Daily update on 20250907-184649 by Nitload Youmu. Additional Message : Matrix parallel task packet is done, parallel task executer is done. Now is working on building parallel wrap and pool.

Signed-off-by: Nitload <YoumuLiu_NSI@whv0t.onmicrosoft.com>
2025-09-07 18:46:49 +08:00
parent bfe3ada4fc
commit a7f82c04ea
5 changed files with 241 additions and 168 deletions
@@ -23,7 +23,7 @@
                (LAST(reset2) << 2) | (LAST(reset1) << 1) | LAST(reset0)
 #define SSE_INSERT_SIMPLE(source, target) SSE_INSERT(source, target, 0, 0, 0, 0)
 #define M256_PERMUTE(s3, s2, s1, s0) (LASTTWO(s3) << 6) | (LASTTWO(s2) << 4) | (LASTTWO(s1) << 2) | (LASTTWO(s0)
-
+#define BIT_CVRT(pack, index, T) *(T *)(pack->data + index)
 #define zero_vec _mm_setzero_ps()
 #define zero_vec_256 _mm256_setzero_ps()

@@ -58,6 +58,10 @@ typedef union column_4 {
        float m[4][4];
 } __4_columnset;

+typedef union scalar_pack {
+        uint64_t data[8];
+} scalar_pack;
+
 typedef void(SN_DECL *VECTORNORMALIZEPROC)(__m128 *source, __m128 *target);
 typedef void(SN_DECL *DOTPROC)(void *transpose, __m128 *vector, __m128 *ans);
 typedef void(SN_DECL *MATRIXTRANSPOSEPROC)(void *source, void *target);