Apply consistent code formatting across the repo. Add clang-format and pre-commit hooks.

2026-10-25 22:28:17 +08:00 · 2025-03-27 10:30:07 -07:00
parent 2cd58fbc9a
commit ceab6e8bcc
782 changed files with 107230 additions and 106548 deletions
--- a/bin/x86_64/linux/release/APM_BlackScholes.txt
+++ b/bin/x86_64/linux/release/APM_BlackScholes.txt
@@ -9,10 +9,10 @@ Initializing data...
 Data init done.

 Executing Black-Scholes GPU kernel (512 iterations)...
-Options count             : 8000000     
+Options count             : 8000000
 BlackScholesGPU() time    : 0.048059 msec
 Effective memory bandwidth: 1664.634581 GB/s
-Gigaoptions per second    : 166.463458     
+Gigaoptions per second    : 166.463458

 BlackScholes, Throughput = 166.4635 GOptions/s, Time = 0.00005 s, Size = 8000000 options, NumDevsUsed = 1, Workgroup = 128

--- a/bin/x86_64/linux/release/APM_BlackScholes_nvrtc.txt
+++ b/bin/x86_64/linux/release/APM_BlackScholes_nvrtc.txt
@@ -10,10 +10,10 @@ Initializing data...
 Data init done.

 Executing Black-Scholes GPU kernel (512 iterations)...
-Options count             : 8000000     
+Options count             : 8000000
 BlackScholesGPU() time    : 0.047896 msec
 Effective memory bandwidth: 1670.268678 GB/s
-Gigaoptions per second    : 167.026868     
+Gigaoptions per second    : 167.026868

 BlackScholes, Throughput = 167.0269 GOptions/s, Time = 0.00005 s, Size = 8000000 options, NumDevsUsed = 1, Workgroup = 128

--- a/bin/x86_64/linux/release/APM_UnifiedMemoryPerf.txt
+++ b/bin/x86_64/linux/release/APM_UnifiedMemoryPerf.txt
@@ -2,7 +2,7 @@ GPU Device 0: "Hopper" with compute capability 9.0

 Running ........................................................

-Overall Time For matrixMultiplyPerf 
+Overall Time For matrixMultiplyPerf

 Printing Average of 20 measurements in (ms)
 Size_KB	 UMhint	UMhntAs	 UMeasy	  0Copy	MemCopy	CpAsync	CpHpglk	CpPglAs
--- a/bin/x86_64/linux/release/APM_batchCUBLAS.txt
+++ b/bin/x86_64/linux/release/APM_batchCUBLAS.txt
@@ -3,7 +3,7 @@ batchCUBLAS Starting...
 GPU Device 0: "Hopper" with compute capability 9.0


- ==== Running single kernels ==== 
+ ==== Running single kernels ====

 Testing sgemm
 #### args: ta=0 tb=0 m=128 n=128 k=128  alpha = (0xbf800000, -1) beta= (0x40000000, 2)
@@ -16,7 +16,7 @@ Testing dgemm
 ^^^^ elapsed = 0.00003910 sec  GFLOPS=107.269
@@@@ dgemm test OK

- ==== Running N=10 without streams ==== 
+ ==== Running N=10 without streams ====

 Testing sgemm
 #### args: ta=0 tb=0 m=128 n=128 k=128  alpha = (0xbf800000, -1) beta= (0x00000000, 0)
@@ -29,7 +29,7 @@ Testing dgemm
 ^^^^ elapsed = 0.00144100 sec  GFLOPS=29.1069
@@@@ dgemm test OK

- ==== Running N=10 with streams ==== 
+ ==== Running N=10 with streams ====

 Testing sgemm
 #### args: ta=0 tb=0 m=128 n=128 k=128  alpha = (0x40000000, 2) beta= (0x40000000, 2)
@@ -42,7 +42,7 @@ Testing dgemm
 ^^^^ elapsed = 0.00014997 sec  GFLOPS=279.685
@@@@ dgemm test OK

- ==== Running N=10 batched ==== 
+ ==== Running N=10 batched ====

 Testing sgemm
 #### args: ta=0 tb=0 m=128 n=128 k=128  alpha = (0x3f800000, 1) beta= (0xbf800000, -1)
--- a/bin/x86_64/linux/release/APM_binaryPartitionCG.txt
+++ b/bin/x86_64/linux/release/APM_binaryPartitionCG.txt
@@ -6,4 +6,3 @@ Launching 228 blocks with 1024 threads...
 Array size = 102400 Num of Odds = 50945 Sum of Odds = 1272565 Sum of Evens 1233938

