diff --git a/benchmark/fft/README.md b/benchmark/fft/README.md
index f0529b826..7481706e8 100644
--- a/benchmark/fft/README.md
+++ b/benchmark/fft/README.md
@@ -4,6 +4,7 @@
 
 ```
 Run on 13th Gen Intel(R) Core(TM) i9-13900K (32 X 5500 MHz CPU s)
+Compiler: clang-15
 CPU Caches:
   L1 Data 48 KiB (x16)
   L1 Instruction 32 KiB (x16)
@@ -17,60 +18,62 @@ CPU Caches:
   L2 Unified 4096 KiB (x12)
 ```
 
+Note: Run with `build --@rules_rust//:extra_rustc_flags="-Ctarget-cpu=native"` in your .bazelrc.user
+
 ### FFT
 
 ```shell
-bazel run --config opt --//:has_matplotlib //benchmark/fft:fft_benchmark -- -k 16 -k 17 -k 18 -k 19 -k 20 -k 21 -k 22 -k 23 --vendor arkworks --vendor bellman --vendor halo2 --check_results
+GOMP_SPINCOUNT=0 bazel run --config maxopt --//:has_matplotlib //benchmark/fft:fft_benchmark -- -k 16 -k 17 -k 18 -k 19 -k 20 -k 21 -k 22 -k 23 --vendor arkworks --vendor bellman --vendor halo2 --check_results
 ```
 
 #### On Intel i9-13900K
 
 | Exponent | Tachyon      | Arkworks     | Bellman  | Halo2    |
 | :------: | ------------ | ------------ | -------- | -------- |
-|    16    | **0.000958** | 0.004086     | 0.007342 | 0.003784 |
-|    17    | 0.032529     | **0.003283** | 0.012624 | 0.005433 |
-|    18    | 0.014067     | **0.005768** | 0.025811 | 0.009372 |
-|    19    | **0.008459** | 0.011465     | 0.05208  | 0.019333 |
-|    20    | **0.016166** | 0.024533     | 0.106217 | 0.042381 |
-|    21    | **0.039447** | 0.069444     | 0.212414 | 0.087621 |
-|    22    | **0.125954** | 0.177245     | 0.431237 | 0.188843 |
-|    23    | **0.297259** | 0.391987     | 0.835686 | 0.427426 |
+|    16    | **0.002058** | 0.005143     | 0.006314 | 0.002249 |
+|    17    | **0.002246** | 0.00334      | 0.015646 | 0.006193 |
+|    18    | **0.010154** | 0.018807     | 0.046443 | 0.007574 |
+|    19    | 0.022984     | **0.014652** | 0.076281 | 0.014506 |
+|    20    | **0.02**     | 0.02497      | 0.100082 | 0.042877 |
+|    21    | **0.044831** | 0.075563     | 0.20222  | 0.067161 |
+|    22    | **0.130201** | 0.179075     | 0.402452 | 0.169194 |
+|    23    | **0.281398** | 0.394068     | 0.792004 | 0.372566 |
 
 ![image](/benchmark/fft/fft_benchmark_ubuntu_i9.png)
 
 #### On Mac M3 Pro
 
-| Exponent | Tachyon      | Arkworks     | Bellman  | Halo2    |
-| :------: | ------------ | ------------ | -------- | -------- |
-|    16    | **0.002735** | 0.003468     | 0.007731 | 0.006372 |
-|    17    | **0.005237** | 0.006043     | 0.015891 | 0.012804 |
-|    18    | **0.009494** | 0.010686     | 0.027312 | 0.02485  |
-|    19    | 0.020251     | **0.020156** | 0.055652 | 0.045714 |
-|    20    | **0.038186** | 0.040006     | 0.110531 | 0.096778 |
-|    21    | **0.085204** | 0.087181     | 0.228044 | 0.191695 |
-|    22    | **0.166863** | 0.179635     | 0.472941 | 0.386844 |
-|    23    | **0.347128** | 0.378249     | 0.970552 | 0.814043 |
+| Exponent | Tachyon      | Arkworks | Bellman  | Halo2    |
+| :------: | ------------ | -------- | -------- | -------- |
+|    16    | **0.002526** | 0.003804 | 0.00784  | 0.005689 |
+|    17    | **0.004694** | 0.005769 | 0.015577 | 0.01121  |
+|    18    | **0.009246** | 0.010243 | 0.027834 | 0.022379 |
+|    19    | **0.018328** | 0.020404 | 0.055661 | 0.041394 |
+|    20    | **0.039683** | 0.041085 | 0.110702 | 0.086299 |
+|    21    | **0.079138** | 0.087336 | 0.230857 | 0.175599 |
+|    22    | **0.166646** | 0.177959 | 0.474296 | 0.352872 |
+|    23    | **0.33996**  | 0.363612 | 0.971581 | 0.748284 |
 
 ![image](/benchmark/fft/fft_benchmark_mac_m3.png)
 
 ### IFFT
 
 ```shell
-bazel run --config opt --//:has_matplotlib //benchmark/fft:fft_benchmark -- -k 16 -k 17 -k 18 -k 19 -k 20 -k 21 -k 22 -k 23 --vendor arkworks --vendor bellman --vendor halo2 --run_ifft --check_results
+GOMP_SPINCOUNT=0 bazel run --config maxopt --//:has_matplotlib //benchmark/fft:fft_benchmark -- -k 16 -k 17 -k 18 -k 19 -k 20 -k 21 -k 22 -k 23 --vendor arkworks --vendor bellman --vendor halo2 --run_ifft --check_results
 ```
 
 #### On Intel i9-13900K
 
-| Exponent | Tachyon      | Arkworks     | Bellman  | Halo2       |
-| :------: | ------------ | ------------ | -------- | ----------- |
-|    16    | 0.003078     | 0.004531     | 0.007794 | **0.00297** |
-|    17    | 0.011666     | **0.005005** | 0.012804 | 0.005309    |
-|    18    | **0.005614** | 0.009204     | 0.025717 | 0.009741    |
-|    19    | **0.007625** | 0.015332     | 0.050253 | 0.018729    |
-|    20    | **0.016751** | 0.030142     | 0.111549 | 0.041873    |
-|    21    | **0.039565** | 0.0715       | 0.222403 | 0.098125    |
-|    22    | **0.140152** | 0.181124     | 0.415709 | 0.188011    |
-|    23    | **0.317353** | 0.400472     | 0.845031 | 0.407396    |
+| Exponent | Tachyon      | Arkworks | Bellman  | Halo2        |
+| :------: | ------------ | -------- | -------- | ------------ |
+|    16    | **0.001392** | 0.012028 | 0.009913 | 0.002413     |
+|    17    | **0.002511** | 0.00427  | 0.01418  | 0.005731     |
+|    18    | 0.01762      | 0.021167 | 0.034676 | **0.010811** |
+|    19    | **0.009646** | 0.01447  | 0.058714 | 0.016038     |
+|    20    | **0.030303** | 0.034815 | 0.104936 | 0.05337      |
+|    21    | **0.047463** | 0.072579 | 0.199788 | 0.093146     |
+|    22    | **0.146697** | 0.181389 | 0.391296 | 0.19874      |
+|    23    | **0.285937** | 0.403596 | 0.82276  | 0.347876     |
 
 ![image](/benchmark/fft/ifft_benchmark_ubuntu_i9.png)
 
@@ -78,14 +81,14 @@ bazel run --config opt --//:has_matplotlib //benchmark/fft:fft_benchmark -- -k 1
 
 | Exponent | Tachyon      | Arkworks | Bellman  | Halo2    |
 | :------: | ------------ | -------- | -------- | -------- |
-|    16    | **0.002766** | 0.004274 | 0.007948 | 0.006638 |
-|    17    | **0.005883** | 0.006978 | 0.016308 | 0.013121 |
-|    18    | **0.010532** | 0.012815 | 0.029066 | 0.028791 |
-|    19    | **0.020781** | 0.024054 | 0.059351 | 0.048824 |
-|    20    | **0.041061** | 0.048806 | 0.11825  | 0.099004 |
-|    21    | **0.090855** | 0.101232 | 0.236775 | 0.210805 |
-|    22    | **0.170776** | 0.203109 | 0.488306 | 0.423618 |
-|    23    | **0.383255** | 0.454968 | 1.03129  | 0.881795 |
+|    16    | **0.002798** | 0.003867 | 0.008102 | 0.005665 |
+|    17    | **0.004882** | 0.005737 | 0.015998 | 0.011672 |
+|    18    | **0.010308** | 0.010962 | 0.028118 | 0.022723 |
+|    19    | **0.018724** | 0.021338 | 0.056855 | 0.042554 |
+|    20    | **0.037687** | 0.043237 | 0.113848 | 0.089899 |
+|    21    | **0.078429** | 0.092134 | 0.234585 | 0.174939 |
+|    22    | **0.162542** | 0.189442 | 0.484644 | 0.361127 |
+|    23    | **0.338646** | 0.392674 | 0.989173 | 0.765592 |
 
 ![image](/benchmark/fft/ifft_benchmark_mac_m3.png)
 
