[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [PATCH] target-ppc: Add quad precision muladd instructions
|
From: |
Bharata B Rao |
|
Subject: |
[Qemu-devel] [PATCH] target-ppc: Add quad precision muladd instructions |
|
Date: |
Wed, 15 Feb 2017 12:07:16 +0530 |
xsmaddqp: VSX Scalar Multiply-Add Quad-Precision
xsmaddqpo: VSX Scalar Multiply-Add Quad-Precision using round to Odd
xsnmaddqp: VSX Scalar Negative Multiply-Add Quad-Precision
xsnmaddqpo: VSX Scalar Negative Multiply-Add Quad-Precision using round to Odd
xsmsubqp: VSX Scalar Multiply-Subtract Quad-Precision
xsmsubqpo: VSX Scalar Multiply-Subtract Quad-Precision using round to Odd
xsnmsubqp: VSX Scalar Negative Multiply-Subtract Quad-Precision
xsnmsubqpo: VSX Scalar Negative Multiply-Subtract Quad-Precision
using round to Odd
Signed-off-by: Bharata B Rao <address@hidden>
---
target/ppc/fpu_helper.c | 69 +++++++++++++++++++++++++++++++++++++
target/ppc/helper.h | 4 +++
target/ppc/translate/vsx-impl.inc.c | 4 +++
target/ppc/translate/vsx-ops.inc.c | 4 +++
4 files changed, 81 insertions(+)
diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c
index 58aee64..201cafd 100644
--- a/target/ppc/fpu_helper.c
+++ b/target/ppc/fpu_helper.c
@@ -2425,6 +2425,75 @@ VSX_MADD(xvnmaddmsp, 4, float32, VsrW(i), NMADD_FLGS, 0,
0, 0)
VSX_MADD(xvnmsubasp, 4, float32, VsrW(i), NMSUB_FLGS, 1, 0, 0)
VSX_MADD(xvnmsubmsp, 4, float32, VsrW(i), NMSUB_FLGS, 0, 0, 0)
+/*
+ * Quadruple-precision version of multiply and add/subtract.
+ *
+ * This implementation is not 100% accurate as we truncate the
+ * intermediate result of multiplication and then add/subtract
+ * separately.
+ *
+ * TODO: When float128_muladd() becomes available, switch this
+ * implementation to use that instead of separate float128_mul()
+ * followed by float128_add().
+ */
+#define VSX_MADD_QP(op, maddflgs) \
+void helper_##op(CPUPPCState *env, uint32_t opcode) \
+{ \
+ ppc_vsr_t xt_in, xa, xb, xt_out; \
+ \
+ getVSR(rA(opcode) + 32, &xa, env); \
+ getVSR(rB(opcode) + 32, &xb, env); \
+ getVSR(rD(opcode) + 32, &xt_in, env); \
+ \
+ xt_out = xt_in; \
+ helper_reset_fpstatus(env); \
+ float_status tstat = env->fp_status; \
+ if (unlikely(Rc(opcode) != 0)) { \
+ tstat.float_rounding_mode = float_round_to_odd; \
+ } \
+ set_float_exception_flags(0, &tstat); \
+ xt_out.f128 = float128_mul(xa.f128, xt_in.f128, &tstat); \
+ \
+ if (maddflgs & float_muladd_negate_c) { \
+ xb.VsrD(0) ^= 0x8000000000000000; \
+ } \
+ xt_out.f128 = float128_add(xt_out.f128, xb.f128, &tstat); \
+ env->fp_status.float_exception_flags |= tstat.float_exception_flags; \
+ \
+ if (unlikely(tstat.float_exception_flags & float_flag_invalid)) { \
+ if (float128_is_signaling_nan(xa.f128, &tstat) || \
+ float128_is_signaling_nan(xt_in.f128, &tstat) || \
+ float128_is_signaling_nan(xb.f128, &tstat)) { \
+ float_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 1); \
+ tstat.float_exception_flags &= ~float_flag_invalid; \
+ } \
+ if ((float128_is_infinity(xa.f128) && float128_is_zero(xt_in.f128)) ||\
+ (float128_is_zero(xa.f128) && float128_is_infinity(xt_in.f128))) {\
+ float_invalid_op_excp(env, POWERPC_EXCP_FP_VXIMZ, 1); \
+ tstat.float_exception_flags &= ~float_flag_invalid; \
+ } \
+ if ((tstat.float_exception_flags & float_flag_invalid) && \
+ ((float128_is_infinity(xa.f128) || \
+ float128_is_infinity(xt_in.f128)) && \
+ float128_is_infinity(xb.f128))) { \
+ float_invalid_op_excp(env, POWERPC_EXCP_FP_VXISI, 1); \
+ } \
+ } \
+ \
+ helper_compute_fprf_float128(env, xt_out.f128); \