 ...Done.
-
--- a/bin/x86_64/linux/release/APM_binomialOptions.txt
+++ b/bin/x86_64/linux/release/APM_binomialOptions.txt
@@ -3,10 +3,10 @@ GPU Device 0: "Hopper" with compute capability 9.0

 Generating input data...
 Running GPU binomial tree...
-Options count            : 1024     
-Time steps               : 2048     
+Options count            : 1024
+Time steps               : 2048
 binomialOptionsGPU() time: 2.081000 msec
-Options per second       : 492071.098457     
+Options per second       : 492071.098457
 Running CPU binomial tree...
 Comparing the results...
 GPU binomial vs. Black-Scholes
--- a/bin/x86_64/linux/release/APM_binomialOptions_nvrtc.txt
+++ b/bin/x86_64/linux/release/APM_binomialOptions_nvrtc.txt
@@ -4,10 +4,10 @@ Running GPU binomial tree...
 > Using CUDA Device [0]: NVIDIA H100 PCIe
 > Using CUDA Device [0]: NVIDIA H100 PCIe
 > GPU Device has SM 9.0 compute capability
-Options count            : 1024     
-Time steps               : 2048     
+Options count            : 1024
+Time steps               : 2048
 binomialOptionsGPU() time: 3021.375000 msec
-Options per second       : 338.918539     
+Options per second       : 338.918539
 Running CPU binomial tree...
 Comparing the results...
 GPU binomial vs. Black-Scholes
--- a/bin/x86_64/linux/release/APM_conjugateGradientMultiBlockCG.txt
+++ b/bin/x86_64/linux/release/APM_conjugateGradientMultiBlockCG.txt
@@ -4,5 +4,5 @@ GPU Device 0: "Hopper" with compute capability 9.0
 > GPU device has 114 Multi-Processors, SM 9.0 compute capabilities

 GPU Final, residual = 1.600115e-06, kernel execution time = 16.014656 ms
-Test Summary:  Error amount = 0.000000 
+Test Summary:  Error amount = 0.000000
 &&&& conjugateGradientMultiBlockCG PASSED
--- a/bin/x86_64/linux/release/APM_conjugateGradientMultiDeviceCG.txt
+++ b/bin/x86_64/linux/release/APM_conjugateGradientMultiDeviceCG.txt
@@ -1,4 +1,4 @@
 Starting [conjugateGradientMultiDeviceCG]...
 GPU Device 0: "NVIDIA H100 PCIe" with compute capability 9.0
-No two or more GPUs with same architecture capable of concurrentManagedAccess found. 
+No two or more GPUs with same architecture capable of concurrentManagedAccess found.
 Waiving the sample
--- a/bin/x86_64/linux/release/APM_conjugateGradientPrecond.txt
+++ b/bin/x86_64/linux/release/APM_conjugateGradientPrecond.txt
@@ -1,19 +1,18 @@
 conjugateGradientPrecond starting...
 GPU Device 0: "Hopper" with compute capability 9.0

-GPU selected Device ID = 0 
+GPU selected Device ID = 0
 > GPU device has 114 Multi-Processors, SM 9.0 compute capabilities

 laplace dimension = 128
-Convergence of CG without preconditioning: 
-  iteration = 564, residual = 9.174634e-13 
-  Convergence Test: OK 
+Convergence of CG without preconditioning:
+  iteration = 564, residual = 9.174634e-13
+  Convergence Test: OK

-Convergence of CG using ILU(0) preconditioning: 
-  iteration = 188, residual = 9.084683e-13 
-  Convergence Test: OK 
+Convergence of CG using ILU(0) preconditioning:
+  iteration = 188, residual = 9.084683e-13
+  Convergence Test: OK

