Merge pull request #155 from arghdos/bf16_flops

fix max BF16 flop rate on CDNA2

[ROCm/rocprofiler-compute commit: c809346b1b]

projects/rocprofiler-compute/src/omniperf_analyze/configs/gfx90a/0200_system-speed-of-light.yaml

@@ -45,9 +45,9 @@ Panel Config:
           MFMA FLOPs (BF16):
             value: AVG(((SQ_INSTS_VALU_MFMA_MOPS_BF16 * 512) / (EndNs - BeginNs)))
             unit: GFLOP
-            peak: ((($sclk * $numCU) * 512) / 1000)
+            peak: ((($sclk * $numCU) * 1024) / 1000)
             pop: ((100 * AVG(((SQ_INSTS_VALU_MFMA_MOPS_BF16 * 512) / (EndNs - BeginNs))))
-              / ((($sclk * $numCU) * 512) / 1000))
+              / ((($sclk * $numCU) * 1024) / 1000))
             tips: 
           MFMA FLOPs (F16):
             value: AVG(((SQ_INSTS_VALU_MFMA_MOPS_F16 * 512) / (EndNs - BeginNs)))