[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-ppc] [V4 PATCH 13/22] target-ppc: Add VSX ISA2.06 xrsqrte Instruct
From: |
Tom Musta |
Subject: |
[Qemu-ppc] [V4 PATCH 13/22] target-ppc: Add VSX ISA2.06 xrsqrte Instructions |
Date: |
Wed, 18 Dec 2013 14:19:12 -0600 |
This patch adds the VSX floating point reciprocal square root
estimate instructions defined by V2.06 of the PowerPC ISA: xsrsqrtedp,
xvrsqrtedp, xvrsqrtesp.
V2: re-implemented VSX_RSQRTE macro.
Signed-off-by: Tom Musta <address@hidden>
Reviewed-by: Richard Henderson <address@hidden>
---
target-ppc/fpu_helper.c | 45 +++++++++++++++++++++++++++++++++++++++++++++
target-ppc/helper.h | 3 +++
target-ppc/translate.c | 6 ++++++
3 files changed, 54 insertions(+), 0 deletions(-)
diff --git a/target-ppc/fpu_helper.c b/target-ppc/fpu_helper.c
index 060e6a0..31669f1 100644
--- a/target-ppc/fpu_helper.c
+++ b/target-ppc/fpu_helper.c
@@ -1983,3 +1983,48 @@ 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++) { \
+ float_status tstat = env->fp_status; \
+ set_float_exception_flags(0, &tstat); \
+ xt.fld[i] = tp##_sqrt(xb.fld[i], &tstat); \
+ xt.fld[i] = tp##_div(tp##_one, xt.fld[i], &tstat); \
+ env->fp_status.float_exception_flags |= tstat.float_exception_flags; \
+ \
+ if (unlikely(tstat.float_exception_flags & float_flag_invalid)) { \
+ if (tp##_is_neg(xb.fld[i]) && !tp##_is_zero(xb.fld[i])) { \
+ fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSQRT, sfprf); \
+ } else if (tp##_is_signaling_nan(xb.fld[i])) { \
+ fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, sfprf); \
+ } \
+ } \
+ \
+ if (sfprf) { \
+ helper_compute_fprf(env, xt.fld[i], 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 a6e7e62..4d5e31b 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 c5c97ba..287b924 100644
--- a/target-ppc/translate.c
+++ b/target-ppc/translate.c
@@ -7301,6 +7301,7 @@ 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, 0x14, 0x05, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xssqrtdp, 0x16, 0x04, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xsrsqrtedp, 0x14, 0x04, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvadddp, 0x00, 0x0C, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX)
@@ -7308,6 +7309,7 @@ GEN_VSX_HELPER_2(xvmuldp, 0x00, 0x0E, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvdivdp, 0x00, 0x0F, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvredp, 0x14, 0x0D, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvsqrtdp, 0x16, 0x0C, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvrsqrtedp, 0x14, 0x0C, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvaddsp, 0x00, 0x08, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvsubsp, 0x00, 0x09, 0, PPC2_VSX)
@@ -7315,6 +7317,7 @@ GEN_VSX_HELPER_2(xvmulsp, 0x00, 0x0A, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvdivsp, 0x00, 0x0B, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvresp, 0x14, 0x09, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvsqrtsp, 0x16, 0x08, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvrsqrtesp, 0x14, 0x08, 0, PPC2_VSX)
