target/hexagon/gen_tcg.h | 10 ++- target/hexagon/genptr.c | 173 +++++++++++++++++++++++++++++++++++++++ tests/tcg/hexagon/usr.c | 30 +++++-- 3 files changed, 206 insertions(+), 7 deletions(-)
These instructions will not be generated by idef-parser, so we override
them manually.
Test cases added to tests/tcg/hexagon/usr.c
Co-authored-by: Matheus Tavares Bernardino <quic_mathbern@quicinc.com>
Signed-off-by: Matheus Tavares Bernardino <quic_mathbern@quicinc.com>
Signed-off-by: Taylor Simpson <tsimpson@quicinc.com>
---
target/hexagon/gen_tcg.h | 10 ++-
target/hexagon/genptr.c | 173 +++++++++++++++++++++++++++++++++++++++
tests/tcg/hexagon/usr.c | 30 +++++--
3 files changed, 206 insertions(+), 7 deletions(-)
diff --git a/target/hexagon/gen_tcg.h b/target/hexagon/gen_tcg.h
index 50634ac459..b5fe22a07a 100644
--- a/target/hexagon/gen_tcg.h
+++ b/target/hexagon/gen_tcg.h
@@ -1,5 +1,5 @@
/*
- * Copyright(c) 2019-2021 Qualcomm Innovation Center, Inc. All Rights Reserved.
+ * Copyright(c) 2019-2022 Qualcomm Innovation Center, Inc. All Rights Reserved.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -612,6 +612,14 @@
tcg_temp_free(tmp); \
} while (0)
+/* r0 = asr(r1, r2):sat */
+#define fGEN_TCG_S2_asr_r_r_sat(SHORTCODE) \
+ gen_asr_r_r_sat(RdV, RsV, RtV)
+
+/* r0 = asl(r1, r2):sat */
+#define fGEN_TCG_S2_asl_r_r_sat(SHORTCODE) \
+ gen_asl_r_r_sat(RdV, RsV, RtV)
+
/* Floating point */
#define fGEN_TCG_F2_conv_sf2df(SHORTCODE) \
gen_helper_conv_sf2df(RddV, cpu_env, RsV)
diff --git a/target/hexagon/genptr.c b/target/hexagon/genptr.c
index 806d0974ff..74adbf5944 100644
--- a/target/hexagon/genptr.c
+++ b/target/hexagon/genptr.c
@@ -456,6 +456,179 @@ static TCGv gen_8bitsof(TCGv result, TCGv value)
return result;
}
+static void gen_set_usr_field(int field, TCGv val)
+{
+ tcg_gen_deposit_tl(hex_new_value[HEX_REG_USR], hex_new_value[HEX_REG_USR],
+ val,
+ reg_field_info[field].offset,
+ reg_field_info[field].width);
+}
+
+static void gen_set_usr_fieldi(int field, int x)
+{
+ TCGv val = tcg_constant_tl(x);
+ gen_set_usr_field(field, val);
+}
+
+static void gen_sat_i64(TCGv_i64 dst, TCGv_i64 src, uint32_t bits)
+{
+ TCGLabel *label = gen_new_label();
+
+ tcg_gen_sextract_i64(dst, src, 0, bits);
+ tcg_gen_brcond_i64(TCG_COND_EQ, dst, src, label);
+ {
+ TCGv_i64 min = tcg_constant_i64(-(1LL << (bits - 1)));
+ TCGv_i64 max = tcg_constant_i64((1LL << (bits - 1)) - 1);
+ tcg_gen_movcond_i64(TCG_COND_LT, dst, src, tcg_constant_i64(0),
+ min, max);
+ gen_set_usr_fieldi(USR_OVF, 1);
+ }
+ gen_set_label(label);
+}
+
+static void gen_satval(TCGv_i64 dest, TCGv_i64 source, uint32_t bits)
+{
+ TCGv_i64 min = tcg_constant_i64(-(1LL << (bits - 1)));
+ TCGv_i64 max = tcg_constant_i64((1LL << (bits - 1)) - 1);
+
+ gen_set_usr_fieldi(USR_OVF, 1);
+ tcg_gen_movcond_i64(TCG_COND_LT, dest, source, tcg_constant_i64(0),
+ min, max);
+}
+
+/* Shift left with saturation */
+static void gen_shl_sat(TCGv RdV, TCGv RsV, TCGv shift_amt)
+{
+ /*
+ * int64_t A = (fCAST4_8s(RsV) << shift_amt;
+ * if (((int32_t)((fSAT(A)) ^ ((int32_t)(RsV)))) < 0) {
