19 changed files with 2063 additions and 652 deletions
--- a/.gitignore
+++ b/.gitignore
@ -1 +1 @@
-SOURCES/papi-6.0.0-noiozone.tar.gz
+SOURCES/papi-5.6.0.tar.gz
--- a/.papi.metadata
+++ b/.papi.metadata
@ -1 +1 @@
-96415af51f021dcbb71c04ac236037941cf5babc SOURCES/papi-6.0.0-noiozone.tar.gz
+377656f6b75cd821de9a9e663cfeb405a70906aa SOURCES/papi-5.6.0.tar.gz
--- a/SOURCES/papi-a64fx.patch
+++ b/SOURCES/papi-a64fx.patch
@ -1,34 +0,0 @@
-commit 9a44d82928ed17ba2ff21eb88b89c5829d0ea30e
-Author: Steve Kaufmann <steven.kaufmann@hpe.com>
-Date:   Wed Jun 24 14:08:08 2020 -0400
-
-    Added PAPI preset support for Fujitsu A64FX.
-    
-    Signed-off-by: Heike Jagode <jagode@icl.utk.edu>
-
-diff --git a/src/papi_events.csv b/src/papi_events.csv
-index 8e96adfbd..1b5c15542 100644
--- a/src/papi_events.csv
-+++ b/src/papi_events.csv
-@@ -1877,6 +1877,21 @@ PRESET,PAPI_L2_DCR,NOT_DERIVED,L2D_CACHE_RD
- PRESET,PAPI_L2_DCW,NOT_DERIVED,L2D_CACHE_WR
- PRESET,PAPI_L2_LDM,NOT_DERIVED,L2D_CACHE_REFILL_RD
- 
-+#########################
-+# ARM Fujitsu A64FX     #
-+#########################
-+CPU,arm_a64fx
-+#
-+PRESET,PAPI_TOT_INS,NOT_DERIVED,INST_RETIRED
-+PRESET,PAPI_TOT_CYC,NOT_DERIVED,CPU_CYCLES
-+PRESET,PAPI_FP_INS,NOT_DERIVED,VFP_SPEC
-+PRESET,PAPI_VEC_INS,NOT_DERIVED,ASE_SPEC
-+PRESET,PAPI_L1_DCM,NOT_DERIVED,L1D_CACHE_REFILL
-+PRESET,PAPI_L1_ICA,NOT_DERIVED,L1I_CACHE
-+PRESET,PAPI_L1_ICM,NOT_DERIVED,L1I_CACHE_REFILL
-+PRESET,PAPI_L2_DCH,NOT_DERIVED,L2D_CACHE
-+PRESET,PAPI_L2_DCM,NOT_DERIVED,L2D_CACHE_REFILL
-+
- #
- CPU,mips_74k
- #
--- a/SOURCES/papi-bz1908126.patch
+++ b/SOURCES/papi-bz1908126.patch
@ -0,0 +1,382 @@
+commit 77ee6b54f4080ca27b7efcb4c91679d0f1e090b5
+Author: Anthony Castaldo <TonyCastaldo@icl.utk.edu>
+Date:   Fri Jan 24 10:25:36 2020 -0500
+
+    New libpfm4 contains "aliased" pmus for backward compatibility,
+    amd64_fam17h == amd64_fam17h_zen1; this causes us to put BOTH pmus
+    into the PMUs supported string and double the events in native_avail.
+    This update recognizes when aliases exist (the names must be hard-coded)
+    and uses only one of the most recent name.
+
+diff --git a/src/components/perf_event/pe_libpfm4_events.c b/src/components/perf_event/pe_libpfm4_events.c
+index 3b5f8d13f..3262608cd 100644
+--- a/src/components/perf_event/pe_libpfm4_events.c
+++ b/src/components/perf_event/pe_libpfm4_events.c
+@@ -31,6 +31,9 @@
+ // used to step through the attributes when enumerating events
+ static int attr_idx;
+ 
+/* alias flags to handle amd_fam17h, amd_fam17h_zen1 both present PMUs*/
+static int amd64_fam17h_zen1_present = 0;
+
+ /** @class  find_existing_event
+  *  @brief  looks up an event, returns it if it exists
+  *
+@@ -482,7 +485,13 @@ static struct native_event_t *allocate_native_event(
+  *
+  *  @returns returns a libpfm event number
+  *  @retval PAPI_ENOEVENT  Could not find an event
+- *
+ *  Operational note: _pe_libpfm4_init() must be called first to set
+ *                    flags for synonymous PMUs. At this writing only 
+ *                    amd64_fam17h_zen1_present is defined.
+ *  Operational note: We indirectly return the pmu_idx within the
+ *                    event data; the calling code uses that to set
+ *                    pmu_idx for subsequent calls. All we do is find
+ *                    the next valid pmu, if any.
+  */
+ 
+ static int
+@@ -511,6 +520,12 @@ get_first_event_next_pmu(int pmu_idx, int pmu_type)
+ 		break;
+ 	}
+ 
+    if ((ret==PFM_SUCCESS) && amd64_fam17h_zen1_present && strcmp(pinfo.name, "amd64_fam17h") == 0) {
+        /* Skip as if invalid; we want the PMU amd64_fam17h_zen1 instead. */
+        pmu_idx++;
+        continue;
+    }
+        
+     if ((ret==PFM_SUCCESS) && pmu_is_present_and_right_type(&pinfo,pmu_type)) {
+ 
+       pidx=pinfo.first_event;
+@@ -1159,6 +1174,35 @@ _pe_libpfm4_init(papi_vector_t *component, int cidx,
+ 	event_table->default_pmu.size = sizeof(pfm_pmu_info_t);
+ 	retval=pfm_get_pmu_info(0, &(event_table->default_pmu));
+ 
+    SUBDBG("Prescan for aliases.")
+    /* We have to see if we have aliases in there as separate PMUs, */
+    /* we don't want both PMUs with all the events duplicated.      */
+    /* For aliases, either is valid alone, but if both are present  */
+    /* specify a preference in the code.                            */
+    /* Alias: amd64_fam17h_zen1 over amd64_fam17h.                  */
+    /* Alias flags are static ints global to this file.             */
+    i=0;
+	while(1) {
+		memset(&pinfo,0,sizeof(pfm_pmu_info_t));
+		pinfo.size = sizeof(pfm_pmu_info_t);
+		retval=pfm_get_pmu_info(i, &pinfo);
+
+		/* We're done if we hit an invalid PMU entry		    */
+		/* We can't check against PFM_PMU_MAX as that might not	*/
+		/* match if libpfm4 is dynamically linked		        */
+
+		if (retval==PFM_ERR_INVAL) {
+			break;
+		}
+
+		if ( (retval==PFM_SUCCESS) && (pinfo.name != NULL) &&
+			(pmu_is_present_and_right_type(&pinfo,pmu_type)) &&
+            (strcmp(pinfo.name,"amd64_fam17h_zen1") == 0) ) {
+            amd64_fam17h_zen1_present = 1;
+        }
+        i++;
+    } 
+
+ 	SUBDBG("Detected pmus:\n");
+ 	i=0;
+ 	while(1) {
+@@ -1177,6 +1221,12 @@ _pe_libpfm4_init(papi_vector_t *component, int cidx,
+ 		if ((retval==PFM_SUCCESS) && (pinfo.name != NULL) &&
+ 			(pmu_is_present_and_right_type(&pinfo,pmu_type))) {
+ 
+            /* skip if it is amd64_fam17h and zen1 is also present. */
+            if (strcmp(pinfo.name,"amd64_fam17h") == 0 && amd64_fam17h_zen1_present) {
+                i++;
+                continue;
+            }
+
+ 			SUBDBG("\t%d %s %s %d\n",i,
+ 				pinfo.name,pinfo.desc,pinfo.type);
+ 
+@@ -1193,11 +1243,9 @@ _pe_libpfm4_init(papi_vector_t *component, int cidx,
+ 				/* Hack to have "default core" PMU */
+ 				if ( (pinfo.type==PFM_PMU_TYPE_CORE) &&
+ 					strcmp(pinfo.name,"ix86arch")) {
+-
+-					SUBDBG("\t  %s is default\n",pinfo.name);
+-					memcpy(&(event_table->default_pmu),
+-						&pinfo,sizeof(pfm_pmu_info_t));
+-					found_default++;
+					    memcpy(&(event_table->default_pmu),
+						    &pinfo,sizeof(pfm_pmu_info_t));
+                        found_default++;
+ 				}
+ 			}
+ 
+commit 79fe2a025afb8acb317032030c8847c9cbfd0162
+Author: Masahiko, Yamada <yamada.masahiko@fujitsu.com>
+Date:   Tue Jan 5 13:45:34 2021 +0900
+
+    Get model_string for ARM processor from pfm_get_pmu_info() function
+    
+    On ARM processors, the model_string does not appear in /proc/cpuinfo.
+    Instead of looking at the /proc/cpuinfo information, you can look at the lscpu command information at the following URL:.
+    https://github.com/google/cpu_features/issues/26
+    http://suihkulokki.blogspot.com/2018/02/making-sense-of-proccpuinfo-on-arm.html
+    
+    The libpfm4 library identifies the ARM processor type from the "CPU implement" and "CPU part" in the /proc/cpuinfo information.
+    The papi library can use the pfm_get_pmu_info() function from the libpfm4 library to obtain a string identifying the ARM processor type.
+
+diff --git a/src/components/perf_event/pe_libpfm4_events.c b/src/components/perf_event/pe_libpfm4_events.c
+index a84819cc0..744851ff0 100644
+--- a/src/components/perf_event/pe_libpfm4_events.c
+++ b/src/components/perf_event/pe_libpfm4_events.c
+@@ -1149,6 +1149,7 @@ _pe_libpfm4_init(papi_vector_t *component, int cidx,
+ 
+ 	pfm_err_t retval = PFM_SUCCESS;
+ 	pfm_pmu_info_t pinfo;
+	unsigned int strSize;
+ 
+ 	/* allocate the native event structure */
+ 	event_table->num_native_events=0;
+@@ -1247,6 +1248,13 @@ _pe_libpfm4_init(papi_vector_t *component, int cidx,
+ 						    &pinfo,sizeof(pfm_pmu_info_t));
+                         found_default++;
+ 				}
+				if ( (pinfo.type==PFM_PMU_TYPE_CORE) &&
+					( _papi_hwi_system_info.hw_info.vendor == PAPI_VENDOR_ARM)) {
+					if (strlen(_papi_hwi_system_info.hw_info.model_string) == 0) {
+						strSize = sizeof(_papi_hwi_system_info.hw_info.model_string);
+						strncpy( _papi_hwi_system_info.hw_info.model_string, pinfo.desc, strSize - 1);
+					}
+				}
+ 			}
+ 
+ 			if (pmu_type==PMU_TYPE_UNCORE) {
+commit 85003c716d76eff47607fa0967537c6cf63d8348
+Author: Steve Walk <swalk.cavium@gmail.com>
+Date:   Fri Jun 8 15:50:50 2018 -0400
+
+    enable Cavium ThunderX2 support
+
+diff --git a/src/papi_events.csv b/src/papi_events.csv
+index bb11f61d3..46827f180 100644
+--- a/src/papi_events.csv
+++ b/src/papi_events.csv
+@@ -1841,6 +1841,31 @@ PRESET,PAPI_L2_DCR,NOT_DERIVED,L2D_READ_ACCESS
+ PRESET,PAPI_L2_DCW,NOT_DERIVED,L2D_WRITE_ACCESS
+ PRESET,PAPI_L2_LDM,NOT_DERIVED,L2D_READ_REFILL
+ PRESET,PAPI_L2_STM,NOT_DERIVED,L2D_WRITE_REFILL
+
+#####################
+# ARM ThunderX2     #
+#####################
+CPU,arm_thunderx2
+#
+PRESET,PAPI_TOT_INS,NOT_DERIVED,INST_RETIRED
+PRESET,PAPI_TOT_CYC,NOT_DERIVED,CPU_CYCLES
+PRESET,PAPI_FP_INS,NOT_DERIVED,VFP_SPEC
+PRESET,PAPI_VEC_INS,NOT_DERIVED,ASE_SPEC
+PRESET,PAPI_BR_INS,NOT_DERIVED,BR_RETIRED
+PRESET,PAPI_LD_INS,NOT_DERIVED,LD_RETIRED
+PRESET,PAPI_SR_INS,NOT_DERIVED,ST_RETIRED
+PRESET,PAPI_L1_DCA,DERIVED_ADD,L1D_CACHE_RD,L1D_CACHE_WR
+PRESET,PAPI_L1_DCM,NOT_DERIVED,L1D_CACHE_REFILL
+PRESET,PAPI_L1_DCR,NOT_DERIVED,L1D_CACHE_RD
+PRESET,PAPI_L1_DCW,NOT_DERIVED,L1D_CACHE_WR
+PRESET,PAPI_L1_ICA,NOT_DERIVED,L1I_CACHE
+PRESET,PAPI_L1_ICM,NOT_DERIVED,L1I_CACHE_REFILL
+PRESET,PAPI_L2_DCH,NOT_DERIVED,L2D_CACHE
+PRESET,PAPI_L2_DCM,NOT_DERIVED,L2D_CACHE_REFILL
+PRESET,PAPI_L2_DCR,NOT_DERIVED,L2D_CACHE_RD
+PRESET,PAPI_L2_DCW,NOT_DERIVED,L2D_CACHE_WR
+PRESET,PAPI_L2_LDM,NOT_DERIVED,L2D_CACHE_REFILL_RD
+
+ #
+ CPU,mips_74k
+ #
+commit 9a44d82928ed17ba2ff21eb88b89c5829d0ea30e
+Author: Steve Kaufmann <steven.kaufmann@hpe.com>
+Date:   Wed Jun 24 14:08:08 2020 -0400
+
+    Added PAPI preset support for Fujitsu A64FX.