 Test Summary:
   Counted total of 0 errors
   qaerr1 = 0.000005 qaerr2 = 0.000003
-
--- a/bin/x86_64/linux/release/APM_cppOverload.txt
+++ b/bin/x86_64/linux/release/APM_cppOverload.txt
@@ -28,4 +28,3 @@ Number of Registers: 14
 PTX Version: 90
 Binary Version: 90
 simple_kernel(const int *pIn1, const int *pIn2, int *pOut, int a) PASSED
-
--- a/bin/x86_64/linux/release/APM_cuSolverDn_LinearSolver.txt
+++ b/bin/x86_64/linux/release/APM_cuSolverDn_LinearSolver.txt
@@ -6,10 +6,10 @@ sparse matrix A is 900 x 900 with 7744 nonzeros, base=1
 step 2: convert CSR(A) to dense matrix
 step 3: set right hand side vector (b) to 1
 step 4: prepare data on device
-step 5: solve A*x = b 
+step 5: solve A*x = b
 timing: cholesky =   0.000789 sec
 step 6: evaluate residual
-|b - A*x| = 1.278977E-13 
-|A| = 1.600000E+01 
-|x| = 2.357708E+01 
-|b - A*x|/(|A|*|x|) = 3.390413E-16 
+|b - A*x| = 1.278977E-13
+|A| = 1.600000E+01
+|x| = 2.357708E+01
+|b - A*x|/(|A|*|x|) = 3.390413E-16
--- a/bin/x86_64/linux/release/APM_cuSolverRf.txt
+++ b/bin/x86_64/linux/release/APM_cuSolverRf.txt
@@ -3,47 +3,47 @@ step 1.1: read matrix market format
 GPU Device 0: "Hopper" with compute capability 9.0

 Using default input file [../../../../Samples/4_CUDA_Libraries/cuSolverRf/lap2D_5pt_n100.mtx]
-WARNING: cusolverRf only works for base-0 
+WARNING: cusolverRf only works for base-0
 sparse matrix A is 10000 x 10000 with 49600 nonzeros, base=0
 step 1.2: set right hand side vector (b) to 1
 step 2: reorder the matrix to reduce zero fill-in
-        Q = symrcm(A) or Q = symamd(A) 
+        Q = symrcm(A) or Q = symamd(A)
 step 3: B = Q*A*Q^T
 step 4: solve A*x = b by LU(B) in cusolverSp
 step 4.1: create opaque info structure
 step 4.2: analyze LU(B) to know structure of Q and R, and upper bound for nnz(L+U)
 step 4.3: workspace for LU(B)
-step 4.4: compute Ppivot*B = L*U 
-step 4.5: check if the matrix is singular 
-step 4.6: solve A*x = b 
-    i.e.  solve B*(Qx) = Q*b 
+step 4.4: compute Ppivot*B = L*U
+step 4.5: check if the matrix is singular
+step 4.6: solve A*x = b
+    i.e.  solve B*(Qx) = Q*b
 step 4.7: evaluate residual r = b - A*x (result on CPU)
-(CPU) |b - A*x| = 4.547474E-12 
-(CPU) |A| = 8.000000E+00 
-(CPU) |x| = 7.513384E+02 
-(CPU) |b - A*x|/(|A|*|x|) = 7.565621E-16 
-step 5: extract P, Q, L and U from P*B*Q^T = L*U 
+(CPU) |b - A*x| = 4.547474E-12
+(CPU) |A| = 8.000000E+00
+(CPU) |x| = 7.513384E+02
+(CPU) |b - A*x|/(|A|*|x|) = 7.565621E-16
+step 5: extract P, Q, L and U from P*B*Q^T = L*U
        L has implicit unit diagonal
 nnzL = 671550, nnzU = 681550
 step 6: form P*A*Q^T = L*U
 step 6.1: P = Plu*Qreroder
-step 6.2: Q = Qlu*Qreorder 
+step 6.2: Q = Qlu*Qreorder
 step 7: create cusolverRf handle
-step 8: set parameters for cusolverRf 
-step 9: assemble P*A*Q = L*U 
-step 10: analyze to extract parallelism 
-step 11: import A to cusolverRf 
-step 12: refactorization 
-step 13: solve A*x = b 
+step 8: set parameters for cusolverRf
+step 9: assemble P*A*Q = L*U
+step 10: analyze to extract parallelism
+step 11: import A to cusolverRf
+step 12: refactorization
+step 13: solve A*x = b
 step 14: evaluate residual r = b - A*x (result on GPU)
-(GPU) |b - A*x| = 4.320100E-12 
-(GPU) |A| = 8.000000E+00 
-(GPU) |x| = 7.513384E+02 
-(GPU) |b - A*x|/(|A|*|x|) = 7.187340E-16 
-===== statistics 
+(GPU) |b - A*x| = 4.320100E-12
+(GPU) |A| = 8.000000E+00
+(GPU) |x| = 7.513384E+02
+(GPU) |b - A*x|/(|A|*|x|) = 7.187340E-16
+===== statistics
 nnz(A) = 49600, nnz(L+U) = 1353100, zero fill-in ratio = 27.280242

