ggml, ci : Windows ARM runner and build fixes (llama/5979)

* windows arm ci * fix `error C2078: too many initializers` with ggml_vld1q_u32 macro for MSVC ARM64 * fix `warning C4146: unary minus operator applied to unsigned type, result still unsigned` * fix `error C2065: '__fp16': undeclared identifier`
wumch · Mar 15, 2024 · d73a636 · d73a636
1 parent f79d0d4
commit d73a636
Show file tree

Hide file tree

Showing 3 changed files with 16 additions and 12 deletions.
diff --git a/ggml-impl.h b/ggml-impl.h
@@ -53,26 +53,30 @@ extern "C" {
 //
 #include <arm_neon.h>
 
+typedef __fp16 ggml_fp16_internal_t;
+
 #define GGML_COMPUTE_FP16_TO_FP32(x) ggml_compute_fp16_to_fp32(x)
 #define GGML_COMPUTE_FP32_TO_FP16(x) ggml_compute_fp32_to_fp16(x)
 
 #define GGML_FP16_TO_FP32(x) ggml_compute_fp16_to_fp32(x)
 
 static inline float ggml_compute_fp16_to_fp32(ggml_fp16_t h) {
-    __fp16 tmp;
+    ggml_fp16_internal_t tmp;
     memcpy(&tmp, &h, sizeof(ggml_fp16_t));
     return (float)tmp;
 }
 
 static inline ggml_fp16_t ggml_compute_fp32_to_fp16(float f) {
     ggml_fp16_t res;
-    __fp16 tmp = f;
+    ggml_fp16_internal_t tmp = f;
     memcpy(&res, &tmp, sizeof(ggml_fp16_t));
     return res;
 }
 
 #else
 
+typedef uint16_t ggml_fp16_internal_t;
+
 #ifdef __wasm_simd128__
 #include <wasm_simd128.h>
 #else

diff --git a/ggml-quants.c b/ggml-quants.c
@@ -9374,15 +9374,15 @@ void ggml_vec_dot_iq3_s_q8_K (int n, float * restrict s, size_t bs, const void *
 
             const uint8x16_t idx_l = vld1q_u8(qs); qs += 16;
             idx.vec_index = vorrq_u16(vmovl_u8(vget_low_u8 (idx_l)), vandq_u16(vshlq_u16(vdupq_n_u16(qh[ib32+0]), hshift), m256));
-            const uint32x4_t aux32x4_0 = {iq3s_grid[idx.index[0]], iq3s_grid[idx.index[1]],
-                                          iq3s_grid[idx.index[2]], iq3s_grid[idx.index[3]]};
-            const uint32x4_t aux32x4_1 = {iq3s_grid[idx.index[4]], iq3s_grid[idx.index[5]],
-                                          iq3s_grid[idx.index[6]], iq3s_grid[idx.index[7]]};
+            const uint32x4_t aux32x4_0 = ggml_vld1q_u32(iq3s_grid[idx.index[0]], iq3s_grid[idx.index[1]],
+                                                        iq3s_grid[idx.index[2]], iq3s_grid[idx.index[3]]);
+            const uint32x4_t aux32x4_1 = ggml_vld1q_u32(iq3s_grid[idx.index[4]], iq3s_grid[idx.index[5]],
+                                                        iq3s_grid[idx.index[6]], iq3s_grid[idx.index[7]]);
             idx.vec_index = vorrq_u16(vmovl_u8(vget_high_u8(idx_l)), vandq_u16(vshlq_u16(vdupq_n_u16(qh[ib32+1]), hshift), m256));
-            const uint32x4_t aux32x4_2 = {iq3s_grid[idx.index[0]], iq3s_grid[idx.index[1]],
-                                          iq3s_grid[idx.index[2]], iq3s_grid[idx.index[3]]};
-            const uint32x4_t aux32x4_3 = {iq3s_grid[idx.index[4]], iq3s_grid[idx.index[5]],
-                                          iq3s_grid[idx.index[6]], iq3s_grid[idx.index[7]]};
+            const uint32x4_t aux32x4_2 = ggml_vld1q_u32(iq3s_grid[idx.index[0]], iq3s_grid[idx.index[1]],
+                                                        iq3s_grid[idx.index[2]], iq3s_grid[idx.index[3]]);
+            const uint32x4_t aux32x4_3 = ggml_vld1q_u32(iq3s_grid[idx.index[4]], iq3s_grid[idx.index[5]],
+                                                        iq3s_grid[idx.index[6]], iq3s_grid[idx.index[7]]);
 
 
             vs.val[0] = vreinterpretq_u8_u32(vdupq_n_u32(signs[0] | (signs[1] << 16)));

diff --git a/ggml.c b/ggml.c
@@ -857,7 +857,7 @@ inline static float vaddvq_f32(float32x4_t v) {
     #define GGML_F16x8              float16x8_t
     #define GGML_F16x8_ZERO         vdupq_n_f16(0.0f)
     #define GGML_F16x8_SET1(x)      vdupq_n_f16(x)
-    #define GGML_F16x8_LOAD(x)      vld1q_f16((const __fp16 *)(x))
+    #define GGML_F16x8_LOAD(x)      vld1q_f16((const ggml_fp16_internal_t *)(x))
     #define GGML_F16x8_STORE        vst1q_f16
     #define GGML_F16x8_FMA(a, b, c) vfmaq_f16(a, b, c)
     #define GGML_F16x8_ADD          vaddq_f16
@@ -900,7 +900,7 @@ inline static float vaddvq_f32(float32x4_t v) {
     #define GGML_F32Cx4              float32x4_t
     #define GGML_F32Cx4_ZERO         vdupq_n_f32(0.0f)
     #define GGML_F32Cx4_SET1(x)      vdupq_n_f32(x)
-    #define GGML_F32Cx4_LOAD(x)      vcvt_f32_f16(vld1_f16((const __fp16 *)(x)))
+    #define GGML_F32Cx4_LOAD(x)      vcvt_f32_f16(vld1_f16((const ggml_fp16_internal_t *)(x)))
     #define GGML_F32Cx4_STORE(x, y)  vst1_f16(x, vcvt_f16_f32(y))
     #define GGML_F32Cx4_FMA(a, b, c) vfmaq_f32(a, b, c)
     #define GGML_F32Cx4_ADD          vaddq_f32