feat(verify): add analyzeO1Range and fastStereoSums 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 = "0.19.0"
+var version = "0.22.0"
 
 func main() {
 	if len(os.Args) < 2 {
@@ -472,7 +472,7 @@ requires -p, the package path, and the installed Go toolchain).
 }
 
 func cmdVerify(args []string) int {
-	fs := newCommand("verify", "gasm verify <file.s>", `
+	fs := newCommand("verify", "gasm verify [-smoke] [-abi] [-profile] <file.s>", `
 Assemble FILE (amd64), map it into executable memory and report the available
 functions.  This confirms the assembled image is self-consistent (no
 unresolved external symbols) and executable — the prerequisite for dynamic
@@ -481,11 +481,18 @@ testing.
 With -smoke, each NOSPLIT function is called with a zeroed argument block to
 confirm the JIT trampoline works end-to-end.  This is safe only for functions
 that tolerate nil pointers and zero lengths in their arguments.
+
+With -abi, each function is called with sentinel values in the callee-saved
+registers (BP, R14) and a red-zone canary below SP; violations are reported.
+
+With -profile, the static basic-block structure is listed for each function.
 `)
 	smoke := fs.Bool("smoke", false, "call each NOSPLIT function with zeroed args")
+	abi := fs.Bool("abi", false, "run ABI-checking calls (sentinel registers + red zone)")
+	profile := fs.Bool("profile", false, "list basic-block structure per function")
 	fs.Parse(args)
 	if fs.NArg() != 1 {
-		fmt.Fprintln(os.Stderr, "usage: gasm verify [-smoke] <file.s>")
+		fmt.Fprintln(os.Stderr, "usage: gasm verify [-smoke] [-abi] [-profile] <file.s>")
 		return 2
 	}
 	path := fs.Arg(0)
@@ -511,6 +518,16 @@ that tolerate nil pointers and zero lengths in their arguments.
 			flags = " NOSPLIT"
 		}
 		fmt.Printf("  %s: %d bytes, args=%d, frame=%d%s\n", name, fl.Size, fl.Args, fl.Frame, flags)
+
+		if *profile {
+			blocks, err := k.Blocks(name)
+			if err != nil {
+				fmt.Printf("    profile: %v\n", err)
+			} else {
+				fmt.Printf("    blocks: %d\n", len(blocks))
+			}
+		}
+
 		if *smoke && fl.NoSplit {
 			args := make([]byte, fl.Args)
 			_, err := k.CallFunc(name, args)
@@ -521,6 +538,20 @@ that tolerate nil pointers and zero lengths in their arguments.
 				fmt.Printf("    smoke: OK\n")
 			}
 		}
+
+		if *abi && fl.NoSplit {
+			args := make([]byte, fl.Args)
+			_, report, err := k.CallFuncChecked(name, args)
+			if err != nil {
+				fmt.Printf("    abi: FAIL — %v\n", err)
+				rc = 1
+			} else if !report.OK() {
+				fmt.Printf("    abi: %s\n", report)
+				rc = 1
+			} else {
+				fmt.Printf("    abi: clean\n")
+			}
+		}
 	}
 	return rc
 }

justfile

@@ -3,7 +3,7 @@
 
 # gasm-devkit — developer tooling for Go's Plan 9 assembler (GAsm).
 
-version := "0.19.0"
+version := "0.22.0"
 
