Patchwork target-arm: fix SMMLA/SMMLS instructions

login
register
mail settings
Submitter Aurelien Jarno
Date Jan. 6, 2011, 6:53 p.m.
Message ID <1294340003-684-1-git-send-email-aurelien@aurel32.net>
Download mbox | patch
Permalink /patch/77796/
State New
Headers show

Comments

Aurelien Jarno - Jan. 6, 2011, 6:53 p.m.
SMMLA and SMMLS are broken on both in normal and thumb mode, that is
both (different) implementations are wrong. They try to avoid a 64-bit
add for the rounding, which is not trivial if you want to support both
SMMLA and SMMLS with the same code.

The code below uses the same implementation for both modes, using the
code from the ARM manual. It also fixes the thumb decoding that was a
mix between normal and thumb mode.

This fixes the issues reported in
https://bugs.launchpad.net/qemu/+bug/629298

v2: improve comments with the help from Peter Maydell.

Cc: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
---
 target-arm/translate.c |   96 +++++++++++++++++++++++++----------------------
 1 files changed, 51 insertions(+), 45 deletions(-)
Peter Maydell - Jan. 6, 2011, 7 p.m.
On 6 January 2011 18:53, Aurelien Jarno <aurelien@aurel32.net> wrote:
> SMMLA and SMMLS are broken on both in normal and thumb mode, that is
> both (different) implementations are wrong. They try to avoid a 64-bit
> add for the rounding, which is not trivial if you want to support both
> SMMLA and SMMLS with the same code.
>
> The code below uses the same implementation for both modes, using the
> code from the ARM manual. It also fixes the thumb decoding that was a
> mix between normal and thumb mode.
>
> This fixes the issues reported in
> https://bugs.launchpad.net/qemu/+bug/629298
>
> v2: improve comments with the help from Peter Maydell.
>
> Cc: Peter Maydell <peter.maydell@linaro.org>
> Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>

Confirmed that this is just comment changes since v1, and it
still passes the tests. So:

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>

-- PMM
Aurelien Jarno - Jan. 6, 2011, 9:26 p.m.
On Thu, Jan 06, 2011 at 07:00:09PM +0000, Peter Maydell wrote:
> On 6 January 2011 18:53, Aurelien Jarno <aurelien@aurel32.net> wrote:
> > SMMLA and SMMLS are broken on both in normal and thumb mode, that is
> > both (different) implementations are wrong. They try to avoid a 64-bit
> > add for the rounding, which is not trivial if you want to support both
> > SMMLA and SMMLS with the same code.
> >
> > The code below uses the same implementation for both modes, using the
> > code from the ARM manual. It also fixes the thumb decoding that was a
> > mix between normal and thumb mode.
> >
> > This fixes the issues reported in
> > https://bugs.launchpad.net/qemu/+bug/629298
> >
> > v2: improve comments with the help from Peter Maydell.
> >
> > Cc: Peter Maydell <peter.maydell@linaro.org>
> > Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
> 
> Confirmed that this is just comment changes since v1, and it
> still passes the tests. So:
> 
> Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
> 

Thanks for the review, applied.

Patch

diff --git a/target-arm/translate.c b/target-arm/translate.c
index 1853b5c..57664bc 100644
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -287,11 +287,32 @@  static void gen_bfi(TCGv dest, TCGv base, TCGv val, int shift, uint32_t mask)
     tcg_gen_or_i32(dest, base, val);
 }
 
-/* Round the top 32 bits of a 64-bit value.  */
-static void gen_roundqd(TCGv a, TCGv b)
+/* Return (b << 32) + a. Mark inputs as dead */
+static TCGv_i64 gen_addq_msw(TCGv_i64 a, TCGv b)
 {
-    tcg_gen_shri_i32(a, a, 31);
-    tcg_gen_add_i32(a, a, b);
+    TCGv_i64 tmp64 = tcg_temp_new_i64();
+
+    tcg_gen_extu_i32_i64(tmp64, b);
+    dead_tmp(b);
+    tcg_gen_shli_i64(tmp64, tmp64, 32);
+    tcg_gen_add_i64(a, tmp64, a);
+
+    tcg_temp_free_i64(tmp64);
+    return a;
+}
+
+/* Return (b << 32) - a. Mark inputs as dead. */
+static TCGv_i64 gen_subq_msw(TCGv_i64 a, TCGv b)
+{
+    TCGv_i64 tmp64 = tcg_temp_new_i64();
+
+    tcg_gen_extu_i32_i64(tmp64, b);
+    dead_tmp(b);
+    tcg_gen_shli_i64(tmp64, tmp64, 32);
+    tcg_gen_sub_i64(a, tmp64, a);
+
+    tcg_temp_free_i64(tmp64);
+    return a;
 }
 
