summary refs log tree commit diff stats
path: root/results/classifier/105/device/852
diff options
context:
space:
mode:
Diffstat (limited to 'results/classifier/105/device/852')
-rw-r--r--results/classifier/105/device/85244
1 files changed, 44 insertions, 0 deletions
diff --git a/results/classifier/105/device/852 b/results/classifier/105/device/852
new file mode 100644
index 000000000..7bb67a6da
--- /dev/null
+++ b/results/classifier/105/device/852
@@ -0,0 +1,44 @@
+device: 0.591
+instruction: 0.463
+semantic: 0.431
+vnc: 0.370
+socket: 0.318
+graphic: 0.307
+network: 0.259
+assembly: 0.216
+mistranslation: 0.102
+other: 0.088
+boot: 0.083
+KVM: 0.042
+
+ppc64le: possible SIMD issue casting double to int
+Description of problem:
+Working with numpy in a ppc64le VM, I ran into a strange double -to casting issue, specifically when casting an array of 1.0 values to 1 values. The numpy folks guided me to a small reproducible test case.
+
+The attached [convert.c](/uploads/2dd7936f4defccf816ffee7c7c002e77/convert.c) creates double and int arrays of length `1 <= n <= 16`. The double array is filled with the value 1.0, and both arrays are passed to a function that converts the value.
+
+With `-O2`, output is as expected (truncated here): 
+
+```
+i =  1:   1
+i =  2:   1 1
+i =  3:   1 1 1
+i =  4:   1 1 1 1
+i =  5:   1 1 1 1 1
+i =  6:   1 1 1 1 1 1
+```
+
+With `-O3`, all values that fit into blocks of four become zero:
+```
+i =  1:   1
+i =  2:   1 1
+i =  3:   1 1 1
+i =  4:   0 0 0 0
+i =  5:   0 0 0 0 1
+i =  6:   0 0 0 0 1 1
+```
+
+I tested this with executables compiled on a physical ppc64le host, where the issue is not reproducible.
+Steps to reproduce:
+1. `gcc -O2 -o convert convert.c && ./convert`
+2. `gcc -O3 -o convert convert.c && ./convert`