+    
+    Signed-off-by: Heike Jagode <jagode@icl.utk.edu>
+
+diff --git a/src/papi_events.csv b/src/papi_events.csv
+index 8e96adfbd..1b5c15542 100644
+--- a/src/papi_events.csv
+++ b/src/papi_events.csv
+@@ -1877,6 +1877,21 @@ PRESET,PAPI_L2_DCR,NOT_DERIVED,L2D_CACHE_RD
+ PRESET,PAPI_L2_DCW,NOT_DERIVED,L2D_CACHE_WR
+ PRESET,PAPI_L2_LDM,NOT_DERIVED,L2D_CACHE_REFILL_RD
+ 
+#########################
+# ARM Fujitsu A64FX     #
+#########################
+CPU,arm_a64fx
+#
+PRESET,PAPI_TOT_INS,NOT_DERIVED,INST_RETIRED
+PRESET,PAPI_TOT_CYC,NOT_DERIVED,CPU_CYCLES
+PRESET,PAPI_FP_INS,NOT_DERIVED,VFP_SPEC
+PRESET,PAPI_VEC_INS,NOT_DERIVED,ASE_SPEC
+PRESET,PAPI_L1_DCM,NOT_DERIVED,L1D_CACHE_REFILL
+PRESET,PAPI_L1_ICA,NOT_DERIVED,L1I_CACHE
+PRESET,PAPI_L1_ICM,NOT_DERIVED,L1I_CACHE_REFILL
+PRESET,PAPI_L2_DCH,NOT_DERIVED,L2D_CACHE
+PRESET,PAPI_L2_DCM,NOT_DERIVED,L2D_CACHE_REFILL
+
+ #
+ CPU,mips_74k
+ #
+commit b87ac4beda096086e0040f8ec1b44c4791a9739c
+Author: Masahiko, Yamada <yamada.masahiko@fujitsu.com>
+Date:   Mon Dec 14 14:06:22 2020 +0900
+
+    Corrected typo for A64FX support (PAPI_L2_DCH is a typo of PAPI_L2_DCA)
+
+diff --git a/src/papi_events.csv b/src/papi_events.csv
+index fd75f9371..164f05641 100644
+--- a/src/papi_events.csv
+++ b/src/papi_events.csv
+@@ -1937,7 +1937,7 @@ PRESET,PAPI_VEC_INS,NOT_DERIVED,ASE_SPEC
+ PRESET,PAPI_L1_DCM,NOT_DERIVED,L1D_CACHE_REFILL
+ PRESET,PAPI_L1_ICA,NOT_DERIVED,L1I_CACHE
+ PRESET,PAPI_L1_ICM,NOT_DERIVED,L1I_CACHE_REFILL
+-PRESET,PAPI_L2_DCH,NOT_DERIVED,L2D_CACHE
+PRESET,PAPI_L2_DCA,NOT_DERIVED,L2D_CACHE
+ PRESET,PAPI_L2_DCM,NOT_DERIVED,L2D_CACHE_REFILL
+ 
+ #
+commit 869864f813f0681b5c9a4b65de2135c8708a2afb
+Author: Masahiko, Yamada <yamada.masahiko@fujitsu.com>
+Date:   Mon Dec 14 19:34:59 2020 +0900
+
+    Add or modify various A64FX support events, including floating point events (PAPI_FP_OPS, PAPI_SP_OPS, PAPI_DP_OPS).
+
+diff --git a/src/papi_events.csv b/src/papi_events.csv
+index 164f05641..9192b1041 100644
+--- a/src/papi_events.csv
+++ b/src/papi_events.csv
+@@ -1930,15 +1930,46 @@ PRESET,PAPI_L2_LDM,NOT_DERIVED,L2D_CACHE_REFILL_RD
+ #########################
+ CPU,arm_a64fx
+ #
+PRESET,PAPI_PRF_DM,DERIVED_SUB,L2D_CACHE_REFILL_PRF,L2D_CACHE_MIBMCH_PRF
+PRESET,PAPI_MEM_SCY,NOT_DERIVED,LD_COMP_WAIT_L2_MISS
+PRESET,PAPI_STL_ICY,DERIVED_ADD,STALL_FRONTEND,STALL_BACKEND
+PRESET,PAPI_STL_CCY,NOT_DERIVED,0INST_COMMIT
+PRESET,PAPI_FUL_CCY,DERIVED_SUB,CPU_CYCLES,0INST_COMMIT,1INST_COMMIT,2INST_COMMIT,3INST_COMMIT,4INST_COMMIT
+PRESET,PAPI_HW_INT,DERIVED_ADD,EXC_IRQ,EXC_FIQ
+PRESET,PAPI_BR_MSP,NOT_DERIVED,BR_MIS_PRED
+PRESET,PAPI_BR_PRC,DERIVED_SUB,BR_PRED,BR_MIS_PRED
+PRESET,PAPI_FMA_INS,NOT_DERIVED,FP_FMA_SPEC
+ PRESET,PAPI_TOT_INS,NOT_DERIVED,INST_RETIRED
+ PRESET,PAPI_TOT_CYC,NOT_DERIVED,CPU_CYCLES
+ PRESET,PAPI_FP_INS,NOT_DERIVED,VFP_SPEC
+PRESET,PAPI_LD_INS,NOT_DERIVED,LD_SPEC
+PRESET,PAPI_SR_INS,NOT_DERIVED,ST_SPEC
+PRESET,PAPI_BR_INS,NOT_DERIVED,BR_PRED
+ PRESET,PAPI_VEC_INS,NOT_DERIVED,ASE_SPEC
+PRESET,PAPI_RES_STL,NOT_DERIVED,STALL_BACKEND
+PRESET,PAPI_LST_INS,NOT_DERIVED,LDST_SPEC
+PRESET,PAPI_SYC_INS,DERIVED_ADD,ISB_SPEC,DSB_SPEC,DMB_SPEC
+PRESET,PAPI_L1_DCA,NOT_DERIVED,L1D_CACHE
+PRESET,PAPI_L1_DCH,DERIVED_SUB,L1D_CACHE,L1D_CACHE_REFILL
+ PRESET,PAPI_L1_DCM,NOT_DERIVED,L1D_CACHE_REFILL
+ PRESET,PAPI_L1_ICA,NOT_DERIVED,L1I_CACHE
+PRESET,PAPI_L1_ICH,DERIVED_SUB,L1I_CACHE,L1I_CACHE_REFILL
+ PRESET,PAPI_L1_ICM,NOT_DERIVED,L1I_CACHE_REFILL
+PRESET,PAPI_L1_TCA,DERIVED_ADD,L1D_CACHE,L1I_CACHE
+PRESET,PAPI_L1_TCH,DERIVED_POSTFIX,N0|N1|-|N2|+|N3|-|,L1D_CACHE,L1D_CACHE_REFILL,L1I_CACHE,L1I_CACHE_REFILL
+PRESET,PAPI_L1_TCM,DERIVED_ADD,L1D_CACHE_REFILL,L1I_CACHE_REFILL
+ PRESET,PAPI_L2_DCA,NOT_DERIVED,L2D_CACHE
+-PRESET,PAPI_L2_DCM,NOT_DERIVED,L2D_CACHE_REFILL
+PRESET,PAPI_L2_DCH,DERIVED_POSTFIX,N0|N1|-|N2|+|N3|+|,L2D_CACHE,L2D_CACHE_REFILL,L2D_SWAP_DM,L2D_CACHE_MIBMCH_PRF
+PRESET,PAPI_L2_DCM,DERIVED_SUB,L2D_CACHE_REFILL,L2D_SWAP_DM,L2D_CACHE_MIBMCH_PRF
+PRESET,PAPI_L2_TCA,NOT_DERIVED,L2D_CACHE
+PRESET,PAPI_L2_TCH,DERIVED_POSTFIX,N0|N1|-|N2|+|N3|+|,L2D_CACHE,L2D_CACHE_REFILL,L2D_SWAP_DM,L2D_CACHE_MIBMCH_PRF
+PRESET,PAPI_L2_TCM,DERIVED_SUB,L2D_CACHE_REFILL,L2D_SWAP_DM,L2D_CACHE_MIBMCH_PRF
+PRESET,PAPI_TLB_DM,NOT_DERIVED,L2D_TLB_REFILL
+PRESET,PAPI_TLB_IM,NOT_DERIVED,L2I_TLB_REFILL
+PRESET,PAPI_TLB_TL,DERIVED_ADD,L2D_TLB_REFILL,L2I_TLB_REFILL
+PRESET,PAPI_FP_OPS,DERIVED_POSTFIX,N0|512|128|/|*|N1|+|,FP_SCALE_OPS_SPEC,FP_FIXED_OPS_SPEC
+PRESET,PAPI_SP_OPS,DERIVED_POSTFIX,N0|512|128|/|*|N1|+|,FP_SP_SCALE_OPS_SPEC,FP_SP_FIXED_OPS_SPEC
+PRESET,PAPI_DP_OPS,DERIVED_POSTFIX,N0|512|128|/|*|N1|+|,FP_DP_SCALE_OPS_SPEC,FP_DP_FIXED_OPS_SPEC
+ 
+ #
+ CPU,mips_74k
+commit 7a3c22763ef2ba00a2b8cb069c3501f35ecb13de
+Author: Masahiko, Yamada <yamada.masahiko@fujitsu.com>
+Date:   Tue Dec 15 13:43:43 2020 +0900
+
+    modify PAPI_FP_INS and PAPI_VEC_INS for A64FX supports
+
+diff --git a/src/papi_events.csv b/src/papi_events.csv
+index 9192b1041..7b4ceb674 100644
+--- a/src/papi_events.csv
+++ b/src/papi_events.csv
+@@ -1941,11 +1941,11 @@ PRESET,PAPI_BR_PRC,DERIVED_SUB,BR_PRED,BR_MIS_PRED
+ PRESET,PAPI_FMA_INS,NOT_DERIVED,FP_FMA_SPEC
+ PRESET,PAPI_TOT_INS,NOT_DERIVED,INST_RETIRED
+ PRESET,PAPI_TOT_CYC,NOT_DERIVED,CPU_CYCLES
+-PRESET,PAPI_FP_INS,NOT_DERIVED,VFP_SPEC
+PRESET,PAPI_FP_INS,NOT_DERIVED,FP_SPEC
+ PRESET,PAPI_LD_INS,NOT_DERIVED,LD_SPEC
+ PRESET,PAPI_SR_INS,NOT_DERIVED,ST_SPEC
+ PRESET,PAPI_BR_INS,NOT_DERIVED,BR_PRED
+-PRESET,PAPI_VEC_INS,NOT_DERIVED,ASE_SPEC
+PRESET,PAPI_VEC_INS,NOT_DERIVED,SIMD_INST_RETIRED
+ PRESET,PAPI_RES_STL,NOT_DERIVED,STALL_BACKEND
+ PRESET,PAPI_LST_INS,NOT_DERIVED,LDST_SPEC
+ PRESET,PAPI_SYC_INS,DERIVED_ADD,ISB_SPEC,DSB_SPEC,DMB_SPEC
+commit 530d4763fb8e6dd52109387bd58c8c1305fd6b63
+Author: Masahiko, Yamada <yamada.masahiko@fujitsu.com>
+Date:   Fri Feb 12 15:01:21 2021 +0900
+
+    remove PAPI_L1_DCA and PAPI_L1_DCH for a64fx
+    
+    There seems to be a problem with PAPI_L1_DCA and PAPI_L1_DCH for a64fx that prefetch overcounts.