-===== timing profile 
+===== timing profile
 reorder A   : 0.003304 sec
 B = Q*A*Q^T : 0.000761 sec

--- a/bin/x86_64/linux/release/APM_cuSolverSp_LinearSolver.txt
+++ b/bin/x86_64/linux/release/APM_cuSolverSp_LinearSolver.txt
@@ -5,27 +5,27 @@ step 1: read matrix market format
 sparse matrix A is 10000 x 10000 with 49600 nonzeros, base=1
 step 2: reorder the matrix A to minimize zero fill-in
        if the user choose a reordering by -P=symrcm, -P=symamd or -P=metis
-step 2.1: no reordering is chosen, Q = 0:n-1 
-step 2.2: B = A(Q,Q) 
-step 3: b(j) = 1 + j/n 
+step 2.1: no reordering is chosen, Q = 0:n-1
+step 2.2: B = A(Q,Q)
+step 3: b(j) = 1 + j/n
 step 4: prepare data on device
-step 5: solve A*x = b on CPU 
+step 5: solve A*x = b on CPU
 step 6: evaluate residual r = b - A*x (result on CPU)
-(CPU) |b - A*x| = 5.393685E-12 
-(CPU) |A| = 8.000000E+00 
-(CPU) |x| = 1.136492E+03 
-(CPU) |b| = 1.999900E+00 
-(CPU) |b - A*x|/(|A|*|x| + |b|) = 5.931079E-16 
+(CPU) |b - A*x| = 5.393685E-12
+(CPU) |A| = 8.000000E+00
+(CPU) |x| = 1.136492E+03
+(CPU) |b| = 1.999900E+00
+(CPU) |b - A*x|/(|A|*|x| + |b|) = 5.931079E-16
 step 7: solve A*x = b on GPU
 step 8: evaluate residual r = b - A*x (result on GPU)
-(GPU) |b - A*x| = 1.970424E-12 
-(GPU) |A| = 8.000000E+00 
-(GPU) |x| = 1.136492E+03 
-(GPU) |b| = 1.999900E+00 
-(GPU) |b - A*x|/(|A|*|x| + |b|) = 2.166745E-16 
+(GPU) |b - A*x| = 1.970424E-12
+(GPU) |A| = 8.000000E+00
+(GPU) |x| = 1.136492E+03
+(GPU) |b| = 1.999900E+00
+(GPU) |b - A*x|/(|A|*|x| + |b|) = 2.166745E-16
 timing chol: CPU =   0.097956 sec , GPU =   0.103812 sec
-show last 10 elements of solution vector (GPU) 
-consistent result for different reordering and solver 
+show last 10 elements of solution vector (GPU)
+consistent result for different reordering and solver
 x[9990] = 3.000016E+01
 x[9991] = 2.807343E+01
 x[9992] = 2.601354E+01
--- a/bin/x86_64/linux/release/APM_cuSolverSp_LowlevelCholesky.txt
+++ b/bin/x86_64/linux/release/APM_cuSolverSp_LowlevelCholesky.txt
@@ -6,19 +6,19 @@ sparse matrix A is 10000 x 10000 with 49600 nonzeros, base=1
 step 2: create opaque info structure
 step 3: analyze chol(A) to know structure of L
 step 4: workspace for chol(A)
-step 5: compute A = L*L^T 
-step 6: check if the matrix is singular 
-step 7: solve A*x = b 
+step 5: compute A = L*L^T
+step 6: check if the matrix is singular
+step 7: solve A*x = b
 step 8: evaluate residual r = b - A*x (result on CPU)
-(CPU) |b - A*x| = 3.637979E-12 
-(CPU) |A| = 8.000000E+00 
-(CPU) |x| = 7.513384E+02 
-(CPU) |b - A*x|/(|A|*|x|) = 6.052497E-16 
+(CPU) |b - A*x| = 3.637979E-12
+(CPU) |A| = 8.000000E+00
+(CPU) |x| = 7.513384E+02
+(CPU) |b - A*x|/(|A|*|x|) = 6.052497E-16
 step 9: create opaque info structure
 step 10: analyze chol(A) to know structure of L
 step 11: workspace for chol(A)
-step 12: compute A = L*L^T 