+ * RdV = fSATVALN(32, ((int32_t)(RsV)))
+ * } else if (((RsV) > 0) && ((A) == 0)) {
+ * RdV = fSATVALN(32, (RsV));
+ * } else {
+ * RdV = fSAT(A);
+ * }
+ */
+ TCGv_i64 RsV_i64 = tcg_temp_local_new_i64();
+ TCGv_i64 shift_amt_i64 = tcg_temp_local_new_i64();
+ TCGv_i64 A = tcg_temp_local_new_i64();
+ TCGv_i64 A_sat_i64 = tcg_temp_local_new_i64();
+ TCGv A_sat = tcg_temp_local_new();
+ TCGv_i64 RdV_i64 = tcg_temp_local_new_i64();
+ TCGv tmp = tcg_temp_new();
+ TCGLabel *label1 = gen_new_label();
+ TCGLabel *label2 = gen_new_label();
+ TCGLabel *done = gen_new_label();
+
+ tcg_gen_ext_i32_i64(RsV_i64, RsV);
+ tcg_gen_ext_i32_i64(shift_amt_i64, shift_amt);
+ tcg_gen_shl_i64(A, RsV_i64, shift_amt_i64);
+
+ /* Check for saturation */
+ gen_sat_i64(A_sat_i64, A, 32);
+ tcg_gen_extrl_i64_i32(A_sat, A_sat_i64);
+ tcg_gen_xor_tl(tmp, A_sat, RsV);
+ tcg_gen_brcondi_tl(TCG_COND_GE, tmp, 0, label1);
+ gen_satval(RdV_i64, RsV_i64, 32);
+ tcg_gen_extrl_i64_i32(RdV, RdV_i64);
+ tcg_gen_br(done);
+
+ gen_set_label(label1);
+ tcg_gen_brcondi_tl(TCG_COND_LE, RsV, 0, label2);
+ tcg_gen_brcondi_i64(TCG_COND_NE, A, 0, label2);
+ gen_satval(RdV_i64, RsV_i64, 32);
+ tcg_gen_extrl_i64_i32(RdV, RdV_i64);
+ tcg_gen_br(done);
+
+ gen_set_label(label2);
+ tcg_gen_mov_tl(RdV, A_sat);
+
+ gen_set_label(done);
+
+ tcg_temp_free_i64(RsV_i64);
+ tcg_temp_free_i64(shift_amt_i64);
+ tcg_temp_free_i64(A);
+ tcg_temp_free_i64(A_sat_i64);
+ tcg_temp_free(A_sat);
+ tcg_temp_free_i64(RdV_i64);
+ tcg_temp_free(tmp);
+}
+
+static void gen_sar(TCGv RdV, TCGv RsV, TCGv shift_amt)
+{
+ /*
+ * if (shift_amt < 32) {
+ * RdV = sar(RsV, shift_amt);
+ * } else {
+ * if (RsV > 0) {
+ * RdV = 0;
+ * } else {
+ * RdV = ~0;
+ * }
+ * }
+ */
+ TCGLabel *shift_ge_32 = gen_new_label();
+ TCGLabel *done = gen_new_label();
+
+ tcg_gen_brcondi_tl(TCG_COND_GE, shift_amt, 32, shift_ge_32);
+ tcg_gen_sar_tl(RdV, RsV, shift_amt);
+ tcg_gen_br(done);
+
+ gen_set_label(shift_ge_32);
+ tcg_gen_movcond_tl(TCG_COND_LT, RdV, RsV, tcg_constant_tl(0),
+ tcg_constant_tl(~0), tcg_constant_tl(0));
+
+ gen_set_label(done);
+}
+
+/* Bidirectional shift right with saturation */
+static void gen_asr_r_r_sat(TCGv RdV, TCGv RsV, TCGv RtV)
+{
+ TCGv shift_amt = tcg_temp_local_new();
+ TCGLabel *positive = gen_new_label();
+ TCGLabel *done = gen_new_label();
+
+ tcg_gen_sextract_i32(shift_amt, RtV, 0, 7);
+ tcg_gen_brcondi_tl(TCG_COND_GE, shift_amt, 0, positive);
+
+ /* Negative shift amount => shift left */
+ tcg_gen_neg_tl(shift_amt, shift_amt);
+ gen_shl_sat(RdV, RsV, shift_amt);
+ tcg_gen_br(done);
+
+ gen_set_label(positive);
+ /* Positive shift amount => shift right */
+ gen_sar(RdV, RsV, shift_amt);
+
+ gen_set_label(done);
+
+ tcg_temp_free(shift_amt);
+}
+
+/* Bidirectional shift left with saturation */
+static void gen_asl_r_r_sat(TCGv RdV, TCGv RsV, TCGv RtV)
+{
+ TCGv shift_amt = tcg_temp_local_new();
+ TCGLabel *positive = gen_new_label();
+ TCGLabel *done = gen_new_label();
+
+ tcg_gen_sextract_i32(shift_amt, RtV, 0, 7);
+ tcg_gen_brcondi_tl(TCG_COND_GE, shift_amt, 0, positive);