+    I delete (comment out) PAPI_L1_DCA and PAPI_L1_DCH for a64fx from the papi_events.csv file.
+    I will issue the pullrequest again once I have identified how to handle the overcount.
+
+diff --git a/src/papi_events.csv b/src/papi_events.csv
+index 7b4ceb674..0f5ec8344 100644
+--- a/src/papi_events.csv
+++ b/src/papi_events.csv
+@@ -1949,8 +1949,8 @@ PRESET,PAPI_VEC_INS,NOT_DERIVED,SIMD_INST_RETIRED
+ PRESET,PAPI_RES_STL,NOT_DERIVED,STALL_BACKEND
+ PRESET,PAPI_LST_INS,NOT_DERIVED,LDST_SPEC
+ PRESET,PAPI_SYC_INS,DERIVED_ADD,ISB_SPEC,DSB_SPEC,DMB_SPEC
+-PRESET,PAPI_L1_DCA,NOT_DERIVED,L1D_CACHE
+-PRESET,PAPI_L1_DCH,DERIVED_SUB,L1D_CACHE,L1D_CACHE_REFILL
+#PRESET,PAPI_L1_DCA,NOT_DERIVED,L1D_CACHE
+#PRESET,PAPI_L1_DCH,DERIVED_SUB,L1D_CACHE,L1D_CACHE_REFILL
+ PRESET,PAPI_L1_DCM,NOT_DERIVED,L1D_CACHE_REFILL
+ PRESET,PAPI_L1_ICA,NOT_DERIVED,L1I_CACHE
+ PRESET,PAPI_L1_ICH,DERIVED_SUB,L1I_CACHE,L1I_CACHE_REFILL
+commit 340f68940234f2db181147fc249907b4f1293e62
+Author: Masahiko, Yamada <yamada.masahiko@fujitsu.com>
+Date:   Tue Feb 16 17:16:24 2021 +0900
+
+    remove PAPI_L1_TCA and PAPI_L1_TCH for a64fx
+    
+    PAPI_L1_TCA and PAPI_L1_TCH for a64fx measure L1D_CACHE just like PAPI_L1_DCA and PAPI_L1_DCH,
+    so I delete (comment out) PAPI_L1_TCA and PAPI_L1_TCH for a64fx from the papi_events.csv file.
+
+diff --git a/src/papi_events.csv b/src/papi_events.csv
+index 0f5ec8344..4ef647959 100644
+--- a/src/papi_events.csv
+++ b/src/papi_events.csv
+@@ -1955,8 +1955,8 @@ PRESET,PAPI_L1_DCM,NOT_DERIVED,L1D_CACHE_REFILL
+ PRESET,PAPI_L1_ICA,NOT_DERIVED,L1I_CACHE
+ PRESET,PAPI_L1_ICH,DERIVED_SUB,L1I_CACHE,L1I_CACHE_REFILL
+ PRESET,PAPI_L1_ICM,NOT_DERIVED,L1I_CACHE_REFILL
+-PRESET,PAPI_L1_TCA,DERIVED_ADD,L1D_CACHE,L1I_CACHE
+-PRESET,PAPI_L1_TCH,DERIVED_POSTFIX,N0|N1|-|N2|+|N3|-|,L1D_CACHE,L1D_CACHE_REFILL,L1I_CACHE,L1I_CACHE_REFILL
+#PRESET,PAPI_L1_TCA,DERIVED_ADD,L1D_CACHE,L1I_CACHE
+#PRESET,PAPI_L1_TCH,DERIVED_POSTFIX,N0|N1|-|N2|+|N3|-|,L1D_CACHE,L1D_CACHE_REFILL,L1I_CACHE,L1I_CACHE_REFILL
+ PRESET,PAPI_L1_TCM,DERIVED_ADD,L1D_CACHE_REFILL,L1I_CACHE_REFILL
+ PRESET,PAPI_L2_DCA,NOT_DERIVED,L2D_CACHE
+ PRESET,PAPI_L2_DCH,DERIVED_POSTFIX,N0|N1|-|N2|+|N3|+|,L2D_CACHE,L2D_CACHE_REFILL,L2D_SWAP_DM,L2D_CACHE_MIBMCH_PRF
--- a/SOURCES/papi-config.patch
+++ b/SOURCES/papi-config.patch
@ -1,348 +0,0 @@
-commit 38290c41abbb105ca198411ec3c466ac027f5b8f
-Author: Frank Winkler <frankbook@Franks-MacBook-Air.local>
-Date:   Fri Apr 24 16:18:22 2020 +0200
-
-    Fixed configure options for shared and static builds.
-    
-    1) --with-static-lib=no (force PAPI to build shared libraries and tools)
-    2) --with-shlib-tools (use internal libpfm via rpath-link)
-
-diff --git a/src/configure.in b/src/configure.in
-index 3cf47edc1..1f58f7c8e 100644
--- a/src/configure.in
-+++ b/src/configure.in
-@@ -200,9 +200,13 @@ else
- 		AC_MSG_ERROR([cannot find dlopen and dlerror symbols neither in the base system libraries nor in -ldl])
- 	fi
- fi
-+
-+# Disable LDL for static builds
-+# if test "x${STATIC}" = "x"; then
-+#   LDL=""
-+# fi
- AC_SUBST(LDL)
-        
-    
-+
- if test "$OS" = "CLE"; then
-   virtualtimer=times
-   tls=__thread
-@@ -827,10 +831,6 @@ AC_ARG_WITH(static_tools,
- 	    AC_MSG_RESULT(yes)],
- 	    [AC_MSG_RESULT(no)])
- 
-if test "$static_lib" = "no"; then
-   AC_MSG_ERROR(Building tests and utilities static but no static papi library to be built)
-fi
-
- AC_MSG_CHECKING(for linking with papi shared library of tests and utilities)
- AC_ARG_WITH(shlib_tools,
- 	        [  --with-shlib-tools		Specify linking with papi library of tests and utilities],
-@@ -839,6 +839,14 @@ AC_ARG_WITH(shlib_tools,
- 		[shlib_tools=no
- 		AC_MSG_RESULT(no)])
- 
-+if test "$static_lib" = "no"; then
-+   shlib_tools=yes
-+fi
-+
-+if test "$static_lib" = "no" -a "$shlib_tools" = "no"; then
-+   AC_MSG_ERROR(Building tests and utilities static but no static papi library to be built)
-+fi
-+
- if test "$shlib_tools" = "yes"; then
-    if test "$shared_lib" != "yes"; then	
-       AC_MSG_ERROR(Building static but specified shared linking for tests and utilities)
-@@ -847,6 +855,8 @@ if test "$shlib_tools" = "yes"; then
-       AC_MSG_ERROR([Building shared but specified static linking])
-    fi
-    LINKLIB='$(SHLIB)'
-+   #WORKAROUND: if libpfm cannot be found at link time
-+   LDFLAGS="$LDFLAGS -Wl,-rpath-link,$PWD/libpfm4/lib"
- elif test "$shlib_tools" = "no"; then
-    if test "$static_lib" != "yes"; then
-       AC_MSG_ERROR([Building shared but specified static linking for tests and utilities])
-commit d6f4e34d083f18cfdba38dd5e4bbfb2a580b8a9e
-Author: Frank Winkler <frankbook@Franks-MacBook-Air.local>
-Date:   Fri Apr 24 16:38:18 2020 +0200
-
-    Another test for "--with-static-tools".
-
-diff --git a/src/configure.in b/src/configure.in
-index 1f58f7c8e..e8d769578 100644
--- a/src/configure.in
-+++ b/src/configure.in
-@@ -201,10 +201,6 @@ else
- 	fi
- fi
- 
-# Disable LDL for static builds
-# if test "x${STATIC}" = "x"; then
-#   LDL=""
-# fi
- AC_SUBST(LDL)
- 
- if test "$OS" = "CLE"; then
-@@ -831,6 +827,11 @@ AC_ARG_WITH(static_tools,
- 	    AC_MSG_RESULT(yes)],
- 	    [AC_MSG_RESULT(no)])
- 
-+# Disable LDL for static builds
-+# if test "$STATIC" = "-static"; then
-+#   LDL=""
-+# fi
-+
- AC_MSG_CHECKING(for linking with papi shared library of tests and utilities)
- AC_ARG_WITH(shlib_tools,
- 	        [  --with-shlib-tools		Specify linking with papi library of tests and utilities],
-commit 1c333c9954b872cda1b4d873fa81b14ec58a58a7
-Author: Frank Winkler <frankbook@Franks-MacBook-Air.local>
-Date:   Thu Apr 30 18:51:34 2020 +0200
-
-    Fixed static build.
