Common: Add 2D vector formatters

src/common/gsvector_formatter.h

@@ -8,6 +8,26 @@
 
 #include "fmt/format.h"
 
+template<>
+struct fmt::formatter<GSVector2i> : formatter<std::string_view>
+{
+  auto format(const GSVector2i& rc, format_context& ctx) const
+  {
+    const TinyString str = TinyString::from_format("{},{}", rc.x, rc.y);
+    return fmt::formatter<std::string_view>::format(str.view(), ctx);
+  }
+};
+
+template<>
+struct fmt::formatter<GSVector2> : formatter<std::string_view>
+{
+  auto format(const GSVector2& rc, format_context& ctx) const
+  {
+    const TinyString str = TinyString::from_format("{},{}", rc.x, rc.y);
+    return fmt::formatter<std::string_view>::format(str.view(), ctx);
+  }
+};
+
 template<>
 struct fmt::formatter<GSVector4i> : formatter<std::string_view>
 {
@@ -19,3 +39,13 @@ struct fmt::formatter<GSVector4i> : formatter<std::string_view>
     return fmt::formatter<std::string_view>::format(str.view(), ctx);
   }
 };
+
+template<>
+struct fmt::formatter<GSVector4> : formatter<std::string_view>
+{
+  auto format(const GSVector4& rc, format_context& ctx) const
+  {
+    const TinyString str = TinyString::from_format("{},{},{},{}", rc.x, rc.y, rc.z, rc.w);
+    return fmt::formatter<std::string_view>::format(str.view(), ctx);
+  }
+};

src/common/gsvector_neon.h

@@ -359,7 +359,7 @@ public:
 
 #endif
 
-  ALWAYS_INLINE GSVector2i i8to16() const
+  ALWAYS_INLINE GSVector2i s8to16() const
   {
     return GSVector2i(vreinterpret_s32_s16(vget_low_s8(vmovl_s8(vreinterpret_s8_s32(v2s)))));
   }
@@ -369,6 +369,23 @@ public:
     return GSVector2i(vreinterpret_s32_u16(vget_low_u8(vmovl_u8(vreinterpret_u8_s32(v2s)))));
   }
 
+  ALWAYS_INLINE GSVector2i s8to32() const
+  {
+    return GSVector2i(vget_low_s32(vmovl_s16(vget_low_s16(vmovl_s8(vreinterpret_s8_s32(v2s))))));
+  }
+
+  ALWAYS_INLINE GSVector2i u8to32() const
+  {
+    return GSVector2i(vreinterpret_s32_u32(vget_low_u32(vmovl_u16(vget_low_u16(vmovl_u8(vreinterpret_u8_s32(v2s)))))));
+  }
+
+  ALWAYS_INLINE GSVector2i s16to32() const { return GSVector2i(vget_low_s32(vmovl_s16(vreinterpret_s16_s32(v2s)))); }
+
+  ALWAYS_INLINE GSVector2i u16to32() const
+  {
+    return GSVector2i(vreinterpret_s32_u32(vget_low_u32(vmovl_u16(vreinterpret_u16_s32(v2s)))));
+  }
+
   template<int i>
   ALWAYS_INLINE GSVector2i srl() const
   {

src/common/gsvector_nosimd.h

@@ -248,7 +248,12 @@ public:
 
   GSVector2i upl32() const { return GSVector2i(S32[0], 0); }
 
-  GSVector2i i8to16() const { ALL_LANES_16(ret.S16[i] = S8[i]); }
+  GSVector2i s8to16() const { ALL_LANES_16(ret.S16[i] = S8[i]); }
+  GSVector2i s8to32() const { ALL_LANES_32(ret.S32[i] = S8[i]); }
+  GSVector2i u8to16() const { ALL_LANES_16(ret.U16[i] = U8[i]); }
+  GSVector2i u8to32() const { ALL_LANES_32(ret.U32[i] = U8[i]); }
+  GSVector2i u16to32() const { ALL_LANES_32(ret.U32[i] = U16[i]); }
+  GSVector2i s16to32() const { ALL_LANES_32(ret.S32[i] = S16[i]); }
 
