tcg_temp_free(temp2);
 }
 
 static void gen_remu(TCGv ret, TCGv source1, TCGv source2)
 {
-    TCGv cond1, zeroreg, resultopt1;
-    cond1 = tcg_temp_new();
-    zeroreg = tcg_constant_tl(0);
-    resultopt1 = tcg_temp_new();
+    TCGv temp, zero, one;
 
-    tcg_gen_movi_tl(resultopt1, (target_ulong)1);
-    tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source2, 0);
-    tcg_gen_movcond_tl(TCG_COND_EQ, source2, cond1, zeroreg, source2,
-            resultopt1);
-    tcg_gen_remu_tl(resultopt1, source1, source2);
-    /* if div by zero, just return the original dividend */
-    tcg_gen_movcond_tl(TCG_COND_EQ, ret, cond1, zeroreg, resultopt1,
-            source1);
+    temp = tcg_temp_new();
+    zero = tcg_constant_tl(0);
+    one = tcg_constant_tl(1);
 
-    tcg_temp_free(cond1);
-    tcg_temp_free(resultopt1);
+    /*
+     * If div by zero, set temp to 1, else source2.
+     * This avoids a possible host trap, but produces an incorrect result.
+     */
+    tcg_gen_movcond_tl(TCG_COND_EQ, temp, source2, zero, one, source2);
+
+    tcg_gen_remu_tl(temp, source1, temp);
+
+    /* If div by zero, the required result is the original dividend. */
+    tcg_gen_movcond_tl(TCG_COND_EQ, ret, source2, zero, source1, temp);
+
+    tcg_temp_free(temp);
 }
 
 static void gen_jal(DisasContext *ctx, int rd, target_ulong imm)
-- 
2.25.1

On Sat, Aug 21, 2021 at 1:46 AM Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Utilize the condition in the movcond more; this allows some of
> the setcond that were feeding into movcond to be removed.
> Do not write into source1 and source2.  Re-name "condN" to "tempN"
> and use the temporaries for more than holding conditions.
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
>  target/riscv/translate.c | 160 ++++++++++++++++++++-------------------
>  1 file changed, 84 insertions(+), 76 deletions(-)
>

Reviewed-by: Bin Meng <bmeng.cn@gmail.com>
Tested-by: Bin Meng <bmeng.cn@gmail.com>

On Sat, Aug 21, 2021 at 3:48 AM Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Utilize the condition in the movcond more; this allows some of
> the setcond that were feeding into movcond to be removed.
> Do not write into source1 and source2.  Re-name "condN" to "tempN"
> and use the temporaries for more than holding conditions.
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Alistair Francis <alistair.francis@wdc.com>

