feat(verify): complete the analyze family and add stereo16 differential tests

Assisted-by: Qwen 3.8 Max Preview

cmd/gasm/main.go

@@ -29,7 +29,7 @@ import (
 
 // version is the release version, stamped at build time via
 // -ldflags "-X main.version=…" (defaulting to the current release).
-var version = "0.23.0"
+var version = "0.24.0"
 
 func main() {
 	if len(os.Args) < 2 {

justfile

@@ -3,7 +3,7 @@
 
 # gasm-devkit — developer tooling for Go's Plan 9 assembler (GAsm).
 
-version := "0.23.0"
+version := "0.24.0"
 
 default:
     @just --list

verify/flac_test.go

@@ -148,6 +148,13 @@ func decodeMono24Go(src []byte, dst []int32) {
 	}
 }
 
+func decodeStereo16Go(src []byte, left, right []int32) {
+	for i := 0; i < len(left); i++ {
+		left[i] = int32(int16(uint16(src[4*i]) | uint16(src[4*i+1])<<8))
+		right[i] = int32(int16(uint16(src[4*i+2]) | uint16(src[4*i+3])<<8))
+	}
+}
+
 // --- Differential tests ---
 
 func TestFLACDecodeMono16(t *testing.T) {
@@ -441,6 +448,62 @@ func TestFLACAnalyzeResRange(t *testing.T) {
 	runAnalyzeTest(t, k, "analyzeResRangeAVX2", 0, analyzeResRangeGo)
 }
 
+func TestFLACAnalyzeO3Range(t *testing.T) {
+	k := loadFLACKernel(t)
+	ref := func(swin []int32, dstP []uint32, hist *[32]uint16) (uint64, bool) {
+		swin = swin[:len(dstP)+3]
+		var partSum uint64
+		var overflow bool
+		for j := 0; j+3 < len(swin); j++ {
+			r := swin[j+3] - 3*swin[j+2] + 3*swin[j+1] - swin[j]
+			if r == -2147483648 {
+				overflow = true
+			}
+			f := uint32(r<<1) ^ uint32(r>>31)
+			dstP[j] = f
+			partSum += uint64(f)
+			bl := 0
+			for v := f; v > 0; v >>= 1 {
+				bl++
+			}
+			if bl > 31 {
+				bl = 31
+			}
+			hist[bl]++
+		}
+		return partSum, overflow
+	}
+	runAnalyzeTest(t, k, "analyzeO3RangeAVX2", 3, ref)
+}
+
+func TestFLACAnalyzeO4Range(t *testing.T) {
+	k := loadFLACKernel(t)
+	ref := func(swin []int32, dstP []uint32, hist *[32]uint16) (uint64, bool) {
+		swin = swin[:len(dstP)+4]
+		var partSum uint64
+		var overflow bool
+		for j := 0; j+4 < len(swin); j++ {
+			r := swin[j+4] - 4*swin[j+3] + 6*swin[j+2] - 4*swin[j+1] + swin[j]
+			if r == -2147483648 {
+				overflow = true
+			}
+			f := uint32(r<<1) ^ uint32(r>>31)
+			dstP[j] = f
+			partSum += uint64(f)
+			bl := 0
+			for v := f; v > 0; v >>= 1 {
+				bl++
+			}
+			if bl > 31 {
+				bl = 31
+			}
+			hist[bl]++
+		}
+		return partSum, overflow
+	}
+	runAnalyzeTest(t, k, "analyzeO4RangeAVX2", 4, ref)
+}
+
 func TestFLACDecodeMono24(t *testing.T) {
 	k := loadFLACKernel(t)
 	rng := rand.New(rand.NewSource(55))
@@ -477,3 +540,46 @@ func TestFLACDecodeMono24(t *testing.T) {
 		}
 	}
 }
+
+func TestFLACDecodeStereo16(t *testing.T) {
+	k := loadFLACKernel(t)
+	rng := rand.New(rand.NewSource(66))
+
+	for iter := 0; iter < 500; iter++ {
+		n := rng.Intn(256)
+		src := make([]byte, 4*n) // [L0,R0,L1,R1,...]
+		rng.Read(src)
+
+		goLeft := make([]int32, n)
+		goRight := make([]int32, n)
+		decodeStereo16Go(src, goLeft, goRight)
+
+		jitLeft := make([]int32, n)
+		jitRight := make([]int32, n)
+		args := make([]byte, 72)
+		if len(src) > 0 {
+			PutPtr(args, 0, unsafe.Pointer(&src[0]))
+		}
+		PutUint64(args, 8, uint64(len(src)))
+		PutUint64(args, 16, uint64(cap(src)))
+		if n > 0 {
+			PutPtr(args, 24, unsafe.Pointer(&jitLeft[0]))
+			PutPtr(args, 48, unsafe.Pointer(&jitRight[0]))
+		}
+		PutUint64(args, 32, uint64(n))
+		PutUint64(args, 40, uint64(cap(jitLeft)))
+		PutUint64(args, 56, uint64(n))
+		PutUint64(args, 64, uint64(cap(jitRight)))
+
+		_, err := k.CallFunc("decodeStereo16AVX2", args)
+		if err != nil {
+			t.Fatalf("iter %d: %v", iter, err)
+		}
+		for i := 0; i < n; i++ {
+			if jitLeft[i] != goLeft[i] || jitRight[i] != goRight[i] {
+				t.Fatalf("iter %d: [%d] L: JIT=%d Go=%d; R: JIT=%d Go=%d",
+					iter, i, jitLeft[i], goLeft[i], jitRight[i], goRight[i])
+			}
+		}
+	}
+}