 default:
     @just --list

verify/avx512_test.go

@@ -0,0 +1,144 @@
+// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
+// SPDX-License-Identifier: BSD-3-Clause
+
+package verify
+
+import (
+	"bytes"
+	"math/rand"
+	"os"
+	"testing"
+	"unsafe"
+)
+
+const lz4AVX512Path = "../../go-libraries/go-lz4/avx512_amd64.s"
+
+func loadLZ4AVX512Kernel(t *testing.T) *Kernel {
+	t.Helper()
+	if _, err := os.Stat(lz4AVX512Path); err != nil {
+		t.Skipf("sibling kernel not available: %v", err)
+	}
+	k, err := Load(lz4AVX512Path)
+	if err != nil {
+		t.Fatalf("Load(%s): %v", lz4AVX512Path, err)
+	}
+	t.Cleanup(k.Close)
+	return k
+}
+
+func TestAVX512DecodeKnownAnswers(t *testing.T) {
+	k := loadLZ4AVX512Kernel(t)
+
+	tests := []struct {
+		name     string
+		src      []byte
+		wantN    int
+		wantCode int
+	}{
+		{"literals_only", []byte{0x50, 'H', 'e', 'l', 'l', 'o'}, 5, 0},
+		{"literals_and_match", []byte{0x54, 'A', 'A', 'A', 'A', 'A', 0x05, 0x00, 0x30, 'B', 'B', 'B'}, 16, 0},
+		{"overlapping", []byte{0x14, 'X', 0x01, 0x00, 0x10, 'Y'}, 10, 0},
+		{"malformed", []byte{0x50, 'H', 'e'}, 0, 1},
+		{"zero_offset", []byte{0x14, 'X', 0x00, 0x00}, 0, 2},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			dst := make([]byte, 64)
+			args := make([]byte, 64)
+			PutPtr(args, 0, unsafe.Pointer(&tt.src[0]))
+			PutUint64(args, 8, uint64(len(tt.src)))
+			PutUint64(args, 16, uint64(cap(tt.src)))
+			PutPtr(args, 24, unsafe.Pointer(&dst[0]))
+			PutUint64(args, 32, uint64(len(dst)))
+			PutUint64(args, 40, uint64(cap(dst)))
+
+			out, err := k.CallFunc("decodeBlockAVX512", args)
+			if err != nil {
+				t.Fatalf("CallFunc: %v", err)
+			}
+			n := int(GetUint64(out, 48))
+			code := int(GetUint64(out, 56))
+			if n != tt.wantN || code != tt.wantCode {
+				t.Errorf("got (n=%d, code=%d), want (n=%d, code=%d)", n, code, tt.wantN, tt.wantCode)
+			}
+		})
+	}
+}
+
+func TestAVX512DifferentialFuzz(t *testing.T) {
+	k := loadLZ4AVX512Kernel(t)
+	rng := rand.New(rand.NewSource(77))
+
+	for i := 0; i < 3000; i++ {
+		wantSize := 1 + rng.Intn(4096)
+		src := genLZ4Block(rng, wantSize)
+		dstSize := wantSize + 64
+
+		goDst := make([]byte, dstSize)
+		goN, goCode := decodeBlockGo(src, goDst)
+
+		jitDst := make([]byte, dstSize)
+		args := make([]byte, 64)
+		if len(src) > 0 {
+			PutPtr(args, 0, unsafe.Pointer(&src[0]))
+		}
+		PutUint64(args, 8, uint64(len(src)))
+		PutUint64(args, 16, uint64(cap(src)))
+		if dstSize > 0 {
+			PutPtr(args, 24, unsafe.Pointer(&jitDst[0]))
+		}
+		PutUint64(args, 32, uint64(dstSize))
+		PutUint64(args, 40, uint64(cap(jitDst)))
+
+		out, err := k.CallFunc("decodeBlockAVX512", args)
+		if err != nil {
+			t.Fatalf("iter %d: %v", i, err)
+		}
+		jitN := int(GetUint64(out, 48))
+		jitCode := int(GetUint64(out, 56))
+
+		if jitCode != goCode {
+			t.Fatalf("iter %d: code mismatch: JIT=%d Go=%d", i, jitCode, goCode)
+		}
+		if jitCode != 0 {
+			continue
+		}
+		if jitN != goN {
+			t.Fatalf("iter %d: n mismatch: JIT=%d Go=%d", i, jitN, goN)
+		}
+		if !bytes.Equal(jitDst[:jitN], goDst[:goN]) {
+			t.Fatalf("iter %d: output mismatch (n=%d)", i, jitN)
+		}
+	}
+}
+
+func TestAVX512WideCopy(t *testing.T) {
+	k := loadLZ4AVX512Kernel(t)
+
+	sizes := []int{0, 1, 31, 32, 63, 64, 65, 127, 128, 256, 1024}
+	for _, n := range sizes {
+		src := make([]byte, n)
+		for i := range src {
+			src[i] = byte(i*11 + 3)
+		}
+		dst := make([]byte, n)
+
+		args := make([]byte, 48)
+		if n > 0 {
+			PutPtr(args, 0, unsafe.Pointer(&dst[0]))
+			PutPtr(args, 24, unsafe.Pointer(&src[0]))
+		}
+		PutUint64(args, 8, uint64(n))
+		PutUint64(args, 16, uint64(n))
+		PutUint64(args, 32, uint64(n))
+		PutUint64(args, 40, uint64(n))
+
+		_, err := k.CallFunc("wideCopyAVX512", args)
+		if err != nil {
+			t.Fatalf("wideCopyAVX512(n=%d): %v", n, err)
+		}
+		if !bytes.Equal(dst, src) {
+			t.Errorf("wideCopyAVX512(n=%d): mismatch", n)
+		}
+	}
+}

