Patchwork [08/14] VSX Stage 4: Add xsdivsp

login
register
mail settings
Submitter Tom Musta
Date Nov. 6, 2013, 8:31 p.m.
Message ID <1383769916-5582-9-git-send-email-tommusta@gmail.com>
Download mbox | patch
Permalink /patch/289010/
State New
Headers show

Comments

Tom Musta - Nov. 6, 2013, 8:31 p.m.
This patch adds the VSX Scalar Divide Single Precision (xsdivsp)
instruction.

The existing VSX_DIV 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 e5127b2..1133591 100644
--- a/target-ppc/fpu_helper.c
+++ b/target-ppc/fpu_helper.c
@@ -1876,7 +1876,7 @@  VSX_MUL(xvmulsp, 4, float32, f32, 0, 0)
  *   fld   - vsr_t field (f32 or f64)
  *   sfprf - set FPRF
  */
-#define VSX_DIV(op, nels, tp, fld, sfprf)                                     \
+#define VSX_DIV(op, nels, tp, fld, sfprf, r2sp)                               \
 void helper_##op(CPUPPCState *env, uint32_t opcode)                           \
 {                                                                             \
     ppc_vsr_t xt, xa, xb;                                                     \
@@ -1905,6 +1905,11 @@  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);                       \
         }                                                                     \
@@ -1914,9 +1919,10 @@  void helper_##op(CPUPPCState *env, uint32_t opcode)                           \
     helper_float_check_status(env);                                           \
 }
 
-VSX_DIV(xsdivdp, 1, float64, f64, 1)
-VSX_DIV(xvdivdp, 2, float64, f64, 0)
-VSX_DIV(xvdivsp, 4, float32, f32, 0)
+VSX_DIV(xsdivdp, 1, float64, f64, 1, 0)
+VSX_DIV(xsdivsp, 1, float64, f64, 1, 1)
+VSX_DIV(xvdivdp, 2, float64, f64, 0, 0)
+VSX_DIV(xvdivsp, 4, float32, f32, 0, 0)
 
 /* VSX_RE  - VSX floating point reciprocal estimate
  *   op    - instruction mnemonic
diff --git a/target-ppc/helper.h b/target-ppc/helper.h
index 0ccdc96..308f97c 100644
--- a/target-ppc/helper.h
+++ b/target-ppc/helper.h
@@ -289,6 +289,7 @@  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(xsdivsp, 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 450ab88..896dbc2 100644
--- a/target-ppc/translate.c
+++ b/target-ppc/translate.c
@@ -7344,6 +7344,7 @@  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(xsdivsp, 0x00, 0x03, 0, PPC2_VSX207)
 
 GEN_VSX_HELPER_2(xvadddp, 0x00, 0x0C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX)
@@ -10155,6 +10156,7 @@  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(xsdivsp, 0x00, 0x03, PPC2_VSX207),
 
 GEN_XX3FORM(xvadddp, 0x00, 0x0C, PPC2_VSX),
 GEN_XX3FORM(xvsubdp, 0x00, 0x0D, PPC2_VSX),