cmake: Added more x86_64 CPU backends when building with `GGML_CPU_ALL_VARIANTS=On` (#18186)

* minor: Consolidated `#include <immintrin.h>` under `ggml-cpu-impl.h`

* cmake: Added more x86-64 CPU backends when building with `GGML_CPU_ALL_VARIANTS=On`

- `ivybridge`
- `piledriver`
- `cannonlake`
- `cascadelake`
- `cooperlake`
- `zen4`

Resolves: #17966

ggml/CMakeLists.txt

@@ -430,10 +430,22 @@ if (MSVC)
     configure_msvc_target(ggml-cpu-x64)
     configure_msvc_target(ggml-cpu-sse42)
     configure_msvc_target(ggml-cpu-sandybridge)
+    # __FMA__ and __F16C__ are not defined in MSVC, however they are implied with AVX2/AVX512
+    # skipping            ggml-cpu-ivybridge
+    # skipping            ggml-cpu-piledriver
     configure_msvc_target(ggml-cpu-haswell)
     configure_msvc_target(ggml-cpu-skylakex)
+    configure_msvc_target(ggml-cpu-cannonlake)
+    configure_msvc_target(ggml-cpu-cascadelake)
     configure_msvc_target(ggml-cpu-icelake)
+    # MSVC 2022 doesn't support BF16 intrinsics without `/arch:AVX10.1` ?!
+    # https://learn.microsoft.com/en-us/cpp/intrinsics/x64-amd64-intrinsics-list?view=msvc-170
+    # https://learn.microsoft.com/en-us/cpp/build/reference/arch-x64?view=msvc-170
+    # skipping            ggml-cpu-cooperlake
+    # skipping            ggml-cpu-zen4
     configure_msvc_target(ggml-cpu-alderlake)
+    # MSVC doesn't support AMX
+    # skipping            ggml-cpu-sapphirerapids
 
     if (GGML_BUILD_EXAMPLES)
         configure_msvc_target(common-ggml)

ggml/src/CMakeLists.txt

@@ -357,15 +357,29 @@ if (GGML_CPU_ALL_VARIANTS)
     endif()
     if (GGML_SYSTEM_ARCH STREQUAL "x86")
         ggml_add_cpu_backend_variant(x64)
-        ggml_add_cpu_backend_variant(sse42        SSE42)
-        ggml_add_cpu_backend_variant(sandybridge  SSE42 AVX)
-        ggml_add_cpu_backend_variant(haswell      SSE42 AVX F16C AVX2 BMI2 FMA)
-        ggml_add_cpu_backend_variant(skylakex     SSE42 AVX F16C AVX2 BMI2 FMA AVX512)
-        ggml_add_cpu_backend_variant(icelake      SSE42 AVX F16C AVX2 BMI2 FMA AVX512 AVX512_VBMI AVX512_VNNI)
-        ggml_add_cpu_backend_variant(alderlake    SSE42 AVX F16C AVX2 BMI2 FMA AVX_VNNI)
+        ggml_add_cpu_backend_variant(sse42              SSE42)
+        ggml_add_cpu_backend_variant(sandybridge        SSE42 AVX)
+        if (NOT MSVC)
+            # __FMA__ and __F16C__ are not defined in MSVC, however they are implied with AVX2/AVX512
+            ggml_add_cpu_backend_variant(ivybridge      SSE42 AVX F16C)
+            ggml_add_cpu_backend_variant(piledriver     SSE42 AVX F16C FMA)
+        endif()
+        ggml_add_cpu_backend_variant(haswell            SSE42 AVX F16C FMA AVX2 BMI2)
+        ggml_add_cpu_backend_variant(skylakex           SSE42 AVX F16C FMA AVX2 BMI2 AVX512)
+        ggml_add_cpu_backend_variant(cannonlake         SSE42 AVX F16C FMA AVX2 BMI2 AVX512 AVX512_VBMI)
+        ggml_add_cpu_backend_variant(cascadelake        SSE42 AVX F16C FMA AVX2 BMI2 AVX512 AVX512_VNNI)
+        ggml_add_cpu_backend_variant(icelake            SSE42 AVX F16C FMA AVX2 BMI2 AVX512 AVX512_VBMI AVX512_VNNI)
+        if (NOT MSVC)
+            # MSVC 2022 doesn't support BF16 intrinsics without `/arch:AVX10.1` ?!
+            # https://learn.microsoft.com/en-us/cpp/intrinsics/x64-amd64-intrinsics-list?view=msvc-170
+            # https://learn.microsoft.com/en-us/cpp/build/reference/arch-x64?view=msvc-170
+            ggml_add_cpu_backend_variant(cooperlake     SSE42 AVX F16C FMA AVX2 BMI2 AVX512 AVX512_VNNI AVX512_BF16)
+            ggml_add_cpu_backend_variant(zen4           SSE42 AVX F16C FMA AVX2 BMI2 AVX512 AVX512_VBMI AVX512_VNNI AVX512_BF16)
+        endif()
+        ggml_add_cpu_backend_variant(alderlake          SSE42 AVX F16C FMA AVX2 BMI2 AVX_VNNI)
         if (NOT MSVC)
             # MSVC doesn't support AMX
-            ggml_add_cpu_backend_variant(sapphirerapids SSE42 AVX F16C AVX2 BMI2 FMA AVX512 AVX512_VBMI AVX512_VNNI AVX512_BF16 AMX_TILE AMX_INT8)
+            ggml_add_cpu_backend_variant(sapphirerapids SSE42 AVX F16C FMA AVX2 BMI2 AVX512 AVX512_VBMI AVX512_VNNI AVX512_BF16 AMX_TILE AMX_INT8)
         endif()
     elseif(GGML_SYSTEM_ARCH STREQUAL "ARM")
         if (CMAKE_SYSTEM_NAME MATCHES "Linux")

ggml/src/ggml-cpu/ggml-cpu-impl.h

@@ -328,7 +328,7 @@ inline static int32x4_t ggml_vdotq_s32(int32x4_t acc, int8x16_t a, int8x16_t b)
 
 #if defined(_MSC_VER) || defined(__MINGW32__)
 #include <intrin.h>
-#elif defined(__AVX__) || defined(__AVX2__) || defined(__AVX512F__) || defined(__SSSE3__) || defined(__SSE3__) || defined(__SSE__)
+#elif defined(__SSE__) || defined(__SSE3__) || defined(__SSSE3__) || defined(__AVX__) || defined(__F16C__) || defined(__AVX2__) || defined(__AVX512F__) || defined(__AVX512BF16__)
 #include <immintrin.h>
 #endif
 

ggml/src/ggml-cpu/simd-mappings.h

@@ -14,10 +14,6 @@
 #include <arm_neon.h>
 #endif
 
-#if defined(__F16C__)
-#include <immintrin.h>
-#endif
-
 #if defined(__riscv_v_intrinsic)
 #include <riscv_vector.h>
 #endif

ggml/src/ggml-impl.h

@@ -24,10 +24,6 @@
 #include <arm_neon.h>
 #endif
 
-#if defined(__F16C__)
-#include <immintrin.h>
-#endif
-
 #ifdef __cplusplus
 extern "C" {
 #endif