verify/coverage.go

@@ -0,0 +1,103 @@
+// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
+// SPDX-License-Identifier: BSD-3-Clause
+
+package verify
+
+import (
+	"fmt"
+	"sort"
+)
+
+// Block describes one basic block within a function: a maximal sequence of
+// instructions with a single entry point (a label or the function start) and
+// a single exit (a jump, conditional jump or RET).
+type Block struct {
+	Offset int    // byte offset within the function
+	Label  string // label name ("" for the entry block)
+}
+
+// Blocks identifies the basic blocks of a function from its local labels.
+// Each label is a potential jump target and therefore a block boundary; the
+// function entry (offset 0) is always a block.  The blocks are returned in
+// ascending offset order.
+func (k *Kernel) Blocks(name string) ([]Block, error) {
+	idx, ok := k.funcs[name]
+	if !ok {
+		return nil, fmt.Errorf("verify: function %q not found", name)
+	}
+	fl := k.img.Funcs[idx]
+
+	blocks := []Block{{Offset: 0, Label: "(entry)"}}
+	// Build a reverse map: offset → label name.
+	offToLabel := make(map[int]string, len(fl.Labels))
+	for label, off := range fl.Labels {
+		if off > 0 && off < fl.Size {
+			offToLabel[off] = label
+		}
+	}
+	// Collect and sort offsets.
+	offsets := make([]int, 0, len(offToLabel))
+	for off := range offToLabel {
+		offsets = append(offsets, off)
+	}
+	sort.Ints(offsets)
+	for _, off := range offsets {
+		blocks = append(blocks, Block{Offset: off, Label: offToLabel[off]})
+	}
+	return blocks, nil
+}
+
+// BlockCount returns the number of identified basic blocks for the function.
+func (k *Kernel) BlockCount(name string) (int, error) {
+	blocks, err := k.Blocks(name)
+	if err != nil {
+		return 0, err
+	}
+	return len(blocks), nil
+}
+
+// PathFingerprint is the observable output of one function execution: the
+// values written back into the result slots of the argument block.  Two
+// executions that produce the same fingerprint took observationally
+// equivalent paths (though they may differ internally).
+type PathFingerprint struct {
+	Results []uint64 // the result words from the arg block
+}
+
+// ProfilePaths runs the function with each of the given argument blocks and
+// collects the distinct output fingerprints.  This measures path diversity:
+// how many observationally different execution paths the input corpus
+// exercises.  Combined with Blocks (the static block count), it gives a
+// lower bound on code coverage.
+func (k *Kernel) ProfilePaths(name string, argSets [][]byte, resultOffsets []int) ([]PathFingerprint, error) {
+	idx, ok := k.funcs[name]
+	if !ok {
+		return nil, fmt.Errorf("verify: function %q not found", name)
+	}
+	fl := k.img.Funcs[idx]
+
+	seen := map[string]bool{}
+	var paths []PathFingerprint
+
+	for _, args := range argSets {
+		if len(args) < fl.Args {
+			return nil, fmt.Errorf("verify: %s: arg block too small", name)
+		}
+		out, err := k.CallFunc(name, args)
+		if err != nil {
+			return nil, err
+		}
+		fp := PathFingerprint{}
+		key := ""
+		for _, off := range resultOffsets {
+			v := GetUint64(out, off)
+			fp.Results = append(fp.Results, v)
+			key += fmt.Sprintf("%016x", v)
+		}
+		if !seen[key] {
+			seen[key] = true
+			paths = append(paths, fp)
+		}
+	}
+	return paths, nil
+}