Alistair

> ---
>  target/riscv/translate.c | 160 ++++++++++++++++++++-------------------
>  1 file changed, 84 insertions(+), 76 deletions(-)
>
> diff --git a/target/riscv/translate.c b/target/riscv/translate.c
> index 20a55c92fb..147b9c2f68 100644
> --- a/target/riscv/translate.c
> +++ b/target/riscv/translate.c
> @@ -213,106 +213,114 @@ static void gen_mulhsu(TCGv ret, TCGv arg1, TCGv arg2)
>
>  static void gen_div(TCGv ret, TCGv source1, TCGv source2)
>  {
> -    TCGv cond1, cond2, zeroreg, resultopt1;
> +    TCGv temp1, temp2, zero, one, mone, min;
> +
> +    temp1 = tcg_temp_new();
> +    temp2 = tcg_temp_new();
> +    zero = tcg_constant_tl(0);
> +    one = tcg_constant_tl(1);
> +    mone = tcg_constant_tl(-1);
> +    min = tcg_constant_tl(1ull << (TARGET_LONG_BITS - 1));
> +
>      /*
> -     * Handle by altering args to tcg_gen_div to produce req'd results:
> -     * For overflow: want source1 in source1 and 1 in source2
> -     * For div by zero: want -1 in source1 and 1 in source2 -> -1 result
> +     * If overflow, set temp2 to 1, else source2.
> +     * This produces the required result of min.
>       */
> -    cond1 = tcg_temp_new();
> -    cond2 = tcg_temp_new();
> -    zeroreg = tcg_constant_tl(0);
> -    resultopt1 = tcg_temp_new();
> +    tcg_gen_setcond_tl(TCG_COND_EQ, temp1, source1, min);
> +    tcg_gen_setcond_tl(TCG_COND_EQ, temp2, source2, mone);
> +    tcg_gen_and_tl(temp1, temp1, temp2);
> +    tcg_gen_movcond_tl(TCG_COND_NE, temp2, temp1, zero, one, source2);
>
> -    tcg_gen_movi_tl(resultopt1, (target_ulong)-1);
> -    tcg_gen_setcondi_tl(TCG_COND_EQ, cond2, source2, (target_ulong)(~0L));
> -    tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source1,
> -                        ((target_ulong)1) << (TARGET_LONG_BITS - 1));
> -    tcg_gen_and_tl(cond1, cond1, cond2); /* cond1 = overflow */
> -    tcg_gen_setcondi_tl(TCG_COND_EQ, cond2, source2, 0); /* cond2 = div 0 */
> -    /* if div by zero, set source1 to -1, otherwise don't change */
> -    tcg_gen_movcond_tl(TCG_COND_EQ, source1, cond2, zeroreg, source1,
> -            resultopt1);
> -    /* if overflow or div by zero, set source2 to 1, else don't change */
> -    tcg_gen_or_tl(cond1, cond1, cond2);
> -    tcg_gen_movi_tl(resultopt1, (target_ulong)1);
> -    tcg_gen_movcond_tl(TCG_COND_EQ, source2, cond1, zeroreg, source2,
> -            resultopt1);
> -    tcg_gen_div_tl(ret, source1, source2);
> +    /*
> +     * If div by zero, set temp1 to -1 and temp2 to 1 to
> +     * produce the required result of -1.
> +     */
> +    tcg_gen_movcond_tl(TCG_COND_EQ, temp1, source2, zero, mone, source1);
> +    tcg_gen_movcond_tl(TCG_COND_EQ, temp2, source2, zero, one, temp2);
>
> -    tcg_temp_free(cond1);
> -    tcg_temp_free(cond2);
> -    tcg_temp_free(resultopt1);
> +    tcg_gen_div_tl(ret, temp1, temp2);
> +
> +    tcg_temp_free(temp1);
> +    tcg_temp_free(temp2);
>  }
>
>  static void gen_divu(TCGv ret, TCGv source1, TCGv source2)
>  {
> -    TCGv cond1, zeroreg, resultopt1;
> -    cond1 = tcg_temp_new();
> +    TCGv temp1, temp2, zero, one, max;
>
> -    zeroreg = tcg_constant_tl(0);
> -    resultopt1 = tcg_temp_new();
> +    temp1 = tcg_temp_new();
> +    temp2 = tcg_temp_new();
> +    zero = tcg_constant_tl(0);
> +    one = tcg_constant_tl(1);
> +    max = tcg_constant_tl(~0);
>
> -    tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source2, 0);
> -    tcg_gen_movi_tl(resultopt1, (target_ulong)-1);
> -    tcg_gen_movcond_tl(TCG_COND_EQ, source1, cond1, zeroreg, source1,
> -            resultopt1);
> -    tcg_gen_movi_tl(resultopt1, (target_ulong)1);
> -    tcg_gen_movcond_tl(TCG_COND_EQ, source2, cond1, zeroreg, source2,
> -            resultopt1);
> -    tcg_gen_divu_tl(ret, source1, source2);
> +    /*
> +     * If div by zero, set temp1 to max and temp2 to 1 to
> +     * produce the required result of max.
> +     */
> +    tcg_gen_movcond_tl(TCG_COND_EQ, temp1, source2, zero, max, source1);
