Patchwork [11/14] VSX Stage 4: add xsrsqrtesp

login
register
mail settings
Submitter Tom Musta
Date Nov. 6, 2013, 8:31 p.m.
Message ID <1383769916-5582-12-git-send-email-tommusta@gmail.com>
Download mbox | patch
Permalink /patch/289022/
State New
Headers show

Comments

Tom Musta - Nov. 6, 2013, 8:31 p.m.
This patch adds the VSX Scalar Reciprocal Square Root Estimate
Single Precision (xsrsqrtesp) instruction.

The existing VSX_RSQRTE() 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 c4e52ea..e08f317 100644
--- a/target-ppc/fpu_helper.c
+++ b/target-ppc/fpu_helper.c
@@ -2023,7 +2023,7 @@  VSX_SQRT(xvsqrtsp, 4, float32, f32, 0, 0)
  *   fld   - vsr_t field (f32 or f64)
  *   sfprf - set FPRF
  */
-#define VSX_RSQRTE(op, nels, tp, fld, sfprf)                                 \
+#define VSX_RSQRTE(op, nels, tp, fld, sfprf, r2sp)                           \
 void helper_##op(CPUPPCState *env, uint32_t opcode)                          \
 {                                                                            \
     ppc_vsr_t xt, xb;                                                        \
@@ -2048,6 +2048,11 @@  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);                      \
         }                                                                    \
@@ -2057,9 +2062,10 @@  void helper_##op(CPUPPCState *env, uint32_t opcode)                          \
     helper_float_check_status(env);                                          \
 }
 
-VSX_RSQRTE(xsrsqrtedp, 1, float64, f64, 1)
-VSX_RSQRTE(xvrsqrtedp, 2, float64, f64, 0)
-VSX_RSQRTE(xvrsqrtesp, 4, float32, f32, 0)
+VSX_RSQRTE(xsrsqrtedp, 1, float64, f64, 1, 0)
+VSX_RSQRTE(xsrsqrtesp, 1, float64, f64, 1, 1)
+VSX_RSQRTE(xvrsqrtedp, 2, float64, f64, 0, 0)
+VSX_RSQRTE(xvrsqrtesp, 4, float32, f32, 0, 0)
 
 static inline int ppc_float32_get_unbiased_exp(float32 f)
 {
diff --git a/target-ppc/helper.h b/target-ppc/helper.h
index 0192043..84c6ee1 100644
--- a/target-ppc/helper.h
+++ b/target-ppc/helper.h
@@ -292,6 +292,7 @@  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(xsrsqrtesp, 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 b9cd35b..ae80289 100644
--- a/target-ppc/translate.c
+++ b/target-ppc/translate.c
@@ -7347,6 +7347,7 @@  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(xsrsqrtesp, 0x14, 0x00, 0, PPC2_VSX207)
 
 GEN_VSX_HELPER_2(xvadddp, 0x00, 0x0C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX)
@@ -10161,6 +10162,7 @@  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_XX2FORM(xsrsqrtesp,  0x14, 0x00, PPC2_VSX207),
 
 GEN_XX3FORM(xvadddp, 0x00, 0x0C, PPC2_VSX),
 GEN_XX3FORM(xvsubdp, 0x00, 0x0D, PPC2_VSX),