-step 13: check if the matrix is singular 
-step 14: solve A*x = b 
-(GPU) |b - A*x| = 1.477929E-12 
-(GPU) |b - A*x|/(|A|*|x|) = 2.458827E-16 
+step 12: compute A = L*L^T
+step 13: check if the matrix is singular
+step 14: solve A*x = b
+(GPU) |b - A*x| = 1.477929E-12
+(GPU) |b - A*x|/(|A|*|x|) = 2.458827E-16
--- a/bin/x86_64/linux/release/APM_cuSolverSp_LowlevelQR.txt
+++ b/bin/x86_64/linux/release/APM_cuSolverSp_LowlevelQR.txt
@@ -6,20 +6,20 @@ sparse matrix A is 1024 x 1024 with 3008 nonzeros, base=1
 step 2: create opaque info structure
 step 3: analyze qr(A) to know structure of L
 step 4: workspace for qr(A)
-step 5: compute A = L*L^T 
-step 6: check if the matrix is singular 
-step 7: solve A*x = b 
+step 5: compute A = L*L^T
+step 6: check if the matrix is singular
+step 7: solve A*x = b
 step 8: evaluate residual r = b - A*x (result on CPU)
-(CPU) |b - A*x| = 5.329071E-15 
-(CPU) |A| = 6.000000E+00 
-(CPU) |x| = 5.000000E-01 
-(CPU) |b - A*x|/(|A|*|x|) = 1.776357E-15 
+(CPU) |b - A*x| = 5.329071E-15
+(CPU) |A| = 6.000000E+00
+(CPU) |x| = 5.000000E-01
+(CPU) |b - A*x|/(|A|*|x|) = 1.776357E-15
 step 9: create opaque info structure
 step 10: analyze qr(A) to know structure of L
 step 11: workspace for qr(A)
 GPU buffer size = 3751424 bytes
-step 12: compute A = L*L^T 
-step 13: check if the matrix is singular 
-step 14: solve A*x = b 
-(GPU) |b - A*x| = 4.218847E-15 
-(GPU) |b - A*x|/(|A|*|x|) = 1.406282E-15 
+step 12: compute A = L*L^T
+step 13: check if the matrix is singular
+step 14: solve A*x = b
+(GPU) |b - A*x| = 4.218847E-15
+(GPU) |b - A*x|/(|A|*|x|) = 1.406282E-15
--- a/bin/x86_64/linux/release/APM_cudaTensorCoreGemm.txt
+++ b/bin/x86_64/linux/release/APM_cudaTensorCoreGemm.txt
@@ -6,6 +6,6 @@ N: 4096 (16 x 256)
 K: 4096 (16 x 256)
 Preparing data for GPU...
 Required shared memory size: 64 Kb
-Computing... using high performance kernel compute_gemm 
+Computing... using high performance kernel compute_gemm
 Time: 1.223904 ms
 TFLOPS: 112.30
--- a/bin/x86_64/linux/release/APM_dct8x8.txt
+++ b/bin/x86_64/linux/release/APM_dct8x8.txt
@@ -16,9 +16,9 @@ Dumping result to teapot512_gold2.bmp... Success
 Dumping result to teapot512_cuda1.bmp... Success
 Dumping result to teapot512_cuda2.bmp... Success
 Dumping result to teapot512_cuda_short.bmp... Success
-Processing time (CUDA 1)    : 0.021800 ms 
-Processing time (CUDA 2)    : 0.003180 ms 
-Processing time (CUDA short): 0.033000 ms 
+Processing time (CUDA 1)    : 0.021800 ms
+Processing time (CUDA 2)    : 0.003180 ms
+Processing time (CUDA short): 0.033000 ms
 PSNR Original    <---> CPU(Gold 1)    : 32.527462
 PSNR Original    <---> CPU(Gold 2)    : 32.527309
 PSNR Original    <---> GPU(CUDA 1)    : 32.527184
--- a/bin/x86_64/linux/release/APM_deviceQueryDrv.txt
+++ b/bin/x86_64/linux/release/APM_deviceQueryDrv.txt
@@ -1,6 +1,6 @@
 ./deviceQueryDrv Starting...