+
+ /* Negative shift amount => shift right */
+ tcg_gen_neg_tl(shift_amt, shift_amt);
+ gen_sar(RdV, RsV, shift_amt);
+ tcg_gen_br(done);
+
+ gen_set_label(positive);
+ /* Positive shift amount => shift left */
+ gen_shl_sat(RdV, RsV, shift_amt);
+
+ gen_set_label(done);
+
+ tcg_temp_free(shift_amt);
+}
+
static intptr_t vreg_src_off(DisasContext *ctx, int num)
{
intptr_t offset = offsetof(CPUHexagonState, VRegs[num]);
diff --git a/tests/tcg/hexagon/usr.c b/tests/tcg/hexagon/usr.c
index fb4514989c..63c7d2700f 100644
--- a/tests/tcg/hexagon/usr.c
+++ b/tests/tcg/hexagon/usr.c
@@ -429,6 +429,7 @@ FUNC_P_OP_P(vabshsat, "%0 = vabsh(%2):sat")
FUNC_P_OP_PP(vnavgwr, "%0 = vnavgw(%2, %3):rnd:sat")
FUNC_R_OP_RI(round_ri_sat, "%0 = round(%2, #%3):sat")
FUNC_R_OP_RR(asr_r_r_sat, "%0 = asr(%2, %3):sat")
+FUNC_R_OP_RR(asl_r_r_sat, "%0 = asl(%2, %3):sat")
FUNC_XPp_OP_PP(ACS, "%0, p2 = vacsh(%3, %4)")
@@ -907,12 +908,29 @@ int main()
TEST_R_OP_RI(round_ri_sat, 0x0000ffff, 2, 0x00004000, USR_CLEAR);
TEST_R_OP_RI(round_ri_sat, 0x7fffffff, 2, 0x1fffffff, USR_OVF);
- TEST_R_OP_RR(asr_r_r_sat, 0x0000ffff, 0x00000002, 0x00003fff,
- USR_CLEAR);
- TEST_R_OP_RR(asr_r_r_sat, 0x00ffffff, 0xfffffff5, 0x7fffffff,
- USR_OVF);
- TEST_R_OP_RR(asr_r_r_sat, 0x80000000, 0xfffffff5, 0x80000000,
- USR_OVF);
+ TEST_R_OP_RR(asr_r_r_sat, 0x0000ffff, 0x02, 0x00003fff, USR_CLEAR);
+ TEST_R_OP_RR(asr_r_r_sat, 0x80000000, 0x01, 0xc0000000, USR_CLEAR);
+ TEST_R_OP_RR(asr_r_r_sat, 0xffffffff, 0x01, 0xffffffff, USR_CLEAR);
+ TEST_R_OP_RR(asr_r_r_sat, 0x00ffffff, 0xf5, 0x7fffffff, USR_OVF);
+ TEST_R_OP_RR(asr_r_r_sat, 0x80000000, 0xf5, 0x80000000, USR_OVF);
+ TEST_R_OP_RR(asr_r_r_sat, 0x7fff0000, 0x42, 0x7fffffff, USR_OVF);
+ TEST_R_OP_RR(asr_r_r_sat, 0xff000000, 0x42, 0x80000000, USR_OVF);
+ TEST_R_OP_RR(asr_r_r_sat, 4096, 32, 0x00000000, USR_CLEAR);
+ TEST_R_OP_RR(asr_r_r_sat, 4096, -32, 0x7fffffff, USR_OVF);
+ TEST_R_OP_RR(asr_r_r_sat, -4096, 32, 0xffffffff, USR_CLEAR);
+ TEST_R_OP_RR(asr_r_r_sat, -4096, -32, 0x80000000, USR_OVF);
+
+ TEST_R_OP_RR(asl_r_r_sat, 0x00000000, 0x40, 0x00000000, USR_CLEAR);
+ TEST_R_OP_RR(asl_r_r_sat, 0x80000000, 0xff, 0xc0000000, USR_CLEAR);
+ TEST_R_OP_RR(asl_r_r_sat, 0xffffffff, 0xff, 0xffffffff, USR_CLEAR);
+ TEST_R_OP_RR(asl_r_r_sat, 0x00ffffff, 0x0b, 0x7fffffff, USR_OVF);
+ TEST_R_OP_RR(asl_r_r_sat, 0x80000000, 0x0b, 0x80000000, USR_OVF);
+ TEST_R_OP_RR(asl_r_r_sat, 0x7fff0000, 0xbe, 0x7fffffff, USR_OVF);
+ TEST_R_OP_RR(asl_r_r_sat, 0xff000000, 0xbe, 0x80000000, USR_OVF);
+ TEST_R_OP_RR(asl_r_r_sat, 4096, 32, 0x7fffffff, USR_OVF);
+ TEST_R_OP_RR(asl_r_r_sat, 4096, -32, 0x00000000, USR_CLEAR);
+ TEST_R_OP_RR(asl_r_r_sat, -4096, 32, 0x80000000, USR_OVF);
+ TEST_R_OP_RR(asl_r_r_sat, -4096, -32, 0xffffffff, USR_CLEAR);
TEST_XPp_OP_PP(ACS, 0x0004000300020001ULL, 0x0001000200030004ULL,
0x0000000000000000ULL, 0x0004000300030004ULL, 0xf0,
--
2.17.1
This enables us to reduce the number of parameters to many functions
In particular, the generated functions previously took all 3 as arguments