@@ -94,41 +97,41 @@ bazel run --config opt --//:has_matplotlib //benchmark/fft:fft_benchmark -- -k 1
 ### FFT
 
 ```shell
-bazel run --config opt --config cuda --//:has_matplotlib //benchmark/fft:fft_benchmark_gpu -- -k 16 -k 17 -k 18 -k 19 -k 20 -k 21 -k 22 -k 23 --check_results
+GOMP_SPINCOUNT=0 bazel run --config maxopt --config cuda --//:has_matplotlib //benchmark/fft:fft_benchmark_gpu -- -k 16 -k 17 -k 18 -k 19 -k 20 -k 21 -k 22 -k 23 --check_results
 ```
 
 #### On RTX-4090
 
 | Exponent | Tachyon CPU | Tachyon GPU  |
 | :------: | ----------- | ------------ |
-|    16    | **0.00097** | 0.001231     |
-|    17    | 0.002156    | **0.000667** |
-|    18    | 0.003524    | **0.001297** |
-|    19    | 0.007366    | **0.002654** |
-|    20    | 0.015787    | **0.005877** |
-|    21    | 0.03753     | **0.012573** |
-|    22    | 0.122167    | **0.027632** |
-|    23    | 0.268875    | **0.055971** |
+|    16    | 0.002348    | **0.001**    |
+|    17    | 0.00204     | **0.001182** |
+|    18    | 0.00393     | **0.002211** |
+|    19    | 0.009317    | **0.004079** |
+|    20    | 0.049204    | **0.008114** |
+|    21    | 0.044158    | **0.01616**  |
+|    22    | 0.134064    | **0.032785** |
+|    23    | 0.274101    | **0.066068** |
 
 ![image](/benchmark/fft/fft_benchmark_ubuntu_rtx_4090.png)
 
 ### IFFT
 
 ```shell
-bazel run --config opt --config cuda --//:has_matplotlib //benchmark/fft:fft_benchmark_gpu -- -k 16 -k 17 -k 18 -k 19 -k 20 -k 21 -k 22 -k 23 --run_ifft --check_results
+GOMP_SPINCOUNT=0 bazel run --config maxopt --config cuda --//:has_matplotlib //benchmark/fft:fft_benchmark_gpu -- -k 16 -k 17 -k 18 -k 19 -k 20 -k 21 -k 22 -k 23 --run_ifft --check_results
 ```
 
 #### On RTX-4090
 
 | Exponent | Tachyon  | Tachyon GPU  |
 | :------: | -------- | ------------ |
-|    16    | 0.000993 | **0.000833** |
-|    17    | 0.001673 | **0.000643** |
-|    18    | 0.003533 | **0.001305** |
-|    19    | 0.007446 | **0.002701** |
-|    20    | 0.016039 | **0.005882** |
-|    21    | 0.03786  | **0.012817** |
-|    22    | 0.126032 | **0.027767** |
-|    23    | 0.32731  | **0.056064** |
+|    16    | 0.002138 | **0.001341** |
+|    17    | 0.00488  | **0.000933** |
+|    18    | 0.003887 | **0.002502** |
+|    19    | 0.00896  | **0.003806** |
+|    20    | 0.017953 | **0.007745** |
+|    21    | 0.043787 | **0.016268** |
+|    22    | 0.132048 | **0.033012** |
+|    23    | 0.291132 | **0.066022** |
 
 ![image](/benchmark/fft/ifft_benchmark_ubuntu_rtx_4090.png)
diff --git a/benchmark/fft/fft_benchmark_mac_m3.png b/benchmark/fft/fft_benchmark_mac_m3.png
index a77f76f74..25235269a 100644
Binary files a/benchmark/fft/fft_benchmark_mac_m3.png and b/benchmark/fft/fft_benchmark_mac_m3.png differ
diff --git a/benchmark/fft/fft_benchmark_ubuntu_i9.png b/benchmark/fft/fft_benchmark_ubuntu_i9.png
index dca5a1e3e..fbb9936d9 100644
Binary files a/benchmark/fft/fft_benchmark_ubuntu_i9.png and b/benchmark/fft/fft_benchmark_ubuntu_i9.png differ
diff --git a/benchmark/fft/fft_benchmark_ubuntu_rtx_4090.png b/benchmark/fft/fft_benchmark_ubuntu_rtx_4090.png
index 65521d6ad..e7ebe10cb 100644
Binary files a/benchmark/fft/fft_benchmark_ubuntu_rtx_4090.png and b/benchmark/fft/fft_benchmark_ubuntu_rtx_4090.png differ
diff --git a/benchmark/fft/ifft_benchmark_mac_m3.png b/benchmark/fft/ifft_benchmark_mac_m3.png
index 5959dad23..548d9bdf1 100644
Binary files a/benchmark/fft/ifft_benchmark_mac_m3.png and b/benchmark/fft/ifft_benchmark_mac_m3.png differ
diff --git a/benchmark/fft/ifft_benchmark_ubuntu_i9.png b/benchmark/fft/ifft_benchmark_ubuntu_i9.png
index fe114cc4d..61622e4cd 100644
Binary files a/benchmark/fft/ifft_benchmark_ubuntu_i9.png and b/benchmark/fft/ifft_benchmark_ubuntu_i9.png differ
diff --git a/benchmark/fft/ifft_benchmark_ubuntu_rtx_4090.png b/benchmark/fft/ifft_benchmark_ubuntu_rtx_4090.png
index 0cd39c982..d18b8a029 100644
Binary files a/benchmark/fft/ifft_benchmark_ubuntu_rtx_4090.png and b/benchmark/fft/ifft_benchmark_ubuntu_rtx_4090.png differ
diff --git a/benchmark/fft_batch/README.md b/benchmark/fft_batch/README.md
index 1528c196c..6c6832030 100644
--- a/benchmark/fft_batch/README.md
+++ b/benchmark/fft_batch/README.md
@@ -4,6 +4,7 @@
 
 ```
 Run on 13th Gen Intel(R) Core(TM) i9-13900K (32 X 5500 MHz CPU s)
+Compiler: clang-15
 CPU Caches:
   L1 Data 48 KiB (x16)
   L1 Instruction 32 KiB (x16)
@@ -17,70 +18,79 @@ CPU Caches:
   L2 Unified 4096 KiB (x12)
 ```
 
-### FFTBatch
+Note: Run with `build --@rules_rust//:extra_rustc_flags="-Ctarget-cpu=native"` in your .bazelrc.user
 
-```shell
-bazel run --config opt --//:has_matplotlib //benchmark/fft_batch:fft_batch_benchmark -- -k 20 -k 21 -k 22 -k 23 -k 24 -k 25 -k 26 --vendor plonky3 -p baby_bear --check_results
-```
+### FFTBatch
 
 WARNING: On Mac M3, tests beyond degree 24 are not feasible due to memory constraints.
 
 #### On Intel i9-13900K
 
+```shell
+GOMP_SPINCOUNT=0 bazel run --config maxopt --//:has_matplotlib //benchmark/fft_batch:fft_batch_benchmark -- -k 20 -k 21 -k 22 -k 23 -k 24 -k 25 -k 26 --vendor plonky3 -p baby_bear --check_results
+```
+
 | Exponent | Tachyon      | Plonky3      |
 | :------- | ------------ | ------------ |
-| 20       | 0.117925     | **0.110098** |
-| 21       | 0.222959     | **0.218505** |
-| 22       | 0.459209     | **0.447758** |
-| 23       | 0.97874      | **0.964644** |
-| 24       | 2.09675      | **2.092210** |
-| 25       | **6.20441**  | 6.98453      |
-| 26       | **18.6084**  | 20.7476      |
+| 20       | **0.092595** | 0.094762     |
+| 21       | **0.191168** | 0.193567     |
+| 22       | 0.406239     | **0.384377** |
+| 23       | 0.892501     | **0.842694** |
+| 24       | 1.91177      | **1.90586**  |
+| 25       | **5.82862**  | 7.34128      |
+| 26       | **17.1807**  | 20.3968      |
 
 ![image](/benchmark/fft_batch/fft_batch_benchmark_ubuntu_i9.png)
 
 #### On Mac M3 Pro
 
-| Exponent | Tachyon   | Plonky3      |
-| :------- | --------- | ------------ |
-| 20       | 0.132521  | **0.072505** |
-| 21       | 0.287744  | **0.140527** |
-| 22       | 0.588894  | **0.280177** |
-| 23       | 1.17446   | **0.621024** |
-| 24       | 3.17213   | **2.399220** |
+```shell
+GOMP_SPINCOUNT=0 bazel run --config maxopt --//:has_matplotlib //benchmark/fft_batch:fft_batch_benchmark -- -k 20 -k 21 -k 22 -k 23 -k 24  --vendor plonky3 -p baby_bear --check_results
+```
+
+| Exponent | Tachyon  | Plonky3      |
+| :------- | -------- | ------------ |
+| 20       | 0.083416 | **0.066952** |
+| 21       | 0.194191 | **0.138168** |
+| 22       | 0.408045 | **0.299547** |
+| 23       | 0.955439 | **0.679252** |
+| 24       | 11.8495  | **6.47188**  |
 
 ![image](/benchmark/fft_batch/fft_batch_benchmark_mac_m3.png)
 
 ### CosetLDEBatch
 
-```shell
-bazel run --config opt --//:has_matplotlib //benchmark/fft_batch:fft_batch_benchmark -- -k 20 -k 21 -k 22 -k 23 -k 24 -k 25 --vendor plonky3 -p baby_bear --run_coset_lde --check_results
-```
-
-WARNING: On Mac M3, tests beyond degree 24 are not feasible due to memory constraints.
+WARNING: On Intel i9-13900K, tests beyond degree 25 are not feasible due to memory constraints, and on Mac M3, tests beyond degree 24 are not feasible due to memory constraints.
 