verify/coverage_test.go

@@ -0,0 +1,85 @@
+// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
+// SPDX-License-Identifier: BSD-3-Clause
+
+package verify
+
+import (
+	"testing"
+	"unsafe"
+)
+
+func TestBlocks(t *testing.T) {
+	k := loadBasic(t)
+
+	// The "sum" function has labels: sum_done, sum_loop.
+	blocks, err := k.Blocks("sum")
+	if err != nil {
+		t.Fatalf("Blocks(sum): %v", err)
+	}
+	if len(blocks) < 3 {
+		t.Errorf("sum: expected at least 3 blocks (entry + 2 labels), got %d", len(blocks))
+	}
+	if blocks[0].Offset != 0 {
+		t.Errorf("first block offset = %d, want 0", blocks[0].Offset)
+	}
+	t.Logf("sum blocks: %v", blocks)
+}
+
+func TestBlockCount(t *testing.T) {
+	k := loadLZ4Kernel(t)
+
+	n, err := k.BlockCount("decodeBlockAVX2")
+	if err != nil {
+		t.Fatalf("BlockCount: %v", err)
+	}
+	// The decoder has many labels (dec_loop, dec_malformed, etc.).
+	if n < 10 {
+		t.Errorf("decodeBlockAVX2: expected at least 10 blocks, got %d", n)
+	}
+	t.Logf("decodeBlockAVX2: %d basic blocks", n)
+}
+
+func TestProfilePaths(t *testing.T) {
+	k := loadLZ4Kernel(t)
+
+	// Build a corpus of varied LZ4 blocks.
+	var argSets [][]byte
+	blocks := []struct {
+		src     []byte
+		dstSize int
+	}{
+		{[]byte{0x00}, 16},                          // empty
+		{[]byte{0x50, 'H', 'e', 'l', 'l', 'o'}, 16}, // literals only
+		{[]byte{0x54, 'A', 'A', 'A', 'A', 'A', 5, 0, 0x30, 'B', 'B', 'B'}, 32}, // match
+		{[]byte{0x14, 'X', 1, 0, 0x10, 'Y'}, 16},                               // overlapping
+		{[]byte{0x50, 'H'}, 16},                                                // malformed
+		{[]byte{0x14, 'X', 0, 0}, 16},                                          // zero offset
+	}
+	for _, b := range blocks {
+		args := make([]byte, 64)
+		if len(b.src) > 0 {
+			PutPtr(args, 0, unsafe.Pointer(&b.src[0]))
+		}
+		PutUint64(args, 8, uint64(len(b.src)))
+		PutUint64(args, 16, uint64(cap(b.src)))
+		dst := make([]byte, b.dstSize)
+		if len(dst) > 0 {
+			PutPtr(args, 24, unsafe.Pointer(&dst[0]))
+		}
+		PutUint64(args, 32, uint64(len(dst)))
+		PutUint64(args, 40, uint64(cap(dst)))
+		argSets = append(argSets, args)
+	}
+
+	// Result offsets: n+48 and code+56.
+	paths, err := k.ProfilePaths("decodeBlockAVX2", argSets, []int{48, 56})
+	if err != nil {
+		t.Fatalf("ProfilePaths: %v", err)
+	}
+
+	// We expect at least 3 distinct paths: success (various n), malformed, zero offset.
+	if len(paths) < 3 {
+		t.Errorf("expected at least 3 distinct paths, got %d", len(paths))
+	}
+	t.Logf("decodeBlockAVX2: %d distinct output paths from %d inputs", len(paths), len(argSets))
+}