+ if ((maddflgs & float_muladd_negate_result) && \
+ !float128_is_any_nan(xt_out.f128)) { \
+ xt_out.VsrD(0) ^= 0x8000000000000000; \
+ } \
+ putVSR(rD(opcode) + 32, &xt_out, env); \
+ float_check_status(env); \
+}
+
+VSX_MADD_QP(xsmaddqp, MADD_FLGS)
+VSX_MADD_QP(xsmsubqp, MSUB_FLGS)
+VSX_MADD_QP(xsnmaddqp, NMADD_FLGS)
+VSX_MADD_QP(xsnmsubqp, NMSUB_FLGS)
+
/* VSX_SCALAR_CMP_DP - VSX scalar floating point compare double precision
* op - instruction mnemonic
* cmp - comparison operation
diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index 6d77661..eade946 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -480,12 +480,16 @@ DEF_HELPER_2(xssqrtsp, void, env, i32)
DEF_HELPER_2(xsrsqrtesp, void, env, i32)
DEF_HELPER_2(xsmaddasp, void, env, i32)
DEF_HELPER_2(xsmaddmsp, void, env, i32)
+DEF_HELPER_2(xsmaddqp, void, env, i32)
DEF_HELPER_2(xsmsubasp, void, env, i32)
DEF_HELPER_2(xsmsubmsp, void, env, i32)
+DEF_HELPER_2(xsmsubqp, void, env, i32)
DEF_HELPER_2(xsnmaddasp, void, env, i32)
DEF_HELPER_2(xsnmaddmsp, void, env, i32)
+DEF_HELPER_2(xsnmaddqp, void, env, i32)
DEF_HELPER_2(xsnmsubasp, void, env, i32)
DEF_HELPER_2(xsnmsubmsp, void, env, i32)
+DEF_HELPER_2(xsnmsubqp, void, env, i32)
DEF_HELPER_2(xvadddp, void, env, i32)
DEF_HELPER_2(xvsubdp, void, env, i32)
diff --git a/target/ppc/translate/vsx-impl.inc.c
b/target/ppc/translate/vsx-impl.inc.c
index 7f12908..0a96e6b 100644
--- a/target/ppc/translate/vsx-impl.inc.c
+++ b/target/ppc/translate/vsx-impl.inc.c
@@ -853,12 +853,16 @@ GEN_VSX_HELPER_2(xssqrtsp, 0x16, 0x00, 0, PPC2_VSX207)
GEN_VSX_HELPER_2(xsrsqrtesp, 0x14, 0x00, 0, PPC2_VSX207)
GEN_VSX_HELPER_2(xsmaddasp, 0x04, 0x00, 0, PPC2_VSX207)
GEN_VSX_HELPER_2(xsmaddmsp, 0x04, 0x01, 0, PPC2_VSX207)
+GEN_VSX_HELPER_2(xsmaddqp, 0x04, 0x0C, 0, PPC2_ISA300)
GEN_VSX_HELPER_2(xsmsubasp, 0x04, 0x02, 0, PPC2_VSX207)
GEN_VSX_HELPER_2(xsmsubmsp, 0x04, 0x03, 0, PPC2_VSX207)
+GEN_VSX_HELPER_2(xsmsubqp, 0x04, 0x0D, 0, PPC2_ISA300)
GEN_VSX_HELPER_2(xsnmaddasp, 0x04, 0x10, 0, PPC2_VSX207)
GEN_VSX_HELPER_2(xsnmaddmsp, 0x04, 0x11, 0, PPC2_VSX207)
+GEN_VSX_HELPER_2(xsnmaddqp, 0x04, 0x0E, 0, PPC2_ISA300)
GEN_VSX_HELPER_2(xsnmsubasp, 0x04, 0x12, 0, PPC2_VSX207)
GEN_VSX_HELPER_2(xsnmsubmsp, 0x04, 0x13, 0, PPC2_VSX207)
+GEN_VSX_HELPER_2(xsnmsubqp, 0x04, 0x0F, 0, PPC2_ISA300)
GEN_VSX_HELPER_2(xscvsxdsp, 0x10, 0x13, 0, PPC2_VSX207)
GEN_VSX_HELPER_2(xscvuxdsp, 0x10, 0x12, 0, PPC2_VSX207)
GEN_VSX_HELPER_2(xststdcsp, 0x14, 0x12, 0, PPC2_ISA300)
diff --git a/target/ppc/translate/vsx-ops.inc.c
b/target/ppc/translate/vsx-ops.inc.c
index 5030c4a..e770fab 100644
--- a/target/ppc/translate/vsx-ops.inc.c
+++ b/target/ppc/translate/vsx-ops.inc.c
@@ -237,12 +237,16 @@ GEN_XX2FORM(xssqrtsp, 0x16, 0x00, PPC2_VSX207),
GEN_XX2FORM(xsrsqrtesp, 0x14, 0x00, PPC2_VSX207),
GEN_XX3FORM(xsmaddasp, 0x04, 0x00, PPC2_VSX207),
GEN_XX3FORM(xsmaddmsp, 0x04, 0x01, PPC2_VSX207),
+GEN_VSX_XFORM_300(xsmaddqp, 0x04, 0x0C, 0x0),
GEN_XX3FORM(xsmsubasp, 0x04, 0x02, PPC2_VSX207),
GEN_XX3FORM(xsmsubmsp, 0x04, 0x03, PPC2_VSX207),
+GEN_VSX_XFORM_300(xsmsubqp, 0x04, 0x0D, 0x0),
GEN_XX3FORM(xsnmaddasp, 0x04, 0x10, PPC2_VSX207),
GEN_XX3FORM(xsnmaddmsp, 0x04, 0x11, PPC2_VSX207),
+GEN_VSX_XFORM_300(xsnmaddqp, 0x04, 0x0E, 0x0),
GEN_XX3FORM(xsnmsubasp, 0x04, 0x12, PPC2_VSX207),
GEN_XX3FORM(xsnmsubmsp, 0x04, 0x13, PPC2_VSX207),
+GEN_VSX_XFORM_300(xsnmsubqp, 0x04, 0x0F, 0x0),
GEN_XX2FORM(xscvsxdsp, 0x10, 0x13, PPC2_VSX207),
GEN_XX2FORM(xscvuxdsp, 0x10, 0x12, PPC2_VSX207),
--
2.7.4
- [Qemu-devel] [PATCH] target-ppc: Add quad precision muladd instructions,
Bharata B Rao <=