Added: lookup8 in VX4B using vlookup

lib_nn/src/asm/lookup8.S

@@ -103,5 +103,91 @@ FUNCTION_NAME:
 
 #endif
 
+#if defined(__VX4B__)
 
+/*
+void lookup8_asm(
+    uint8_t* Y,
+    const uint8_t* X,
+    const uint8_t* lut,
+    const unsigned elm_start,
+    const unsigned elm_count);
+*/
 
+#define FUNCTION_NAME lookup8_asm
+
+.p2align 2
+.globl FUNCTION_NAME
+.type FUNCTION_NAME,@function
+
+#define STACK_S2            (0)
+#define STACK_S3            (STACK_S2 + 4)
+#define STACK_S4            (STACK_S3 + 4)
+#define STACK_S5            (STACK_S4 + 4)
+#define STACK_S6            (STACK_S5 + 4)
+#define STACK_VEC1_TMP      (STACK_S6 + 4)
+#define STACK_RA            (STACK_VEC1_TMP + 32)
+#define NSTACKBYTES         (STACK_RA + 4)
+#define ROUND_UP(X, Y)      (((X+Y-1)/Y)*Y)
+
+#define out_data    a0
+#define in_data     a1
+#define lut         a2
+#define start       a3
+#define count       s2
+#define mask        s3
+#define counter     s4
+#define thirty_two  s5
+#define vec1_tmp    s6
+
+FUNCTION_NAME:
+
+    xm.entsp ROUND_UP(NSTACKBYTES, 16)
+    xm.stdsp s2, s3, 0*8
+    xm.stdsp s4, s5, 1*8
+    sw s6, 2*8(sp)
+    mv count, a4
+    { add out_data, out_data, start         ; add in_data, in_data, start           }
+    { addi vec1_tmp, sp, STACK_VEC1_TMP     ; xm.ldcu thirty_two, 32                }
+    { xm.mkmski mask, 32                    ; sub out_data, out_data, thirty_two    }   // out_data substract 32 first for optimize in the loop
+
+    // Set VPU to 8-bit mode
+    li x28, 512
+    { xm.vsetc x28                          ; xm.shri counter, count, 5 }
+    xm.vldc lut
+
+    FUNCTION_NAME.loop:
+        { xm.vldr in_data                   ; add in_data, in_data, thirty_two }
+        xm.vlookup lut, 0, 1
+        xm.vlookup lut, 1, 2
+        xm.vlookup lut, 2, 3
+        xm.vlookup lut, 3, 4
+        xm.vlookup lut, 4, 5
+        xm.vlookup lut, 5, 6
+        xm.vlookup lut, 6, 7
+        xm.vlookup lut, 7, 0
+        xm.bt counter, FUNCTION_NAME.save
+        // In last loop - make mask for remaining elements
+        xm.zexti count, 4
+        xm.mkmsk mask, count
+
+        FUNCTION_NAME.save:
+            xm.vstd vec1_tmp
+            { xm.vldr vec1_tmp                  ; add out_data, out_data, thirty_two    }
+            xm.vstrpv out_data, mask
+            { addi counter, counter, -1         ; xm.bt counter, FUNCTION_NAME.loop     }
+
+
+    xm.lddsp s2, s3, 0*8
+    xm.lddsp s4, s5, 1*8
+    lw s6, 3*8(sp)
+
+    xm.retsp ROUND_UP(NSTACKBYTES, 16)
+
+.size FUNCTION_NAME, . -FUNCTION_NAME
+.resource_const FUNCTION_NAME, "stack_frame_bytes",  ROUND_UP(NSTACKBYTES, 16)
+.resource_list_empty FUNCTION_NAME, "callees"
+.resource_list_empty FUNCTION_NAME, "tail_callees"
+.resource_list_empty FUNCTION_NAME, "parallel_callees"
+
+#endif

lib_nn/src/c/nn_operator.c

@@ -139,6 +139,15 @@ void lookup8_ref(uint8_t *Y, const uint8_t *X, const uint8_t *lut,
   }
 }
 
+#if defined(__XS3A__) || defined(__VX4B__)
+void lookup8_asm(
+    uint8_t* Y,
+    const uint8_t* X,
+    const uint8_t* lut,
+    const unsigned elm_start,
+    const unsigned elm_count);
+#endif
+
 #ifdef NN_USE_REF
 void requantize_16_to_8(int8_t *y, const int16_t *x, const unsigned elm_start,
                         const unsigned elm_count) {
@@ -148,10 +157,12 @@ void requantize_16_to_8(int8_t *y, const int16_t *x, const unsigned elm_start,
 
 void lookup8(uint8_t *Y, const uint8_t *X, const uint8_t *lut,
              const unsigned elm_start, const unsigned elm_count) {
-#if defined(NN_USE_REF) || defined(__VX4A__) || defined(__VX4B__)
+#if defined(NN_USE_REF)
   lookup8_ref(Y, X, lut, elm_start, elm_count);
-#elif defined(__XS3A__)
+#elif defined(__XS3A__) || defined(__VX4B__)
   lookup8_asm(Y, X, lut, elm_start, elm_count);
+#else
+  lookup8_ref(Y, X, lut, elm_start, elm_count);
 #endif // NN_USE_REF
 }