-CUDA Device Query (Driver API) statically linked version 
+CUDA Device Query (Driver API) statically linked version
 Detected 1 CUDA Capable device(s)

 Device 0: "NVIDIA H100 PCIe"
--- a/bin/x86_64/linux/release/APM_fp16ScalarProduct.txt
+++ b/bin/x86_64/linux/release/APM_fp16ScalarProduct.txt
@@ -1,5 +1,5 @@
 GPU Device 0: "Hopper" with compute capability 9.0

-Result native operators	: 644622.000000 
-Result intrinsics	: 644622.000000 
+Result native operators	: 644622.000000
+Result intrinsics	: 644622.000000
 &&&& fp16ScalarProduct PASSED
--- a/bin/x86_64/linux/release/APM_immaTensorCoreGemm.txt
+++ b/bin/x86_64/linux/release/APM_immaTensorCoreGemm.txt
@@ -6,6 +6,6 @@ N: 4096 (16 x 256)
 K: 4096 (16 x 256)
 Preparing data for GPU...
 Required shared memory size: 64 Kb
-Computing... using high performance kernel compute_gemm_imma 
+Computing... using high performance kernel compute_gemm_imma
 Time: 0.629184 ms
 TOPS: 218.44
--- a/bin/x86_64/linux/release/APM_interval.txt
+++ b/bin/x86_64/linux/release/APM_interval.txt
@@ -13,4 +13,3 @@ Number of equations solved: 65536
 Time per equation: 0.616870105266571 us

 Check against Host computation...
-
--- a/bin/x86_64/linux/release/APM_p2pBandwidthLatencyTest.txt
+++ b/bin/x86_64/linux/release/APM_p2pBandwidthLatencyTest.txt
@@ -8,28 +8,28 @@ P2P Connectivity Matrix
     D\D     0
     0	     1
 Unidirectional P2P=Disabled Bandwidth Matrix (GB/s)
-   D\D     0 
-     0 1628.72 
+   D\D     0
+     0 1628.72
 Unidirectional P2P=Enabled Bandwidth (P2P Writes) Matrix (GB/s)
-   D\D     0 
-     0 1625.75 
+   D\D     0
+     0 1625.75
 Bidirectional P2P=Disabled Bandwidth Matrix (GB/s)
-   D\D     0 
-     0 1668.11 
+   D\D     0
+     0 1668.11
 Bidirectional P2P=Enabled Bandwidth Matrix (GB/s)
-   D\D     0 
-     0 1668.39 
+   D\D     0
+     0 1668.39
 P2P=Disabled Latency Matrix (us)
-   GPU     0 
-     0   2.67 
+   GPU     0
+     0   2.67

-   CPU     0 
-     0   2.04 
+   CPU     0
+     0   2.04
 P2P=Enabled Latency (P2P Writes) Matrix (us)
-   GPU     0 
-     0   2.68 
+   GPU     0
+     0   2.68

-   CPU     0 
-     0   2.02 
+   CPU     0
+     0   2.02

 NOTE: The CUDA Samples are not meant for performance measurements. Results may vary when GPU Boost is enabled.
--- a/bin/x86_64/linux/release/APM_segmentationTreeThrust.txt
+++ b/bin/x86_64/linux/release/APM_segmentationTreeThrust.txt
@@ -4,4 +4,3 @@ GPU Device 0: "Hopper" with compute capability 9.0

 * Building segmentation tree... done in 24.6388 (ms)
 * Dumping levels for each tree...
-
--- a/bin/x86_64/linux/release/APM_shfl_scan.txt
+++ b/bin/x86_64/linux/release/APM_shfl_scan.txt
@@ -20,5 +20,5 @@ CPU sum (naive) took 0.017810 ms
 Computing Integral Image Test on size 1920 x 1080 synthetic data
 ---------------------------------------------------
 Method: Fast  Time (GPU Timer): 0.008032 ms Diff = 0
-Method: Vertical Scan  Time (GPU Timer): 0.068576 ms 
+Method: Vertical Scan  Time (GPU Timer): 0.068576 ms
 CheckSum: 2073600, (expect 1920x1080=2073600)
--- a/bin/x86_64/linux/release/APM_simpleCUBLASXT.txt
+++ b/bin/x86_64/linux/release/APM_simpleCUBLASXT.txt
@@ -1,4 +1,4 @@
 Using 1 GPUs
-GPU ID = 0, Name = NVIDIA H100 PCIe 
+GPU ID = 0, Name = NVIDIA H100 PCIe
 simpleCUBLASXT test running..
 simpleCUBLASXT test passed.
--- a/bin/x86_64/linux/release/APM_simpleCooperativeGroups.txt
+++ b/bin/x86_64/linux/release/APM_simpleCooperativeGroups.txt
@@ -11,4 +11,3 @@ Launching a single block with 64 threads...
   Sum of all ranks 0..15 in this tiledPartition16 group is 120 (expected 120)

