Introduce macro operation fusion

Through our observations, we have identified certain patterns in instruction
sequences. By converting these specific RISC-V instruction patterns into
faster and equivalent code, we can significantly improve execution efficiency.

In our current analysis, we focus on a commonly used benchmark and have
found the following frequently occurring instruction patterns: auipc + addi,
auipc + add, multiple sw, and multiple lw.

|  Metric  |     commit fba5802       |    macro fuse operation   |Speedup|
|----------+--------------------------+---------------------------+-------|
| CoreMark | 1351.065 (Iterations/Sec)|  1352.843 (Iterations/Sec)|+0.13% |
| dhrystone|       1073 DMIPS         |        1146 DMIPS         | +6.8% |
| nqueens  |       8295 msec          |        7824 msec          | +6.0% |

Author: qwe661234

src/decode.h

@@ -156,7 +156,15 @@
         _(cjalr, 1)                        \
         _(cadd, 0)                         \
         _(cswsp, 0)                        \
-    )
+    )                                      \
+    /* macro operation fusion: convert specific RISC-V instruction patterns 
+     * into faster and equivalent code 
+     */                                    \
+    _(fuse1, 0)                            \
+    _(fuse2, 0)                            \
+    _(fuse3, 0)                            \
+    _(fuse4, 0)                            \
+    _(empty, 0)
 /* clang-format on */
 
 /* IR list */
@@ -228,6 +236,11 @@ enum {
     INSN_32 = 4,
 };
 
+typedef struct {
+    int32_t imm;
+    uint8_t rd, rs1, rs2;
+} opcode_fuse_t;
+
 typedef struct rv_insn {
     union {
         int32_t imm;
@@ -240,6 +253,9 @@ typedef struct rv_insn {
 #if RV32_HAS(EXT_C)
     uint8_t shamt;
 #endif
+    /* fuse operation */
+    int32_t imm2;
+    opcode_fuse_t *fuse;
 
     /* instruction length */
     uint8_t insn_len;

src/emulate.c

@@ -31,6 +31,7 @@ extern struct target_ops gdbstub_ops;
 #include "decode.h"
 #include "riscv.h"
 #include "riscv_private.h"
+#include "state.h"
 #include "utils.h"
 
 /* RISC-V exception code list */
@@ -1219,6 +1220,60 @@ RVOP(cswsp, {
 })
 #endif
 
+/* auipc + addi */
+RVOP(fuse1, {
+    rv->X[ir->rd] = (int32_t) (rv->PC + ir->imm + ir->imm2);
+    rv->PC += ir->insn_len;
+})
+
+/* auipc + add */
+RVOP(fuse2, {
+    rv->X[ir->rd] = (int32_t) (rv->X[ir->rs1]) + (int32_t) (rv->PC + ir->imm);
+    rv->PC += ir->insn_len;
+})
+
+/* multiple sw */
+RVOP(fuse3, {
+    opcode_fuse_t *fuse = ir->fuse;
+    uint32_t addr = rv->X[fuse[0].rs1] + fuse[0].imm;
+    /* the memory addresses of the sw instructions are contiguous, so we only
+     * need to check the first sw instruction to determine if its memory address
+     * is misaligned or if the memory chunk does not exist.
+     */
+    RV_EXC_MISALIGN_HANDLER(3, store, false, 1);
+    rv->io.mem_write_w(rv, addr, rv->X[fuse[0].rs2]);
+    for (int i = 1; i < ir->imm2; i++) {
+        addr = rv->X[fuse[i].rs1] + fuse[i].imm;
+        rv->io.mem_write_w(rv, addr, rv->X[fuse[i].rs2]);
+    }
+    rv->PC += ir->insn_len * (ir->imm2 - 1);
+})
+
+/* multiple lw */
+RVOP(fuse4, {
+    opcode_fuse_t *fuse = ir->fuse;
+    uint32_t addr = rv->X[fuse[0].rs1] + fuse[0].imm;
+    /* the memory addresses of the lw instructions are contiguous, so we only
+     * need to check the first lw instruction to determine if its memory address
+     * is misaligned or if the memory chunk does not exist.
+     */
+    RV_EXC_MISALIGN_HANDLER(3, load, false, 1);
+    rv->X[fuse[0].rd] = rv->io.mem_read_w(rv, addr);
+    for (int i = 1; i < ir->imm2; i++) {
+        addr = rv->X[fuse[i].rs1] + fuse[i].imm;
+        rv->X[fuse[i].rd] = rv->io.mem_read_w(rv, addr);
+    }
+    rv->PC += ir->insn_len * (ir->imm2 - 1);
+})
+
+static bool do_empty(riscv_t *rv, const rv_insn_t *ir)
+{
+    rv->X[rv_reg_zero] = 0;
+    rv->csr_cycle++;
+    const rv_insn_t *next = ir + 1;
+    MUST_TAIL return next->impl(rv, next);
+}
+
 static const void *dispatch_table[] = {
 #define _(inst, can_branch) [rv_insn_##inst] = do_##inst,
     RISCV_INSN_LIST
@@ -1337,7 +1392,6 @@ static void block_translate(riscv_t *rv, block_t *block)
         /* compute the end of pc */
         block->pc_end += ir->insn_len;
         block->n_insn++;
-
         /* stop on branch */
         if (insn_is_branch(ir->opcode)) {
             /* recursive jump translation */
@@ -1356,6 +1410,78 @@ static void block_translate(riscv_t *rv, block_t *block)
     block->ir[block->n_insn - 1].tailcall = true;
 }
 
