[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH v2 7/7] target/ppc: add vdiv{su}{wd} vmod{su}{wd} instructions
From: |
Lijun Pan |
Subject: |
[PATCH v2 7/7] target/ppc: add vdiv{su}{wd} vmod{su}{wd} instructions |
Date: |
Wed, 17 Jun 2020 19:11:27 -0500 |
vdivsw: Vector Divide Signed Word
vdivuw: Vector Divide Unsigned Word
vdivsd: Vector Divide Signed Doubleword
vdivud: Vector Divide Unsigned Doubleword
vmodsw: Vector Modulo Signed Word
vmoduw: Vector Modulo Unsigned Word
vmodsd: Vector Modulo Signed Doubleword
vmodud: Vector Modulo Unsigned Doubleword
Signed-off-by: Lijun Pan <ljp@linux.ibm.com>
---
v2: fix coding style
use Power ISA 3.1 flag
target/ppc/helper.h | 8 ++++++++
target/ppc/int_helper.c | 19 +++++++++++++++++++
target/ppc/translate.c | 3 +++
target/ppc/translate/vmx-impl.inc.c | 15 +++++++++++++++
target/ppc/translate/vmx-ops.inc.c | 17 +++++++++++++++--
5 files changed, 60 insertions(+), 2 deletions(-)
diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index 1aed2087cf..823999a8c2 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -190,6 +190,14 @@ DEF_HELPER_3(vmulhsw, void, avr, avr, avr)
DEF_HELPER_3(vmulhuw, void, avr, avr, avr)
DEF_HELPER_3(vmulhsd, void, avr, avr, avr)
DEF_HELPER_3(vmulhud, void, avr, avr, avr)
+DEF_HELPER_3(vdivsw, void, avr, avr, avr)
+DEF_HELPER_3(vdivuw, void, avr, avr, avr)
+DEF_HELPER_3(vdivsd, void, avr, avr, avr)
+DEF_HELPER_3(vdivud, void, avr, avr, avr)
+DEF_HELPER_3(vmodsw, void, avr, avr, avr)
+DEF_HELPER_3(vmoduw, void, avr, avr, avr)
+DEF_HELPER_3(vmodsd, void, avr, avr, avr)
+DEF_HELPER_3(vmodud, void, avr, avr, avr)
DEF_HELPER_3(vslo, void, avr, avr, avr)
DEF_HELPER_3(vsro, void, avr, avr, avr)
DEF_HELPER_3(vsrv, void, avr, avr, avr)
diff --git a/target/ppc/int_helper.c b/target/ppc/int_helper.c
index 9a0937810f..bc3640166d 100644
--- a/target/ppc/int_helper.c
+++ b/target/ppc/int_helper.c
@@ -575,6 +575,25 @@ VARITH_DO(mulld, *, s64)
#undef VARITH_DO
#undef VARITH
+#define VDIV_MOD_DO(name, op, element) \
+ void helper_v##name(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) \
+ { \
+ int i; \
+ \
+ for (i = 0; i < ARRAY_SIZE(r->element); i++) { \
+ r->element[i] = a->element[i] op b->element[i]; \
+ } \
+ }
+VDIV_MOD_DO(divsw, /, s32)
+VDIV_MOD_DO(divuw, /, u32)
+VDIV_MOD_DO(divsd, /, s64)
+VDIV_MOD_DO(divud, /, u64)
+VDIV_MOD_DO(modsw, %, s32)