Not only does this simplify the code, it improves the translation time
Signed-off-by: Taylor Simpson <tsimpson@quicinc.com>
---
target/hexagon/gen_tcg_hvx.h | 4 +-
target/hexagon/insn.h | 5 +-
target/hexagon/macros.h | 10 +--
target/hexagon/mmvec/macros.h | 4 +-
target/hexagon/translate.h | 7 +-
target/hexagon/genptr.c | 6 +-
target/hexagon/translate.c | 120 +++++++++++++++++---------------
target/hexagon/gen_tcg_funcs.py | 15 ++--
8 files changed, 86 insertions(+), 85 deletions(-)
diff --git a/target/hexagon/gen_tcg_hvx.h b/target/hexagon/gen_tcg_hvx.h
index cdcc9382bb..c4fb005a8d 100644
--- a/target/hexagon/gen_tcg_hvx.h
+++ b/target/hexagon/gen_tcg_hvx.h
@@ -697,7 +697,7 @@ static inline void assert_vhist_tmp(DisasContext *ctx)
#define fGEN_TCG_NEWVAL_VEC_STORE(GET_EA, INC) \
do { \
GET_EA; \
- gen_vreg_store(ctx, insn, pkt, EA, OsN_off, insn->slot, true); \
+ gen_vreg_store(ctx, EA, OsN_off, insn->slot, true); \
INC; \
} while (0)
@@ -736,7 +736,7 @@ static inline void assert_vhist_tmp(DisasContext *ctx)
PRED; \
tcg_gen_brcondi_tl(TCG_COND_EQ, LSB, 0, false_label); \
tcg_temp_free(LSB); \
- gen_vreg_store(ctx, insn, pkt, EA, SRCOFF, insn->slot, ALIGN); \
+ gen_vreg_store(ctx, EA, SRCOFF, insn->slot, ALIGN); \
INC; \
tcg_gen_br(end_label); \
gen_set_label(false_label); \
diff --git a/target/hexagon/insn.h b/target/hexagon/insn.h
index aa26389147..a930118886 100644
--- a/target/hexagon/insn.h
+++ b/target/hexagon/insn.h
@@ -28,10 +28,7 @@ struct Instruction;
struct Packet;
struct DisasContext;
-typedef void (*SemanticInsn)(CPUHexagonState *env,
- struct DisasContext *ctx,
- struct Instruction *insn,
- struct Packet *pkt);
+typedef void (*SemanticInsn)(struct DisasContext *ctx);
struct Instruction {
SemanticInsn generate; /* pointer to genptr routine */
diff --git a/target/hexagon/macros.h b/target/hexagon/macros.h
index c8805bdaeb..93ee4739a1 100644
--- a/target/hexagon/macros.h
+++ b/target/hexagon/macros.h
@@ -94,9 +94,9 @@
*/
#define CHECK_NOSHUF(VA, SIZE) \
do { \
- if (insn->slot == 0 && pkt->pkt_has_store_s1) { \
+ if (insn->slot == 0 && ctx->pkt->pkt_has_store_s1) { \
probe_noshuf_load(VA, SIZE, ctx->mem_idx); \
- process_store(ctx, pkt, 1); \
+ process_store(ctx, 1); \
} \
} while (0)
@@ -105,12 +105,12 @@
TCGLabel *label = gen_new_label(); \
tcg_gen_brcondi_tl(TCG_COND_EQ, PRED, 0, label); \
GET_EA; \
- if (insn->slot == 0 && pkt->pkt_has_store_s1) { \
+ if (insn->slot == 0 && ctx->pkt->pkt_has_store_s1) { \
probe_noshuf_load(EA, SIZE, ctx->mem_idx); \
} \
gen_set_label(label); \
- if (insn->slot == 0 && pkt->pkt_has_store_s1) { \
- process_store(ctx, pkt, 1); \
+ if (insn->slot == 0 && ctx->pkt->pkt_has_store_s1) { \
+ process_store(ctx, 1); \
} \
} while (0)
diff --git a/target/hexagon/mmvec/macros.h b/target/hexagon/mmvec/macros.h
index 8345753580..8c864e8c68 100644
--- a/target/hexagon/mmvec/macros.h
+++ b/target/hexagon/mmvec/macros.h
@@ -288,7 +288,7 @@
#endif
#ifdef QEMU_GENERATE
#define fSTOREMMV(EA, SRC) \
- gen_vreg_store(ctx, insn, pkt, EA, SRC##_off, insn->slot, true)
+ gen_vreg_store(ctx, EA, SRC##_off, insn->slot, true)