+#define pack_memory_operation(RW)                                          \
+    count = 1;                                                             \
+    next_ir = ir + 1;                                                      \
+    if (next_ir->opcode != IIF(RW)(rv_insn_lw, rv_insn_sw))                \
+        break;                                                             \
+    sign = (ir->imm - next_ir->imm) >> 31 ? -1 : 1;                        \
+    for (uint32_t j = 1; j < block->n_insn - 1 - i; j++) {                 \
+        next_ir = ir + j;                                                  \
+        if (next_ir->opcode != IIF(RW)(rv_insn_lw, rv_insn_sw) ||          \
+            ir->rs1 != next_ir->rs1 || ir->imm - next_ir->imm != 4 * sign) \
+            break;                                                         \
+        count++;                                                           \
+    }                                                                      \
+    if (count > 1) {                                                       \
+        ir->opcode = IIF(RW)(rv_insn_fuse4, rv_insn_fuse3);                \
+        ir->fuse = malloc(count * sizeof(opcode_fuse_t));           \
+        ir->imm2 = count;                                                  \
+        memcpy(ir->fuse, ir, sizeof(opcode_fuse_t));                \
+        ir->impl = dispatch_table[ir->opcode];                             \
+        for (int j = 1; j < count; j++) {                                  \
+            next_ir = ir + j;                                              \
+            memcpy(ir->fuse + j, next_ir, sizeof(opcode_fuse_t));   \
+            next_ir->opcode = rv_insn_empty;                               \
+            next_ir->impl = dispatch_table[next_ir->opcode];               \
+        }                                                                  \
+    }                                                                      \
+    break;
+
+
+/* examine whether instructions in a block match a specific pattern. If so,
+ * rewrite them into fused instructions. */
+static void match_pattern(block_t *block)
+{
+    for (uint32_t i = 0; i < block->n_insn - 1; i++) {
+        rv_insn_t *ir = block->ir + i, *next_ir = NULL;
+        int32_t count = 0, sign = 1;
+        switch (ir->opcode) {
+        case rv_insn_auipc:
+            next_ir = ir + 1;
+            if (next_ir->opcode == rv_insn_addi && ir->rd == next_ir->rs1) {
+                /* the destination register of instruction auipc is equal to the
+                 * source register 1 of next instruction addi */
+                ir->opcode = rv_insn_fuse1;
+                ir->rd = next_ir->rd;
+                ir->imm2 = next_ir->imm;
+                ir->impl = dispatch_table[ir->opcode];
+                next_ir->opcode = rv_insn_empty;
+                next_ir->impl = dispatch_table[next_ir->opcode];
+            } else if (next_ir->opcode == rv_insn_add &&
+                       ir->rd == next_ir->rs2) {
+                /* the destination register of instruction auipc is equal to the
+                 * source register 2 of next instruction add */
+                ir->opcode = rv_insn_fuse2;
+                ir->rd = next_ir->rd;
+                ir->rs1 = next_ir->rs1;
+                ir->impl = dispatch_table[ir->opcode];
+                next_ir->opcode = rv_insn_empty;
+                next_ir->impl = dispatch_table[next_ir->opcode];
+            }
+            break;
+        case rv_insn_sw:
+            /* If the memory addresses of a sequence of store instructions for
+             * data are contiguous, pack these instructions. */
+            pack_memory_operation(0);
+        case rv_insn_lw:
+            /* If the memory addresses of a sequence of load instructions for
+             * data are contiguous, pack these instructions. */
+            pack_memory_operation(1);
+        }
+    }
+}
+
 static block_t *prev = NULL;
 static block_t *block_find_or_translate(riscv_t *rv)
 {
@@ -1375,6 +1501,9 @@ static block_t *block_find_or_translate(riscv_t *rv)
         /* translate the basic block */
         block_translate(rv, next);
 
+        /* macro operation fusion */
+        match_pattern(next);
+
         /* insert the block into block map */
         block_insert(&rv->block_map, next);
 

src/riscv.c

@@ -25,6 +25,10 @@ void block_map_clear(block_map_t *map)
         block_t *block = map->map[i];
         if (!block)
             continue;
+        for (uint32_t i = 0; i < block->n_insn; i++) {
+            if (block->ir[i].fuse)
+                free(block->ir[i].fuse);
+        }
         free(block->ir);
         free(block);
         map->map[i] = NULL;