+VDIV_MOD_DO(moduw, %, u32)
+VDIV_MOD_DO(modsd, %, s64)
+VDIV_MOD_DO(modud, %, u64)
+#undef VDIV_MOD_DO
+
#define VARITHFP(suffix, func) \
void helper_v##suffix(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a, \
ppc_avr_t *b) \
diff --git a/target/ppc/translate.c b/target/ppc/translate.c
index d686e6084a..6d5af650e4 100644
--- a/target/ppc/translate.c
+++ b/target/ppc/translate.c
@@ -388,6 +388,9 @@ GEN_OPCODE3(name, opc1, opc2, opc3, opc4, inval, type,
type2)
#define GEN_HANDLER2_E_2(name, onam, opc1, opc2, opc3, opc4, inval, typ, typ2)
\
GEN_OPCODE4(name, onam, opc1, opc2, opc3, opc4, inval, typ, typ2)
+#define GEN_HANDLER_BOTH(name, opc1, opc2, opc3, inval0, inval1, type0, type1)
\
+GEN_OPCODE_DUAL(name, opc1, opc2, opc3, inval0, inval1, type0, type1)
+
typedef struct opcode_t {
unsigned char opc1, opc2, opc3, opc4;
#if HOST_LONG_BITS == 64 /* Explicitly align to 64 bits */
diff --git a/target/ppc/translate/vmx-impl.inc.c
b/target/ppc/translate/vmx-impl.inc.c
index c494a7aebb..e0b8658d1f 100644
--- a/target/ppc/translate/vmx-impl.inc.c
+++ b/target/ppc/translate/vmx-impl.inc.c
@@ -798,6 +798,9 @@ static void trans_vclzd(DisasContext *ctx)
tcg_temp_free_i64(avr);
}
+static void gen_vexptefp(DisasContext *ctx);
+static void gen_vlogefp(DisasContext *ctx);
+
GEN_VXFORM(vmuloub, 4, 0);
GEN_VXFORM(vmulouh, 4, 1);
GEN_VXFORM(vmulouw, 4, 2);
@@ -822,6 +825,18 @@ GEN_VXFORM(vmulhsw, 4, 14);
GEN_VXFORM_DUAL(vmulesw, PPC_ALTIVEC, PPC_NONE,
vmulhsw, PPC_NONE, PPC2_ISA310);
GEN_VXFORM(vmulhsd, 4, 15);
+GEN_VXFORM(vdivuw, 5, 2);
+GEN_VXFORM(vdivud, 5, 3);
+GEN_VXFORM(vdivsw, 5, 6);
+GEN_VXFORM_DUAL_EXT(vexptefp, PPC_ALTIVEC, PPC_NONE, 0x001f0000,
+ vdivsw, PPC_NONE, PPC2_ISA310, 0x00000000);
+GEN_VXFORM(vdivsd, 5, 7);
+GEN_VXFORM_DUAL_EXT(vlogefp, PPC_ALTIVEC, PPC_NONE, 0x001f0000,
+ vdivsd, PPC_NONE, PPC2_ISA310, 0x00000000);
+GEN_VXFORM(vmoduw, 5, 26);
+GEN_VXFORM(vmodud, 5, 27);
+GEN_VXFORM(vmodsw, 5, 30);
+GEN_VXFORM(vmodsd, 5, 31);
GEN_VXFORM_V(vslb, MO_8, tcg_gen_gvec_shlv, 2, 4);
GEN_VXFORM_V(vslh, MO_16, tcg_gen_gvec_shlv, 2, 5);
GEN_VXFORM_V(vslw, MO_32, tcg_gen_gvec_shlv, 2, 6);
diff --git a/target/ppc/translate/vmx-ops.inc.c
b/target/ppc/translate/vmx-ops.inc.c
index f3f4855111..528458cb25 100644
--- a/target/ppc/translate/vmx-ops.inc.c
+++ b/target/ppc/translate/vmx-ops.inc.c
