diff --git a/evm/src/bn254.rs b/evm/src/bn254.rs
index 6c993d8c..8f29e12d 100644
--- a/evm/src/bn254.rs
+++ b/evm/src/bn254.rs
@@ -115,6 +115,27 @@ fn neg_fp(x: Fp) -> Fp {
     (BN_BASE - x) % BN_BASE
 }
 
+fn exp_fp(x: Fp, e: U256) -> Fp {
+    let mut current = x;
+    let mut product = U256::one();
+
+    for j in 0..256 {
+        if e.bit(j) {
+            product = U256::try_from(product.full_mul(current) % BN_BASE).unwrap();
+        }
+        current = U256::try_from(current.full_mul(current) % BN_BASE).unwrap();
+    }
+    product
+}
+
+fn inv_fp(x: Fp) -> Fp {
+    exp_fp(x, BN_BASE - 2)
+}
+
+fn div_fp(x: Fp, y: Fp) -> Fp {
+    mul_fp(x, inv_fp(y))
+}
+
 fn conj_fp2(a: Fp2) -> Fp2 {
     let [a, a_] = a;
     [a, neg_fp(a_)]
@@ -246,23 +267,6 @@ pub fn frob_fp12(n: usize, f: Fp12) -> Fp12 {
     [frob_fp6(n, f0), mul_fp6(scale, frob_fp6(n, f1))]
 }
 
-fn exp_fp(x: Fp, e: U256) -> Fp {
-    let mut current = x;
-    let mut product = U256::one();
-
-    for j in 0..256 {
-        if e.bit(j) {
-            product = U256::try_from(product.full_mul(current) % BN_BASE).unwrap();
-        }
-        current = U256::try_from(current.full_mul(current) % BN_BASE).unwrap();
-    }
-    product
-}
-
-fn inv_fp(x: Fp) -> Fp {
-    exp_fp(x, BN_BASE - 2)
-}
-
 // fn inv_fp2(a: Fp2) -> Fp2 {
 //     let [a0, a1] = a;
 //     let norm = inv_fp(mul_fp(a0, a0) + mul_fp(a1, a1));
@@ -655,3 +659,69 @@ pub fn cord(p1: Curve, p2: Curve, q: TwistedCurve) -> Fp12 {
         mul_fp2(embed_fp2(cy), qy),
     )
 }
+
+fn tangent_slope(p: Curve) -> Fp {
+    let [px, py] = p;
+    let num = mul_fp(mul_fp(px, px), U256::from(3));
+    let denom = mul_fp(py, U256::from(2));
+    div_fp(num, denom)
+}
+
+fn cord_slope(p: Curve, q: Curve) -> Fp {
+    let [px, py] = p;
+    let [qx, qy] = q;
+    let num = sub_fp(qy, py);
+    let denom = sub_fp(qx, px);
+    div_fp(num, denom)
+}
+
+fn third_point(m: Fp, p: Curve, q: Curve) -> Curve {
+    let [px, py] = p;
+    let [qx, _] = q;
+    let ox = sub_fp(mul_fp(m, m), add_fp(px, qx));
+    let oy = sub_fp(mul_fp(m, sub_fp(px, ox)), py);
+    [ox, oy]
+}
+
+fn curve_add(p: Curve, q: Curve) -> Curve {
+    if p == q {
+        curve_double(p)
+    }
+    else { 
+        third_point(cord_slope(p, q), p, q)
+    }
+}
+
+fn curve_double(p: Curve) -> Curve {
+    third_point(tangent_slope(p), p, p)
+}
+
+const EXP: [usize; 253] = [
+    1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0, 1, 1, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 1, 1, 1,
+    0, 0, 0, 0, 1, 0, 0, 1, 1, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 1, 1, 0, 1,
+    1, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 0, 0,
+    0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 1, 0, 0, 0, 0, 1, 0, 1, 1, 1, 0, 1, 0, 0, 1,
+    0, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 1,
+    1, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 0, 1, 0, 1, 1, 1, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 1, 0, 1, 0,
+    0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 0, 0, 1, 0, 0, 1, 1, 1, 1, 1,
+    1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+];
+
+pub fn miller_loop(p: Curve, q: TwistedCurve) -> Fp12 {
+    let mut o = p;
+    let mut acc = embed_fp12(U256::one());
+    let mut line;
+
+    for i in EXP {
+        acc = mul_fp12(acc, acc);
+        line = tangent(o, q);
+        acc = mul_fp12(line, acc);
+        o = curve_double(o);
+        if i != 0 {
+            line = cord(p, o, q);
+            acc = mul_fp12(line, acc);
+            o = curve_add(p, o);
+        }
+    }
+    acc
+}
diff --git a/evm/src/cpu/kernel/asm/curve/bn254/curve_arithmetic/miller_loop.asm b/evm/src/cpu/kernel/asm/curve/bn254/curve_arithmetic/miller_loop.asm
index e2b39c7c..0f860047 100644
--- a/evm/src/cpu/kernel/asm/curve/bn254/curve_arithmetic/miller_loop.asm
+++ b/evm/src/cpu/kernel/asm/curve/bn254/curve_arithmetic/miller_loop.asm
@@ -126,6 +126,12 @@ miller_zero_final:
 ///     out = mul_fp12_sparse(out, line)
 ///     O += O
 
+global test_mul_tan:
+    // stack: out, f, retdest, 0xnm, times, O, P, Q, out
+    %store_fp12
+    // stack:         retdest, 0xnm, times, O, P, Q, out
+    %jump(mul_tangent)
+
 mul_tangent:
     // stack:                                              retdest, 0xnm, times, O, P, Q, out
     PUSH mul_tangent_2  DUP13  PUSH mul_tangent_1
@@ -154,7 +160,13 @@ mul_tangent_2:
 after_double:
     // stack:             2*O, retdest, 0xnm, times,   O, P, Q, out  {100: line}
     SWAP5  POP  SWAP5  POP
+
     // stack:                  retdest, 0xnm, times, 2*O, P, Q, out  {100: line}
+
+    %pop3  %pop2  %pop2  %pop4
+    %load_fp12
+    %jump(0xdeadbeef)
+
     JUMP
 
 
@@ -163,6 +175,12 @@ after_double:
 ///     out = mul_fp12_sparse(out, line)
 ///     O += P
 
+global test_mul_cord:
+    // stack: out, f, 0xnm, times, O, P, Q, out
+    %store_fp12
+    // stack:         0xnm, times, O, P, Q, out
+    %jump(mul_cord)
+
 mul_cord:
     // stack:                            0xnm, times, O, P, Q, out
     PUSH mul_cord_1
@@ -196,12 +214,6 @@ after_add:
     %jump(miller_one)
 
 
-global test_cord:
-    // stack: p1x , p1y, p2x , p2y, qx, qx_, qy, qy_
-    %cord
-    // stack:
-    %check(100)
-
 /// def cord(p1x, p1y, p2x, p2y, qx, qy):
 ///     return sparse_store(
 ///         p1y*p2x - p2y*p1x, 
@@ -249,12 +261,6 @@ global test_cord:
 %endmacro
 
 
-global test_tangent:
-    // stack: px, py, qx, qx_, qy, qy_
-    %tangent
-    // stack:
-    %check(100)
-
 /// def tangent(px, py, qx, qy):
 ///     return sparse_store(
 ///         py**2 - 9,