target/i386: DPPS rounding fix

The DPPS (Dot Product) instruction is defined to first sum pairs of
intermediate results, then sum those values to get the final result.
i.e. (A+B)+(C+D)

We incrementally sum the results, i.e. ((A+B)+C)+D, which can result
in incorrect rouding.

For consistency, also change the variable names to the ones used
in the Intel SDM and implement DPPD following the manual.

Based on a patch by Paul Brook <paul@nowt.org>.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 35 insertions, 32 deletions

diff --git a/target/i386/ops_sse.h b/target/i386/ops_sse.h
index 2524db4c25..b12b271fcd 100644
--- a/target/i386/ops_sse.h
+++ b/target/i386/ops_sse.h
@@ -1943,56 +1943,59 @@ SSE_HELPER_I(helper_pblendw, W, 8, FBLENDP)
 
 void glue(helper_dpps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s, uint32_t mask)
 {
-    float32 iresult = float32_zero;
+    float32 prod1, prod2, temp2, temp3, temp4;
 
+    /*
+     * We must evaluate (A+B)+(C+D), not ((A+B)+C)+D
+     * to correctly round the intermediate results
+     */
     if (mask & (1 << 4)) {
-        iresult = float32_add(iresult,
-                              float32_mul(d->ZMM_S(0), s->ZMM_S(0),
-                                          &env->sse_status),
-                              &env->sse_status);
+        prod1 = float32_mul(d->ZMM_S(0), s->ZMM_S(0), &env->sse_status);
+    } else {
+        prod1 = float32_zero;
     }
     if (mask & (1 << 5)) {
-        iresult = float32_add(iresult,
-                              float32_mul(d->ZMM_S(1), s->ZMM_S(1),
-                                          &env->sse_status),
-                              &env->sse_status);
+        prod2 = float32_mul(d->ZMM_S(1), s->ZMM_S(1), &env->sse_status);
+    } else {
+        prod2 = float32_zero;
     }
+    temp2 = float32_add(prod1, prod2, &env->sse_status);
     if (mask & (1 << 6)) {
-        iresult = float32_add(iresult,
-                              float32_mul(d->ZMM_S(2), s->ZMM_S(2),
-                                          &env->sse_status),
-                              &env->sse_status);
+        prod1 = float32_mul(d->ZMM_S(2), s->ZMM_S(2), &env->sse_status);
+    } else {
+        prod1 = float32_zero;
     }
     if (mask & (1 << 7)) {
-        iresult = float32_add(iresult,
-                              float32_mul(d->ZMM_S(3), s->ZMM_S(3),
-                                          &env->sse_status),
-                              &env->sse_status);
+        prod2 = float32_mul(d->ZMM_S(3), s->ZMM_S(3), &env->sse_status);
+    } else {
+        prod2 = float32_zero;
     }
-    d->ZMM_S(0) = (mask & (1 << 0)) ? iresult : float32_zero;
-    d->ZMM_S(1) = (mask & (1 << 1)) ? iresult : float32_zero;
-    d->ZMM_S(2) = (mask & (1 << 2)) ? iresult : float32_zero;
-    d->ZMM_S(3) = (mask & (1 << 3)) ? iresult : float32_zero;
+    temp3 = float32_add(prod1, prod2, &env->sse_status);
+    temp4 = float32_add(temp2, temp3, &env->sse_status);
+
+    d->ZMM_S(0) = (mask & (1 << 0)) ? temp4 : float32_zero;
+    d->ZMM_S(1) = (mask & (1 << 1)) ? temp4 : float32_zero;
+    d->ZMM_S(2) = (mask & (1 << 2)) ? temp4 : float32_zero;
+    d->ZMM_S(3) = (mask & (1 << 3)) ? temp4 : float32_zero;
 }
 
 void glue(helper_dppd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s, uint32_t mask)
 {
-    float64 iresult = float64_zero;
+    float64 prod1, prod2, temp2;
 
     if (mask & (1 << 4)) {
-        iresult = float64_add(iresult,
-                              float64_mul(d->ZMM_D(0), s->ZMM_D(0),
-                                          &env->sse_status),
-                              &env->sse_status);
+        prod1 = float64_mul(d->ZMM_D(0), s->ZMM_D(0), &env->sse_status);
+    } else {
+        prod1 = float64_zero;
     }
     if (mask & (1 << 5)) {
-        iresult = float64_add(iresult,
-                              float64_mul(d->ZMM_D(1), s->ZMM_D(1),
-                                          &env->sse_status),
-                              &env->sse_status);
+        prod2 = float64_mul(d->ZMM_D(1), s->ZMM_D(1), &env->sse_status);
+    } else {
+        prod2 = float64_zero;
     }
-    d->ZMM_D(0) = (mask & (1 << 0)) ? iresult : float64_zero;
-    d->ZMM_D(1) = (mask & (1 << 1)) ? iresult : float64_zero;
+    temp2 = float64_add(prod1, prod2, &env->sse_status);
+    d->ZMM_D(0) = (mask & (1 << 0)) ? temp2 : float64_zero;
+    d->ZMM_D(1) = (mask & (1 << 1)) ? temp2 : float64_zero;
 }
 
 void glue(helper_mpsadbw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,