#endif
#ifdef QEMU_GENERATE
#define fSTOREMMVQ(EA, SRC, MASK) \
@@ -300,7 +300,7 @@
#endif
#ifdef QEMU_GENERATE
#define fSTOREMMVU(EA, SRC) \
- gen_vreg_store(ctx, insn, pkt, EA, SRC##_off, insn->slot, false)
+ gen_vreg_store(ctx, EA, SRC##_off, insn->slot, false)
#endif
#define fVFOREACH(WIDTH, VAR) for (VAR = 0; VAR < fVELEM(WIDTH); VAR++)
#define fVARRAY_ELEMENT_ACCESS(ARRAY, TYPE, INDEX) \
diff --git a/target/hexagon/translate.h b/target/hexagon/translate.h
index a245172827..58dbed71cf 100644
--- a/target/hexagon/translate.h
+++ b/target/hexagon/translate.h
@@ -23,10 +23,13 @@
#include "cpu.h"
#include "exec/translator.h"
#include "tcg/tcg-op.h"
+#include "insn.h"
#include "internal.h"
typedef struct DisasContext {
DisasContextBase base;
+ Packet *pkt;
+ Insn *insn;
uint32_t mem_idx;
uint32_t num_packets;
uint32_t num_insns;
@@ -147,6 +150,6 @@ extern TCGv hex_vstore_addr[VSTORES_MAX];
extern TCGv hex_vstore_size[VSTORES_MAX];
extern TCGv hex_vstore_pending[VSTORES_MAX];
-bool is_gather_store_insn(Insn *insn, Packet *pkt);
-void process_store(DisasContext *ctx, Packet *pkt, int slot_num);
+bool is_gather_store_insn(DisasContext *ctx);
+void process_store(DisasContext *ctx, int slot_num);
#endif
diff --git a/target/hexagon/genptr.c b/target/hexagon/genptr.c
index 806d0974ff..85416dd530 100644
--- a/target/hexagon/genptr.c
+++ b/target/hexagon/genptr.c
@@ -551,13 +551,13 @@ static void gen_vreg_load(DisasContext *ctx, intptr_t dstoff, TCGv src,
tcg_temp_free_i64(tmp);
}
-static void gen_vreg_store(DisasContext *ctx, Insn *insn, Packet *pkt,
- TCGv EA, intptr_t srcoff, int slot, bool aligned)
+static void gen_vreg_store(DisasContext *ctx, TCGv EA, intptr_t srcoff,
+ int slot, bool aligned)
{
intptr_t dstoff = offsetof(CPUHexagonState, vstore[slot].data);
intptr_t maskoff = offsetof(CPUHexagonState, vstore[slot].mask);
- if (is_gather_store_insn(insn, pkt)) {
+ if (is_gather_store_insn(ctx)) {
TCGv sl = tcg_constant_tl(slot);
gen_helper_gather_store(cpu_env, EA, sl);
return;
diff --git a/target/hexagon/translate.c b/target/hexagon/translate.c
index 2329177537..0940d0f2c1 100644
--- a/target/hexagon/translate.c
+++ b/target/hexagon/translate.c
@@ -209,8 +209,9 @@ static bool need_pred_written(Packet *pkt)
return check_for_attrib(pkt, A_WRITES_PRED_REG);
}
-static void gen_start_packet(DisasContext *ctx, Packet *pkt)
+static void gen_start_packet(DisasContext *ctx)
{
+ Packet *pkt = ctx->pkt;
target_ulong next_PC = ctx->base.pc_next + pkt->encod_pkt_size_in_bytes;
int i;
@@ -260,8 +261,10 @@ static void gen_start_packet(DisasContext *ctx, Packet *pkt)
}
}
-bool is_gather_store_insn(Insn *insn, Packet *pkt)
+bool is_gather_store_insn(DisasContext *ctx)
{
+ Packet *pkt = ctx->pkt;
+ Insn *insn = ctx->insn;
if (GET_ATTRIB(insn->opcode, A_CVI_NEW) &&
insn->new_value_producer_slot == 1) {
/* Look for gather instruction */
@@ -280,15 +283,15 @@ bool is_gather_store_insn(Insn *insn, Packet *pkt)
* However, there are some implicit writes marked as attributes
* of the applicable instructions.