@@ -54,6 +54,11 @@ GEN_HANDLER_E(name, 0x04, opc2, opc3, 0x00000000, PPC_NONE,
PPC2_ISA310)
#define GEN_VXFORM_DUAL(name0, name1, opc2, opc3, type0, type1) \
GEN_HANDLER_E(name0##_##name1, 0x4, opc2, opc3, 0x00000000, type0, type1)
+#define GEN_VXFORM_DUAL_BOTH(name0, name1, opc2, opc3, inval0, \
+ inval1, type0, type1) \
+GEN_HANDLER_BOTH(name0##_##name1, 0x4, opc2, opc3, inval0, \
+ inval1, type0, type1)
+
#define GEN_VXRFORM_DUAL(name0, name1, opc2, opc3, tp0, tp1) \
GEN_HANDLER_E(name0##_##name1, 0x4, opc2, opc3, 0x00000000, tp0, tp1), \
GEN_HANDLER_E(name0##_##name1, 0x4, opc2, (opc3 | 0x10), 0x00000000, tp0, tp1),
@@ -116,6 +121,16 @@ GEN_VXFORM(vmulesb, 4, 12),
GEN_VXFORM(vmulesh, 4, 13),
GEN_VXFORM_DUAL(vmulesw, vmulhsw, 4, 14, PPC_ALTIVEC, PPC_NONE),
GEN_VXFORM_310(vmulhsd, 4, 15),
+GEN_VXFORM_310(vdivuw, 5, 2),
+GEN_VXFORM_310(vdivud, 5, 3),
+GEN_VXFORM_DUAL_BOTH(vexptefp, vdivsw, 5, 6, 0x001f0000, 0x00000000,
+ PPC_ALTIVEC, PPC2_ISA310),
+GEN_VXFORM_DUAL_BOTH(vlogefp, vdivsd, 5, 7, 0x001f0000, 0x00000000,
+ PPC_ALTIVEC, PPC2_ISA310),
+GEN_VXFORM_310(vmoduw, 5, 26),
+GEN_VXFORM_310(vmodud, 5, 27),
+GEN_VXFORM_310(vmodsw, 5, 30),
+GEN_VXFORM_310(vmodsd, 5, 31),
GEN_VXFORM(vslb, 2, 4),
GEN_VXFORM(vslh, 2, 5),
GEN_VXFORM_DUAL(vslw, vrlwnm, 2, 6, PPC_ALTIVEC, PPC_NONE),
@@ -259,8 +274,6 @@ GEN_VXFORM_NOA(vupkhpx, 7, 13),
GEN_VXFORM_NOA(vupklpx, 7, 15),
GEN_VXFORM_NOA(vrefp, 5, 4),
GEN_VXFORM_NOA(vrsqrtefp, 5, 5),
-GEN_VXFORM_NOA(vexptefp, 5, 6),
-GEN_VXFORM_NOA(vlogefp, 5, 7),
GEN_VXFORM_NOA(vrfim, 5, 11),
GEN_VXFORM_NOA(vrfin, 5, 8),
GEN_VXFORM_NOA(vrfip, 5, 10),
--
2.23.0
- [PATCH v2 0/7] Add several Power ISA 3.1 32/64-bit vector instructions, Lijun Pan, 2020/06/17
- [PATCH v2 3/7] target/ppc: add vmulld instruction, Lijun Pan, 2020/06/17
- [PATCH v2 2/7] target/ppc: add byte-reverse br[dwh] instructions, Lijun Pan, 2020/06/17
- [PATCH v2 1/7] target/ppc: Introduce Power ISA 3.1 flag, Lijun Pan, 2020/06/17
- [PATCH v2 5/7] fix the prototype of muls64/mulu64, Lijun Pan, 2020/06/17
- [PATCH v2 7/7] target/ppc: add vdiv{su}{wd} vmod{su}{wd} instructions,
Lijun Pan <=
- [PATCH v2 6/7] target/ppc: add vmulh{su}d instructions, Lijun Pan, 2020/06/17
- [PATCH v2 4/7] target/ppc: add vmulh{su}w instructions, Lijun Pan, 2020/06/17
- Re: [PATCH v2 0/7] Add several Power ISA 3.1 32/64-bit vector instructions, no-reply, 2020/06/17