Hexagon (target/hexagon) Improve code gen for predicated HVX instructions

[mirror_qemu.git] / target / hexagon / README

diff --git a/target/hexagon/README b/target/hexagon/README
index 372e24747c9fb29c433dd7ade3e9c4de901d5f09..ebafc78b1cff1ae61f333b330c73ec2fd838dd05 100644 (file)
--- a/target/hexagon/README
+++ b/target/hexagon/README
@@ -27,6 +27,10 @@ Hexagon-specific code are
         encode*.def             Encoding patterns for each instruction
         iclass.def              Instruction class definitions used to determine
                                 legal VLIW slots for each instruction
+    qemu/target/hexagon/idef-parser
+        Parser that, given the high-level definitions of an instruction,
+        produces a C function generating equivalent tiny code instructions.
+        See README.rst.
     qemu/linux-user/hexagon
         Helpers for loading the ELF file and making Linux system calls,
         signals, etc
@@ -47,6 +51,8 @@ header files in <BUILD_DIR>/target/hexagon
         gen_tcg_funcs.py                -> tcg_funcs_generated.c.inc
         gen_tcg_func_table.py           -> tcg_func_table_generated.c.inc
         gen_helper_funcs.py             -> helper_funcs_generated.c.inc
+        gen_idef_parser_funcs.py        -> idef_parser_input.h
+        gen_analyze_funcs.py            -> analyze_funcs_generated.c.inc
 
 Qemu helper functions have 3 parts
     DEF_HELPER declaration indicates the signature of the helper
@@ -76,14 +82,12 @@ tcg_funcs_generated.c.inc
                     Insn *insn,
                     Packet *pkt)
     {
-        TCGv RdV = tcg_temp_local_new();
+        TCGv RdV = tcg_temp_new();
         const int RdN = insn->regno[0];
         TCGv RsV = hex_gpr[insn->regno[1]];
         TCGv RtV = hex_gpr[insn->regno[2]];
         gen_helper_A2_add(RdV, cpu_env, RsV, RtV);
         gen_log_reg_write(RdN, RdV);
-        ctx_log_reg_write(ctx, RdN);
-        tcg_temp_free(RdV);
     }
 
 helper_funcs_generated.c.inc
@@ -132,35 +136,25 @@ For HVX vectors, the generator behaves slightly differently.  The wide vectors
 won't fit in a TCGv or TCGv_i64, so we pass TCGv_ptr variables to pass the
 address to helper functions.  Here's an example for an HVX vector-add-word
 istruction.
-    static void generate_V6_vaddw(
-                    CPUHexagonState *env,
-                    DisasContext *ctx,
-                    Insn *insn,
-                    Packet *pkt)
+    static void generate_V6_vaddw(DisasContext *ctx)
     {
+        Insn *insn __attribute__((unused)) = ctx->insn;
         const int VdN = insn->regno[0];
         const intptr_t VdV_off =
             ctx_future_vreg_off(ctx, VdN, 1, true);
-        TCGv_ptr VdV = tcg_temp_local_new_ptr();
+        TCGv_ptr VdV = tcg_temp_new_ptr();
         tcg_gen_addi_ptr(VdV, cpu_env, VdV_off);
         const int VuN = insn->regno[1];
         const intptr_t VuV_off =
             vreg_src_off(ctx, VuN);
-        TCGv_ptr VuV = tcg_temp_local_new_ptr();
+        TCGv_ptr VuV = tcg_temp_new_ptr();
         const int VvN = insn->regno[2];
         const intptr_t VvV_off =
             vreg_src_off(ctx, VvN);
-        TCGv_ptr VvV = tcg_temp_local_new_ptr();
+        TCGv_ptr VvV = tcg_temp_new_ptr();
         tcg_gen_addi_ptr(VuV, cpu_env, VuV_off);
         tcg_gen_addi_ptr(VvV, cpu_env, VvV_off);
-        TCGv slot = tcg_constant_tl(insn->slot);
-        gen_helper_V6_vaddw(cpu_env, VdV, VuV, VvV, slot);
-        tcg_temp_free(slot);
-        gen_log_vreg_write(ctx, VdV_off, VdN, EXT_DFL, insn->slot, false);
-        ctx_log_vreg_write(ctx, VdN, EXT_DFL, false);
-        tcg_temp_free_ptr(VdV);
-        tcg_temp_free_ptr(VuV);
-        tcg_temp_free_ptr(VvV);
+        gen_helper_V6_vaddw(cpu_env, VdV, VuV, VvV);
     }
 
 Notice that we also generate a variable named <operand>_off for each operand of
@@ -173,12 +167,9 @@ functions from tcg-op-gvec.h.  Here's the override for this instruction.
 Finally, we notice that the override doesn't use the TCGv_ptr variables, so
 we don't generate them when an override is present.  Here is what we generate
 when the override is present.
-    static void generate_V6_vaddw(
-                    CPUHexagonState *env,
-                    DisasContext *ctx,
-                    Insn *insn,
-                    Packet *pkt)
+    static void generate_V6_vaddw(DisasContext *ctx)
     {
+        Insn *insn __attribute__((unused)) = ctx->insn;
         const int VdN = insn->regno[0];
         const intptr_t VdV_off =
             ctx_future_vreg_off(ctx, VdN, 1, true);
@@ -189,10 +180,14 @@ when the override is present.
         const intptr_t VvV_off =
             vreg_src_off(ctx, VvN);
         fGEN_TCG_V6_vaddw({ fHIDE(int i;) fVFOREACH(32, i) { VdV.w[i] = VuV.w[i] + VvV.w[i] ; } });
-        gen_log_vreg_write(ctx, VdV_off, VdN, EXT_DFL, insn->slot, false);
-        ctx_log_vreg_write(ctx, VdN, EXT_DFL, false);
     }
 
+We also generate an analyze_<tag> function for each instruction.  Currently,
+these functions record the writes to registers by calling ctx_log_*.  During
+gen_start_packet, we invoke the analyze_<tag> function for each instruction in
+the packet, and we mark the implicit writes.  After the analysis is performed,
+we initialize hex_new_value for each of the predicated assignments.
+
 In addition to instruction semantics, we use a generator to create the decode
 tree.  This generation is also a two step process.  The first step is to run
 target/hexagon/gen_dectree_import.c to produce
@@ -277,10 +272,8 @@ For Hexagon Vector eXtensions (HVX), the following fields are used
     VRegs                       Vector registers
     future_VRegs                Registers to be stored during packet commit
     tmp_VRegs                   Temporary registers *not* stored during commit
-    VRegs_updated               Mask of predicated vector writes
     QRegs                       Q (vector predicate) registers
     future_QRegs                Registers to be stored during packet commit
-    QRegs_updated               Mask of predicated vector writes
 
 *** Debugging ***