-    - SDE component is disabled
-    - "ctest" shlib is disabled
-
-diff --git a/src/configure.in b/src/configure.in
-index e8d769578..0eee98ea1 100644
--- a/src/configure.in
-+++ b/src/configure.in
-@@ -827,10 +827,11 @@ AC_ARG_WITH(static_tools,
- 	    AC_MSG_RESULT(yes)],
- 	    [AC_MSG_RESULT(no)])
- 
-# Disable LDL for static builds
-# if test "$STATIC" = "-static"; then
-#   LDL=""
-# fi
-+# Disable LDL AND SDE for static builds
-+if test "$STATIC" = "-static"; then
-+  LDL=""
-+  SDE_ENABLED=
-+fi
- 
- AC_MSG_CHECKING(for linking with papi shared library of tests and utilities)
- AC_ARG_WITH(shlib_tools,
-@@ -1768,6 +1769,7 @@ for comp in $components; do
-   if test "x$comp" = "xsde" ; then
-     LDFLAGS="$LDFLAGS $LRT"
-     LIBS="$LIBS $LRT"
-+    SDE_ENABLED=1
-   fi
- done
- 
-@@ -1862,6 +1864,7 @@ AC_SUBST(BGP_SYSDIR)
- AC_SUBST(BITFLAGS)
- AC_SUBST(COMPONENT_RULES)
- AC_SUBST(COMPONENTS)
-+AC_SUBST(SDE_ENABLED)
- AC_SUBST(FTEST_TARGETS)
- AC_SUBST(HAVE_NO_OVERRIDE_INIT)
- AC_SUBST(BGPM_INSTALL_DIR)
-diff --git a/src/ctests/Makefile.recipies b/src/ctests/Makefile.recipies
-index b7c1963d7..44e19b398 100644
--- a/src/ctests/Makefile.recipies
-+++ b/src/ctests/Makefile.recipies
-@@ -11,7 +11,11 @@ MPX	= max_multiplex multiplex1 multiplex2 mendes-alt sdsc-mpx sdsc2-mpx \
- MPXPTHR	= multiplex1_pthreads multiplex3_pthreads kufrin
- MPI	= mpi_hl mpi_omp_hl \
- 	mpifirst
-+
-+ifeq ($(STATIC),)
- SHARED  = shlib
-+endif
-+
- SERIAL  = serial_hl serial_hl_ll_comb\
- 	all_events all_native_events branches calibrate case1 case2 \
- 	cmpinfo code2name derived describe destroy disable_component \
-@@ -344,8 +348,10 @@ case2: case2.c $(TESTLIB) $(PAPILIB)
- low-level: low-level.c $(TESTLIB) $(DOLOOPS) $(PAPILIB)
- 	$(CC) $(INCLUDE) $(CFLAGS) $(TOPTFLAGS) low-level.c $(TESTLIB) $(DOLOOPS) $(PAPILIB) $(LDFLAGS) -o low-level
- 
-+ifeq ($(STATIC),)
- shlib: shlib.c $(TESTLIB) $(PAPILIB)
- 	$(CC) $(INCLUDE) $(CFLAGS) $(TOPTFLAGS) shlib.c $(TESTLIB) $(PAPILIB) $(LDFLAGS) -o shlib $(LDL)
-+endif
- 
- exeinfo: exeinfo.c $(TESTLIB) $(PAPILIB)
- 	-$(CC) $(INCLUDE) $(CFLAGS) $(TOPTFLAGS) exeinfo.c $(TESTLIB) $(PAPILIB) $(LDFLAGS) -o exeinfo 
-diff --git a/src/ctests/Makefile.target.in b/src/ctests/Makefile.target.in
-index edc04f1b7..af64e157c 100644
--- a/src/ctests/Makefile.target.in
-+++ b/src/ctests/Makefile.target.in
-@@ -10,6 +10,7 @@ INCLUDE = -I. -I@includedir@ -I$(testlibdir) -I$(validationlibdir)
- LIBDIR  = @libdir@
- LIBRARY = @LIBRARY@
- SHLIB   = @SHLIB@
-+STATIC  = @STATIC@
- PAPILIB = ../@LINKLIB@
- TESTLIB = $(testlibdir)/libtestlib.a
- LDFLAGS = @LDFLAGS@ @LDL@ @STATIC@
-diff --git a/src/utils/Makefile b/src/utils/Makefile
-index 4abfd6cb8..64a2b8f9f 100644
--- a/src/utils/Makefile
-+++ b/src/utils/Makefile
-@@ -48,8 +48,13 @@ papi_mem_info: papi_mem_info.o $(PAPILIB)
- papi_multiplex_cost: papi_multiplex_cost.o $(PAPILIB) cost_utils.o
- 	$(CC) -o papi_multiplex_cost papi_multiplex_cost.o cost_utils.o $(PAPILIB) -lm $(LDFLAGS)
- 
-+ifneq ($(SDE_ENABLED),)
- papi_native_avail: papi_native_avail.o $(PAPILIB) print_header.o papi_sde_interface.o
- 	$(CC) -o papi_native_avail papi_native_avail.o $(PAPILIB) print_header.o $(LDFLAGS) papi_sde_interface.o
-+else
-+papi_native_avail: papi_native_avail.o $(PAPILIB) print_header.o
-+	$(CC) -o papi_native_avail papi_native_avail.o $(PAPILIB) print_header.o $(LDFLAGS)
-+endif
- 
- papi_version: papi_version.o $(PAPILIB)
- 	$(CC) -o papi_version papi_version.o $(PAPILIB) $(LDFLAGS)
-@@ -65,8 +70,10 @@ cost_utils.o: ../testlib/papi_test.h cost_utils.c
- print_header.o: print_header.h print_header.c
- 	$(CC) $(INCLUDE) $(CFLAGS) $(OPTFLAGS) -c print_header.c
- 
-+ifneq ($(SDE_ENABLED),)
- papi_sde_interface.o: papi_sde_interface.c
- 	$(CC) $(INCLUDE) $(CFLAGS) $(OPTFLAGS) -c papi_sde_interface.c
-+endif
- 
- clean:
- 	rm -f *.o *.stderr *.stdout core *~ $(ALL)
-diff --git a/src/utils/Makefile.target.in b/src/utils/Makefile.target.in
-index bcdbe94e9..9c76b37af 100644
--- a/src/utils/Makefile.target.in
-+++ b/src/utils/Makefile.target.in
-@@ -9,6 +9,7 @@ INCLUDE = -I. -I@includedir@ -I$(testlibdir)
- LIBDIR  = @libdir@
- LIBRARY = @LIBRARY@
- SHLIB   = @SHLIB@
-+SDE_ENABLED  = @SDE_ENABLED@
- PAPILIB = ../@LINKLIB@
- TESTLIB = $(testlibdir)/libtestlib.a
- LDFLAGS = @LDFLAGS@ @LDL@ @STATIC@
-diff --git a/src/utils/papi_native_avail.c b/src/utils/papi_native_avail.c
-index ae6dbb9e5..902ed7996 100644
--- a/src/utils/papi_native_avail.c
-+++ b/src/utils/papi_native_avail.c
-@@ -51,8 +51,9 @@
- 
- #include "papi.h"
- #include "print_header.h"
-+#ifdef SDE_ENABLED
- #include "components/sde/interface/papi_sde_interface.h"
-
-+#endif
- #define EVT_LINE 80
- #define EVT_LINE_BUF_SIZE 4096
- 
-@@ -84,7 +85,9 @@ print_help( char **argv )
- 	printf( "\nGeneral command options:\n" );
- 	printf( "\t-h, --help       print this help message\n" );
- 	printf( "\t-c, --check      attempts to add each event\n");
-+#ifdef SDE_ENABLED
- 	printf( "\t-sde FILE        lists SDEs that are registered by the library or executable in FILE\n" );
-+#endif
- 	printf( "\t-e EVENTNAME     display detailed information about named native event\n" );
- 	printf( "\t-i EVENTSTR      include only event names that contain EVENTSTR\n" );
- 	printf( "\t-x EVENTSTR      exclude any event names that contain EVENTSTR\n" );
-@@ -368,6 +371,7 @@ parse_event_qualifiers( PAPI_event_info_t * info )
- 	return ( 1 );
- }
- 
-+#ifdef SDE_ENABLED
- void
- invoke_hook_fptr( char *lib_path )
- {
-@@ -394,6 +398,7 @@ invoke_hook_fptr( char *lib_path )
-     dlclose(dl_handle);
-     return;
- }
-+#endif
- 
- int
- main( int argc, char **argv )
-@@ -444,6 +449,7 @@ main( int argc, char **argv )
- 		return 2;
- 	}
- 
-+#ifdef SDE_ENABLED
-     /*
-        The following code will execute if the user wants to list the SDEs in the
-        library (or executable) stored in flags.path. This code will not list the
-@@ -514,6 +520,7 @@ skip_lib:
-         if( NULL != cmd ) free(cmd);
-     }
- no_sdes:
-+#endif //SDE_ENABLED
- 
- 	/* Do this code if the event name option was specified on the commandline */
- 	if ( flags.named ) {
-commit b5111efaf1b234541c94b8ef7e5791bf8eb094b3
-Author: Frank Winkler <frankbook@franks-air.localdomain>
-Date:   Thu May 7 09:00:53 2020 +0200
-
-    Added CFLAG -DSDE.
-
-diff --git a/src/configure.in b/src/configure.in
-index 0eee98ea1..781148e5b 100644
--- a/src/configure.in
-+++ b/src/configure.in
-@@ -1767,6 +1767,7 @@ tests="$tests comp_tests"
- # check for SDE component to determine if we need -lrt in LDFLAGS
- for comp in $components; do
-   if test "x$comp" = "xsde" ; then
-+    CFLAGS="$CFLAGS -DSDE"
-     LDFLAGS="$LDFLAGS $LRT"
-     LIBS="$LIBS $LRT"
-     SDE_ENABLED=1
-diff --git a/src/utils/papi_native_avail.c b/src/utils/papi_native_avail.c
-index 902ed7996..7d90c4064 100644
--- a/src/utils/papi_native_avail.c
-+++ b/src/utils/papi_native_avail.c
-@@ -51,9 +51,10 @@
- 
- #include "papi.h"
- #include "print_header.h"
-#ifdef SDE_ENABLED
-+#if SDE
- #include "components/sde/interface/papi_sde_interface.h"
- #endif
-+
- #define EVT_LINE 80
- #define EVT_LINE_BUF_SIZE 4096
- 
-@@ -85,7 +86,7 @@ print_help( char **argv )
- 	printf( "\nGeneral command options:\n" );
- 	printf( "\t-h, --help       print this help message\n" );
- 	printf( "\t-c, --check      attempts to add each event\n");
-#ifdef SDE_ENABLED
-+#if SDE
- 	printf( "\t-sde FILE        lists SDEs that are registered by the library or executable in FILE\n" );
- #endif
- 	printf( "\t-e EVENTNAME     display detailed information about named native event\n" );
-@@ -371,7 +372,7 @@ parse_event_qualifiers( PAPI_event_info_t * info )
- 	return ( 1 );
- }
- 
-#ifdef SDE_ENABLED
-+#if SDE
- void
- invoke_hook_fptr( char *lib_path )
- {
-@@ -449,7 +450,7 @@ main( int argc, char **argv )
- 		return 2;
- 	}
- 
-#ifdef SDE_ENABLED
-+#if SDE
-     /*
-        The following code will execute if the user wants to list the SDEs in the
-        library (or executable) stored in flags.path. This code will not list the
-@@ -520,7 +521,7 @@ skip_lib:
-         if( NULL != cmd ) free(cmd);
-     }
- no_sdes:
-#endif //SDE_ENABLED
-+#endif //SDE
- 
- 	/* Do this code if the event name option was specified on the commandline */
- 	if ( flags.named ) {
--- a/SOURCES/papi-divzero.patch
+++ b/SOURCES/papi-divzero.patch
@ -0,0 +1,43 @@
+commit 7a6ae407b62615d3ffa9b0d2ac17771b7fc63056
+Author: Vince Weaver <vince@deater.net>
+Date:   Thu Sep 27 23:47:58 2018 -0400
+
+    perf_event: avoid floating point exception if running is 0
+    
+    The perf_event interface isn't supposed to return 0 for running, but
+    it happens occasionally.  So be sure not to divide by zero if this
+    happens.  This makes the rdpmc code match the generic perf code in this
+    case.