 #### On Intel i9-13900K
 
-| Exponent | Tachyon      | Plonky3  |
-| :------- | ------------ | -------- |
-| 20       | **0.414096** | 0.783275 |
-| 21       | **0.828539** | 1.47701  |
-| 22       | **1.784080** | 3.06198  |
-| 23       | **3.673930** | 6.49181  |
-| 24       | **9.325390** | 16.2383  |
-| 25       | **25.66560** | 41.3335  |
+```shell
+GOMP_SPINCOUNT=0 bazel run --config maxopt --//:has_matplotlib //benchmark/fft_batch:fft_batch_benchmark -- -k 20 -k 21 -k 22 -k 23 -k 24 -k 25 --vendor plonky3 -p baby_bear --run_coset_lde --check_results
+```
+
+| Exponent | Tachyon     | Plonky3  |
+| :------- | ----------- | -------- |
+| 20       | **0.46917** | 0.639744 |
+| 21       | **0.92528** | 1.2923   |
+| 22       | **1.87363** | 2.68427  |
+| 23       | **4.06008** | 5.67987  |
+| 24       | **9.6627**  | 14.6164  |
+| 25       | **25.7953** | 39.5498  |
 
 ![image](/benchmark/fft_batch/coset_lde_batch_benchmark_ubuntu_i9.png)
 
 #### On Mac M3 Pro
 
+```shell
+GOMP_SPINCOUNT=0 bazel run --config maxopt --//:has_matplotlib //benchmark/fft_batch:fft_batch_benchmark -- -k 20 -k 21 -k 22 -k 23 -k 24 --vendor plonky3 -p baby_bear --run_coset_lde --check_results
+```
+
 | Exponent | Tachyon      | Plonky3      |
 | :------- | ------------ | ------------ |
-| 18       | 0.100942     | **0.086087** |
-| 19       | 0.214471     | **0.182212** |
-| 20       | 0.481229     | **0.359246** |
-| 21       | **0.981806** | 1.518190     |
-| 22       | 3.86094      | **3.244580** |
-| 23       | 7.50879      | **6.052250** |
+| 20       | **0.318485** | 0.323865     |
+| 21       | 0.667106     | **0.660975** |
+| 22       | **1.44873**  | 3.40795      |
+| 23       | 8.27201      | **5.91238**  |
+| 24       | 39.9678      | **23.1033**  |
 
 ![image](/benchmark/fft_batch/coset_lde_batch_benchmark_mac_m3.png)
diff --git a/benchmark/fft_batch/coset_lde_batch_benchmark_mac_m3.png b/benchmark/fft_batch/coset_lde_batch_benchmark_mac_m3.png
index d2e076547..bc2d12d42 100644
Binary files a/benchmark/fft_batch/coset_lde_batch_benchmark_mac_m3.png and b/benchmark/fft_batch/coset_lde_batch_benchmark_mac_m3.png differ
diff --git a/benchmark/fft_batch/coset_lde_batch_benchmark_ubuntu_i9.png b/benchmark/fft_batch/coset_lde_batch_benchmark_ubuntu_i9.png
index 538f22908..3142cf2f5 100644
Binary files a/benchmark/fft_batch/coset_lde_batch_benchmark_ubuntu_i9.png and b/benchmark/fft_batch/coset_lde_batch_benchmark_ubuntu_i9.png differ
diff --git a/benchmark/fft_batch/fft_batch_benchmark_mac_m3.png b/benchmark/fft_batch/fft_batch_benchmark_mac_m3.png
index 16235970a..ebe611711 100644
Binary files a/benchmark/fft_batch/fft_batch_benchmark_mac_m3.png and b/benchmark/fft_batch/fft_batch_benchmark_mac_m3.png differ
diff --git a/benchmark/fft_batch/fft_batch_benchmark_ubuntu_i9.png b/benchmark/fft_batch/fft_batch_benchmark_ubuntu_i9.png
index e1f07bf3d..17dc46f6e 100644
Binary files a/benchmark/fft_batch/fft_batch_benchmark_ubuntu_i9.png and b/benchmark/fft_batch/fft_batch_benchmark_ubuntu_i9.png differ
diff --git a/benchmark/fft_batch/fft_batch_runner.h b/benchmark/fft_batch/fft_batch_runner.h
index 6491675b5..5310d6e28 100644
--- a/benchmark/fft_batch/fft_batch_runner.h
+++ b/benchmark/fft_batch/fft_batch_runner.h
@@ -35,16 +35,18 @@ class FFTBatchRunner {
     math::RowMajorMatrix<F> result;
     std::unique_ptr<Domain> domain =
         Domain::Create(static_cast<size_t>(input.rows()));
-    base::TimeTicks start = base::TimeTicks::Now();
+    base::TimeTicks start;
     if (run_coset_lde) {
       const size_t kAddedBits = 1;
       result =
           math::RowMajorMatrix<F>(input.rows() << kAddedBits, input.cols());
+      start = base::TimeTicks::Now();
       domain->CosetLDEBatch(input, kAddedBits,
                             F::FromMontgomery(F::Config::kSubgroupGenerator),
                             result);
     } else {
       result = input;
+      start = base::TimeTicks::Now();
       domain->FFTBatch(result);
     }
     reporter_.AddTime(vendor, base::TimeTicks::Now() - start);
diff --git a/benchmark/fri/README.md b/benchmark/fri/README.md
index bfdfc2b39..6e01a635d 100644
--- a/benchmark/fri/README.md
+++ b/benchmark/fri/README.md
@@ -2,8 +2,9 @@
 
 ## CPU
 
-```bash
+```
 Run on 13th Gen Intel(R) Core(TM) i9-13900K (32 X 5500 MHz CPU s)
+Compiler: clang-15
 CPU Caches:
   L1 Data 48 KiB (x16)
   L1 Instruction 32 KiB (x16)
@@ -17,19 +18,21 @@ CPU Caches:
   L2 Unified 4096 KiB (x12)
 ```
 
+Note: Run with `build --@rules_rust//:extra_rustc_flags="-Ctarget-cpu=native"` in your .bazelrc.user
+
 ```shell
-bazel run --config opt --//:has_matplotlib //benchmark/fri:fri_benchmark -- -k 18 -k 19 -k 20 -k 21 -k 22 --batch_size 100 --input_num 4 --round_num 4 --log_blowup 2 --vendor plonky3 --check_results
+GOMP_SPINCOUNT=0 bazel run --config maxopt --//:has_matplotlib //benchmark/fri:fri_benchmark -- -k 18 -k 19 -k 20 -k 21 -k 22 --batch_size 100 --input_num 4 --round_num 4 --log_blowup 2 --vendor plonky3 --check_results
 ```
 
 ## On Intel i9-13900K
 
 | Exponent | Tachyon     | Plonky3 |
 | :------- | ----------- | ------- |
-| 18       | **2.97871** | 3.73433 |
-| 19       | **5.76021** | 7.22556 |
-| 20       | **11.2744** | 14.3306 |
-| 21       | **22.5167** | 28.8935 |
-| 22       | **47.6511** | 58.5402 |
+| 18       | **1.59124** | 2.36518 |
+| 19       | **2.87866** | 4.65791 |
+| 20       | **6.06711** | 9.5114  |
+| 21       | **12.1177** | 19.0475 |
+| 22       | **24.4839** | 38.4716 |
 
 ![image](/benchmark/fri/fri_benchmark_ubuntu_i9.png)
 
@@ -37,12 +40,12 @@ bazel run --config opt --//:has_matplotlib //benchmark/fri:fri_benchmark -- -k 1
 
 WARNING: On Mac M3, high degree tests are not feasible due to memory constraints.
 
-| Exponent | Tachyon | Plonky3      |
-| :------- | ------- | ------------ |
-| 18       | 3.68509 | **1.39107**  |
-| 19       | 7.37079 | **2.76483**  |
-| 20       | 14.9081 | **5.62375**  |
-| 21       | 30.3153 | **11.8295**  |
-| 22       | 64.8022 | **25.4490**  |
+| Exponent | Tachyon | Plonky3 |
+| :------- | ------- | ------- |
+| 18       | 3.96588 | 2.92354 |
+| 19       | 7.95329 | 5.89079 |
+| 20       | 15.8636 | 11.8225 |
+| 21       | 46.1967 | 34.4965 |
+| 22       | 182.084 | 124.7   |
 
 ![image](/benchmark/fri/fri_benchmark_mac_m3.png)
diff --git a/benchmark/fri/fri_benchmark_mac_m3.png b/benchmark/fri/fri_benchmark_mac_m3.png
index 1065aaf2b..4a28a9a29 100644
Binary files a/benchmark/fri/fri_benchmark_mac_m3.png and b/benchmark/fri/fri_benchmark_mac_m3.png differ
diff --git a/benchmark/fri/fri_benchmark_ubuntu_i9.png b/benchmark/fri/fri_benchmark_ubuntu_i9.png
index 111f9cee5..f008dfdaf 100644
Binary files a/benchmark/fri/fri_benchmark_ubuntu_i9.png and b/benchmark/fri/fri_benchmark_ubuntu_i9.png differ
diff --git a/benchmark/msm/README.md b/benchmark/msm/README.md
index 0ffaf18f7..3869f29b8 100644
--- a/benchmark/msm/README.md
+++ b/benchmark/msm/README.md
@@ -4,6 +4,7 @@
 