*/
-static void mark_implicit_reg_write(DisasContext *ctx, Insn *insn,
- int attrib, int rnum)
+static void mark_implicit_reg_write(DisasContext *ctx, int attrib, int rnum)
{
- if (GET_ATTRIB(insn->opcode, attrib)) {
+ uint16_t opcode = ctx->insn->opcode;
+ if (GET_ATTRIB(opcode, attrib)) {
/*
* USR is used to set overflow and FP exceptions,
* so treat it as conditional
*/
- bool is_predicated = GET_ATTRIB(insn->opcode, A_CONDEXEC) ||
+ bool is_predicated = GET_ATTRIB(opcode, A_CONDEXEC) ||
rnum == HEX_REG_USR;
if (is_predicated && !is_preloaded(ctx, rnum)) {
tcg_gen_mov_tl(hex_new_value[rnum], hex_gpr[rnum]);
@@ -298,39 +301,38 @@ static void mark_implicit_reg_write(DisasContext *ctx, Insn *insn,
}
}
-static void mark_implicit_pred_write(DisasContext *ctx, Insn *insn,
- int attrib, int pnum)
+static void mark_implicit_pred_write(DisasContext *ctx, int attrib, int pnum)
{
- if (GET_ATTRIB(insn->opcode, attrib)) {
+ if (GET_ATTRIB(ctx->insn->opcode, attrib)) {
ctx_log_pred_write(ctx, pnum);
}
}
-static void mark_implicit_reg_writes(DisasContext *ctx, Insn *insn)
+static void mark_implicit_reg_writes(DisasContext *ctx)
{
- mark_implicit_reg_write(ctx, insn, A_IMPLICIT_WRITES_FP, HEX_REG_FP);
- mark_implicit_reg_write(ctx, insn, A_IMPLICIT_WRITES_SP, HEX_REG_SP);
- mark_implicit_reg_write(ctx, insn, A_IMPLICIT_WRITES_LR, HEX_REG_LR);
- mark_implicit_reg_write(ctx, insn, A_IMPLICIT_WRITES_LC0, HEX_REG_LC0);
- mark_implicit_reg_write(ctx, insn, A_IMPLICIT_WRITES_SA0, HEX_REG_SA0);
- mark_implicit_reg_write(ctx, insn, A_IMPLICIT_WRITES_LC1, HEX_REG_LC1);
- mark_implicit_reg_write(ctx, insn, A_IMPLICIT_WRITES_SA1, HEX_REG_SA1);
- mark_implicit_reg_write(ctx, insn, A_IMPLICIT_WRITES_USR, HEX_REG_USR);
- mark_implicit_reg_write(ctx, insn, A_FPOP, HEX_REG_USR);
+ mark_implicit_reg_write(ctx, A_IMPLICIT_WRITES_FP, HEX_REG_FP);
+ mark_implicit_reg_write(ctx, A_IMPLICIT_WRITES_SP, HEX_REG_SP);
+ mark_implicit_reg_write(ctx, A_IMPLICIT_WRITES_LR, HEX_REG_LR);
+ mark_implicit_reg_write(ctx, A_IMPLICIT_WRITES_LC0, HEX_REG_LC0);
+ mark_implicit_reg_write(ctx, A_IMPLICIT_WRITES_SA0, HEX_REG_SA0);
+ mark_implicit_reg_write(ctx, A_IMPLICIT_WRITES_LC1, HEX_REG_LC1);
+ mark_implicit_reg_write(ctx, A_IMPLICIT_WRITES_SA1, HEX_REG_SA1);
+ mark_implicit_reg_write(ctx, A_IMPLICIT_WRITES_USR, HEX_REG_USR);
+ mark_implicit_reg_write(ctx, A_FPOP, HEX_REG_USR);
}
-static void mark_implicit_pred_writes(DisasContext *ctx, Insn *insn)
+static void mark_implicit_pred_writes(DisasContext *ctx)
{
- mark_implicit_pred_write(ctx, insn, A_IMPLICIT_WRITES_P0, 0);
- mark_implicit_pred_write(ctx, insn, A_IMPLICIT_WRITES_P1, 1);
- mark_implicit_pred_write(ctx, insn, A_IMPLICIT_WRITES_P2, 2);
- mark_implicit_pred_write(ctx, insn, A_IMPLICIT_WRITES_P3, 3);
+ mark_implicit_pred_write(ctx, A_IMPLICIT_WRITES_P0, 0);
+ mark_implicit_pred_write(ctx, A_IMPLICIT_WRITES_P1, 1);
+ mark_implicit_pred_write(ctx, A_IMPLICIT_WRITES_P2, 2);
+ mark_implicit_pred_write(ctx, A_IMPLICIT_WRITES_P3, 3);
}
-static void mark_store_width(DisasContext *ctx, Insn *insn)
+static void mark_store_width(DisasContext *ctx)
{
- uint16_t opcode = insn->opcode;
- uint32_t slot = insn->slot;
+ uint16_t opcode = ctx->insn->opcode;
+ uint32_t slot = ctx->insn->slot;
uint8_t width = 0;
if (GET_ATTRIB(opcode, A_SCALAR_STORE)) {
@@ -351,14 +353,13 @@ static void mark_store_width(DisasContext *ctx, Insn *insn)
}
}
-static void gen_insn(CPUHexagonState *env, DisasContext *ctx,
