Fix progress bar and test larger file

4 files changed, 11 insertions, 5 deletions

diff --git a/premake5.lua b/premake5.lua
index 1f70694..0a20977 100644
--- a/premake5.lua
+++ b/premake5.lua
@@ -61,7 +61,7 @@ project "gemma"
    files { "src/*.h src/*.c src/**.hpp", "src/**.cpp" }
    removefiles { "src/gemma_api.cpp" }
    includedirs { "src/" }
-   links { "openblas" }
+   links { }
 
    filter "configurations:Debug"
       defines { "DEBUG" }
diff --git a/src/gemma_io.cpp b/src/gemma_io.cpp
index 3bec483..3826cea 100644
--- a/src/gemma_io.cpp
+++ b/src/gemma_io.cpp
@@ -61,7 +61,7 @@ void ProgressBar(string str, double p, double total, double ratio) {
   const double progress = (100.0 * p / total);
   const uint barsize = (int)(progress / 2.0); // characters
   // cout << barsize << endl;
-  // cout << str << " ";
+  cout << str << " ";
   // cout << p << "/" << total << endl;
   assert(barsize < 101); // corrupted data somehow
   if (barsize > 0) {
@@ -1348,7 +1348,7 @@ void ReadFile_kin(const string &file_kin, vector<int> &indicator_idv,
 
   infile.close();
   infile.clear();
-  checkpoint("read-kinship-file",file_kin);
+  checkpoint("end-read-file-kin",file_kin);
 
   return;
 }
diff --git a/src/lmm.cpp b/src/lmm.cpp
index fb3a255..1ef3990 100644
--- a/src/lmm.cpp
+++ b/src/lmm.cpp
@@ -1723,6 +1723,7 @@ void LMM::Analyze(std::function< SnpNameValues(size_t) >& fetch_snp,
 
     gsl_matrix_set_zero(Xlarge);
     for (size_t i = 0; i < l; i++) {
+      ProgressBar("GWA compute   ", i, l - 1);
       // for each snp batch item extract transformed genotype:
       gsl_vector_view UtXlarge_col = gsl_matrix_column(UtXlarge, i);
       gsl_vector_safe_memcpy(Utx, &UtXlarge_col.vector);
@@ -1850,7 +1851,7 @@ void LMM::Analyze(std::function< SnpNameValues(size_t) >& fetch_snp,
   }
 
   batch_compute(c % msize);
-  ProgressBar("Reading SNPs", num_snps - 1, num_snps - 1);
+  ProgressBar("Computed      ", num_snps - 1, num_snps - 1);
   // cout << "Counted SNPs " << c << " sumStat " << sumStat.size() << endl;
   cout << endl;
   checkpoint_nofile("end-lmm-analyze");
diff --git a/test/performance/releases.org b/test/performance/releases.org
index 792cb2e..ff18287 100644
--- a/test/performance/releases.org
+++ b/test/performance/releases.org
@@ -9,7 +9,7 @@ We are facing a time regression.
 
 premake5 gmake2 && make verbose=1 config=release -j 8 gemma && time LD_LIBRARY_PATH=$GUIX_ENVIRONMENT/lib ./build/bin/Release/gemma -g ./example/mouse_hs1940.geno.txt.gz -p ./example/mouse_hs1940.pheno.txt -n 1 -a ./example/mouse_hs1940.anno.txt -k ./output/result.cXX.txt -lmm -no-check -debug
 
-With openblas 0.3.21 we go a bit faster. Still 10% behind though, there is room for tweaking. But I want to run some bigger files first.
+With openblas 0.3.21 we go a bit faster. Still 10% behind though, there is room for tweaking. It may actually be a new SSD. I want to run some bigger files first.
 
 #+begin_src sh
 Pangemma --- GEMMA 0.98.5 compatible executable 1.0.0 (2025-11-22) with guile 3.0.9 by Xiang Zhou, Pjotr Prins and team (C) 2012-2025
@@ -82,8 +82,13 @@ to
 
 ```
 time LD_LIBRARY_PATH=$GUIX_ENVIRONMENT/lib ./build/bin/Release/gemma -g tmp/pangenome-13M-genotypes.txt -p tmp/pheno.json.txt -n 1 -a tmp/snps-matched.txt -k tmp/93f6b39ec06c09fb9ba9ca628b5fb990921b6c60.3.cXX.txt.cXX.txt -lmm 9 -no-check
+real    20m4.687s
+user    23m42.508s
+sys     9m51.929s
 ```
 
+On my AMD Ryzen 7 3700X it uses about ~10Gb of RAM. With the -debug switch it clapped out because of sqrt(NaN). There is a lot that can be gained with better IO and multi-core use.
+
 ** GEMMA 0.98.5-pre1
 
 Measurements taken on a recent AMD Ryzen 7 3700X 8-Core Processor @2.195GHz.