Please pull JSON Metrics for Intel CPUs

similarity index 100%
copy from tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json
copy to tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json

similarity index 86%
copy from tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
copy to tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json
index 49c5f12..057a832 100644
@@ -13,7 +13,7 @@
     },
     {
         "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
-        "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
         "MetricGroup": "Frontend",
         "MetricName": "IFetch_Line_Utilization"
     },

@@ -61,7 +61,7 @@
     },
     {
         "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
-	"MetricExpr": "2* ( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL  - ( 14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7* ITLB_MISSES.WALK_COMPLETED ) ) / RS_EVENTS.EMPTY_END",
+        "MetricExpr": "2* ( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFETCH_STALL ) / RS_EVENTS.EMPTY_END",
         "MetricGroup": "Unknown_Branches",
         "MetricName": "BAClear_Cost"
     },

@@ -85,7 +85,7 @@
     },
     {
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-	"MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED)) / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles",
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles",
         "MetricGroup": "TLB",
         "MetricName": "Page_Walks_Utilization"
     },

@@ -97,7 +97,7 @@
     },
     {
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / 1000000000 / duration_time",
+        "MetricExpr": "( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE ) / 1000000000 / duration_time",
         "MetricGroup": "FLOPS;Summary",
         "MetricName": "GFLOPs"
     },

similarity index 88%
copy from tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json
copy to tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json
index 057a832..03d8949 100644
@@ -13,7 +13,7 @@
     },
     {
         "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
-        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
+        "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
         "MetricGroup": "Frontend",
         "MetricName": "IFetch_Line_Utilization"
     },

@@ -55,13 +55,13 @@
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / ( cpu@uops_executed.core\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
+	"MetricExpr": "( UOPS_EXECUTED.CORE / 2 / ( cpu@uops_executed.core\\,cmask\\=1@ / 2)) if #SMT_on else (UOPS_EXECUTED.CORE / cpu@uops_executed.core\\,cmask\\=1@)",
         "MetricGroup": "Pipeline;Ports_Utilization",
         "MetricName": "ILP"
     },
     {
         "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
-        "MetricExpr": "2* ( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFETCH_STALL ) / RS_EVENTS.EMPTY_END",
+        "MetricExpr": "2* ( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL  - ( 14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION ) ) / RS_EVENTS.EMPTY_END",
         "MetricGroup": "Unknown_Branches",
         "MetricName": "BAClear_Cost"
     },

@@ -96,12 +96,6 @@
         "MetricName": "CPU_Utilization"
     },
     {
-        "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE ) / 1000000000 / duration_time",
-        "MetricGroup": "FLOPS;Summary",
-        "MetricName": "GFLOPs"
-    },
-    {
         "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Power",

similarity index 100%
copy from tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json
copy to tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json

similarity index 98%
copy from tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json
copy to tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json
index 03d8949..0bae5ed 100644
@@ -55,7 +55,7 @@
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-	"MetricExpr": "( UOPS_EXECUTED.CORE / 2 / ( cpu@uops_executed.core\\,cmask\\=1@ / 2)) if #SMT_on else (UOPS_EXECUTED.CORE / cpu@uops_executed.core\\,cmask\\=1@)",
+	"MetricExpr": "( UOPS_EXECUTED.CORE / 2 / ( cpu@uops_executed.core\\,cmask\\=1@ / 2)) if #SMT_on else UOPS_EXECUTED.CORE / cpu@uops_executed.core\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ports_Utilization",
         "MetricName": "ILP"
     },

similarity index 95%
copy from tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
copy to tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
index 49c5f12..4248b02 100644
@@ -85,7 +85,7 @@
     },
     {
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-	"MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED)) / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles",
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED) ) / (2*( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "TLB",
         "MetricName": "Page_Walks_Utilization"
     },

similarity index 100%
copy from tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
copy to tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json

similarity index 74%
copy from tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
copy to tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
index 411f941..68f12a2 100644
@@ -18,7 +18,7 @@
         "MetricName": "IFetch_Line_Utilization"
     },
     {
-        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
         "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
         "MetricGroup": "DSB; Frontend_Bandwidth",
         "MetricName": "DSB_Coverage"

@@ -36,8 +36,8 @@
         "MetricName": "CLKS"
     },
     {
-        "BriefDescription": "Total issue-pipeline slots",
-        "MetricExpr": "4*( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles",
+        "BriefDescription": "Total issue-pipeline slots (per-core)",
+        "MetricExpr": "4*cycles if not #SMT_on else (( CPU_CLK_UNHALTED.THREAD / 2) * (CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK )) if #EBS_Mode else ( CPU_CLK_UNHALTED.THREAD_ANY / 2 )",
         "MetricGroup": "TopDownL1",
         "MetricName": "SLOTS"
     },

@@ -49,7 +49,7 @@
     },
     {
         "BriefDescription": "Instructions Per Cycle (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles",
+        "MetricExpr": "INST_RETIRED.ANY / cycles if not #SMT_on else (( CPU_CLK_UNHALTED.THREAD / 2) * (CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK )) if #EBS_Mode else ( CPU_CLK_UNHALTED.THREAD_ANY / 2 )",
         "MetricGroup": "SMT",
         "MetricName": "CoreIPC"
     },

@@ -61,19 +61,19 @@
     },
     {
         "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
-        "MetricExpr": "2* ( RS_EVENTS.EMPTY_CYCLES - ICACHE_16B.IFDATA_STALL  - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END",
+        "MetricExpr": "( RS_EVENTS.EMPTY_CYCLES - (ICACHE_16B.IFDATA_STALL +2* ICACHE_16B.IFDATA_STALL:c1:e1) - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END",
         "MetricGroup": "Unknown_Branches",
         "MetricName": "BAClear_Cost"
     },
     {
         "BriefDescription": "Core actual clocks when any thread is active on the physical core",
-        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD if not #SMT_on else (( CPU_CLK_UNHALTED.THREAD / 2) * (CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK )) if 1 else ( CPU_CLK_UNHALTED.THREAD_ANY / 2 )",
         "MetricGroup": "SMT",
         "MetricName": "CORE_CLKS"
     },
     {
         "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
-	"MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS_PS + MEM_LOAD_RETIRED.FB_HIT_PS )",
         "MetricGroup": "Memory_Bound;Memory_Lat",
         "MetricName": "Load_Miss_Real_Latency"
     },

@@ -85,11 +85,29 @@
     },
     {
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles )",
+        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles if not #SMT_on else (( CPU_CLK_UNHALTED.THREAD / 2) * (CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK )) if #EBS_Mode else ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) )",
         "MetricGroup": "TLB",
         "MetricName": "Page_Walks_Utilization"
     },
     {
+        "BriefDescription": "L1 cache miss per kilo instruction for demand loads",
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS_PS / INST_RETIRED.ANY",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L1MPKI"
+    },
+    {
+        "BriefDescription": "L2 cache miss per kilo instruction for demand loads",
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS_PS / INST_RETIRED.ANY",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI"
+    },
+    {
+        "BriefDescription": "L3 cache miss per kilo instruction for demand loads",
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS_PS / INST_RETIRED.ANY",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L3MPKI"
+    },
+    {
         "BriefDescription": "Average CPU Utilization",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
         "MetricGroup": "Summary",

@@ -97,7 +115,7 @@
     },
     {
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / 1000000000 / duration_time",
+        "MetricExpr": "( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16* FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1000000000 / duration_time",
         "MetricGroup": "FLOPS;Summary",
         "MetricName": "GFLOPs"
     },