 ```
 Run on 13th Gen Intel(R) Core(TM) i9-13900K (32 X 5500 MHz CPU s)
+Compiler: clang-15
 CPU Caches:
   L1 Data 48 KiB (x16)
   L1 Instruction 32 KiB (x16)
@@ -17,24 +18,26 @@ CPU Caches:
   L2 Unified 4096 KiB (x12)
 ```
 
+Note: Run with `build --@rules_rust//:extra_rustc_flags="-Ctarget-cpu=native"` in your .bazelrc.user
+
 ### Uniform points
 
 ```shell
-bazel run --config opt --//:has_matplotlib //benchmark/msm:msm_benchmark -- -k 16 -k 17 -k 18 -k 19 -k 20 -k 21 -k 22 -k 23 --vendor arkworks --vendor bellman --vendor halo2 --check_results
+GOMP_SPINCOUNT=0 bazel run --config maxopt --//:has_matplotlib //benchmark/msm:msm_benchmark -- -k 16 -k 17 -k 18 -k 19 -k 20 -k 21 -k 22 -k 23 --vendor arkworks --vendor bellman --vendor halo2 --check_results
 ```
 
 #### On Intel i9-13900K
 
 | Exponent | Tachyon      | Arkworks | Bellman  | Halo2    |
 | :------: | ------------ | -------- | -------- | -------- |
-|    16    | **0.037107** | 0.043005 | 0.079576 | 0.04854  |
-|    17    | **0.051857** | 0.078176 | 0.11077  | 0.087005 |
-|    18    | **0.10235**  | 0.15416  | 0.179148 | 0.146375 |
-|    19    | **0.185314** | 0.301129 | 0.360499 | 0.273742 |
-|    20    | **0.352276** | 0.592931 | 0.516447 | 0.533842 |
-|    21    | **0.630413** | 1.07979  | 1.00715  | 1.01114  |
-|    22    | **1.22393**  | 2.18742  | 2.00827  | 1.99418  |
-|    23    | **2.34737**  | 4.34471  | 3.2081   | 3.62107  |
+|    16    | **0.028461** | 0.037741 | 0.077416 | 0.045742 |
+|    17    | **0.059648** | 0.074936 | 0.105104 | 0.08211  |
+|    18    | **0.08743**  | 0.12735  | 0.196602 | 0.151715 |
+|    19    | **0.181646** | 0.252424 | 0.319185 | 0.282056 |
+|    20    | **0.303829** | 0.454595 | 0.471094 | 0.526231 |
+|    21    | **0.549287** | 0.951397 | 0.886244 | 1.00624  |
+|    22    | **1.11021**  | 2.00783  | 1.72011  | 1.9662   |
+|    23    | **2.06762**  | 3.78478  | 2.76673  | 3.68139  |
 
 ![image](/benchmark/msm/msm_benchmark_uniform_ubuntu_i9.png)
 
@@ -42,35 +45,35 @@ bazel run --config opt --//:has_matplotlib //benchmark/msm:msm_benchmark -- -k 1
 
 | Exponent | Tachyon      | Arkworks | Bellman  | Halo2    |
 | :------: | ------------ | -------- | -------- | -------- |
-|    16    | **0.049285** | 0.052368 | 0.118564 | 0.079168 |
-|    17    | **0.088628** | 0.105875 | 0.16704  | 0.142758 |
-|    18    | **0.157609** | 0.19186  | 0.299953 | 0.278592 |
-|    19    | **0.282686** | 0.351326 | 0.578682 | 0.506371 |
-|    20    | **0.571241** | 0.702036 | 0.901252 | 0.974515 |
-|    21    | **1.106550** | 1.54553  | 1.63521  | 1.85615  |
-|    22    | **2.276600** | 3.35888  | 3.274    | 3.68391  |
-|    23    | **4.191330** | 6.41272  | 5.86292  | 6.89936  |
+|    16    | **0.046099** | 0.051773 | 0.110882 | 0.09505  |
+|    17    | **0.079298** | 0.097698 | 0.166183 | 0.174984 |
+|    18    | **0.151962** | 0.173607 | 0.296879 | 0.337657 |
+|    19    | **0.287848** | 0.34129  | 0.5563   | 0.592885 |
+|    20    | **0.504987** | 0.630489 | 0.840907 | 1.07097  |
+|    21    | **0.980302** | 1.33391  | 1.56196  | 1.98335  |
+|    22    | **1.89977**  | 2.86768  | 3.04392  | 3.9341   |
+|    23    | **3.73015**  | 5.71419  | 5.45636  | 7.51033  |
 
 ![image](/benchmark/msm/msm_benchmark_uniform_mac_m3.png)
 
 ### Non-uniform points
 
 ```shell
-bazel run --config opt --//:has_matplotlib //benchmark/msm:msm_benchmark -- -k 16 -k 17 -k 18 -k 19 -k 20 -k 21 -k 22 -k 23 --vendor arkworks --vendor bellman --vendor halo2 --test_set non_uniform --check_results
+GOMP_SPINCOUNT=0 bazel run --config maxopt --//:has_matplotlib //benchmark/msm:msm_benchmark -- -k 16 -k 17 -k 18 -k 19 -k 20 -k 21 -k 22 -k 23 --vendor arkworks --vendor bellman --vendor halo2 --test_set non_uniform --check_results
 ```
 
 #### On Intel i9-13900K
 
-| Exponent | Tachyon      | Arkworks     | Bellman  | Halo2    |
-| :------: | ------------ | ------------ | -------- | -------- |
-|    16    | 0.041756     | **0.038514** | 0.050397 | 0.040222 |
-|    17    | **0.06304**  | 0.069963     | 0.067314 | 0.07276  |
-|    18    | **0.09546**  | 0.137724     | 0.126665 | 0.138729 |
-|    19    | **0.189892** | 0.261193     | 0.262439 | 0.26166  |
-|    20    | **0.313575** | 0.475754     | 0.387448 | 0.51257  |
-|    21    | **0.550828** | 0.901562     | 0.666334 | 0.955411 |
-|    22    | **1.14408**  | 1.61699      | 1.29853  | 1.88522  |
-|    23    | **1.91659**  | 3.13911      | 2.16368  | 3.46701  |
+| Exponent | Tachyon      | Arkworks | Bellman  | Halo2    |
+| :------: | ------------ | -------- | -------- | -------- |
+|    16    | **0.030188** | 0.033608 | 0.057795 | 0.060642 |
+|    17    | **0.048851** | 0.064059 | 0.132584 | 0.099568 |
+|    18    | **0.080146** | 0.121525 | 0.124192 | 0.147496 |
+|    19    | **0.147626** | 0.227517 | 0.234429 | 0.27793  |
+|    20    | **0.289661** | 0.445139 | 0.341189 | 0.509375 |
+|    21    | **0.495707** | 0.801975 | 0.702259 | 1.0386   |
+|    22    | **0.993738** | 1.51266  | 1.24812  | 1.88462  |
+|    23    | **1.69944**  | 3.07904  | 2.00071  | 3.57452  |
 
 ![image](/benchmark/msm/msm_benchmark_non_uniform_ubuntu_i9.png)
 
@@ -78,14 +81,14 @@ bazel run --config opt --//:has_matplotlib //benchmark/msm:msm_benchmark -- -k 1
 
 | Exponent | Tachyon      | Arkworks | Bellman  | Halo2    |
 | :------: | ------------ | -------- | -------- | -------- |
-|    16    | **0.040045** | 0.049862 | 0.083292 | 0.082423 |
-|    17    | **0.074318** | 0.091205 | 0.128679 | 0.157111 |
-|    18    | **0.140125** | 0.177842 | 0.232212 | 0.310648 |
-|    19    | **0.287691** | 0.330268 | 0.437016 | 0.535915 |
-|    20    | **0.55437**  | 0.651841 | 0.713282 | 1.01238  |
-|    21    | **1.01053**  | 1.36348  | 1.29945  | 1.75816  |
-|    22    | **2.00677**  | 2.56     | 2.49532  | 3.55769  |
-|    23    | **4.02119**  | 5.2982   | 4.56454  | 7.11582  |
+|    16    | **0.040954** | 0.046663 | 0.076068 | 0.089352 |
+|    17    | **0.069956** | 0.089339 | 0.119363 | 0.166812 |
+|    18    | **0.146869** | 0.163578 | 0.225768 | 0.326553 |
+|    19    | **0.268475** | 0.302439 | 0.460063 | 0.579915 |
+|    20    | **0.501956** | 0.627272 | 0.723071 | 1.09316  |
+|    21    | **0.920728** | 1.20662  | 1.22352  | 1.98457  |
+|    22    | **1.78902**  | 2.40124  | 2.24543  | 3.83765  |
+|    23    | **3.47906**  | 4.70651  | 4.13381  | 7.43978  |
 
 ![image](/benchmark/msm/msm_benchmark_non_uniform_mac_m3.png)
 
@@ -94,41 +97,41 @@ bazel run --config opt --//:has_matplotlib //benchmark/msm:msm_benchmark -- -k 1
 ### Uniform points
 
