Re: [Qemu-devel] [PATCH 10/19] Add VSX ISA2.06 xrsqrte Instructions

2013-10-24 Thread Richard Henderson
On 10/24/2013 09:23 AM, Tom Musta wrote:
> This patch adds the VSX floating point reciprocal square root
> estimate instructions defined by V2.06 of the PowerPC ISA: xsrsqrtedp,
> xvrsqrtedp, xvrsqrtesp.
> 
> Signed-off-by: Tom Musta 
> ---

Reviewed-by: Richard Henderson 


r~



[Qemu-devel] [PATCH 10/19] Add VSX ISA2.06 xrsqrte Instructions

2013-10-24 Thread Tom Musta

This patch adds the VSX floating point reciprocal square root
estimate instructions defined by V2.06 of the PowerPC ISA: xsrsqrtedp,
xvrsqrtedp, xvrsqrtesp.

Signed-off-by: Tom Musta 
---
 target-ppc/fpu_helper.c |   44 
 target-ppc/helper.h |3 +++
 target-ppc/translate.c  |6 ++
 3 files changed, 53 insertions(+), 0 deletions(-)

diff --git a/target-ppc/fpu_helper.c b/target-ppc/fpu_helper.c
index d03e8f9..902cb76 100644
--- a/target-ppc/fpu_helper.c
+++ b/target-ppc/fpu_helper.c
@@ -2027,3 +2027,47 @@ void helper_##op(CPUPPCState *env, uint32_t opcode)  
 \
 VSX_SQRT(xssqrtdp, 1, float64, f64, 1)
 VSX_SQRT(xvsqrtdp, 2, float64, f64, 0)
 VSX_SQRT(xvsqrtsp, 4, float32, f32, 0)
+
+/* VSX_RSQRTE - VSX floating point reciprocal square root estimate
+ *   op- instruction mnemonic
+ *   nels  - number of elements (1, 2 or 4)
+ *   tp- type (float32 or float64)
+ *   fld   - vsr_t field (f32 or f64)
+ *   sfprf - set FPRF
+ */
+#define VSX_RSQRTE(op, nels, tp, fld, sfprf)  \
+void helper_##op(CPUPPCState *env, uint32_t opcode)   \
+{ \
+ppc_vsr_t xt, xb; \
+int i;\
+  \
+getVSR(xB(opcode), &xb, env); \
+getVSR(xT(opcode), &xt, env); \
+helper_reset_fpstatus(env);   \
+  \
+for (i = 0; i < nels; i++) {  \
+if (unlikely(tp##_is_neg(xb.fld[i]) &&\
+!tp##_is_zero(xb.fld[i]))) {  \
+xt.fld[i] = float64_to_##tp(  \
+fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSQRT,\
+  sfprf), \
+&env->fp_status); \
+} else {  \
+if (unlikely(tp##_is_signaling_nan(xb.fld[i]))) { \
+fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, sfprf);\
+} \
+xt.fld[i] = tp##_sqrt(xb.fld[i], &env->fp_status);\
+xt.fld[i] = tp##_div(tp##_one, xt.fld[i], &env->fp_status);   \
+if (sfprf) {  \
+helper_compute_fprf(env, xt.fld[0], sfprf);   \
+} \
+} \
+} \
+  \
+putVSR(xT(opcode), &xt, env); \
+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)
diff --git a/target-ppc/helper.h b/target-ppc/helper.h
index 27ca4e5..02ea86c 100644
--- a/target-ppc/helper.h
+++ b/target-ppc/helper.h
@@ -257,6 +257,7 @@ DEF_HELPER_2(xsmuldp, void, env, i32)
 DEF_HELPER_2(xsdivdp, void, env, i32)
 DEF_HELPER_2(xsredp, void, env, i32)
 DEF_HELPER_2(xssqrtdp, void, env, i32)
+DEF_HELPER_2(xsrsqrtedp, void, env, i32)

 DEF_HELPER_2(xvadddp, void, env, i32)
 DEF_HELPER_2(xvsubdp, void, env, i32)
@@ -264,6 +265,7 @@ DEF_HELPER_2(xvmuldp, void, env, i32)
 DEF_HELPER_2(xvdivdp, void, env, i32)
 DEF_HELPER_2(xvredp, void, env, i32)
 DEF_HELPER_2(xvsqrtdp, void, env, i32)
+DEF_HELPER_2(xvrsqrtedp, void, env, i32)

 DEF_HELPER_2(xvaddsp, void, env, i32)
 DEF_HELPER_2(xvsubsp, void, env, i32)
@@ -271,6 +273,7 @@ DEF_HELPER_2(xvmulsp, void, env, i32)
 DEF_HELPER_2(xvdivsp, void, env, i32)
 DEF_HELPER_2(xvresp, void, env, i32)
 DEF_HELPER_2(xvsqrtsp, void, env, i32)
+DEF_HELPER_2(xvrsqrtesp, void, env, i32)

 DEF_HELPER_2(efscfsi, i32, env, i32)
 DEF_HELPER_2(efscfui, i32, env, i32)
diff --git a/target-ppc/translate.c b/target-ppc/translate.c
index 66cbad1..b5253fc 100644
--- a/target-ppc/translate.c
+++ b/target-ppc/translate.c
@@ -7299,6 +7299,7 @@ GEN_VSX_HELPER_2(xsmuldp, 0x00, 0x06, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsdivdp, 0x00, 0x07, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsredp, 0