target-ppc: VSX Stage 4: Add xsmulsp

This patch adds the VSX Scalar Multiply Single-Precision (xsmulsp)
instruction.

The existing VSX_MUL macro is modified to support 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

@@ -1822,7 +1822,7 @@ VSX_ADD_SUB(xvsubsp, sub, 4, float32, f32, 0, 0)
  *   fld   - vsr_t field (f32 or f64)
  *   sfprf - set FPRF
  */
-#define VSX_MUL(op, nels, tp, fld, sfprf)                                    \
+#define VSX_MUL(op, nels, tp, fld, sfprf, r2sp)                              \
 void helper_##op(CPUPPCState *env, uint32_t opcode)                          \
 {                                                                            \
     ppc_vsr_t xt, xa, xb;                                                    \
@@ -1849,6 +1849,10 @@ void helper_##op(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);                      \
         }                                                                    \
@@ -1858,9 +1862,10 @@ void helper_##op(CPUPPCState *env, uint32_t opcode)                          \
     helper_float_check_status(env);                                          \
 }
 
-VSX_MUL(xsmuldp, 1, float64, f64, 1)
-VSX_MUL(xvmuldp, 2, float64, f64, 0)
-VSX_MUL(xvmulsp, 4, float32, f32, 0)
+VSX_MUL(xsmuldp, 1, float64, f64, 1, 0)
+VSX_MUL(xsmulsp, 1, float64, f64, 1, 1)
+VSX_MUL(xvmuldp, 2, float64, f64, 0, 0)
+VSX_MUL(xvmulsp, 4, float32, f32, 0, 0)
 
 /* VSX_DIV - VSX floating point divide
  *   op    - instruction mnemonic

target-ppc/helper.h

@@ -288,6 +288,7 @@ DEF_HELPER_2(xsrdpiz, void, env, i32)
 
 DEF_HELPER_2(xsaddsp, void, env, i32)
 DEF_HELPER_2(xssubsp, void, env, i32)
+DEF_HELPER_2(xsmulsp, void, env, i32)
 
 DEF_HELPER_2(xvadddp, void, env, i32)
 DEF_HELPER_2(xvsubdp, void, env, i32)

target-ppc/translate.c

@@ -7360,6 +7360,7 @@ 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(xsmulsp, 0x00, 0x02, 0, PPC2_VSX207)
 
 GEN_VSX_HELPER_2(xvadddp, 0x00, 0x0C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX)
@@ -10169,6 +10170,7 @@ GEN_XX2FORM(xsrdpiz, 0x12, 0x05, PPC2_VSX),
 
 GEN_XX3FORM(xsaddsp, 0x00, 0x00, PPC2_VSX207),
 GEN_XX3FORM(xssubsp, 0x00, 0x01, PPC2_VSX207),
+GEN_XX3FORM(xsmulsp, 0x00, 0x02, PPC2_VSX207),
 
 GEN_XX3FORM(xvadddp, 0x00, 0x0C, PPC2_VSX),
 GEN_XX3FORM(xvsubdp, 0x00, 0x0D, PPC2_VSX),