 ```shell
-bazel run --config opt --//:has_matplotlib --config cuda //benchmark/msm:msm_benchmark_gpu -- -k 16 -k 17 -k 18 -k 19 -k 20 -k 21 -k 22 -k 23 --test_set non_uniform --check_results
+GOMP_SPINCOUNT=0 bazel run --config maxopt --//:has_matplotlib --config cuda //benchmark/msm:msm_benchmark_gpu -- -k 16 -k 17 -k 18 -k 19 -k 20 -k 21 -k 22 -k 23 --test_set non_uniform --check_results
 ```
 
 #### On RTX-4090
 
 | Exponent | Tachyon CPU | Tachyon GPU  |
 | :------: | ----------- | ------------ |
-|    16    | 0.044828    | **0.02644**  |
-|    17    | 0.070154    | **0.008896** |
-|    18    | 0.120668    | **0.015391** |
-|    19    | 0.191098    | **0.021299** |
-|    20    | 0.369561    | **0.032302** |
-|    21    | 0.675571    | **0.060279** |
-|    22    | 1.26675     | **0.166554** |
-|    23    | 2.41323     | **0.219751** |
+|    16    | 0.026688    | **0.01981**  |
+|    17    | 0.041291    | **0.006624** |
+|    18    | 0.081467    | **0.008306** |
+|    19    | 0.148929    | **0.012553** |
+|    20    | 0.260831    | **0.02423**  |
+|    21    | 0.474542    | **0.044591** |
+|    22    | 0.921276    | **0.088349** |
+|    23    | 1.70264     | **0.162646** |
 
 ![image](/benchmark/msm/msm_benchmark_uniform_ubuntu_rtx_4090.png)
 
 ### Non-uniform points
 
 ```shell
-bazel run --config opt --//:has_matplotlib --config cuda //benchmark/msm:msm_benchmark_gpu -- -k 16 -k 17 -k 18 -k 19 -k 20 -k 21 -k 22 -k 23 --check_results
+GOMP_SPINCOUNT=0 bazel run --config maxopt --//:has_matplotlib --config cuda //benchmark/msm:msm_benchmark_gpu -- -k 16 -k 17 -k 18 -k 19 -k 20 -k 21 -k 22 -k 23 --check_results
 ```
 
 #### On RTX-4090
 
 | Exponent | Tachyon CPU | Tachyon GPU  |
 | :------: | ----------- | ------------ |
-|    16    | 0.044986    | **0.025648** |
-|    17    | 0.061027    | **0.010882** |
-|    18    | 0.108204    | **0.012794** |
-|    19    | 0.182035    | **0.022456** |
-|    20    | 0.326646    | **0.033684** |
-|    21    | 0.589097    | **0.060135** |
-|    22    | 1.11816     | **0.169485** |
-|    23    | 2.11566     | **0.219624** |
+|    16    | 0.029045    | **0.020228** |
+|    17    | 0.047588    | **0.006565** |
+|    18    | 0.089673    | **0.008864** |
+|    19    | 0.164875    | **0.012308** |
+|    20    | 0.29135     | **0.023396** |
+|    21    | 0.541067    | **0.043512** |
+|    22    | 1.0379      | **0.08407**  |
+|    23    | 2.08601     | **0.157046** |
 
 ![image](/benchmark/msm/msm_benchmark_non_uniform_ubuntu_rtx_4090.png)
diff --git a/benchmark/msm/msm_benchmark_non_uniform_mac_m3.png b/benchmark/msm/msm_benchmark_non_uniform_mac_m3.png
index ea7962ee0..85e14d747 100644
Binary files a/benchmark/msm/msm_benchmark_non_uniform_mac_m3.png and b/benchmark/msm/msm_benchmark_non_uniform_mac_m3.png differ
diff --git a/benchmark/msm/msm_benchmark_non_uniform_ubuntu_i9.png b/benchmark/msm/msm_benchmark_non_uniform_ubuntu_i9.png
index 80eb790a9..cbfa22832 100644
Binary files a/benchmark/msm/msm_benchmark_non_uniform_ubuntu_i9.png and b/benchmark/msm/msm_benchmark_non_uniform_ubuntu_i9.png differ
diff --git a/benchmark/msm/msm_benchmark_non_uniform_ubuntu_rtx_4090.png b/benchmark/msm/msm_benchmark_non_uniform_ubuntu_rtx_4090.png
index 345013b02..50015ffe3 100644
Binary files a/benchmark/msm/msm_benchmark_non_uniform_ubuntu_rtx_4090.png and b/benchmark/msm/msm_benchmark_non_uniform_ubuntu_rtx_4090.png differ
diff --git a/benchmark/msm/msm_benchmark_uniform_mac_m3.png b/benchmark/msm/msm_benchmark_uniform_mac_m3.png
index 2ad4fa8b9..13d487118 100644
Binary files a/benchmark/msm/msm_benchmark_uniform_mac_m3.png and b/benchmark/msm/msm_benchmark_uniform_mac_m3.png differ
diff --git a/benchmark/msm/msm_benchmark_uniform_ubuntu_i9.png b/benchmark/msm/msm_benchmark_uniform_ubuntu_i9.png
index 187158ca4..106d7f9a5 100644
Binary files a/benchmark/msm/msm_benchmark_uniform_ubuntu_i9.png and b/benchmark/msm/msm_benchmark_uniform_ubuntu_i9.png differ
diff --git a/benchmark/msm/msm_benchmark_uniform_ubuntu_rtx_4090.png b/benchmark/msm/msm_benchmark_uniform_ubuntu_rtx_4090.png
index 4e5ccee25..e2774ec9e 100644
Binary files a/benchmark/msm/msm_benchmark_uniform_ubuntu_rtx_4090.png and b/benchmark/msm/msm_benchmark_uniform_ubuntu_rtx_4090.png differ
diff --git a/benchmark/poseidon/README.md b/benchmark/poseidon/README.md
index 80589849f..f4e9272ae 100644
--- a/benchmark/poseidon/README.md
+++ b/benchmark/poseidon/README.md
@@ -2,6 +2,7 @@
 
 ```
 Run on 13th Gen Intel(R) Core(TM) i9-13900K (32 X 5500 MHz CPU s)
+Compiler: clang-15
 CPU Caches:
   L1 Data 48 KiB (x16)
   L1 Instruction 32 KiB (x16)
@@ -16,24 +17,24 @@ CPU Caches:
 ```
 
