target/ppc: change xs[n]madd[am]sp to use float64r32_muladd

Change VSX Scalar Multiply-Add/Subtract Type-A/M Single Precision
helpers to use float64r32_muladd. This method should correctly handle
all rounding modes, so the workaround for float_round_nearest_even can
be dropped.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Matheus Ferst <matheus.ferst@eldorado.org.br>
Message-Id: <20220304165417.1981159-3-matheus.ferst@eldorado.org.br>
Signed-off-by: Cédric Le Goater <clg@kaod.org>

diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c
index 8f970288f50eaa33553443969a270afee9492c86..2cad05c9cf7e27a2fe9350a00517deebaa749c6c 100644 (file)
--- a/target/ppc/fpu_helper.c
+++ b/target/ppc/fpu_helper.c
@@ -2156,9 +2156,8 @@ VSX_TSQRT(xvtsqrtsp, 4, float32, VsrW(i), -126, 23)
  *   maddflgs - flags for the float*muladd routine that control the
  *           various forms (madd, msub, nmadd, nmsub)
  *   sfprf - set FPRF
- *   r2sp  - round intermediate double precision result to single precision
  */
-#define VSX_MADD(op, nels, tp, fld, maddflgs, sfprf, r2sp)                    \
+#define VSX_MADD(op, nels, tp, fld, maddflgs, sfprf)                          \
 void helper_##op(CPUPPCState *env, ppc_vsr_t *xt,                             \
                  ppc_vsr_t *s1, ppc_vsr_t *s2, ppc_vsr_t *s3)                 \
 {                                                                             \
@@ -2170,20 +2169,7 @@ void helper_##op(CPUPPCState *env, ppc_vsr_t *xt,                             \
     for (i = 0; i < nels; i++) {                                              \
         float_status tstat = env->fp_status;                                  \
         set_float_exception_flags(0, &tstat);                                 \
-        if (r2sp && (tstat.float_rounding_mode == float_round_nearest_even)) {\
-            /*                                                                \
-             * Avoid double rounding errors by rounding the intermediate      \
-             * result to odd.                                                 \
-             */                                                               \
-            set_float_rounding_mode(float_round_to_zero, &tstat);             \
-            t.fld = tp##_muladd(s1->fld, s3->fld, s2->fld,                    \
-                                maddflgs, &tstat);                            \
-            t.fld |= (get_float_exception_flags(&tstat) &                     \
-                      float_flag_inexact) != 0;                               \
-        } else {                                                              \
-            t.fld = tp##_muladd(s1->fld, s3->fld, s2->fld,                    \
-                                maddflgs, &tstat);                            \
-        }                                                                     \
+        t.fld = tp##_muladd(s1->fld, s3->fld, s2->fld, maddflgs, &tstat);     \
         env->fp_status.float_exception_flags |= tstat.float_exception_flags;  \
                                                                               \
         if (unlikely(tstat.float_exception_flags & float_flag_invalid)) {     \
@@ -2191,10 +2177,6 @@ void helper_##op(CPUPPCState *env, ppc_vsr_t *xt,                             \
                                   sfprf, GETPC());                            \
         }                                                                     \
                                                                               \
-        if (r2sp) {                                                           \
-            t.fld = do_frsp(env, t.fld, GETPC());                             \
-        }                                                                     \
-                                                                              \
         if (sfprf) {                                                          \
             helper_compute_fprf_float64(env, t.fld);                          \
         }                                                                     \
@@ -2203,24 +2185,24 @@ void helper_##op(CPUPPCState *env, ppc_vsr_t *xt,                             \
     do_float_check_status(env, GETPC());                                      \
 }
 
-VSX_MADD(XSMADDDP, 1, float64, VsrD(0), MADD_FLGS, 1, 0)
-VSX_MADD(XSMSUBDP, 1, float64, VsrD(0), MSUB_FLGS, 1, 0)
-VSX_MADD(XSNMADDDP, 1, float64, VsrD(0), NMADD_FLGS, 1, 0)
-VSX_MADD(XSNMSUBDP, 1, float64, VsrD(0), NMSUB_FLGS, 1, 0)
-VSX_MADD(XSMADDSP, 1, float64, VsrD(0), MADD_FLGS, 1, 1)
-VSX_MADD(XSMSUBSP, 1, float64, VsrD(0), MSUB_FLGS, 1, 1)
-VSX_MADD(XSNMADDSP, 1, float64, VsrD(0), NMADD_FLGS, 1, 1)
-VSX_MADD(XSNMSUBSP, 1, float64, VsrD(0), NMSUB_FLGS, 1, 1)
-
-VSX_MADD(xvmadddp, 2, float64, VsrD(i), MADD_FLGS, 0, 0)
-VSX_MADD(xvmsubdp, 2, float64, VsrD(i), MSUB_FLGS, 0, 0)
-VSX_MADD(xvnmadddp, 2, float64, VsrD(i), NMADD_FLGS, 0, 0)
-VSX_MADD(xvnmsubdp, 2, float64, VsrD(i), NMSUB_FLGS, 0, 0)
-
-VSX_MADD(xvmaddsp, 4, float32, VsrW(i), MADD_FLGS, 0, 0)
-VSX_MADD(xvmsubsp, 4, float32, VsrW(i), MSUB_FLGS, 0, 0)
-VSX_MADD(xvnmaddsp, 4, float32, VsrW(i), NMADD_FLGS, 0, 0)
-VSX_MADD(xvnmsubsp, 4, float32, VsrW(i), NMSUB_FLGS, 0, 0)
+VSX_MADD(XSMADDDP, 1, float64, VsrD(0), MADD_FLGS, 1)
+VSX_MADD(XSMSUBDP, 1, float64, VsrD(0), MSUB_FLGS, 1)
+VSX_MADD(XSNMADDDP, 1, float64, VsrD(0), NMADD_FLGS, 1)
+VSX_MADD(XSNMSUBDP, 1, float64, VsrD(0), NMSUB_FLGS, 1)
+VSX_MADD(XSMADDSP, 1, float64r32, VsrD(0), MADD_FLGS, 1)
+VSX_MADD(XSMSUBSP, 1, float64r32, VsrD(0), MSUB_FLGS, 1)
+VSX_MADD(XSNMADDSP, 1, float64r32, VsrD(0), NMADD_FLGS, 1)
+VSX_MADD(XSNMSUBSP, 1, float64r32, VsrD(0), NMSUB_FLGS, 1)
+
+VSX_MADD(xvmadddp, 2, float64, VsrD(i), MADD_FLGS, 0)
+VSX_MADD(xvmsubdp, 2, float64, VsrD(i), MSUB_FLGS, 0)
+VSX_MADD(xvnmadddp, 2, float64, VsrD(i), NMADD_FLGS, 0)
+VSX_MADD(xvnmsubdp, 2, float64, VsrD(i), NMSUB_FLGS, 0)
+
+VSX_MADD(xvmaddsp, 4, float32, VsrW(i), MADD_FLGS, 0)
+VSX_MADD(xvmsubsp, 4, float32, VsrW(i), MSUB_FLGS, 0)
+VSX_MADD(xvnmaddsp, 4, float32, VsrW(i), NMADD_FLGS, 0)
+VSX_MADD(xvnmsubsp, 4, float32, VsrW(i), NMSUB_FLGS, 0)
 
 /*
  * VSX_MADDQ - VSX floating point quad-precision muliply/add