target-ppc: VSX Stage 4: Add xsaddsp and xssubsp

This patch adds the VSX Scalar Add Single-Precision (xsaddsp) and
VSX Scalar Subtract Single-Precision (xssubsp) instructions.

The existing VSX_ADD_SUB macro is modified to support the rounding
of the (intermediate) result to single-precision.
Signed-off-by: NTom Musta <tommusta@gmail.com>
Reviewed-by: NRichard Henderson <rth@twiddle.net>
Signed-off-by: NAlexander Graf <agraf@suse.de>

target-ppc/fpu_helper.c

@@ -1768,7 +1768,7 @@ static void putVSR(int n, ppc_vsr_t *vsr, CPUPPCState *env)
  *   fld   - vsr_t field (f32 or f64)
  *   sfprf - set FPRF
  */
-#define VSX_ADD_SUB(name, op, nels, tp, fld, sfprf)                          \
+#define VSX_ADD_SUB(name, op, nels, tp, fld, sfprf, r2sp)                    \
 void helper_##name(CPUPPCState *env, uint32_t opcode)                        \
 {                                                                            \
     ppc_vsr_t xt, xa, xb;                                                    \
@@ -1794,6 +1794,10 @@ void helper_##name(CPUPPCState *env, uint32_t opcode)                        \
             }                                                                \
         }                                                                    \
                                                                              \
+        if (r2sp) {                                                          \
+            xt.fld[i] = helper_frsp(env, xt.fld[i]);                         \
+        }                                                                    \
+                                                                             \
         if (sfprf) {                                                         \
             helper_compute_fprf(env, xt.fld[i], sfprf);                      \
         }                                                                    \
@@ -1802,12 +1806,14 @@ void helper_##name(CPUPPCState *env, uint32_t opcode)                        \
     helper_float_check_status(env);                                          \
 }
 
-VSX_ADD_SUB(xsadddp, add, 1, float64, f64, 1)
-VSX_ADD_SUB(xvadddp, add, 2, float64, f64, 0)
-VSX_ADD_SUB(xvaddsp, add, 4, float32, f32, 0)
-VSX_ADD_SUB(xssubdp, sub, 1, float64, f64, 1)
-VSX_ADD_SUB(xvsubdp, sub, 2, float64, f64, 0)
-VSX_ADD_SUB(xvsubsp, sub, 4, float32, f32, 0)
+VSX_ADD_SUB(xsadddp, add, 1, float64, f64, 1, 0)
+VSX_ADD_SUB(xsaddsp, add, 1, float64, f64, 1, 1)
+VSX_ADD_SUB(xvadddp, add, 2, float64, f64, 0, 0)
+VSX_ADD_SUB(xvaddsp, add, 4, float32, f32, 0, 0)
+VSX_ADD_SUB(xssubdp, sub, 1, float64, f64, 1, 0)
+VSX_ADD_SUB(xssubsp, sub, 1, float64, f64, 1, 1)
+VSX_ADD_SUB(xvsubdp, sub, 2, float64, f64, 0, 0)
+VSX_ADD_SUB(xvsubsp, sub, 4, float32, f32, 0, 0)
 
 /* VSX_MUL - VSX floating point multiply
  *   op    - instruction mnemonic

target-ppc/helper.h

@@ -286,6 +286,9 @@ DEF_HELPER_2(xsrdpim, void, env, i32)
 DEF_HELPER_2(xsrdpip, void, env, i32)
 DEF_HELPER_2(xsrdpiz, void, env, i32)
 
+DEF_HELPER_2(xsaddsp, void, env, i32)
+DEF_HELPER_2(xssubsp, void, env, i32)
+
 DEF_HELPER_2(xvadddp, void, env, i32)
 DEF_HELPER_2(xvsubdp, void, env, i32)
 DEF_HELPER_2(xvmuldp, void, env, i32)

target-ppc/translate.c

@@ -7358,6 +7358,9 @@ GEN_VSX_HELPER_2(xsrdpim, 0x12, 0x07, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsrdpip, 0x12, 0x06, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsrdpiz, 0x12, 0x05, 0, PPC2_VSX)
 
+GEN_VSX_HELPER_2(xsaddsp, 0x00, 0x00, 0, PPC2_VSX207)
+GEN_VSX_HELPER_2(xssubsp, 0x00, 0x01, 0, PPC2_VSX207)
+
 GEN_VSX_HELPER_2(xvadddp, 0x00, 0x0C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvmuldp, 0x00, 0x0E, 0, PPC2_VSX)
@@ -10164,6 +10167,9 @@ GEN_XX2FORM(xsrdpim, 0x12, 0x07, PPC2_VSX),
 GEN_XX2FORM(xsrdpip, 0x12, 0x06, PPC2_VSX),
 GEN_XX2FORM(xsrdpiz, 0x12, 0x05, PPC2_VSX),
 
+GEN_XX3FORM(xsaddsp, 0x00, 0x00, PPC2_VSX207),
+GEN_XX3FORM(xssubsp, 0x00, 0x01, PPC2_VSX207),
+
 GEN_XX3FORM(xvadddp, 0x00, 0x0C, PPC2_VSX),
 GEN_XX3FORM(xvsubdp, 0x00, 0x0D, PPC2_VSX),
 GEN_XX3FORM(xvmuldp, 0x00, 0x0E, PPC2_VSX),