 /* FIXME: Most targets have native widening multiplication.
@@ -325,22 +346,6 @@  static TCGv_i64 gen_muls_i64_i32(TCGv a, TCGv b)
     return tmp1;
 }
 
-/* Signed 32x32->64 multiply.  */
-static void gen_imull(TCGv a, TCGv b)
-{
-    TCGv_i64 tmp1 = tcg_temp_new_i64();
-    TCGv_i64 tmp2 = tcg_temp_new_i64();
-
-    tcg_gen_ext_i32_i64(tmp1, a);
-    tcg_gen_ext_i32_i64(tmp2, b);
-    tcg_gen_mul_i64(tmp1, tmp1, tmp2);
-    tcg_temp_free_i64(tmp2);
-    tcg_gen_trunc_i64_i32(a, tmp1);
-    tcg_gen_shri_i64(tmp1, tmp1, 32);
-    tcg_gen_trunc_i64_i32(b, tmp1);
-    tcg_temp_free_i64(tmp1);
-}
-
 /* Swap low and high halfwords.  */
 static void gen_swap_half(TCGv var)
 {
@@ -6974,23 +6979,25 @@  static void disas_arm_insn(CPUState * env, DisasContext *s)
                     tmp = load_reg(s, rm);
                     tmp2 = load_reg(s, rs);
                     if (insn & (1 << 20)) {
-                        /* Signed multiply most significant [accumulate].  */
+                        /* Signed multiply most significant [accumulate].
+                           (SMMUL, SMMLA, SMMLS) */
                         tmp64 = gen_muls_i64_i32(tmp, tmp2);
-                        if (insn & (1 << 5))
-                            tcg_gen_addi_i64(tmp64, tmp64, 0x80000000u);
-                        tcg_gen_shri_i64(tmp64, tmp64, 32);
-                        tmp = new_tmp();
-                        tcg_gen_trunc_i64_i32(tmp, tmp64);
-                        tcg_temp_free_i64(tmp64);
+
                         if (rd != 15) {
-                            tmp2 = load_reg(s, rd);
+                            tmp = load_reg(s, rd);
                             if (insn & (1 << 6)) {
-                                tcg_gen_sub_i32(tmp, tmp, tmp2);
+                                tmp64 = gen_subq_msw(tmp64, tmp);
                             } else {
-                                tcg_gen_add_i32(tmp, tmp, tmp2);
+                                tmp64 = gen_addq_msw(tmp64, tmp);
                             }
-                            dead_tmp(tmp2);
                         }
+                        if (insn & (1 << 5)) {
+                            tcg_gen_addi_i64(tmp64, tmp64, 0x80000000u);
+                        }
+                        tcg_gen_shri_i64(tmp64, tmp64, 32);
+                        tmp = new_tmp();
+                        tcg_gen_trunc_i64_i32(tmp, tmp64);
+                        tcg_temp_free_i64(tmp64);
                         store_reg(s, rn, tmp);
                     } else {
                         if (insn & (1 << 5))
@@ -7861,24 +7868,23 @@  static int disas_thumb2_insn(CPUState *env, DisasContext *s, uint16_t insn_hw1)
                     dead_tmp(tmp2);
                   }
                 break;
-            case 5: case 6: /* 32 * 32 -> 32msb */
-                gen_imull(tmp, tmp2);
-                if (insn & (1 << 5)) {
-                    gen_roundqd(tmp, tmp2);
-                    dead_tmp(tmp2);
-                } else {
-                    dead_tmp(tmp);
-                    tmp = tmp2;
-                }
+            case 5: case 6: /* 32 * 32 -> 32msb (SMMUL, SMMLA, SMMLS) */
+                tmp64 = gen_muls_i64_i32(tmp, tmp2);
                 if (rs != 15) {
-                    tmp2 = load_reg(s, rs);
-                    if (insn & (1 << 21)) {
-                        tcg_gen_add_i32(tmp, tmp, tmp2);
+                    tmp = load_reg(s, rs);
+                    if (insn & (1 << 20)) {
+                        tmp64 = gen_addq_msw(tmp64, tmp);
                     } else {
-                        tcg_gen_sub_i32(tmp, tmp2, tmp);
+                        tmp64 = gen_subq_msw(tmp64, tmp);
                     }
-                    dead_tmp(tmp2);
                 }
+                if (insn & (1 << 4)) {
+                    tcg_gen_addi_i64(tmp64, tmp64, 0x80000000u);
+                }
+                tcg_gen_shri_i64(tmp64, tmp64, 32);
+                tmp = new_tmp();
+                tcg_gen_trunc_i64_i32(tmp, tmp64);
+                tcg_temp_free_i64(tmp64);
                 break;
             case 7: /* Unsigned sum of absolute differences.  */
                 gen_helper_usad8(tmp, tmp, tmp2);