- Insn *insn, Packet *pkt)
+static void gen_insn(DisasContext *ctx)
{
- if (insn->generate) {
- mark_implicit_reg_writes(ctx, insn);
- insn->generate(env, ctx, insn, pkt);
- mark_implicit_pred_writes(ctx, insn);
- mark_store_width(ctx, insn);
+ if (ctx->insn->generate) {
+ mark_implicit_reg_writes(ctx);
+ ctx->insn->generate(ctx);
+ mark_implicit_pred_writes(ctx);
+ mark_store_width(ctx);
} else {
gen_exception_end_tb(ctx, HEX_EXCP_INVALID_OPCODE);
}
@@ -378,7 +379,7 @@ static void gen_reg_writes(DisasContext *ctx)
}
}
-static void gen_pred_writes(DisasContext *ctx, Packet *pkt)
+static void gen_pred_writes(DisasContext *ctx)
{
int i;
@@ -393,7 +394,7 @@ static void gen_pred_writes(DisasContext *ctx, Packet *pkt)
* instructions, we can use the non-conditional
* write of the predicates.
*/
- if (pkt->pkt_has_endloop) {
+ if (ctx->pkt->pkt_has_endloop) {
TCGv zero = tcg_constant_tl(0);
TCGv pred_written = tcg_temp_new();
for (i = 0; i < ctx->preg_log_idx; i++) {
@@ -439,9 +440,9 @@ static bool slot_is_predicated(Packet *pkt, int slot_num)
g_assert_not_reached();
}
-void process_store(DisasContext *ctx, Packet *pkt, int slot_num)
+void process_store(DisasContext *ctx, int slot_num)
{
- bool is_predicated = slot_is_predicated(pkt, slot_num);
+ bool is_predicated = slot_is_predicated(ctx->pkt, slot_num);
TCGLabel *label_end = NULL;
/*
@@ -517,27 +518,28 @@ void process_store(DisasContext *ctx, Packet *pkt, int slot_num)
}
}
-static void process_store_log(DisasContext *ctx, Packet *pkt)
+static void process_store_log(DisasContext *ctx)
{
/*
* When a packet has two stores, the hardware processes
* slot 1 and then slot 0. This will be important when
* the memory accesses overlap.
*/
+ Packet *pkt = ctx->pkt;
if (pkt->pkt_has_store_s1) {
g_assert(!pkt->pkt_has_dczeroa);
- process_store(ctx, pkt, 1);
+ process_store(ctx, 1);
}
if (pkt->pkt_has_store_s0) {
g_assert(!pkt->pkt_has_dczeroa);
- process_store(ctx, pkt, 0);
+ process_store(ctx, 0);
}
}
/* Zero out a 32-bit cache line */
-static void process_dczeroa(DisasContext *ctx, Packet *pkt)
+static void process_dczeroa(DisasContext *ctx)
{
- if (pkt->pkt_has_dczeroa) {
+ if (ctx->pkt->pkt_has_dczeroa) {
/* Store 32 bytes of zero starting at (addr & ~0x1f) */
TCGv addr = tcg_temp_new();
TCGv_i64 zero = tcg_constant_i64(0);
@@ -567,7 +569,7 @@ static bool pkt_has_hvx_store(Packet *pkt)
return false;
}
-static void gen_commit_hvx(DisasContext *ctx, Packet *pkt)
+static void gen_commit_hvx(DisasContext *ctx)
{
int i;
@@ -637,13 +639,14 @@ static void gen_commit_hvx(DisasContext *ctx, Packet *pkt)
}
}
- if (pkt_has_hvx_store(pkt)) {
+ if (pkt_has_hvx_store(ctx->pkt)) {
gen_helper_commit_hvx_stores(cpu_env);
}
}
-static void update_exec_counters(DisasContext *ctx, Packet *pkt)
+static void update_exec_counters(DisasContext *ctx)
{
+ Packet *pkt = ctx->pkt;
int num_insns = pkt->num_insns;
int num_real_insns = 0;
int num_hvx_insns = 0;
@@ -664,8 +667,7 @@ static void update_exec_counters(DisasContext *ctx, Packet *pkt)
ctx->num_hvx_insns += num_hvx_insns;
}
-static void gen_commit_packet(CPUHexagonState *env, DisasContext *ctx,
- Packet *pkt)
+static void gen_commit_packet(DisasContext *ctx)
{
/*
* If there is more than one store in a packet, make sure they are all OK
@@ -684,6 +686,7 @@ static void gen_commit_packet(CPUHexagonState *env, DisasContext *ctx,
* store. Therefore, we call process_store_log before anything else
* involved in committing the packet.
