We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent f0924e0 commit 0513b0cCopy full SHA for 0513b0c
test/external/speed_v_theoretical.py
@@ -91,7 +91,7 @@ def test_conv_3x3_256_32_32_256_256(self): self._test_conv_3x3(256, 32, 32, 256,
91
92
# theoretical is nv_tflops=165, amd_tflops=123
93
def test_gemm_4096(self): self._test_matmul(4096, nv_tflops=115, amd_tflops=80)
94
- def test_gemm_8192(self): self._test_matmul(8192, nv_tflops=130, amd_tflops=73)
+ def test_gemm_8192(self): self._test_matmul(8192, nv_tflops=125, amd_tflops=73)
95
96
# theoretical is nv_gbs=1008, amd_gbs=960
97
def test_gemv_16384_4096(self): self._test_matmul(16384, 4096, 1, nv_gbs=840, amd_gbs=750)
0 commit comments