target-ppc: VSX Stage 4: Add xssqrtsp

This patch adds the VSX Scalar Square Root Single Precision (xssqrtsp)
instruction.

The existing VSX_SQRT() macro is modified to support rounding of the
intermediate double-precision result to single-precision.

Signed-off-by: Tom Musta <tommusta@gmail.com>
Reviewed-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Alexander Graf <agraf@suse.de>

diff --git a/target-ppc/fpu_helper.c b/target-ppc/fpu_helper.c
index ac52c23ee36894b36ad707a1a14652717fef4b8f..fec9d1b15f732350e5c7bb67fc0457a8bd14c9fa 100644 (file)
--- a/target-ppc/fpu_helper.c
+++ b/target-ppc/fpu_helper.c
@@ -1969,7 +1969,7 @@ VSX_RE(xvresp, 4, float32, f32, 0, 0)
  *   fld   - vsr_t field (f32 or f64)
  *   sfprf - set FPRF
  */
-#define VSX_SQRT(op, nels, tp, fld, sfprf)                                   \
+#define VSX_SQRT(op, nels, tp, fld, sfprf, r2sp)                             \
 void helper_##op(CPUPPCState *env, uint32_t opcode)                          \
 {                                                                            \
     ppc_vsr_t xt, xb;                                                        \
@@ -1993,6 +1993,10 @@ 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);                      \
         }                                                                    \
@@ -2002,9 +2006,10 @@ void helper_##op(CPUPPCState *env, uint32_t opcode)                          \
     helper_float_check_status(env);                                          \
 }
 
-VSX_SQRT(xssqrtdp, 1, float64, f64, 1)
-VSX_SQRT(xvsqrtdp, 2, float64, f64, 0)
-VSX_SQRT(xvsqrtsp, 4, float32, f32, 0)
+VSX_SQRT(xssqrtdp, 1, float64, f64, 1, 0)
+VSX_SQRT(xssqrtsp, 1, float64, f64, 1, 1)
+VSX_SQRT(xvsqrtdp, 2, float64, f64, 0, 0)
+VSX_SQRT(xvsqrtsp, 4, float32, f32, 0, 0)
 
 /* VSX_RSQRTE - VSX floating point reciprocal square root estimate
  *   op    - instruction mnemonic

diff --git a/target-ppc/helper.h b/target-ppc/helper.h
index b1cf3c00e0a0acfb650b463ef66ce673450fd55d..0192043c30e18be80f8c5d25f618fd407b7c8a89 100644 (file)
--- a/target-ppc/helper.h
+++ b/target-ppc/helper.h
@@ -291,6 +291,7 @@ DEF_HELPER_2(xssubsp, void, env, i32)
 DEF_HELPER_2(xsmulsp, void, env, i32)
 DEF_HELPER_2(xsdivsp, void, env, i32)
 DEF_HELPER_2(xsresp, void, env, i32)
+DEF_HELPER_2(xssqrtsp, void, env, i32)
 
 DEF_HELPER_2(xvadddp, void, env, i32)
 DEF_HELPER_2(xvsubdp, void, env, i32)

diff --git a/target-ppc/translate.c b/target-ppc/translate.c
index 0dd6220ccfa76937126f0db0109ead63e098e36e..13099fc79933622cef02abde3b8c856f01eb2552 100644 (file)
--- a/target-ppc/translate.c
+++ b/target-ppc/translate.c
@@ -7363,6 +7363,7 @@ GEN_VSX_HELPER_2(xssubsp, 0x00, 0x01, 0, PPC2_VSX207)
 GEN_VSX_HELPER_2(xsmulsp, 0x00, 0x02, 0, PPC2_VSX207)
 GEN_VSX_HELPER_2(xsdivsp, 0x00, 0x03, 0, PPC2_VSX207)
 GEN_VSX_HELPER_2(xsresp, 0x14, 0x01, 0, PPC2_VSX207)
+GEN_VSX_HELPER_2(xssqrtsp, 0x16, 0x00, 0, PPC2_VSX207)
 
 GEN_VSX_HELPER_2(xvadddp, 0x00, 0x0C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX)
@@ -10175,6 +10176,7 @@ GEN_XX3FORM(xssubsp, 0x00, 0x01, PPC2_VSX207),
 GEN_XX3FORM(xsmulsp, 0x00, 0x02, PPC2_VSX207),
 GEN_XX3FORM(xsdivsp, 0x00, 0x03, PPC2_VSX207),
 GEN_XX2FORM(xsresp,  0x14, 0x01, PPC2_VSX207),
+GEN_XX2FORM(xssqrtsp,  0x16, 0x00, PPC2_VSX207),
 
 GEN_XX3FORM(xvadddp, 0x00, 0x0C, PPC2_VSX),
 GEN_XX3FORM(xvsubdp, 0x00, 0x0D, PPC2_VSX),