+    
+    This is in response to bitbucket issue #52
+
+diff --git a/src/components/perf_event/perf_event.c b/src/components/perf_event/perf_event.c
+index 7fd753ed..82b7d398 100644
+--- a/src/components/perf_event/perf_event.c
+++ b/src/components/perf_event/perf_event.c
+@@ -1099,14 +1099,23 @@ _pe_rdpmc_read( hwd_context_t *ctx, hwd_control_state_t *ctl,
+ 		count = mmap_read_self(pe_ctl->events[i].mmap_buf,
+ 						&enabled,&running);
+ 
+-		/* TODO: error checking? */
+		/* TODO: more error checking? */
+ 
+ 		/* Handle multiplexing case */
+-		if (enabled!=running) {
+		if (enabled == running) {
+			/* no adjustment needed */
+		}
+		else if (enabled && running) {
+ 			adjusted = (enabled * 128LL) / running;
+ 			adjusted = adjusted * count;
+ 			adjusted = adjusted / 128LL;
+ 			count = adjusted;
+		} else {
+			/* This should not happen, but we have had it reported */
+			SUBDBG("perf_event kernel bug(?) count, enabled, "
+				"running: %lld, %lld, %lld\n",
+				papi_pe_buffer[0],enabled,running);
+
+ 		}
+ 
+ 		pe_ctl->counts[i] = count;
--- a/SOURCES/papi-ldflags.patch
+++ b/SOURCES/papi-ldflags.patch
@ -0,0 +1,115 @@
+commit bde3da26f1f2755689e16fc9f5ab404367d1fdc8
+Author: Vince Weaver <vincent.weaver@maine.edu>
+Date:   Wed Jan 24 14:13:28 2018 -0500
+
+    build: fix various LDFLAGS/CFLAGS issues
+    
+    issues were reported by Andreas Beckmann <anbe@debian.org>
+
+diff --git a/src/components/Makefile_comp_tests.target.in b/src/components/Makefile_comp_tests.target.in
+index 9a369adb..a4412bea 100644
+--- a/src/components/Makefile_comp_tests.target.in
+++ b/src/components/Makefile_comp_tests.target.in
+@@ -9,7 +9,7 @@ INCLUDE = -I. -I@includedir@ -I$(datadir) -I$(testlibdir) -I$(validationlibdir)
+ LIBDIR  = @libdir@
+ PAPILIB = $(datadir)/@LIBRARY@
+ TESTLIB = $(testlibdir)/libtestlib.a
+-LDFLAGS = @LDL@
+LDFLAGS = @LDFLAGS@ @LDL@
+ CC	= @CC@
+ F77	= @F77@
+ CC_R	= @CC_R@
+diff --git a/src/components/perf_event_uncore/tests/Makefile b/src/components/perf_event_uncore/tests/Makefile
+index 3ee8fc2a..d70debe6 100644
+--- a/src/components/perf_event_uncore/tests/Makefile
+++ b/src/components/perf_event_uncore/tests/Makefile
+@@ -17,19 +17,19 @@ perf_event_uncore_lib.o:	perf_event_uncore_lib.c perf_event_uncore_lib.h
+ 
+ 
+ perf_event_amd_northbridge:	perf_event_amd_northbridge.o $(DOLOOPS) $(UTILOBJS) $(PAPILIB) $(DOLOOPS)
+-	$(CC) $(LFLAGS) -o perf_event_amd_northbridge perf_event_amd_northbridge.o $(UTILOBJS) $(DOLOOPS) $(PAPILIB) $(LDFLAGS)
+	$(CC) $(CFLAGS) -o perf_event_amd_northbridge perf_event_amd_northbridge.o $(UTILOBJS) $(DOLOOPS) $(PAPILIB) $(LDFLAGS)
+ 
+ perf_event_uncore:	perf_event_uncore.o $(UTILOBJS) $(DOLOOPS) $(PAPILIB) perf_event_uncore_lib.o
+-	$(CC) $(LFLAGS) -o perf_event_uncore perf_event_uncore.o perf_event_uncore_lib.o $(UTILOBJS) $(DOLOOPS) $(PAPILIB) $(LDFLAGS)
+	$(CC) $(CFLAGS) -o perf_event_uncore perf_event_uncore.o perf_event_uncore_lib.o $(UTILOBJS) $(DOLOOPS) $(PAPILIB) $(LDFLAGS)
+ 
+ perf_event_uncore_attach:	perf_event_uncore_attach.o $(UTILOBJS) $(DOLOOPS) $(PAPILIB) perf_event_uncore_lib.o
+-	$(CC) $(LFLAGS) -o perf_event_uncore_attach perf_event_uncore_attach.o perf_event_uncore_lib.o $(UTILOBJS) $(DOLOOPS) $(PAPILIB) $(LDFLAGS)
+	$(CC) $(CFLAGS) -o perf_event_uncore_attach perf_event_uncore_attach.o perf_event_uncore_lib.o $(UTILOBJS) $(DOLOOPS) $(PAPILIB) $(LDFLAGS)
+ 
+ perf_event_uncore_multiple:	perf_event_uncore_multiple.o perf_event_uncore_lib.o $(UTILOBJS) $(DOLOOPS) $(PAPILIB)
+-	$(CC) $(LFLAGS) $(INCLUDE) -o perf_event_uncore_multiple perf_event_uncore_multiple.o perf_event_uncore_lib.o $(UTILOBJS) $(DOLOOPS) $(PAPILIB) $(LDFLAGS) 
+	$(CC) $(CFLAGS) $(INCLUDE) -o perf_event_uncore_multiple perf_event_uncore_multiple.o perf_event_uncore_lib.o $(UTILOBJS) $(DOLOOPS) $(PAPILIB) $(LDFLAGS) 
+ 
+ perf_event_uncore_cbox:	perf_event_uncore_cbox.o perf_event_uncore_lib.o $(UTILOBJS) $(DOLOOPS) $(PAPILIB)
+-	$(CC) $(LFLAGS) $(INCLUDE) -o perf_event_uncore_cbox perf_event_uncore_cbox.o perf_event_uncore_lib.o $(UTILOBJS) $(DOLOOPS) $(PAPILIB) $(LDFLAGS)
+	$(CC) $(CFLAGS) $(INCLUDE) -o perf_event_uncore_cbox perf_event_uncore_cbox.o perf_event_uncore_lib.o $(UTILOBJS) $(DOLOOPS) $(PAPILIB) $(LDFLAGS)
+ 
+ 
+ 
+diff --git a/src/ctests/Makefile.recipies b/src/ctests/Makefile.recipies
+index 63c107c0..201f3c85 100644
+--- a/src/ctests/Makefile.recipies
+++ b/src/ctests/Makefile.recipies
+@@ -350,7 +350,7 @@ code2name: code2name.c $(TESTLIB) $(PAPILIB)
+ 	$(CC) $(INCLUDE) $(CFLAGS) $(TOPTFLAGS) code2name.c $(TESTLIB) $(PAPILIB) $(LDFLAGS) -o code2name
+ 
+ attach_target: attach_target.c $(DOLOOPS)
+-	-$(CC) $(INCLUDE) $(CFLAGS) $(TOPTFLAGS) attach_target.c -o attach_target $(DOLOOPS) $(TESTLIB)
+	-$(CC) $(INCLUDE) $(CFLAGS) $(TOPTFLAGS) attach_target.c -o attach_target $(DOLOOPS) $(TESTLIB) $(LDFLAGS)
+ 
+ zero_attach: zero_attach.c $(TESTLIB) $(DOLOOPS) $(PAPILIB)
+ 	-$(CC) $(INCLUDE) $(CFLAGS) $(TOPTFLAGS) zero_attach.c $(TESTLIB) $(DOLOOPS) $(PAPILIB) $(LDFLAGS) -o zero_attach
+diff --git a/src/ctests/Makefile.target.in b/src/ctests/Makefile.target.in
+index bb51c350..fcc3373b 100644
+--- a/src/ctests/Makefile.target.in
+++ b/src/ctests/Makefile.target.in
+@@ -12,7 +12,7 @@ LIBRARY=@LIBRARY@
+ SHLIB=@SHLIB@
+ PAPILIB = ../@LINKLIB@
+ TESTLIB = $(testlibdir)/libtestlib.a
+-LDFLAGS = @LDL@ @STATIC@
+LDFLAGS = @LDFLAGS@ @LDL@ @STATIC@
+ CC	= @CC@
+ MPICC	= @MPICC@
+ F77	= @F77@
+diff --git a/src/ftests/Makefile.target.in b/src/ftests/Makefile.target.in
+index 718586e5..8006dd8d 100644
+--- a/src/ftests/Makefile.target.in
+++ b/src/ftests/Makefile.target.in
+@@ -11,7 +11,7 @@ LIBRARY = @LIBRARY@
+ SHLIB=@SHLIB@
+ PAPILIB = ../@LINKLIB@
+ TESTLIB = $(testlibdir)/libtestlib.a
+-LDFLAGS = @LDL@
+LDFLAGS = @LDFLAGS@ @LDL@
+ CC	= @CC@
+ F77	= @F77@
+ CC_R	= @CC_R@
+diff --git a/src/utils/Makefile.target.in b/src/utils/Makefile.target.in
+index a5eab438..58d438a1 100644
+--- a/src/utils/Makefile.target.in
+++ b/src/utils/Makefile.target.in
+@@ -11,7 +11,7 @@ LIBRARY=@LIBRARY@
+ SHLIB=@SHLIB@
+ PAPILIB = ../@LINKLIB@
+ TESTLIB = $(testlibdir)/libtestlib.a
+-LDFLAGS = @LDL@ @STATIC@
+LDFLAGS = @LDFLAGS@ @LDL@ @STATIC@
+ CC	= @CC@
+ MPICC	= @MPICC@
+ F77	= @F77@
+diff --git a/src/validation_tests/Makefile.target.in b/src/validation_tests/Makefile.target.in
+index a5eab438..58d438a1 100644
+--- a/src/validation_tests/Makefile.target.in
+++ b/src/validation_tests/Makefile.target.in
+@@ -11,7 +11,7 @@ LIBRARY=@LIBRARY@
+ SHLIB=@SHLIB@
+ PAPILIB = ../@LINKLIB@
+ TESTLIB = $(testlibdir)/libtestlib.a
+-LDFLAGS = @LDL@ @STATIC@
+LDFLAGS = @LDFLAGS@ @LDL@ @STATIC@
+ CC	= @CC@
+ MPICC	= @MPICC@
+ F77	= @F77@
--- a/SOURCES/papi-lto.patch
+++ b/SOURCES/papi-lto.patch
@ -1,124 +0,0 @@
-commit cbca67dae5722d65590e33b8b885a561ac3fff5d
-Author: William Cohen <wcohen@redhat.com>
-Date:   Tue Jun 15 21:48:15 2021 -0400
-
-    Use numeric local labels to allow compilation with LTO enabled
-    
-    Some assembly snippets in instructions_testcode.c used regular label
-    names.  Unfortunately, when multiple copies of the snippets are
-    inlined in different places with LTO enabled the multiple copies of a
-    label by the same name cause the build to fail because of the
-    redefinition of the label.  To avoid this problem all those labels
-    have been converted to numeric local labels to allow multiple copies
-    to peacefully coexist in the LTO enabled code.