 ```shell
-bazel run --config opt --//:has_matplotlib //benchmark/poseidon:poseidon_benchmark -- --check_results
+GOMP_SPINCOUNT=0 bazel run --config maxopt --//:has_matplotlib //benchmark/poseidon:poseidon_benchmark -- --check_results
 ```
 
 ## On Intel i9-13900K
 
 | Repetition | Tachyon     | Arkworks |
 | :--------: | ----------- | -------- |
-|     0      | **3.4e-05** | 0.000103 |
-|     1      | **3.4e-05** | 0.000103 |
-|     2      | **3.3e-05** | 0.000101 |
-|     3      | **3.3e-05** | 0.000103 |
-|     4      | **3.3e-05** | 0.000103 |
-|     5      | **3.3e-05** | 0.000108 |
-|     6      | **3.3e-05** | 0.000102 |
-|     7      | **3.2e-05** | 0.000104 |
-|     8      | **3.3e-05** | 0.000102 |
-|     9      | **3.1e-05** | 0.000103 |
-|    avg     | **3.2e-05** | 0.000103 |
+|     0      | **3.5e-05** | 0.000107 |
+|     1      | **3.2e-05** | 0.000106 |
+|     2      | **3.2e-05** | 0.000108 |
+|     3      | **3.1e-05** | 0.000107 |
+|     4      | **3.1e-05** | 0.000107 |
+|     5      | **3.1e-05** | 0.000107 |
+|     6      | **3.1e-05** | 0.000104 |
+|     7      | **3.1e-05** | 0.000105 |
+|     8      | **3.1e-05** | 0.000106 |
+|     9      | **3.1e-05** | 0.000107 |
+|    avg     | **3.1e-05** | 0.000106 |
 
 ![image](/benchmark/poseidon/poseidon_benchmark_ubuntu_i9.png)
 
@@ -41,16 +42,16 @@ bazel run --config opt --//:has_matplotlib //benchmark/poseidon:poseidon_benchma
 
 | Repetition | Tachyon     | Arkworks |
 | :--------: | ----------- | -------- |
-|     1      | **3.9e-05** | 0.000108 |
-|     0      | **3.8e-05** | 0.000111 |
-|     2      | **3.7e-05** | 0.000106 |
-|     3      | **3.6e-05** | 0.000104 |
-|     4      | **3.6e-05** | 0.000106 |
-|     5      | **3.5e-05** | 0.000103 |
-|     6      | **3.5e-05** | 0.000103 |
-|     7      | **3.5e-05** | 0.000103 |
-|     8      | **3.5e-05** | 0.000103 |
-|     9      | **3.5e-05** | 0.000105 |
-|    avg     | **3.6e-05** | 0.000105 |
+|     0      | **3.7e-05** | 0.000111 |
+|     1      | **3.5e-05** | 0.000105 |
+|     2      | **3.3e-05** | 0.000103 |
+|     3      | **3.2e-05** | 0.000104 |
+|     4      | **3.2e-05** | 0.000101 |
+|     5      | **3.2e-05** | 0.000103 |
+|     6      | **3.2e-05** | 0.000105 |
+|     7      | **3.2e-05** | 0.000102 |
+|     8      | **3.2e-05** | 0.000102 |
+|     9      | **3.2e-05** | 0.000102 |
+|    avg     | **3.2e-05** | 0.000103 |
 
 ![image](/benchmark/poseidon/poseidon_benchmark_mac_m3.png)
diff --git a/benchmark/poseidon/poseidon_benchmark_mac_m3.png b/benchmark/poseidon/poseidon_benchmark_mac_m3.png
index 0d1d3ed44..1ef1139bc 100644
Binary files a/benchmark/poseidon/poseidon_benchmark_mac_m3.png and b/benchmark/poseidon/poseidon_benchmark_mac_m3.png differ
diff --git a/benchmark/poseidon/poseidon_benchmark_ubuntu_i9.png b/benchmark/poseidon/poseidon_benchmark_ubuntu_i9.png
index 7b74c02ff..5103867e9 100644
Binary files a/benchmark/poseidon/poseidon_benchmark_ubuntu_i9.png and b/benchmark/poseidon/poseidon_benchmark_ubuntu_i9.png differ
diff --git a/benchmark/poseidon2/README.md b/benchmark/poseidon2/README.md
index ca57c5f0e..2a0a5c943 100644
--- a/benchmark/poseidon2/README.md
+++ b/benchmark/poseidon2/README.md
@@ -2,6 +2,7 @@
 
 ```
 Run on 13th Gen Intel(R) Core(TM) i9-13900K (32 X 5500 MHz CPU s)
+Compiler: clang-15
 CPU Caches:
   L1 Data 48 KiB (x16)
   L1 Instruction 32 KiB (x16)
@@ -15,29 +16,30 @@ CPU Caches:
   L2 Unified 4096 KiB (x12)
 ```
 
+Note: Run with `build --@rules_rust//:extra_rustc_flags="-Ctarget-cpu=native"` in your .bazelrc.user
 Note that Poseidon2 runs 10000x per test due to some time results being too small when running a single iteration.
 
 ## BN254
 
 ```shell
-bazel run --config opt --//:has_matplotlib //benchmark/poseidon2:poseidon2_benchmark -- -p bn254_fr --vendor horizen --vendor plonky3 --check_results
+GOMP_SPINCOUNT=0 bazel run --config maxopt --//:has_matplotlib //benchmark/poseidon2:poseidon2_benchmark -- -p bn254_fr --vendor horizen --vendor plonky3 --check_results
 ```
 
 ### On Intel i9-13900K
 
 | Trial Number | Tachyon  | Horizen      | Plonky3  |
 | :----------- | -------- | ------------ | -------- |
-| 0            | 0.064726 | **0.050047** | 0.082464 |
-| 1            | 0.061723 | **0.049997** | 0.082598 |
-| 2            | 0.060917 | **0.050063** | 0.08257  |
-| 3            | 0.06086  | **0.049952** | 0.082493 |
-| 4            | 0.060655 | **0.050173** | 0.082409 |
-| 5            | 0.060768 | **0.050683** | 0.08268  |
-| 6            | 0.060843 | **0.050278** | 0.082675 |
-| 7            | 0.060696 | **0.050062** | 0.082579 |
-| 8            | 0.060688 | **0.05004**  | 0.082592 |
-| 9            | 0.060677 | **0.050128** | 0.083144 |
-| avg          | 0.061255 | **0.050142** | 0.08262  |
+| 0            | 0.069228 | **0.050903** | 0.085679 |
+| 1            | 0.062046 | **0.050892** | 0.085772 |
+| 2            | 0.06053  | **0.050848** | 0.08553  |
+| 3            | 0.060648 | **0.050825** | 0.085643 |
+| 4            | 0.060553 | **0.051126** | 0.08583  |
+| 5            | 0.060592 | **0.05362**  | 0.085475 |
+| 6            | 0.060576 | **0.050936** | 0.085731 |
+| 7            | 0.06051  | **0.05081**  | 0.085613 |
+| 8            | 0.060561 | **0.050889** | 0.086382 |
+| 9            | 0.060558 | **0.050896** | 0.086557 |
+| avg          | 0.06158  | **0.051174** | 0.085821 |
 
 ![image](/benchmark/poseidon2/poseidon2_benchmark_bn254_ubuntu_i9.png)
 
@@ -45,17 +47,17 @@ bazel run --config opt --//:has_matplotlib //benchmark/poseidon2:poseidon2_bench
 
 | Trial Number | Tachyon  | Horizen      | Plonky3  |
 | :----------- | -------- | ------------ | -------- |
-| 0            | 0.072979 | **0.055031** | 0.081624 |
-| 1            | 0.072478 | **0.054731** | 0.081525 |
-| 2            | 0.071973 | **0.055768** | 0.081633 |
-| 3            | 0.071969 | **0.054835** | 0.081638 |
-| 4            | 0.072009 | **0.054884** | 0.081545 |
-| 5            | 0.071933 | **0.055**    | 0.081572 |
-| 6            | 0.07201  | **0.054946** | 0.081521 |
-| 7            | 0.072033 | **0.054883** | 0.081539 |
-| 8            | 0.071967 | **0.054989** | 0.081626 |
-| 9            | 0.071934 | **0.054942** | 0.081556 |
-| avg          | 0.072128 | **0.055**    | 0.081577 |
+| 0            | 0.068967 | **0.058728** | 0.086994 |
+| 1            | 0.068786 | **0.05839**  | 0.086825 |
+| 2            | 0.068658 | **0.058245** | 0.086779 |
+| 3            | 0.068673 | **0.058189** | 0.086693 |
+| 4            | 0.068675 | **0.058303** | 0.08674  |
+| 5            | 0.068693 | **0.058109** | 0.08681  |
+| 6            | 0.068621 | **0.058405** | 0.086816 |
+| 7            | 0.068747 | **0.058247** | 0.086871 |
+| 8            | 0.068637 | **0.058383** | 0.086842 |
+| 9            | 0.068665 | **0.058162** | 0.086846 |
+| avg          | 0.068712 | **0.058316** | 0.086821 |
 
 ![image](/benchmark/poseidon2/poseidon2_benchmark_bn254_mac_m3.png)
 
@@ -66,24 +68,24 @@ Note: Horizen and Plonky3 compute values with a different internal matrix, requi
 ### Horizen
 