> +    tcg_gen_movcond_tl(TCG_COND_EQ, temp2, source2, zero, one, source2);
> +    tcg_gen_divu_tl(ret, temp1, temp2);
>
> -    tcg_temp_free(cond1);
> -    tcg_temp_free(resultopt1);
> +    tcg_temp_free(temp1);
> +    tcg_temp_free(temp2);
>  }
>
>  static void gen_rem(TCGv ret, TCGv source1, TCGv source2)
>  {
> -    TCGv cond1, cond2, zeroreg, resultopt1;
> +    TCGv temp1, temp2, zero, one, mone, min;
>
> -    cond1 = tcg_temp_new();
> -    cond2 = tcg_temp_new();
> -    zeroreg = tcg_constant_tl(0);
> -    resultopt1 = tcg_temp_new();
> +    temp1 = tcg_temp_new();
> +    temp2 = tcg_temp_new();
> +    zero = tcg_constant_tl(0);
> +    one = tcg_constant_tl(1);
> +    mone = tcg_constant_tl(-1);
> +    min = tcg_constant_tl(1ull << (TARGET_LONG_BITS - 1));
>
> -    tcg_gen_movi_tl(resultopt1, 1L);
> -    tcg_gen_setcondi_tl(TCG_COND_EQ, cond2, source2, (target_ulong)-1);
> -    tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source1,
> -                        (target_ulong)1 << (TARGET_LONG_BITS - 1));
> -    tcg_gen_and_tl(cond2, cond1, cond2); /* cond1 = overflow */
> -    tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source2, 0); /* cond2 = div 0 */
> -    /* if overflow or div by zero, set source2 to 1, else don't change */
> -    tcg_gen_or_tl(cond2, cond1, cond2);
> -    tcg_gen_movcond_tl(TCG_COND_EQ, source2, cond2, zeroreg, source2,
> -            resultopt1);
> -    tcg_gen_rem_tl(resultopt1, source1, source2);
> -    /* if div by zero, just return the original dividend */
> -    tcg_gen_movcond_tl(TCG_COND_EQ, ret, cond1, zeroreg, resultopt1,
> -            source1);
> +    /*
> +     * If overflow, set temp1 to 0, else source1.
> +     * This avoids a possible host trap, and produces the required result of 0.
> +     */
> +    tcg_gen_setcond_tl(TCG_COND_EQ, temp1, source1, min);
> +    tcg_gen_setcond_tl(TCG_COND_EQ, temp2, source2, mone);
> +    tcg_gen_and_tl(temp1, temp1, temp2);
> +    tcg_gen_movcond_tl(TCG_COND_NE, temp1, temp1, zero, zero, source1);
>
> -    tcg_temp_free(cond1);
> -    tcg_temp_free(cond2);
> -    tcg_temp_free(resultopt1);
> +    /*
> +     * If div by zero, set temp2 to 1, else source2.
> +     * This avoids a possible host trap, but produces an incorrect result.
> +     */
> +    tcg_gen_movcond_tl(TCG_COND_EQ, temp2, source2, zero, one, source2);
> +
> +    tcg_gen_rem_tl(temp1, temp1, temp2);
> +
> +    /* If div by zero, the required result is the original dividend. */
> +    tcg_gen_movcond_tl(TCG_COND_EQ, ret, source2, zero, source1, temp1);
> +
> +    tcg_temp_free(temp1);
> +    tcg_temp_free(temp2);
>  }
>
>  static void gen_remu(TCGv ret, TCGv source1, TCGv source2)
>  {
> -    TCGv cond1, zeroreg, resultopt1;
> -    cond1 = tcg_temp_new();
> -    zeroreg = tcg_constant_tl(0);
> -    resultopt1 = tcg_temp_new();
> +    TCGv temp, zero, one;
>
> -    tcg_gen_movi_tl(resultopt1, (target_ulong)1);
> -    tcg_gen_setcondi_tl(TCG_COND_EQ, cond1, source2, 0);
> -    tcg_gen_movcond_tl(TCG_COND_EQ, source2, cond1, zeroreg, source2,
> -            resultopt1);
> -    tcg_gen_remu_tl(resultopt1, source1, source2);
> -    /* if div by zero, just return the original dividend */
> -    tcg_gen_movcond_tl(TCG_COND_EQ, ret, cond1, zeroreg, resultopt1,
> -            source1);
> +    temp = tcg_temp_new();
> +    zero = tcg_constant_tl(0);
> +    one = tcg_constant_tl(1);
>
> -    tcg_temp_free(cond1);
> -    tcg_temp_free(resultopt1);
> +    /*
> +     * If div by zero, set temp to 1, else source2.
> +     * This avoids a possible host trap, but produces an incorrect result.
> +     */
> +    tcg_gen_movcond_tl(TCG_COND_EQ, temp, source2, zero, one, source2);
> +
> +    tcg_gen_remu_tl(temp, source1, temp);
> +
> +    /* If div by zero, the required result is the original dividend. */
> +    tcg_gen_movcond_tl(TCG_COND_EQ, ret, source2, zero, source1, temp);
> +
> +    tcg_temp_free(temp);
>  }
>
>  static void gen_jal(DisasContext *ctx, int rd, target_ulong imm)
> --
> 2.25.1
>
>