verify/flac_test.go

@@ -0,0 +1,330 @@
+// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
+// SPDX-License-Identifier: BSD-3-Clause
+
+package verify
+
+import (
+	"bytes"
+	"math/rand"
+	"os"
+	"testing"
+	"unsafe"
+)
+
+const flacKernelPath = "../../go-libraries/go-flac/avx2_amd64.s"
+
+func loadFLACKernel(t *testing.T) *Kernel {
+	t.Helper()
+	if _, err := os.Stat(flacKernelPath); err != nil {
+		t.Skipf("sibling kernel not available: %v", err)
+	}
+	k, err := Load(flacKernelPath)
+	if err != nil {
+		t.Fatalf("Load(%s): %v", flacKernelPath, err)
+	}
+	t.Cleanup(k.Close)
+	return k
+}
+
+// --- Portable Go references (from go-flac/simd.go) ---
+
+func decodeMono16Go(src []byte, dst []int32) {
+	for i := 0; i < len(dst); i++ {
+		dst[i] = int32(int16(uint16(src[2*i]) | uint16(src[2*i+1])<<8))
+	}
+}
+
+func pack16Go(dst []byte, src []int32) {
+	for i, v := range src {
+		dst[2*i] = byte(v)
+		dst[2*i+1] = byte(v >> 8)
+	}
+}
+
+func decorrelateLeftSideGo(left, right, out []int32) {
+	for i := range left {
+		l := left[i]
+		out[2*i] = l
+		out[2*i+1] = l - right[i]
+	}
+}
+
+func decorrelateSideRightGo(left, right, out []int32) {
+	for i := range left {
+		side := left[i]
+		rch := right[i]
+		out[2*i] = rch + side
+		out[2*i+1] = rch
+	}
+}
+
+func decorrelateMidSideGo(left, right, out []int32) {
+	for i := range left {
+		mid := left[i]
+		side := right[i]
+		mid2 := mid<<1 | (side & 1)
+		out[2*i] = (mid2 + side) >> 1
+		out[2*i+1] = (mid2 - side) >> 1
+	}
+}
+
+func decorrelateInterleaveGo(left, right, out []int32) {
+	for i := range left {
+		out[2*i] = left[i]
+		out[2*i+1] = right[i]
+	}
+}
+
+func analyzeO1RangeGo(swin []int32, dstP []uint32, hist *[32]uint16) (partSum uint64, overflow bool) {
+	swin = swin[:len(dstP)+1]
+	for j := 0; j+1 < len(swin); j++ {
+		r := swin[j+1] - swin[j]
+		if r == -2147483648 { // math.MinInt32
+			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
+}
+
+// --- Differential tests ---
+
+func TestFLACDecodeMono16(t *testing.T) {
+	k := loadFLACKernel(t)
+	rng := rand.New(rand.NewSource(7))
+
+	for iter := 0; iter < 500; iter++ {
+		n := rng.Intn(256)
+		src := make([]byte, 2*n)
+		rng.Read(src)
+
+		goDst := make([]int32, n)
+		decodeMono16Go(src, goDst)
+
+		jitDst := make([]int32, n)
+		args := make([]byte, 48)
+		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(&jitDst[0]))
+		}
+		PutUint64(args, 32, uint64(n))
+		PutUint64(args, 40, uint64(cap(jitDst)))
+
+		_, err := k.CallFunc("decodeMono16AVX2", args)
+		if err != nil {
+			t.Fatalf("iter %d: %v", iter, err)
+		}
+		for i := range goDst {
+			if jitDst[i] != goDst[i] {
+				t.Fatalf("iter %d: mismatch at [%d]: JIT=%d Go=%d", iter, i, jitDst[i], goDst[i])
