Patchwork [10/14] VSX Stage 4: Add xssqrtsp

login
register
mail settings
Submitter Tom Musta
Date Nov. 6, 2013, 8:31 p.m.
Message ID <1383769916-5582-11-git-send-email-tommusta@gmail.com>
Download mbox | patch
Permalink /patch/289023/
State New
Headers show

Comments

Tom Musta - Nov. 6, 2013, 8:31 p.m.
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>
---
 target-ppc/fpu_helper.c |   14 ++++++++++----
 target-ppc/helper.h     |    1 +
 target-ppc/translate.c  |    2 ++
 3 files changed, 13 insertions(+), 4 deletions(-)

Patch

diff --git a/target-ppc/fpu_helper.c b/target-ppc/fpu_helper.c
index 862f855..c4e52ea 100644
--- a/target-ppc/fpu_helper.c
+++ b/target-ppc/fpu_helper.c
@@ -1973,7 +1973,7 @@  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;                                                        \
@@ -1997,6 +1997,11 @@  void helper_##op(CPUPPCState *env, uint32_t opcode)                          \
             }                                                                \
         }                                                                    \
                                                                              \
+        if (r2sp) {                                                          \
+            float32 tmp32 = float64_to_float32(xt.fld[i], &env->fp_status);  \
+            xt.fld[i] = float32_to_float64(tmp32, &env->fp_status);          \
+        }                                                                    \
+                                                                             \
         if (sfprf) {                                                         \
             helper_compute_fprf(env, xt.fld[i], sfprf);                      \
         }                                                                    \
@@ -2006,9 +2011,10 @@  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 b1cf3c0..0192043 100644
--- 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 c4c57a1..b9cd35b 100644
--- a/target-ppc/translate.c
+++ b/target-ppc/translate.c
@@ -7346,6 +7346,7 @@  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)
@@ -10159,6 +10160,7 @@  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),