 ```shell
-bazel run --config opt --//:has_matplotlib //benchmark/poseidon2:poseidon2_benchmark -- -p baby_bear --vendor horizen --check_results
+GOMP_SPINCOUNT=0 bazel run --config maxopt --//:has_matplotlib //benchmark/poseidon2:poseidon2_benchmark -- -p baby_bear --vendor horizen --check_results
 ```
 
 #### On Intel i9-13900K
 
 | Trial Number | Tachyon      | Horizen  |
 | :----------- | ------------ | -------- |
-| 0            | **0.011549** | 0.034751 |
-| 1            | **0.011439** | 0.034627 |
-| 2            | **0.011475** | 0.034581 |
-| 3            | **0.011543** | 0.035442 |
-| 4            | **0.011455** | 0.03632  |
-| 5            | **0.011372** | 0.034545 |
-| 6            | **0.011381** | 0.034538 |
-| 7            | **0.011142** | 0.03459  |
-| 8            | **0.010845** | 0.034522 |
-| 9            | **0.010819** | 0.034589 |
-| avg          | **0.011302** | 0.03485  |
+| 0            | **0.011424** | 0.034238 |
+| 1            | **0.011975** | 0.034214 |
+| 2            | **0.011505** | 0.034245 |
+| 3            | **0.011304** | 0.03418  |
+| 4            | **0.011313** | 0.034231 |
+| 5            | **0.011354** | 0.034234 |
+| 6            | **0.010743** | 0.034487 |
+| 7            | **0.01071**  | 0.034259 |
+| 8            | **0.010706** | 0.034229 |
+| 9            | **0.010708** | 0.034246 |
+| avg          | **0.011174** | 0.034256 |
 
 ![image](/benchmark/poseidon2/poseidon2_benchmark_baby_bear_horizen_ubuntu_i9.png)
 
@@ -91,41 +93,41 @@ bazel run --config opt --//:has_matplotlib //benchmark/poseidon2:poseidon2_bench
 
 | Trial Number | Tachyon      | Horizen  |
 | :----------- | ------------ | -------- |
-| 0            | **0.010979** | 0.013892 |
-| 1            | **0.010574** | 0.013858 |
-| 2            | **0.010544** | 0.014098 |
-| 3            | **0.010642** | 0.013843 |
-| 4            | **0.010517** | 0.013842 |
-| 5            | **0.010599** | 0.013938 |
-| 6            | **0.010519** | 0.013913 |
-| 7            | **0.010474** | 0.013889 |
-| 8            | **0.010572** | 0.013892 |
-| 9            | **0.010533** | 0.013979 |
-| avg          | **0.010595** | 0.013914 |
+| 0            | **0.010679** | 0.014511 |
+| 1            | **0.010448** | 0.014653 |
+| 2            | **0.010286** | 0.014961 |
+| 3            | **0.01024**  | 0.014769 |
+| 4            | **0.010233** | 0.014717 |
+| 5            | **0.010267** | 0.014761 |
+| 6            | **0.010226** | 0.01514  |
+| 7            | **0.010303** | 0.01475  |
+| 8            | **0.010253** | 0.014693 |
+| 9            | **0.010326** | 0.014533 |
+| avg          | **0.010326** | 0.014748 |
 
 ![image](/benchmark/poseidon2/poseidon2_benchmark_baby_bear_horizen_mac_m3.png)
 
 ### Plonky3
 