#define VSX_LOGICAL(name, tcg_op) \
static void glue(gen_, name)(DisasContext * ctx) \
@@ -10004,6 +10007,7 @@ GEN_XX3FORM(xsmuldp, 0x00, 0x06, PPC2_VSX),
GEN_XX3FORM(xsdivdp, 0x00, 0x07, PPC2_VSX),
GEN_XX2FORM(xsredp, 0x14, 0x05, PPC2_VSX),
GEN_XX2FORM(xssqrtdp, 0x16, 0x04, PPC2_VSX),
+GEN_XX2FORM(xsrsqrtedp, 0x14, 0x04, PPC2_VSX),
GEN_XX3FORM(xvadddp, 0x00, 0x0C, PPC2_VSX),
GEN_XX3FORM(xvsubdp, 0x00, 0x0D, PPC2_VSX),
@@ -10011,6 +10015,7 @@ GEN_XX3FORM(xvmuldp, 0x00, 0x0E, PPC2_VSX),
GEN_XX3FORM(xvdivdp, 0x00, 0x0F, PPC2_VSX),
GEN_XX2FORM(xvredp, 0x14, 0x0D, PPC2_VSX),
GEN_XX2FORM(xvsqrtdp, 0x16, 0x0C, PPC2_VSX),
+GEN_XX2FORM(xvrsqrtedp, 0x14, 0x0C, PPC2_VSX),
GEN_XX3FORM(xvaddsp, 0x00, 0x08, PPC2_VSX),
GEN_XX3FORM(xvsubsp, 0x00, 0x09, PPC2_VSX),
@@ -10018,6 +10023,7 @@ GEN_XX3FORM(xvmulsp, 0x00, 0x0A, PPC2_VSX),
GEN_XX3FORM(xvdivsp, 0x00, 0x0B, PPC2_VSX),
GEN_XX2FORM(xvresp, 0x14, 0x09, PPC2_VSX),
GEN_XX2FORM(xvsqrtsp, 0x16, 0x08, PPC2_VSX),
+GEN_XX2FORM(xvrsqrtesp, 0x14, 0x08, PPC2_VSX),
#undef VSX_LOGICAL
#define VSX_LOGICAL(name, opc2, opc3, fl2) \
--
1.7.1
- [Qemu-ppc] [V4 PATCH 05/22] softfloat: Fix float64_to_uint32_round_to_zero, (continued)
- [Qemu-ppc] [V4 PATCH 05/22] softfloat: Fix float64_to_uint32_round_to_zero, Tom Musta, 2013/12/18
- [Qemu-ppc] [V4 PATCH 06/22] target-ppc: Add set_fprf Argument to fload_invalid_op_excp(), Tom Musta, 2013/12/18
- [Qemu-ppc] [V4 PATCH 07/22] target-ppc: General Support for VSX Helpers, Tom Musta, 2013/12/18
- [Qemu-ppc] [V4 PATCH 08/22] target-ppc: Add VSX ISA2.06 xadd/xsub Instructions, Tom Musta, 2013/12/18
- [Qemu-ppc] [V4 PATCH 10/22] target-ppc: Add VSX ISA2.06 xdiv Instructions, Tom Musta, 2013/12/18
- [Qemu-ppc] [V4 PATCH 09/22] target-ppc: Add VSX ISA2.06 xmul Instructions, Tom Musta, 2013/12/18
- [Qemu-ppc] [V4 PATCH 12/22] target-ppc: Add VSX ISA2.06 xsqrt Instructions, Tom Musta, 2013/12/18
- [Qemu-ppc] [V4 PATCH 11/22] target-ppc: Add VSX ISA2.06 xre Instructions, Tom Musta, 2013/12/18
- [Qemu-ppc] [V4 PATCH 16/22] target-ppc: Add VSX ISA2.06 Multiply Add Instructions, Tom Musta, 2013/12/18
- [Qemu-ppc] [V4 PATCH 13/22] target-ppc: Add VSX ISA2.06 xrsqrte Instructions,
Tom Musta <=
- [Qemu-ppc] [V4 PATCH 14/22] target-ppc: Add VSX ISA2.06 xtdiv Instructions, Tom Musta, 2013/12/18
- [Qemu-ppc] [V4 PATCH 17/22] target-ppc: Add VSX xscmp*dp Instructions, Tom Musta, 2013/12/18
- [Qemu-ppc] [V4 PATCH 18/22] target-ppc: Add VSX xmax/xmin Instructions, Tom Musta, 2013/12/18
- [Qemu-ppc] [V4 PATCH 19/22] target-ppc: Add VSX Vector Compare Instructions, Tom Musta, 2013/12/18
- [Qemu-ppc] [V4 PATCH 15/22] target-ppc: Add VSX ISA2.06 xtsqrt Instructions, Tom Musta, 2013/12/18
- [Qemu-ppc] [V4 PATCH 20/22] target-ppc: Add VSX Floating Point to Floating Point Conversion Instructions, Tom Musta, 2013/12/18
- [Qemu-ppc] [V4 PATCH 21/22] target-ppc: Add VSX ISA2.06 Integer Conversion Instructions, Tom Musta, 2013/12/18
- [Qemu-ppc] [V4 PATCH 22/22] target-ppc: Add VSX Rounding Instructions, Tom Musta, 2013/12/18