 ...Done.
-
--- a/bin/x86_64/linux/release/APM_simpleCudaGraphs.txt
+++ b/bin/x86_64/linux/release/APM_simpleCudaGraphs.txt
@@ -8,7 +8,7 @@ Num of nodes in the graph created manually = 7
 [cudaGraphsManual] Host callback final reduced sum = 0.996214
 [cudaGraphsManual] Host callback final reduced sum = 0.996214
 [cudaGraphsManual] Host callback final reduced sum = 0.996214
-Cloned Graph Output.. 
+Cloned Graph Output..
 [cudaGraphsManual] Host callback final reduced sum = 0.996214
 [cudaGraphsManual] Host callback final reduced sum = 0.996214
 [cudaGraphsManual] Host callback final reduced sum = 0.996214
@@ -17,7 +17,7 @@ Num of nodes in the graph created using stream capture API = 7
 [cudaGraphsUsingStreamCapture] Host callback final reduced sum = 0.996214
 [cudaGraphsUsingStreamCapture] Host callback final reduced sum = 0.996214
 [cudaGraphsUsingStreamCapture] Host callback final reduced sum = 0.996214
-Cloned Graph Output.. 
+Cloned Graph Output..
 [cudaGraphsUsingStreamCapture] Host callback final reduced sum = 0.996214
 [cudaGraphsUsingStreamCapture] Host callback final reduced sum = 0.996214
 [cudaGraphsUsingStreamCapture] Host callback final reduced sum = 0.996214
--- a/bin/x86_64/linux/release/APM_simpleMultiCopy.txt
+++ b/bin/x86_64/linux/release/APM_simpleMultiCopy.txt
@@ -18,7 +18,7 @@ Measured timings (throughput):
 Kernel			: 0.033408 ms (5021.915549 GB/s)

 Theoretical limits for speedup gained from overlapped data transfers:
-No overlap at all (transfer-kernel-transfer): 1.338048 ms 
+No overlap at all (transfer-kernel-transfer): 1.338048 ms
 Compute can overlap with one transfer: 1.304640 ms
 Compute can overlap with both data transfers: 0.694048 ms

--- a/bin/x86_64/linux/release/APM_simpleMultiGPU.txt
+++ b/bin/x86_64/linux/release/APM_simpleMultiGPU.txt
@@ -10,5 +10,4 @@ Computing with Host CPU...
 Comparing GPU and Host CPU results...
  GPU sum: 16777296.000000
  CPU sum: 16777294.395033
-  Relative difference: 9.566307E-08 
-
+  Relative difference: 9.566307E-08
--- a/bin/x86_64/linux/release/APM_simpleOccupancy.txt
+++ b/bin/x86_64/linux/release/APM_simpleOccupancy.txt
@@ -11,4 +11,3 @@ Potential occupancy: 100%
 Elapsed time: 0.012384ms

 Test PASSED
-
--- a/bin/x86_64/linux/release/APM_systemWideAtomics.txt
+++ b/bin/x86_64/linux/release/APM_systemWideAtomics.txt
@@ -1,4 +1,4 @@
 GPU Device 0: "Hopper" with compute capability 9.0

 CANNOT access pageable memory
-systemWideAtomics completed, returned OK 
+systemWideAtomics completed, returned OK
--- a/bin/x86_64/linux/release/APM_threadMigration.txt
+++ b/bin/x86_64/linux/release/APM_threadMigration.txt
@@ -15,4 +15,3 @@ Device 0: "NVIDIA H100 PCIe" (Compute 9.0)
 <CUDA Device=0, Context=0x564dc26bc230, Thread=1> - ThreadProc() Finished!

 <CUDA Device=0, Context=0x564dc26bc230, Thread=0> - ThreadProc() Finished!
-
--- a/bin/x86_64/linux/release/APM_warpAggregatedAtomicsCG.txt
+++ b/bin/x86_64/linux/release/APM_warpAggregatedAtomicsCG.txt
@@ -2,4 +2,4 @@ GPU Device 0: "Hopper" with compute capability 9.0

 CPU max matches GPU max

-Warp Aggregated Atomics PASSED 
+Warp Aggregated Atomics PASSED