*/
+ Packet *pkt = ctx->pkt;
bool has_store_s0 = pkt->pkt_has_store_s0;
bool has_store_s1 = (pkt->pkt_has_store_s1 && !ctx->s1_store_processed);
bool has_hvx_store = pkt_has_hvx_store(pkt);
@@ -693,7 +696,7 @@ static void gen_commit_packet(CPUHexagonState *env, DisasContext *ctx,
* a store in slot 1 or an HVX store.
*/
g_assert(!has_store_s1 && !has_hvx_store);
- process_dczeroa(ctx, pkt);
+ process_dczeroa(ctx);
} else if (has_hvx_store) {
TCGv mem_idx = tcg_constant_tl(ctx->mem_idx);
@@ -724,14 +727,14 @@ static void gen_commit_packet(CPUHexagonState *env, DisasContext *ctx,
gen_helper_probe_pkt_scalar_store_s0(cpu_env, mem_idx);
}
- process_store_log(ctx, pkt);
+ process_store_log(ctx);
gen_reg_writes(ctx);
- gen_pred_writes(ctx, pkt);
+ gen_pred_writes(ctx);
if (pkt->pkt_has_hvx) {
- gen_commit_hvx(ctx, pkt);
+ gen_commit_hvx(ctx);
}
- update_exec_counters(ctx, pkt);
+ update_exec_counters(ctx);
if (HEX_DEBUG) {
TCGv has_st0 =
tcg_constant_tl(pkt->pkt_has_store_s0 && !pkt->pkt_has_dczeroa);
@@ -744,7 +747,8 @@ static void gen_commit_packet(CPUHexagonState *env, DisasContext *ctx,
if (pkt->vhist_insn != NULL) {
ctx->pre_commit = false;
- pkt->vhist_insn->generate(env, ctx, pkt->vhist_insn, pkt);
+ ctx->insn = pkt->vhist_insn;
+ pkt->vhist_insn->generate(ctx);
}
if (pkt->pkt_has_cof) {
@@ -767,11 +771,13 @@ static void decode_and_translate_packet(CPUHexagonState *env, DisasContext *ctx)
if (decode_packet(nwords, words, &pkt, false) > 0) {
HEX_DEBUG_PRINT_PKT(&pkt);
- gen_start_packet(ctx, &pkt);
+ ctx->pkt = &pkt;
+ gen_start_packet(ctx);
for (i = 0; i < pkt.num_insns; i++) {
- gen_insn(env, ctx, &pkt.insn[i], &pkt);
+ ctx->insn = &pkt.insn[i];
+ gen_insn(ctx);
}
- gen_commit_packet(env, ctx, &pkt);
+ gen_commit_packet(ctx);
ctx->base.pc_next += pkt.encod_pkt_size_in_bytes;
} else {
gen_exception_end_tb(ctx, HEX_EXCP_INVALID_PACKET);
diff --git a/target/hexagon/gen_tcg_funcs.py b/target/hexagon/gen_tcg_funcs.py
index 6dea02b0b9..02a6565685 100755
--- a/target/hexagon/gen_tcg_funcs.py
+++ b/target/hexagon/gen_tcg_funcs.py
@@ -561,11 +561,7 @@ def genptr_dst_write_opn(f,regtype, regid, tag):
## Generate the TCG code to call the helper
## For A2_add: Rd32=add(Rs32,Rt32), { RdV=RsV+RtV;}
## We produce:
-## static void generate_A2_add()
-## CPUHexagonState *env
-## DisasContext *ctx,
-## Insn *insn,
-## Packet *pkt)
+## static void generate_A2_add(DisasContext *ctx)
## {
## TCGv RdV = tcg_temp_local_new();
## const int RdN = insn->regno[0];
@@ -584,12 +580,11 @@ def genptr_dst_write_opn(f,regtype, regid, tag):
## <GEN> is gen_helper_A2_add(RdV, cpu_env, RsV, RtV);
##
def gen_tcg_func(f, tag, regs, imms):
- f.write("static void generate_%s(\n" %tag)
- f.write(" CPUHexagonState *env,\n")
- f.write(" DisasContext *ctx,\n")
- f.write(" Insn *insn,\n")
- f.write(" Packet *pkt)\n")
+ f.write("static void generate_%s(DisasContext *ctx)\n" %tag)
f.write('{\n')
+
+ f.write(" Insn *insn __attribute__((unused)) = ctx->insn;\n")
+
if hex_common.need_ea(tag): gen_decl_ea_tcg(f, tag)
i=0
## Declare all the operands (regs and immediates)
--
2.17.1
© 2016 - 2024 Red Hat, Inc.