   template<s32 v>
   GSVector2i srl() const
@@ -1244,7 +1249,7 @@ public:
   GSVector4i s16to32() const { ALL_LANES_32(ret.S32[i] = S16[i]); }
   GSVector4i s16to64() const { ALL_LANES_64(ret.S64[i] = S16[i]); }
   GSVector4i s32to64() const { ALL_LANES_64(ret.S64[i] = S32[i]); }
-  GSVector4i u8to16() const { ALL_LANES_64(ret.U16[i] = U8[i]); }
+  GSVector4i u8to16() const { ALL_LANES_16(ret.U16[i] = U8[i]); }
   GSVector4i u8to32() const { ALL_LANES_32(ret.U32[i] = U8[i]); }
   GSVector4i u8to64() const { ALL_LANES_64(ret.U64[i] = U8[i]); }
   GSVector4i u16to32() const { ALL_LANES_32(ret.U32[i] = U16[i]); }
@@ -1846,10 +1851,7 @@ public:
 
   GSVector4 hsub(const GSVector4& v) const { return GSVector4(x - y, z - w, v.x - v.y, v.z - v.w); }
 
-  ALWAYS_INLINE float dot(const GSVector4& v) const
-  {
-    return (x * v.x) + (y * v.y) + (z * v.z) + (w * v.w);
-  }
+  ALWAYS_INLINE float dot(const GSVector4& v) const { return (x * v.x) + (y * v.y) + (z * v.z) + (w * v.w); }
 
   GSVector4 sat(const GSVector4& min, const GSVector4& max) const
   {
@@ -2316,10 +2318,7 @@ public:
 
   ALWAYS_INLINE GSVector2 zw() const { return GSVector2(z, w); }
 
-  ALWAYS_INLINE static GSVector4 xyxy(const GSVector2& l, const GSVector2& h)
-  {
-    return GSVector4(l.x, l.y, h.x, h.y);
-  }
+  ALWAYS_INLINE static GSVector4 xyxy(const GSVector2& l, const GSVector2& h) { return GSVector4(l.x, l.y, h.x, h.y); }
 
 #define VECTOR4_SHUFFLE_4(xs, xn, ys, yn, zs, zn, ws, wn)                                                              \
   ALWAYS_INLINE GSVector4 xs##ys##zs##ws() const { return GSVector4(F32[xn], F32[yn], F32[zn], F32[wn]); }

src/common/gsvector_sse.h

@@ -369,10 +369,21 @@ public:
   ALWAYS_INLINE GSVector2i upl32() const { return GSVector2i(_mm_unpacklo_epi32(m, _mm_setzero_si128())); }
   ALWAYS_INLINE GSVector2i uph32() const { return GSVector2i(_mm_unpackhi_epi32(m, _mm_setzero_si128())); }
 
-  ALWAYS_INLINE GSVector2i i8to16() const { return GSVector2i(_mm_cvtepi8_epi16(m)); }
-
 #ifdef CPU_ARCH_SSE41
   ALWAYS_INLINE GSVector2i u8to16() const { return GSVector2i(_mm_cvtepu8_epi16(m)); }
+  ALWAYS_INLINE GSVector2i u8to32() const { return GSVector2i(_mm_cvtepu8_epi32(m)); }
+  ALWAYS_INLINE GSVector2i s16to32() const { return GSVector2i(_mm_cvtepi16_epi32(m)); }
+  ALWAYS_INLINE GSVector2i u16to32() const { return GSVector2i(_mm_cvtepu16_epi32(m)); }
+#else
+  // These are a pain, adding only as needed...
+  ALWAYS_INLINE GSVector2i u8to16() const { return upl8(); }
+  ALWAYS_INLINE GSVector2i u8to32() const
+  {
+    return GSVector2i(_mm_unpacklo_epi16(_mm_unpacklo_epi8(m, _mm_setzero_si128()), _mm_setzero_si128()));
+  }
+
+  ALWAYS_INLINE GSVector2i s16to32() const { return upl16().sll32<16>().sra32<16>(); }
+  ALWAYS_INLINE GSVector2i u16to32() const { return upl16(); }
 #endif
 
   template<s32 i>