Merge remote-tracking branch 'upstream/master' into raii

.github/workflows/main.yml

@@ -19,14 +19,14 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        # Note: macOS 12 runs on x86 hardware, and 14 runs on M1 hardware
-        os: ['macos-12', 'macos-14', 'windows-2022']
+        # Note: macOS 13 runs on x86 hardware, and 14 runs on M1 hardware
+        os: ['macos-13', 'macos-14', 'windows-2022']
         llvm: ['11', '12', '13', '14', '15', '16', '17', '18']
         cuda: ['0', '1']
         lua: ['luajit', 'moonjit']
         exclude:
           # macOS: exclude cuda
-          - os: 'macos-12'
+          - os: 'macos-13'
             cuda: '1'
           - os: 'macos-14'
             cuda: '1'

src/tcompiler.cpp

@@ -228,6 +228,25 @@ bool HostHasAVX() {
     return Features["avx"];
 }
 
+bool HostHasAVX512() {
+    StringMap<bool> Features;
+    sys::getHostCPUFeatures(Features);
+    // The following instructions sets are supported by Intel CPUs starting 2017
+    // (Skylake-SP and beyond) and AMD CPUs starting 2022 (Zen4 and beyond)
+    const char *instruction_set[] = {
+            "avx512f",   // Foundation
+            "avx512dq",  // Double Word, Quad Word
+            "avx512bw",  // Vector Byte and Word
+            "avx512vl",  // Vector Length
+            "avx512cd",  // Conflict Detection
+    };
+    bool has_avx512 = true;
+    for (auto &instr : instruction_set) {
+        has_avx512 &= Features[instr];
+    }
+    return has_avx512;
+}
+
 int terra_inittarget(lua_State *L) {
     terra_State *T = terra_getstate(L, 1);
     TerraTarget *TT = new TerraTarget();
@@ -257,7 +276,13 @@ int terra_inittarget(lua_State *L) {
 #ifdef DISABLE_AVX
         TT->Features = "-avx";
 #else
-        TT->Features = HostHasAVX() ? "+avx" : "";
+        if (HostHasAVX512()) {
+            TT->Features = "+avx512f,+avx512dq,+avx512bw,+avx512vl,+avx512cd";
+        } else if (HostHasAVX()) {
+            TT->Features = "+avx";
+        } else {
+            TT->Features = "";
+        }
 #endif
     }
 

tests/avx512.t

@@ -0,0 +1,8 @@
+local vec = vector(int8, 64)
+terra compute(x: vec, y: vec)
+    -- vec has a size of 8 * 64 = 512 bits so this operation should compile
+    -- to a single AVX512 instruction
+    return x + y
+end
+compute:compile()
+compute:disas()