-
-diff --git a/src/validation_tests/instructions_testcode.c b/src/validation_tests/instructions_testcode.c
-index 3634b1f90..128127c25 100644
--- a/src/validation_tests/instructions_testcode.c
-+++ b/src/validation_tests/instructions_testcode.c
-@@ -10,9 +10,9 @@ int instructions_million(void) {
- #if defined(__i386__) || (defined __x86_64__)
- 	asm(	"	xor	%%ecx,%%ecx\n"
- 		"	mov	$499999,%%ecx\n"
-		"test_loop:\n"
-+		"55:\n"
- 		"	dec	%%ecx\n"
-		"	jnz	test_loop\n"
-+		"	jnz	55b\n"
- 		: /* no output registers */
- 		: /* no inputs */
- 		: "cc", "%ecx" /* clobbered */
-@@ -47,9 +47,9 @@ int instructions_million(void) {
- #elif defined(__sparc__)
- 	asm(	"	sethi	%%hi(333333), %%l0\n"
- 		"	or	%%l0,%%lo(333333),%%l0\n"
-		"test_loop:\n"
-+		"55:\n"
- 		"	deccc	%%l0		! decrement count\n"
-		"	bnz	test_loop	! repeat until zero\n"
-+		"	bnz	55b		! repeat until zero\n"
- 		"	nop			! branch delay slot\n"
- 		: /* no output registers */
- 		: /* no inputs */
-@@ -57,13 +57,13 @@ int instructions_million(void) {
- 	);
- 	return 0;
- #elif defined(__arm__)
-	asm(	"	ldr	r2,count	@ set count\n"
-		"	b       test_loop\n"
-		"count:	.word 333332\n"
-		"test_loop:\n"
-+	asm(	"	ldr	r2,42f		@ set count\n"
-+		"	b       55f\n"
-+		"42:	.word 333332\n"
-+		"55:\n"
- 		"	add	r2,r2,#-1\n"
- 		"	cmp	r2,#0\n"
-		"	bne	test_loop	@ repeat till zero\n"
-+		"	bne	55b		@ repeat till zero\n"
- 		: /* no output registers */
- 		: /* no inputs */
- 		: "cc", "r2" /* clobbered */
-@@ -71,10 +71,10 @@ int instructions_million(void) {
- 	return 0;
- #elif defined(__aarch64__)
- 	asm(	"	ldr	x2,=333332	// set count\n"
-		"test_loop:\n"
-+		"55:\n"
- 		"	add	x2,x2,#-1\n"
- 		"	cmp	x2,#0\n"
-		"	bne	test_loop	// repeat till zero\n"
-+		"	bne	55b		// repeat till zero\n"
- 		: /* no output registers */
- 		: /* no inputs */
- 		: "cc", "r2" /* clobbered */
-@@ -97,7 +97,7 @@ int instructions_fldcw(void) {
- 	double three=3.0;
- 
- 	asm(	"	mov	$100000,%%ecx\n"
-		"big_loop:\n"
-+		"44:\n"
- 		"	fldl	%1		# load value onto fp stack\n"
- 		"	fnstcw	%0		# store control word to mem\n"
- 		"	movzwl	%0, %%eax	# load cw from mem, zero extending\n"
-@@ -106,7 +106,7 @@ int instructions_fldcw(void) {
- 		"	fldcw	%3		# save new rounding mode\n"
- 		"	fistpl	%2		# save stack value as integer to mem\n"
- 		"	fldcw	%0		# restore old cw\n"
-		"	loop	big_loop	# loop to make the count more obvious\n"
-+		"	loop	44b		# loop to make the count more obvious\n"
- 		: /* no output registers */
- 		: "m"(saved_cw), "m"(three), "m"(result), "m"(cw) /* inputs */
- 		: "cc", "%ecx","%eax" /* clobbered */
-@@ -129,13 +129,13 @@ int instructions_rep(void) {
- 
- 	asm(	"	mov	$1000,%%edx\n"
- 		"	cld\n"
-		"loadstore:			# test 8-bit store\n"
-+		"66:				# test 8-bit store\n"
- 		"	mov	$0xd, %%al	# set eax to d\n"
- 		"	mov	$16384, %%ecx\n"
- 		"	mov	%0, %%edi	# set destination\n"
- 		"	rep	stosb		# store d 16384 times, auto-increment\n"
- 		"	dec	%%edx\n"
-		"	jnz	loadstore\n"
-+		"	jnz	66b\n"
- 		: /* outputs */
- 		: "rm" (buffer_out) /* inputs */
- 		: "cc", "%esi","%edi","%edx","%ecx","%eax","memory" /* clobbered */
-@@ -147,13 +147,13 @@ int instructions_rep(void) {
- 
- 	asm(	"	mov	$1000,%%edx\n"
- 		"	cld\n"
-		"loadstore:			# test 8-bit store\n"
-+		"66:				# test 8-bit store\n"
- 		"	mov	$0xd, %%al	# set eax to d\n"
- 		"	mov	$16384, %%ecx\n"
- 		"	mov	%0, %%rdi	# set destination\n"
- 		"	rep	stosb		# store d 16384 times, auto-increment\n"
- 		"	dec	%%edx\n"
-		"	jnz	loadstore\n"
-+		"	jnz	66b\n"
- 		: /* outputs */
- 		: "rm" (buffer_out) /* inputs */
- 		: "cc", "%esi","%edi","%edx","%ecx","%eax","memory" /* clobbered */
--- a/SOURCES/papi-mx.patch
+++ b/SOURCES/papi-mx.patch
@ -0,0 +1,144 @@
+commit 3a6c9a855195e6f6f44ad6dffe2cd4046426ab53
+Author: Masahiko, Yamada <yamada.masahiko@fujitsu.com>
+Date:   Wed Nov 25 21:46:26 2020 +0900
+
+    fix for performance improvement of _mx_init_component() function
+
+diff --git a/src/components/mx/linux-mx.c b/src/components/mx/linux-mx.c
+index 2da406d14..34e6f02c2 100644
+--- a/src/components/mx/linux-mx.c
+++ b/src/components/mx/linux-mx.c
+@@ -224,26 +224,35 @@ _mx_init_component( int cidx )
+ {
+ 
+ 	FILE *fff;
+-	char test_string[BUFSIZ];
+	char *path;
+	int len, pathlen;
+ 
+ 	/* detect if MX available */
+ 
+-	strncpy(mx_counters_exe,"mx_counters 2> /dev/null",BUFSIZ);
+-	fff=popen(mx_counters_exe,"r");
+-	/* popen only returns NULL if "sh" fails, not the actual command */
+-	if (fgets(test_string,BUFSIZ,fff)==NULL) {
+-	   pclose(fff);
+-	   strncpy(mx_counters_exe,"./components/mx/utils/fake_mx_counters 2> /dev/null",BUFSIZ);
+-	   fff=popen(mx_counters_exe,"r");
+-	   if (fgets(test_string,BUFSIZ,fff)==NULL) {
+-	      pclose(fff);
+-	      /* neither real nor fake found */
+-	      strncpy(_mx_vector.cmp_info.disabled_reason,
+-		      "No MX utilities found",PAPI_MAX_STR_LEN);
+-	      return PAPI_ECMP;
+	path = getenv("PATH");
+	pathlen = strlen(path);
+	while(pathlen > 0) {
+	   len = strcspn(path, ":");
+	   strncpy(mx_counters_exe, path, len);
+	   mx_counters_exe[len] = '\0';
+	   strcat(mx_counters_exe, "/mx_counters");
+	   fff = fopen(mx_counters_exe, "r");
+	   if (fff != NULL) {
+	      strcat(mx_counters_exe, " 2> /dev/null");
+	      break;
+ 	   }
+	   pathlen = pathlen - len - 1;
+	   if (pathlen > 0) {
+	      path = path + len + 1;
+	   }
+	}
+	if (fff == NULL) {
+	   /* neither real nor fake found */
+	   strncpy(_mx_vector.cmp_info.disabled_reason,
+		   "No MX utilities found",PAPI_MAX_STR_LEN);
+	   return PAPI_ECMP;
+ 	}
+-	pclose(fff);
+	fclose(fff);
+ 
+ 	num_events=MX_MAX_COUNTERS;
+ 	_mx_vector.cmp_info.num_native_events=num_events;
+commit 3a2560a86be44f4b15d96a45eda8e7f387b9166c
+Author: Masahiko, Yamada <yamada.masahiko@fujitsu.com>
+Date:   Tue Jan 26 16:30:40 2021 +0900
+
+    Add string length check before strncpy() and strcat() calls in _mx_init_component()
+    
+    Myrinet Express-related component MX modules are initialized with the _mx_init_component() function,
+    which is called from the PAPI_library_init() function.
+    The popen(3) call runs a loadable module called "mx_counters",
+    and if the loadable module does not exist,
+    it attempts to run a loadable module called "./components/mx/utils/fake_mx_counters".
+    In an environment where there are no "mx_counters" and "./components/mx/utils/fake_mx_counters" loadable modules,
+    popen(3) will be called twice uselessly.
+    popen(3) internally calls pipe(2) once, fork(2) twice and exec(2) once.
+    
+    The size of the user space of the application calling the PAPI_library_init() function affects the performance of fork(2),
+    which is called as an extension of popen(3).
+    As a result, the performance of the PAPI_library_init() function is affected by the amount of user space in the application
+    that called the PAPI_library_init() function.
+    
+    In the _mx_init_component() function,
+    the MX module only needs to be able to verify that a load module named "mx_counters" exists.
+    We improved the _mx_init_component() function to call fopen(3) instead of popen(3).
+    We add string length check before strncpy() and strcat() calls in _mx_init_component() function.
+
+diff --git a/src/components/mx/linux-mx.c b/src/components/mx/linux-mx.c
+index 34e6f02c2..c2920d65b 100644
+--- a/src/components/mx/linux-mx.c
+++ b/src/components/mx/linux-mx.c
+@@ -225,7 +225,7 @@ _mx_init_component( int cidx )
+ 
+ 	FILE *fff;
+ 	char *path;
+-	int len, pathlen;
+	int checklen, len, pathlen;
+ 
+ 	/* detect if MX available */
+ 
+@@ -233,13 +233,31 @@ _mx_init_component( int cidx )
+ 	pathlen = strlen(path);
+ 	while(pathlen > 0) {
+ 	   len = strcspn(path, ":");
+-	   strncpy(mx_counters_exe, path, len);
+	   if (len < BUFSIZ) {
+	      strncpy(mx_counters_exe, path, len);
+	   } else {
+	      fff = NULL;
+	      break;
+	   }
+ 	   mx_counters_exe[len] = '\0';
+-	   strcat(mx_counters_exe, "/mx_counters");
+	   checklen = len + strlen("/mx_counters");
+	   if (checklen < BUFSIZ) {
+	      strcat(mx_counters_exe, "/mx_counters");
+	   } else {
+	      fff = NULL;
+	      break;
+	   }
+ 	   fff = fopen(mx_counters_exe, "r");
+ 	   if (fff != NULL) {
+-	      strcat(mx_counters_exe, " 2> /dev/null");
+-	      break;
+	      checklen = checklen + strlen(" 2> /dev/null");
+	      if (checklen < BUFSIZ) {
+	         strcat(mx_counters_exe, " 2> /dev/null");
+	         break;
+	      } else {
+	         fclose(fff);
+	         fff = NULL;
+	         break;
+	      }
+ 	   }
+ 	   pathlen = pathlen - len - 1;
+ 	   if (pathlen > 0) {
+@@ -247,7 +265,7 @@ _mx_init_component( int cidx )
+ 	   }
+ 	}
+ 	if (fff == NULL) {
+-	   /* neither real nor fake found */
+	   /* mx_counters not found */
+ 	   strncpy(_mx_vector.cmp_info.disabled_reason,
+ 		   "No MX utilities found",PAPI_MAX_STR_LEN);
+ 	   return PAPI_ECMP;
--- a/SOURCES/papi-nostatic.patch
+++ b/SOURCES/papi-nostatic.patch
@ -1,30 +0,0 @@
-commit cc34c978778adb40df1a200059a31c8d628b10ee
-Author: William Cohen <wcohen@redhat.com>
-Date:   Thu Jan 21 14:48:01 2021 -0500
-
-    Only check for libpfm.a if static libraries are being used.
-    
-    Even when static libraries are not be used papi was checking for
-    libpfm.a, this would cause a failure if libpfm.a wasn't installed.
-    Exclude checking for libpfm.a if no static libpfm library is needed.
-
-diff --git a/src/Rules.pfm4_pe b/src/Rules.pfm4_pe
-index 61eedc8a3..65a9635c6 100644
--- a/src/Rules.pfm4_pe
-+++ b/src/Rules.pfm4_pe
-@@ -32,6 +32,7 @@ ifeq (yes,$(MIC))
- 	FORCE_PFM_ARCH="CONFIG_PFMLIB_ARCH_X86=y"
- endif
- 
-+ifneq (,$(STATIC))
- ifeq (,$(PFM_OBJS))
- $(PFM_LIB_PATH)/libpfm.a:
- ifneq (,${PFM_ROOT})
-@@ -49,6 +50,7 @@ else
- endif
- 	$(MAKE)
- endif
-+endif
- 
- include Makefile.inc
- 
--- a/SOURCES/papi-python3.patch
+++ b/SOURCES/papi-python3.patch
@ -1,10 +0,0 @@
-diff --git a/src/high-level/scripts/papi_hl_output_writer.py b/src/high-level/scripts/papi_hl_output_writer.py
-index 123d2cd0..34bfbd73 100755
--- a/src/high-level/scripts/papi_hl_output_writer.py
-+++ b/src/high-level/scripts/papi_hl_output_writer.py
-@@ -1,4 +1,4 @@
-#!/usr/bin/python
-+#!/usr/bin/python3
- from __future__ import division
- from collections import OrderedDict
- 
--- a/SOURCES/papi-rhbz1807346.patch
+++ b/SOURCES/papi-rhbz1807346.patch
@ -0,0 +1,607 @@
+commit 660bfd20bc89a26629e99de958d38b031db4250d
+Author: William Cohen <wcohen@redhat.com>
+Date:   Thu Oct 31 15:30:00 2019 -0400
+
+    This code is a modification of krentel_pthreads.c, to better test
+    some race conditions. It is not included in the standard tests;
+    it is a diagnostic that should be run with "valgrind --tool=helgrind".
+    
+    Signed-off-by: Anthony Castaldo <TonyCastaldo@icl.utk.edu>
+
+diff --git a/src/ctests/krentel_pthreads_race.c b/src/ctests/krentel_pthreads_race.c
+new file mode 100644
+index 000000000..0ebfb5056
+--- /dev/null
+++ b/src/ctests/krentel_pthreads_race.c
+@@ -0,0 +1,236 @@
+/*
+ *  Test PAPI with multiple threads.
+ *  This code is a modification of krentel_pthreads.c by William Cohen
+ *  <wcohen@redhat.com>, on Sep 10 2019, to exercise and test for the race
+ *  condition in papi_internal.c involving the formerly static variables
+ *  papi_event_code and papi_event_code_changed.  This code should be run with
+ *  "valgrind --tool=helgrind" to show any data races. If run with:
+ *  "valgrind --tool=helgrind --log-file=helgrind_out.txt"
+ *  The output will be captured in helgrind_out.txt and can then be processed
+ *  with the program filter_helgrind.c; see commentary at the top of that file.