 ```shell
-bazel run --config opt --//:has_matplotlib //benchmark/poseidon2:poseidon2_benchmark -- -p baby_bear --vendor plonky3 --check_results
+GOMP_SPINCOUNT=0 bazel run --config maxopt --//:has_matplotlib //benchmark/poseidon2:poseidon2_benchmark -- -p baby_bear --vendor plonky3 --check_results
 ```
 
 #### On Intel i9-13900K
 
 | Trial Number | Tachyon  | Plonky3      |
 | :----------- | -------- | ------------ |
-| 0            | 0.009848 | **0.006655** |
-| 1            | 0.00992  | **0.006582** |
-| 2            | 0.009955 | **0.006616** |
-| 3            | 0.009811 | **0.006572** |
-| 4            | 0.009851 | **0.006537** |
-| 5            | 0.009776 | **0.006645** |
-| 6            | 0.009822 | **0.006548** |
-| 7            | 0.009738 | **0.006586** |
-| 8            | 0.009757 | **0.006594** |
-| 9            | 0.009717 | **0.006619** |
-| avg          | 0.009819 | **0.006595** |
+| 0            | 0.00999  | **0.005391** |
+| 1            | 0.009882 | **0.005298** |
+| 2            | 0.009848 | **0.00513**  |
+| 3            | 0.009772 | **0.005157** |
+| 4            | 0.00977  | **0.005072** |
+| 5            | 0.009774 | **0.005032** |
+| 6            | 0.009783 | **0.005062** |
+| 7            | 0.009878 | **0.005077** |
+| 8            | 0.009778 | **0.005014** |
+| 9            | 0.009762 | **0.005016** |
+| avg          | 0.009823 | **0.005124** |
 
 ![image](/benchmark/poseidon2/poseidon2_benchmark_baby_bear_plonky3_ubuntu_i9.png)
 
@@ -133,16 +135,16 @@ bazel run --config opt --//:has_matplotlib //benchmark/poseidon2:poseidon2_bench
 
 | Trial Number | Tachyon  | Plonky3      |
 | :----------- | -------- | ------------ |
-| 0            | 0.009201 | **0.00732**  |
-| 1            | 0.008927 | **0.007346** |
-| 2            | 0.008922 | **0.007309** |
-| 3            | 0.008735 | **0.007324** |
-| 4            | 0.008765 | **0.0076**   |
-| 5            | 0.008715 | **0.007335** |
-| 6            | 0.008704 | **0.007439** |
-| 7            | 0.008664 | **0.007369** |
-| 8            | 0.008679 | **0.007347** |
-| 9            | 0.008657 | **0.007353** |
-| avg          | 0.008796 | **0.007374** |
+| 0            | 0.009116 | **0.007311** |
+| 1            | 0.008967 | **0.007352** |
+| 2            | 0.008805 | **0.007312** |
+| 3            | 0.008748 | **0.007315** |
+| 4            | 0.008742 | **0.007339** |
+| 5            | 0.008741 | **0.007309** |
+| 6            | 0.008774 | **0.00732**  |
+| 7            | 0.00873  | **0.007696** |
+| 8            | 0.008791 | **0.007342** |
+| 9            | 0.008741 | **0.007353** |
+| avg          | 0.008815 | **0.007364** |
 
 ![image](/benchmark/poseidon2/poseidon2_benchmark_baby_bear_plonky3_mac_m3.png)\*\*\*\*
diff --git a/benchmark/poseidon2/poseidon2_benchmark_baby_bear_horizen_mac_m3.png b/benchmark/poseidon2/poseidon2_benchmark_baby_bear_horizen_mac_m3.png
index 1499d73ad..863a78143 100644
Binary files a/benchmark/poseidon2/poseidon2_benchmark_baby_bear_horizen_mac_m3.png and b/benchmark/poseidon2/poseidon2_benchmark_baby_bear_horizen_mac_m3.png differ
diff --git a/benchmark/poseidon2/poseidon2_benchmark_baby_bear_horizen_ubuntu_i9.png b/benchmark/poseidon2/poseidon2_benchmark_baby_bear_horizen_ubuntu_i9.png
index 502f3b277..a4304a880 100644
Binary files a/benchmark/poseidon2/poseidon2_benchmark_baby_bear_horizen_ubuntu_i9.png and b/benchmark/poseidon2/poseidon2_benchmark_baby_bear_horizen_ubuntu_i9.png differ
diff --git a/benchmark/poseidon2/poseidon2_benchmark_baby_bear_plonky3_mac_m3.png b/benchmark/poseidon2/poseidon2_benchmark_baby_bear_plonky3_mac_m3.png
index fbf658958..1452cfb38 100644
Binary files a/benchmark/poseidon2/poseidon2_benchmark_baby_bear_plonky3_mac_m3.png and b/benchmark/poseidon2/poseidon2_benchmark_baby_bear_plonky3_mac_m3.png differ
diff --git a/benchmark/poseidon2/poseidon2_benchmark_baby_bear_plonky3_ubuntu_i9.png b/benchmark/poseidon2/poseidon2_benchmark_baby_bear_plonky3_ubuntu_i9.png
index 107e66a96..edc8db8d2 100644
Binary files a/benchmark/poseidon2/poseidon2_benchmark_baby_bear_plonky3_ubuntu_i9.png and b/benchmark/poseidon2/poseidon2_benchmark_baby_bear_plonky3_ubuntu_i9.png differ
diff --git a/benchmark/poseidon2/poseidon2_benchmark_bn254_mac_m3.png b/benchmark/poseidon2/poseidon2_benchmark_bn254_mac_m3.png
index dbabac2b1..eae247fd2 100644
Binary files a/benchmark/poseidon2/poseidon2_benchmark_bn254_mac_m3.png and b/benchmark/poseidon2/poseidon2_benchmark_bn254_mac_m3.png differ
diff --git a/benchmark/poseidon2/poseidon2_benchmark_bn254_ubuntu_i9.png b/benchmark/poseidon2/poseidon2_benchmark_bn254_ubuntu_i9.png
index 7b2a8d3f2..f65e64a5d 100644
Binary files a/benchmark/poseidon2/poseidon2_benchmark_bn254_ubuntu_i9.png and b/benchmark/poseidon2/poseidon2_benchmark_bn254_ubuntu_i9.png differ
diff --git a/tachyon/base/bits.h b/tachyon/base/bits.h
index 3cd0d75e5..fa454f5a9 100644
--- a/tachyon/base/bits.h
+++ b/tachyon/base/bits.h
@@ -163,6 +163,7 @@ constexpr T LeftmostBit() {
 
 TACHYON_EXPORT uint64_t BitRev(uint64_t n);
 
+// Reverses the |bit_len| least significant bits of |x|.
 inline size_t ReverseBitsLen(size_t x, size_t bit_len) {
   return BitRev(x) >> (sizeof(size_t) * 8 - bit_len);
 }
diff --git a/tachyon/base/openmp_util.h b/tachyon/base/openmp_util.h
index 19b111a55..945cb1696 100644
--- a/tachyon/base/openmp_util.h
+++ b/tachyon/base/openmp_util.h
@@ -21,6 +21,8 @@
 #define OMP_PARALLEL_FOR(expr) _Pragma("omp parallel for") for (expr)
 #define OMP_PARALLEL_NESTED_FOR(expr) \
   _Pragma("omp parallel for collapse(2)") for (expr)
+#define OMP_PARALLEL_DYNAMIC_FOR(expr) \
+  _Pragma("omp parallel for schedule(dynamic)") for (expr)
 #else
 #define CONSTEXPR_IF_NOT_OPENMP constexpr
 #define OMP_FOR(expr) for (expr)
@@ -29,6 +31,7 @@
 #define OMP_PARALLEL
 #define OMP_PARALLEL_FOR(expr) for (expr)
 #define OMP_PARALLEL_NESTED_FOR(expr) for (expr)
+#define OMP_PARALLEL_DYNAMIC_FOR(expr) for (expr)
 #endif  // defined(TACHYON_HAS_OPENMP)
 
 namespace tachyon::base {
diff --git a/tachyon/base/parallelize.h b/tachyon/base/parallelize.h
index 7efc21509..281898d09 100644
--- a/tachyon/base/parallelize.h
+++ b/tachyon/base/parallelize.h
@@ -139,6 +139,42 @@ void ParallelizeByChunkSize(size_t size, size_t chunk_size, Callable callback) {
   }
 }
 
+// Splits the |container| by |chunk_size| and executes |callback| in parallel.
+// Dynamically schedules tasks to ensure most efficient use of threads.
+template <typename Container, typename Callable>
+void DynamicParallelizeByChunkSize(Container& container, size_t chunk_size,
+                                   Callable callback) {
+  if (chunk_size == 0) return;
+  size_t num_chunks = (std::size(container) + chunk_size - 1) / chunk_size;
+  if (num_chunks == 1) {
+    internal::InvokeParallelizeCallback(container, 0, num_chunks, chunk_size,
+                                        callback);
+    return;
+  }
+  OMP_PARALLEL_DYNAMIC_FOR(size_t i = 0; i < num_chunks; ++i) {
+    internal::InvokeParallelizeCallback(container, i, num_chunks, chunk_size,
+                                        callback);
+  }
+}
+
+// Splits the |size| by |chunk_size| and executes |callback| in parallel.
+// Dynamically schedules tasks to ensure most efficient use of threads.
+template <typename Callable>
+void DynamicParallelizeByChunkSize(size_t size, size_t chunk_size,
+                                   Callable callback) {
+  if (chunk_size == 0) return;
+  size_t num_chunks = (size + chunk_size - 1) / chunk_size;
+  if (num_chunks == 1) {
+    internal::InvokeParallelizeCallback(size, 0, num_chunks, chunk_size,
+                                        callback);
+    return;
+  }
+  OMP_PARALLEL_DYNAMIC_FOR(size_t i = 0; i < num_chunks; ++i) {
+    internal::InvokeParallelizeCallback(size, i, num_chunks, chunk_size,
+                                        callback);
+  }
+}
+
 // Splits the |container| into threads and executes |callback| in parallel.
 // See parallelize_unittest.cc for more details.
 template <typename Container, typename Callable>
diff --git a/tachyon/crypto/commitments/fri/simple_fri.h b/tachyon/crypto/commitments/fri/simple_fri.h
index fecaf5c61..35c0e56f3 100644
--- a/tachyon/crypto/commitments/fri/simple_fri.h
+++ b/tachyon/crypto/commitments/fri/simple_fri.h
@@ -66,7 +66,7 @@ class SimpleFRI final
     if (num_layers > 1) {
       for (uint32_t i = 1; i < num_layers; ++i) {
         // Pᵢ(X)   = Pᵢ_even(X²) + X * Pᵢ_odd(X²)
-        // Pᵢ₊₁(X) = Pᵢ_even(X²) + β * Pᵢ_odd(X²)
+        // Pᵢ₊₁(X) = Pᵢ_even(X) + β * Pᵢ_odd(X)
         beta = writer->SqueezeChallenge();
         VLOG(2) << "SimpleFRI(beta[" << i - 1
                 << "]): " << beta.ToHexString(true);
@@ -150,14 +150,14 @@ class SimpleFRI final
       // Pᵢ_odd(X²)  = (Pᵢ(X) - Pᵢ(-X)) / (2 * X)
       //
       // Next layer equation:
-      // Pᵢ₊₁(X) = Pᵢ_even(X²) + β * Pᵢ_odd(X²)
+      // Pᵢ₊₁(X) = Pᵢ_even(X) + β * Pᵢ_odd(X)
       //
       // If the domain of Pᵢ(X) is Dᵢ = {ω⁰, ω¹, ..., ωⁿ⁻¹},
       // then the domain of Pᵢ₊₁(X) is Dᵢ₊₁ = {ω⁰, ω¹, ..., ωᵏ⁻¹},
       // where k = n / 2.
       //
       // As per the definition:
-      // Pᵢ₊₁(ωʲ) = Pᵢ_even((ωʲ)²) + β * Pᵢ_odd((ωʲ)²)
+      // Pᵢ₊₁(ωʲ) = Pᵢ_even(ωʲ) + β * Pᵢ_odd(ωʲ)
       //
       // Substituting Pᵢ_even and Pᵢ_odd:
       // Pᵢ₊₁(ωʲ) = (Pᵢ(ωʲ) + Pᵢ(-ωʲ)) / 2 + β * (Pᵢ(ωʲ) - Pᵢ(-ωʲ)) / (2 * ωʲ)
diff --git a/tachyon/crypto/commitments/merkle_tree/field_merkle_tree/field_merkle_tree.h b/tachyon/crypto/commitments/merkle_tree/field_merkle_tree/field_merkle_tree.h
index 308be0f4f..7014d65c7 100644
--- a/tachyon/crypto/commitments/merkle_tree/field_merkle_tree/field_merkle_tree.h
+++ b/tachyon/crypto/commitments/merkle_tree/field_merkle_tree/field_merkle_tree.h
@@ -271,7 +271,7 @@ class FieldMerkleTree {
 
     std::vector<Digest> ret(max_rows_padded);
     absl::Span<Digest> sub_ret = absl::MakeSpan(ret).subspan(0, max_rows);
-    base::ParallelizeByChunkSize(
+    base::DynamicParallelizeByChunkSize(
         sub_ret, PackedPrimeField::N,
         [&hasher, &packed_hasher, tallest_matrices](
             absl::Span<Digest> chunk, size_t chunk_offset, size_t chunk_size) {
@@ -314,7 +314,7 @@ class FieldMerkleTree {
 
     std::vector<Digest> ret(next_rows_padded);
     absl::Span<Digest> sub_ret = absl::MakeSpan(ret).subspan(0, next_rows);
-    base::ParallelizeByChunkSize(
+    base::DynamicParallelizeByChunkSize(
         sub_ret, PackedPrimeField::N,
         [&hasher, &packed_hasher, &compressor, &packed_compressor, &prev_layer,
          matrices_to_inject](absl::Span<Digest> chunk, size_t chunk_offset,
@@ -361,8 +361,7 @@ class FieldMerkleTree {
           }
         });
 
-    Digest default_digest =
-        base::CreateArray<N>([]() { return PrimeField::Zero(); });
+    Digest default_digest = {PrimeField::Zero()};
     Digest inputs_with_default_digest[] = {
         default_digest,
         default_digest,
@@ -386,7 +385,7 @@ class FieldMerkleTree {
     size_t next_rows = prev_layer.size() / 2;
 
     std::vector<Digest> ret(next_rows);
-    base::ParallelizeByChunkSize(
+    base::DynamicParallelizeByChunkSize(
         ret, PackedPrimeField::N,
         [&compressor, &packed_compressor, &prev_layer](
             absl::Span<Digest> chunk, size_t chunk_offset, size_t chunk_size) {
diff --git a/tachyon/math/polynomials/univariate/radix2_twiddle_cache.h b/tachyon/math/polynomials/univariate/radix2_twiddle_cache.h
index 4a219b6b1..d3ae1d966 100644
--- a/tachyon/math/polynomials/univariate/radix2_twiddle_cache.h
+++ b/tachyon/math/polynomials/univariate/radix2_twiddle_cache.h
@@ -126,19 +126,21 @@ class Radix2TwiddleCache {
     static base::NoDestructor<Radix2TwiddleCache> twiddle_cache;
 
     absl::MutexLock lock(&twiddle_cache->mutex_);
-    auto it = twiddle_cache->items_.find(domain->size());
+    auto it = twiddle_cache->items_.find(
+        std::make_pair(domain->size(), domain->group_gen()));
     if (it == twiddle_cache->items_.end() ||
         (it->second->packed_vec_only && !packed_vec_only)) {
       it = twiddle_cache->items_.insert(
-          it, std::make_pair(domain->size(),
-                             std::make_unique<Item>(domain, packed_vec_only)));
+          it,
+          std::make_pair(std::make_pair(domain->size(), domain->group_gen()),
+                         std::make_unique<Item>(domain, packed_vec_only)));
     }
     return it->second.get();
   }
 
  private:
   absl::Mutex mutex_;
-  absl::flat_hash_map<size_t, std::unique_ptr<Item>> items_
+  absl::flat_hash_map<std::pair<size_t, F>, std::unique_ptr<Item>> items_
       ABSL_GUARDED_BY(mutex_);
 };