+			}
+		}
+	}
+}
+
+func TestFLACPack16(t *testing.T) {
+	k := loadFLACKernel(t)
+	rng := rand.New(rand.NewSource(13))
+
+	for iter := 0; iter < 500; iter++ {
+		n := rng.Intn(256)
+		src := make([]int32, n)
+		for i := range src {
+			src[i] = int32(rng.Intn(65536) - 32768)
+		}
+
+		goDst := make([]byte, 2*n)
+		pack16Go(goDst, src)
+
+		jitDst := make([]byte, 2*n)
+		args := make([]byte, 48)
+		if len(jitDst) > 0 {
+			PutPtr(args, 0, unsafe.Pointer(&jitDst[0]))
+		}
+		PutUint64(args, 8, uint64(len(jitDst)))
+		PutUint64(args, 16, uint64(cap(jitDst)))
+		if n > 0 {
+			PutPtr(args, 24, unsafe.Pointer(&src[0]))
+		}
+		PutUint64(args, 32, uint64(n))
+		PutUint64(args, 40, uint64(cap(src)))
+
+		_, err := k.CallFunc("pack16AVX2", args)
+		if err != nil {
+			t.Fatalf("iter %d: %v", iter, err)
+		}
+		if !bytes.Equal(jitDst, goDst) {
+			t.Fatalf("iter %d: output mismatch (n=%d)", iter, n)
+		}
+	}
+}
+
+func TestFLACDecorrelate(t *testing.T) {
+	k := loadFLACKernel(t)
+	rng := rand.New(rand.NewSource(21))
+
+	kernels := []struct {
+		name string
+		ref  func(left, right, out []int32)
+	}{
+		{"decorrelateLeftSideAVX2", decorrelateLeftSideGo},
+		{"decorrelateSideRightAVX2", decorrelateSideRightGo},
+		{"decorrelateMidSideAVX2", decorrelateMidSideGo},
+		{"decorrelateInterleaveAVX2", decorrelateInterleaveGo},
+	}
+
+	for _, kk := range kernels {
+		t.Run(kk.name, func(t *testing.T) {
+			for iter := 0; iter < 200; iter++ {
+				n := rng.Intn(128)
+				left := make([]int32, n)
+				right := make([]int32, n)
+				for i := range left {
+					left[i] = int32(rng.Intn(1<<24) - 1<<23)
+					right[i] = int32(rng.Intn(1<<24) - 1<<23)
+				}
+
+				goOut := make([]int32, 2*n)
+				kk.ref(left, right, goOut)
+
+				jitOut := make([]int32, 2*n)
+				args := make([]byte, 72)
+				if n > 0 {
+					PutPtr(args, 0, unsafe.Pointer(&left[0]))
+					PutPtr(args, 24, unsafe.Pointer(&right[0]))
+					PutPtr(args, 48, unsafe.Pointer(&jitOut[0]))
+				}
+				PutUint64(args, 8, uint64(n))
+				PutUint64(args, 16, uint64(cap(left)))
+				PutUint64(args, 32, uint64(n))
+				PutUint64(args, 40, uint64(cap(right)))
+				PutUint64(args, 56, uint64(2*n))
+				PutUint64(args, 64, uint64(cap(jitOut)))
+
+				_, err := k.CallFunc(kk.name, args)
+				if err != nil {
+					t.Fatalf("iter %d: %v", iter, err)
+				}
+				for i := range goOut {
+					if jitOut[i] != goOut[i] {
+						t.Fatalf("iter %d: mismatch at [%d]: JIT=%d Go=%d", iter, i, jitOut[i], goOut[i])
+					}
+				}
+			}
+		})
+	}
+}
+
+func TestFLACAnalyzeO1Range(t *testing.T) {
+	k := loadFLACKernel(t)
+	rng := rand.New(rand.NewSource(33))
+
+	for iter := 0; iter < 300; iter++ {