+ */
+
+#define MAX_THREADS 256
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <pthread.h>
+#include <sys/time.h>
+
+#include "papi.h"
+#include "papi_test.h"
+
+#define EVENT  PAPI_TOT_CYC
+
+static int program_time = 5;
+static int threshold = 20000000;
+static int num_threads = 3;
+
+static long count[MAX_THREADS];
+static long iter[MAX_THREADS];
+static struct timeval last[MAX_THREADS];
+
+static pthread_key_t key;
+
+static struct timeval start;
+
+static void
+my_handler( int EventSet, void *pc, long long ovec, void *context )
+{
+	( void ) EventSet;
+	( void ) pc;
+	( void ) ovec;
+	( void ) context;
+
+	long num = ( long ) pthread_getspecific( key );
+
+	if ( num < 0 || num > num_threads )
+		test_fail( __FILE__, __LINE__, "getspecific failed", 1 );
+	count[num]++;
+}
+
+static void
+print_rate( long num )
+{
+	struct timeval now;
+	long st_secs;
+	double last_secs;
+
+	gettimeofday( &now, NULL );
+	st_secs = now.tv_sec - start.tv_sec;
+	last_secs = ( double ) ( now.tv_sec - last[num].tv_sec )
+		+ ( ( double ) ( now.tv_usec - last[num].tv_usec ) ) / 1000000.0;
+	if ( last_secs <= 0.001 )
+		last_secs = 0.001;
+
+	if (!TESTS_QUIET) {
+		printf( "[%ld] time = %ld, count = %ld, iter = %ld, "
+			"rate = %.1f/Kiter\n",
+			num, st_secs, count[num], iter[num],
+			( 1000.0 * ( double ) count[num] ) / ( double ) iter[num] );
+	}
+
+	count[num] = 0;
+	iter[num] = 0;
+	last[num] = now;
+}
+
+static void
+do_cycles( long num, int len )
+{
+	struct timeval start, now;
+	double x, sum;
+
+	gettimeofday( &start, NULL );
+
+	for ( ;; ) {
+		sum = 1.0;
+		for ( x = 1.0; x < 250000.0; x += 1.0 )
+			sum += x;
+		if ( sum < 0.0 )
+			printf( "==>>  SUM IS NEGATIVE !!  <<==\n" );
+
+		iter[num]++;
+
+		gettimeofday( &now, NULL );
+		if ( now.tv_sec >= start.tv_sec + len )
+			break;
+	}
+}
+
+static void *
+my_thread( void *v )
+{
+	long num = ( long ) v;
+	int n;
+	int EventSet = PAPI_NULL;
+	int event_code;
+	long long value;
+
+	int retval;
+
+	retval = PAPI_register_thread(  );
+	if ( retval != PAPI_OK ) {
+		test_fail( __FILE__, __LINE__, "PAPI_register_thread", retval );
+	}
+	pthread_setspecific( key, v );
+
+	count[num] = 0;
+	iter[num] = 0;
+	last[num] = start;
+
+	retval = PAPI_create_eventset( &EventSet );
+	if ( retval != PAPI_OK ) {
+		test_fail( __FILE__, __LINE__, "PAPI_create_eventset failed", retval );
+	}
+
+	retval = PAPI_event_name_to_code("PAPI_TOT_CYC", &event_code);
+	if (retval != PAPI_OK ) {
+		if (!TESTS_QUIET) printf("Trouble creating event name\n");
+		test_fail( __FILE__, __LINE__, "PAPI_event_name_to_code failed", retval );
+	}
+
+	retval = PAPI_add_event( EventSet, EVENT );
+	if (retval != PAPI_OK ) {
+		if (!TESTS_QUIET) printf("Trouble adding event\n");
+		test_fail( __FILE__, __LINE__, "PAPI_add_event failed", retval );
+	}
+
+	if ( PAPI_overflow( EventSet, EVENT, threshold, 0, my_handler ) != PAPI_OK )
+		test_fail( __FILE__, __LINE__, "PAPI_overflow failed", 1 );
+
+	if ( PAPI_start( EventSet ) != PAPI_OK )
+		test_fail( __FILE__, __LINE__, "PAPI_start failed", 1 );
+
+	if (!TESTS_QUIET) printf( "launched timer in thread %ld\n", num );
+
+	for ( n = 1; n <= program_time; n++ ) {
+		do_cycles( num, 1 );
+		print_rate( num );
+	}
+
+	PAPI_stop( EventSet, &value );
+
+        retval = PAPI_overflow( EventSet, EVENT, 0, 0, my_handler);
+	if ( retval != PAPI_OK )
+            test_fail( __FILE__, __LINE__, "PAPI_overflow failed to reset the overflow handler", retval );
+
+	if ( PAPI_remove_event( EventSet, EVENT ) != PAPI_OK ) 
+	    test_fail( __FILE__, __LINE__, "PAPI_remove_event", 1 );
+
+	if ( PAPI_destroy_eventset( &EventSet ) != PAPI_OK ) 
+	    test_fail( __FILE__, __LINE__, "PAPI_destroy_eventset", 1 );
+
+	if ( PAPI_unregister_thread( ) != PAPI_OK ) 
+            test_fail( __FILE__, __LINE__, "PAPI_unregister_thread", 1 );
+
+	return ( NULL );
+}
+
+int
+main( int argc, char **argv )
+{
+	pthread_t *td = NULL;
+	long n;
+	int quiet,retval;
+
+	/* Set TESTS_QUIET variable */
+	quiet=tests_quiet( argc, argv );
+
+	if ( argc < 2 || sscanf( argv[1], "%d", &program_time ) < 1 )
+		program_time = 6;
+	if ( argc < 3 || sscanf( argv[2], "%d", &threshold ) < 1 )
+		threshold = 20000000;
+	if ( argc < 4 || sscanf( argv[3], "%d", &num_threads ) < 1 )
+		num_threads = 32;
+
+	td = malloc((num_threads+1) * sizeof(pthread_t));
+	if (!td) {
+		test_fail( __FILE__, __LINE__, "td malloc failed", 1 );
+	}
+
+	if (!quiet) {
+		printf( "program_time = %d, threshold = %d, num_threads = %d\n\n",
+			program_time, threshold, num_threads );
+	}
+
+	if ( PAPI_library_init( PAPI_VER_CURRENT ) != PAPI_VER_CURRENT )
+		test_fail( __FILE__, __LINE__, "PAPI_library_init failed", 1 );
+
+	/* Test to be sure we can add events */
+	retval = PAPI_query_event( EVENT );
+	if (retval!=PAPI_OK) {
+		if (!quiet) printf("Trouble finding event\n");
+		test_skip(__FILE__,__LINE__,"Event not available",1);
+	}
+
+	if ( PAPI_thread_init( ( unsigned long ( * )( void ) ) ( pthread_self ) ) !=
+		 PAPI_OK )
+		test_fail( __FILE__, __LINE__, "PAPI_thread_init failed", 1 );
+
+	if ( pthread_key_create( &key, NULL ) != 0 )
+		test_fail( __FILE__, __LINE__, "pthread key create failed", 1 );
+
+	gettimeofday( &start, NULL );
+
+	for ( n = 1; n <= num_threads; n++ ) {
+		if ( pthread_create( &(td[n]), NULL, my_thread, ( void * ) n ) != 0 )
+			test_fail( __FILE__, __LINE__, "pthread create failed", 1 );
+	}
+
+	my_thread( ( void * ) 0 );
+
+	/* wait for all the threads */
+	for ( n = 1; n <= num_threads; n++ ) {
+	  	if ( pthread_join( td[n], NULL))
+			test_fail( __FILE__, __LINE__, "pthread join failed", 1 );
+	}
+
+	free(td);
+
+	if (!quiet) printf( "done\n" );
+
+	test_pass( __FILE__ );
+
+	return 0;
+}
+commit 979e80136fd5e0ee2fb26f7374b36a8433147a68
+Author: Anthony Castaldo <TonyCastaldo@icl.utk.edu>
+Date:   Thu Oct 31 15:56:55 2019 -0400
+
+    The changes to papi.c, papi_internal.c, threads.h and threads.c
+    correct a race condition that was the result of all threads using
+    the same two static variables (papi_event_code and papi_event_code_changed)
+    to temporarily record a state of operation. The solution was to
+    make these variables unique per thread, using the ThreadInfo_t
+    structure already provided in PAPI for such purposes. The file
+    krentel_pthread_race.c is a stress test to produce race conditions.
+    filter_helgrind.c reduces the volume of --tool-helgrind output to
+    a more manageable summary. Both are added to Makefile.recipies.
+
+diff --git a/src/ctests/Makefile.recipies b/src/ctests/Makefile.recipies
+index 87340831d..b7c1963d7 100644
+--- a/src/ctests/Makefile.recipies
+++ b/src/ctests/Makefile.recipies
+@@ -161,6 +161,12 @@ locks_pthreads: locks_pthreads.c $(TESTLIB) $(PAPILIB)
+ krentel_pthreads: krentel_pthreads.c $(TESTLIB) $(PAPILIB)
+ 	$(CC_R) $(INCLUDE) $(CFLAGS) $(TOPTFLAGS) krentel_pthreads.c $(TESTLIB) $(PAPILIB) $(LDFLAGS) -o krentel_pthreads -lpthread
+ 
+# krentel_pthreads_race is not included with the standard tests;
+# it is a modification of krentel_pthreads intended to be run with 
+# "valgrind --tool=helgrind" to test for race conditions.
+krentel_pthreads_race: krentel_pthreads_race.c $(TESTLIB) $(PAPILIB)
+	$(CC_R) $(INCLUDE) $(CFLAGS) $(TOPTFLAGS) krentel_pthreads_race.c $(TESTLIB) $(PAPILIB) $(LDFLAGS) -o krentel_pthreads_race -lpthread
+
+ overflow_pthreads: overflow_pthreads.c $(TESTLIB) $(DOLOOPS) $(PAPILIB)
+ 	$(CC_R) $(INCLUDE) $(CFLAGS) $(TOPTFLAGS) overflow_pthreads.c $(TESTLIB) $(DOLOOPS) $(PAPILIB) $(LDFLAGS) -o overflow_pthreads -lpthread
+ 
+@@ -434,6 +440,9 @@ forkexec4: forkexec4.c $(TESTLIB) $(PAPILIB)
+ prof_utils.o: prof_utils.c $(testlibdir)/papi_test.h prof_utils.h
+ 	$(CC) $(INCLUDE) $(CFLAGS) $(TOPTFLAGS) -c prof_utils.c
+ 
+filter_helgrind: filter_helgrind.c $(TESTLIB) $(PAPILIB)
+	-$(CC) $(INCLUDE) $(CFLAGS) $(TOPTFLAGS) filter_helgrind.c $(TESTLIB) $(PAPILIB) $(LDFLAGS) -o filter_helgrind 
+
+ .PHONY : all default ctests ctest clean
+ 
+ clean:
+diff --git a/src/ctests/filter_helgrind.c b/src/ctests/filter_helgrind.c
+new file mode 100644
+index 000000000..d918a789e
+--- /dev/null
+++ b/src/ctests/filter_helgrind.c
+@@ -0,0 +1,170 @@
+/*
+ *  This code is a simple filter for the helgrind_out.txt file
+ *  produced by:
+ *  "valgrind --tool=helgrind --log-file=helgrind_out.txt someProgram"
+ *
+ * This is useful because the tool does not recognize PAPI locks,
+ * thus reports as possible race conditions reads/writes by
+ * different threads that are actually fine (surrounded by locks).
+ *
+ * This was written particularly for krentel_pthreads_race.c 
+ * when processed by the above valgrind. We produce a line per
+ * condition, in the form:
+ * OP@file:line OP@file:line
+ * where OP is R or W. The first file:line code occurred
+ * after the second file:line code, and on a different thread.
+ * 
+ * We print the results to stdout. It is useful to filter this
+ * through the standard utility 'uniq', each occurrence only 
+ * needs to be investigated once. Just insure there are
+ * MATCHING locks around each operation within the code.