+		n := 1 + rng.Intn(128) // partition size
+		swin := make([]int32, n+1)
+		for i := range swin {
+			swin[i] = int32(rng.Intn(1<<20) - 1<<19)
+		}
+
+		goDstP := make([]uint32, n)
+		var goHist [32]uint16
+		goSum, goOvf := analyzeO1RangeGo(swin, goDstP, &goHist)
+
+		jitDstP := make([]uint32, n)
+		var jitHist [32]uint16
+		args := make([]byte, 72) // 65 rounded up
+		PutPtr(args, 0, unsafe.Pointer(&swin[0]))
+		PutUint64(args, 8, uint64(len(swin)))
+		PutUint64(args, 16, uint64(cap(swin)))
+		PutPtr(args, 24, unsafe.Pointer(&jitDstP[0]))
+		PutUint64(args, 32, uint64(n))
+		PutUint64(args, 40, uint64(cap(jitDstP)))
+		PutPtr(args, 48, unsafe.Pointer(&jitHist[0]))
+
+		out, err := k.CallFunc("analyzeO1RangeAVX2", args)
+		if err != nil {
+			t.Fatalf("iter %d: %v", iter, err)
+		}
+		jitSum := GetUint64(out, 56)
+		jitOvf := out[64] != 0
+
+		if jitSum != goSum {
+			t.Fatalf("iter %d: partSum mismatch: JIT=%d Go=%d", iter, jitSum, goSum)
+		}
+		if jitOvf != goOvf {
+			t.Fatalf("iter %d: overflow mismatch: JIT=%v Go=%v", iter, jitOvf, goOvf)
+		}
+		for i := range goDstP {
+			if jitDstP[i] != goDstP[i] {
+				t.Fatalf("iter %d: dstP[%d] mismatch: JIT=%d Go=%d", iter, i, jitDstP[i], goDstP[i])
+			}
+		}
+		if jitHist != goHist {
+			t.Fatalf("iter %d: hist mismatch: JIT=%v Go=%v", iter, jitHist, goHist)
+		}
+	}
+}
+
+func TestFLACFastStereoSums(t *testing.T) {
+	k := loadFLACKernel(t)
+	rng := rand.New(rand.NewSource(44))
+
+	for iter := 0; iter < 300; iter++ {
+		n := 1 + rng.Intn(256)
+		left := make([]int32, n)
+		right := make([]int32, n)
+		for i := range left {
+			left[i] = int32(rng.Intn(1<<24) - 1<<23)
+			right[i] = int32(rng.Intn(1<<24) - 1<<23)
+		}
+
+		// Go reference: compute the four sums.
+		var goSums [4]uint64
+		for i := 0; i < n; i++ {
+			l := left[i]
+			r := right[i]
+			side := l - r
+			mid := (l + r) >> 1
+			goSums[0] += foldAbs(l) + foldAbs(r)
+			goSums[1] += foldAbs(l) + foldAbs(side)
+			goSums[2] += foldAbs(side) + foldAbs(r)
+			goSums[3] += foldAbs(mid) + foldAbs(side)
+		}
+
+		var jitSums [4]uint64
+		args := make([]byte, 56)
+		PutPtr(args, 0, unsafe.Pointer(&left[0]))
+		PutUint64(args, 8, uint64(n))
+		PutUint64(args, 16, uint64(cap(left)))
+		PutPtr(args, 24, unsafe.Pointer(&right[0]))
+		PutUint64(args, 32, uint64(n))
+		PutUint64(args, 40, uint64(cap(right)))
+		PutPtr(args, 48, unsafe.Pointer(&jitSums[0]))
+
+		_, err := k.CallFunc("fastStereoSumsAVX2", args)
+		if err != nil {
+			t.Fatalf("iter %d: %v", iter, err)
+		}
+		if jitSums != goSums {
+			t.Fatalf("iter %d: sums mismatch:\n  JIT=%v\n  Go =%v", iter, jitSums, goSums)
+		}
+	}
+}
+
+func foldAbs(v int32) uint64 {
+	return uint64(uint32(v<<1) ^ uint32(v>>31))
+}