+ *
+ * An example run (using uniq): The options -uc will print 
+ * only unique lines, preceeded by a count of how many times
+ * it occurs.
+ *
+ * ./filter_helgrind | uniq -uc
+ *
+ * An example output line (piped through uniq as above):
+ *       1 R@threads.c:190                    W@threads.c:206
+ * An investigation shows threads.c:190 is protected by 
+ * _papi_hwi_lock(THREADS_LOCK); and threads.c:206 is
+ * protected by the same lock. Thus no data race can 
+ * occur for this instance.
+ *
+ * Compilation within the papi/src/ctests directory:
+ * make filter_helgrind
+ * 
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+int main(int argc, char** args) {
+   (void) argc;
+   (void) args;
+
+   char myLine[16384];
+   int state, size;
+   char type1, type2;
+   char fname1[256], fname2[256];
+   char *paren1, *paren2;
+
+   FILE *HELOUT = fopen("helgrind_out.txt", "r");  // Read the file.
+   if (HELOUT == NULL) {
+      fprintf(stderr, "Could not open helgrind_out.txt.\n");
+      exit(-1);
+   }
+
+   char PDRR[]="Possible data race during read";
+   char PDRW[]="Possible data race during write";
+   char TCWW[]="This conflicts with a previous write";
+   char TCWR[]="This conflicts with a previous read";
+   char atSTR[]="   at ";
+
+   // State machine:
+   // State 0: We are looking for a line with PDRR or PDRW.
+   //          We don't exit until we find it, or run out of lines.
+   //          if we find it, we remember which and go to state 1.
+   // State 1: Looking for "   at " in column 11. 
+   //          When found, we extract the string betweeen '(' and ')'
+   //          which is program name:line. go to state 2.
+   // State 2: We are searching for TCWW, TCWR, PDRW, PDRR.
+   //          If we find the first two:
+   //             Remember which, and go to state 3.
+   //          If we find either of the second two, go back to State 1.
+   // State 3: Looking for "   at " in column 11.
+   //          When found, extract the string betweeen '(' and ')',
+   //          which is program name:line.
+   //          OUTPUT LINE for an investigation.
+   //          Go to State 0.
+
+   state = 0;        // looking for PDRR, PDRW. 
+   while (fgets(myLine, 16384, HELOUT) != NULL) {
+      if (strlen(myLine) < 20) continue;
+      switch (state) {
+         case 0:  // Looking for PDRR or PRDW.
+            if (strstr(myLine, PDRR) != NULL) { 
+               type1='R';
+               state=1;
+               continue;
+            }
+
+            if (strstr(myLine, PDRW) != NULL) {
+               type1='W';
+               state=1;
+               continue;
+            }
+      
+            continue;
+            break;
+
+         case 1: // Looking for atSTR in column 11.
+            if (strncmp(myLine+10, atSTR, 6) != 0) continue;
+            paren1=strchr(myLine, '(');
+            paren2=strchr(myLine, ')');
+            if (paren1 == NULL || paren2 == NULL ||
+                paren1 > paren2) {
+               state=0;             // Abort, found something I don't understand.
+               continue;
+            }
+
+            size = paren2-paren1-1;          // compute length of name.
+            strncpy(fname1, paren1+1, size); // Copy the name.
+            fname1[size]=0;                  // install z-terminator.
+            state=2;
+            continue;
+            break;
+
+         case 2: // Looking for TCWW, TCWR, PDRR, PDRW.
+            if (strstr(myLine, TCWR) != NULL) {
+               type2='R';
+               state=3;
+               continue;
+            }
+
+            if (strstr(myLine, TCWW) != NULL) { 
+               type2='W';
+               state=3;
+               continue;
+            }
+
+            if (strstr(myLine, PDRR) != NULL) { 
+               type1='R';
+               state=1;
+               continue;
+            }
+
+            if (strstr(myLine, PDRW) != NULL) {
+               type1='W';
+               state=1;
+               continue;
+            }
+
+            continue;
+            break;
+
+         case 3: // Looking for atSTR in column 11.
+            if (strncmp(myLine+10, atSTR, 6) != 0) continue;
+            paren1=strchr(myLine, '(');
+            paren2=strchr(myLine, ')');
+            if (paren1 == NULL || paren2 == NULL ||
+                paren1 > paren2) {
+               state=0;             // Abort, found something I don't understand.
+               continue;
+            }
+
+            size = paren2-paren1-1;          // compute length of name.
+            strncpy(fname2, paren1+1, size); // Copy the name.
+            fname2[size]=0;                  // install z-terminator.
+            fprintf(stdout, "%c@%-32s %c@%-32s\n", type1, fname1, type2, fname2);
+            state=0;
+            continue;
+            break;
+      } // end switch.
+   } // end while.
+   
+   fclose(HELOUT);
+   exit(0);
+}  
+diff --git a/src/papi.c b/src/papi.c
+index 4e08dc840..070e3f8c6 100644
+--- a/src/papi.c
+++ b/src/papi.c
+@@ -608,32 +608,26 @@ PAPI_library_init( int version )
+ 	   papi_return( init_retval );
+ 	}
+ 
+-	/* Initialize component globals */
+	/* Initialize thread globals, including the main threads  */
+ 
+-	tmp = _papi_hwi_init_global(  );
+	tmp = _papi_hwi_init_global_threads(  );
+ 	if ( tmp ) {
+ 		init_retval = tmp;
+ 		_papi_hwi_shutdown_global_internal(  );
+-		_in_papi_library_init_cnt--;
+   	_in_papi_library_init_cnt--;
+ 		papi_return( init_retval );
+ 	}
+-	
+-	/* Initialize thread globals, including the main threads  */
+ 
+-	tmp = _papi_hwi_init_global_threads(  );
+	/* Initialize component globals */
+
+	tmp = _papi_hwi_init_global(  );
+ 	if ( tmp ) {
+-		int i;
+ 		init_retval = tmp;
+ 		_papi_hwi_shutdown_global_internal(  );
+-		for ( i = 0; i < papi_num_components; i++ ) {
+-		    if (!_papi_hwd[i]->cmp_info.disabled) {
+-                       _papi_hwd[i]->shutdown_component(  );
+-		    }
+-		}
+ 		_in_papi_library_init_cnt--;
+ 		papi_return( init_retval );
+ 	}
+-
+	
+ 	init_level = PAPI_LOW_LEVEL_INITED;
+ 	_in_papi_library_init_cnt--;
+ 
+diff --git a/src/papi_internal.c b/src/papi_internal.c
+index 2412eca63..f0e457bf7 100644
+--- a/src/papi_internal.c
+++ b/src/papi_internal.c
+@@ -111,31 +111,28 @@ _papi_hwi_free_papi_event_string() {
+ 	}
+ 	return;
+ }
+-// A place to keep the current papi event code so some component functions can fetch its value
+-// The current event code can be stored here prior to component calls and cleared after the component returns
+-static unsigned int papi_event_code = -1;
+-static int papi_event_code_changed = -1;
+
+ void
+ _papi_hwi_set_papi_event_code (unsigned int event_code, int update_flag) {
+ 	INTDBG("new event_code: %#x, update_flag: %d, previous event_code: %#x\n", event_code, update_flag, papi_event_code);
+ 
+ 	// if call is just to reset and start over, set both flags to show nothing saved yet
+ 	if (update_flag < 0) {
+-		papi_event_code_changed = -1;
+-		papi_event_code = -1;
+		_papi_hwi_my_thread->tls_papi_event_code_changed = -1;
+		_papi_hwi_my_thread->tls_papi_event_code = -1;
+ 		return;
+ 	}
+ 
+ 	// if 0, it is being set prior to calling a component, if >0 it is being changed by the component
+-	papi_event_code_changed = update_flag;
+	_papi_hwi_my_thread->tls_papi_event_code_changed = update_flag;
+ 	// save the event code passed in
+-	papi_event_code = event_code;
+	_papi_hwi_my_thread->tls_papi_event_code = event_code;
+ 	return;
+ }
+ unsigned int
+ _papi_hwi_get_papi_event_code () {
+ 	INTDBG("papi_event_code: %#x\n", papi_event_code);
+-	return papi_event_code;
+	return _papi_hwi_my_thread->tls_papi_event_code;
+ }
+ /* Get the index into the ESI->NativeInfoArray for the current PAPI event code */
+ int
+@@ -560,7 +557,7 @@ _papi_hwi_native_to_eventcode(int cidx, int event_code, int ntv_idx, const char
+ 
+   int result;
+ 
+-  if (papi_event_code_changed > 0) {
+  if (_papi_hwi_my_thread->tls_papi_event_code_changed > 0) {
+ 	  result = _papi_hwi_get_papi_event_code();
+ 	  INTDBG("EXIT: papi_event_code: %#x set by the component\n", result);
+ 	  return result;
+diff --git a/src/threads.c b/src/threads.c
+index 4dd0cf4e3..9f586c415 100644
+--- a/src/threads.c
+++ b/src/threads.c
+@@ -286,6 +286,10 @@ _papi_hwi_initialize_thread( ThreadInfo_t ** dest, int tid )
+ 		return PAPI_ENOMEM;
+ 	}
+ 
+   /* init event memory variables, used by papi_internal.c  */
+   thread->tls_papi_event_code = -1;
+   thread->tls_papi_event_code_changed = -1;
+
+ 	/* Call the component to fill in anything special. */
+ 
+ 	for ( i = 0; i < papi_num_components; i++ ) {
+@@ -421,6 +425,11 @@ _papi_hwi_shutdown_thread( ThreadInfo_t * thread, int force_shutdown )
+ 	unsigned long tid;
+ 	int i, failure = 0;
+ 
+   /* Clear event memory variables */
+   thread->tls_papi_event_code = -1;
+   thread->tls_papi_event_code_changed = -1;
+
+   /* Get thread id */
+ 	if ( _papi_hwi_thread_id_fn )
+ 		tid = ( *_papi_hwi_thread_id_fn ) (  );
+ 	else
+diff --git a/src/threads.h b/src/threads.h
+index cd3369068..264d9f3a6 100644
+--- a/src/threads.h
+++ b/src/threads.h
+@@ -30,6 +30,11 @@ typedef struct _ThreadInfo
+ 	EventSetInfo_t **running_eventset;
+ 	EventSetInfo_t *from_esi;          /* ESI used for last update this control state */
+ 	int wants_signal;
+
+   // The current event code can be stored here prior to 
+   // component calls and cleared after the component returns.
+   unsigned int tls_papi_event_code;
+   int tls_papi_event_code_changed;
+ } ThreadInfo_t;
+ 
+ /** The list of threads, gets initialized to master process with TID of getpid() 
--- a/SOURCES/papi-rhbz1918721.patch
+++ b/SOURCES/papi-rhbz1918721.patch
@ -0,0 +1,22 @@
+diff -up papi-5.6.0/src/papi_events.csv.p9 papi-5.6.0/src/papi_events.csv
+--- papi-5.6.0/src/papi_events.csv.p9	2021-05-25 16:19:17.342588151 -0400
+++ papi-5.6.0/src/papi_events.csv	2021-05-25 16:54:06.357460525 -0400
+@@ -1580,15 +1580,15 @@ PRESET,PAPI_L1_DCR,DERIVED_SUB,PM_LD_REF
+ #PRESET,PAPI_L1_DCA,DERIVED_POSTFIX,N0|N1|-|N2|+|N3|-,PM_ST_FIN,PM_ST_MISS_L1,PM_LD_REF_L1,PM_LD_MISS_L1_ALT
+ PRESET,PAPI_L1_DCA,DERIVED_ADD,PM_LD_REF_L1,PM_ST_CMPL
+ PRESET,PAPI_L2_DCM,NOT_DERIVED,PM_DATA_FROM_L2MISS
+-PRESET,PAPI_L2_LDM,NOT_DERIVED,PM_L2_LD_MISS
+-PRESET,PAPI_L2_STM,NOT_DERIVED,PM_L2_ST_MISS
+#PRESET,PAPI_L2_LDM,NOT_DERIVED,PM_L2_LD_MISS
+#PRESET,PAPI_L2_STM,NOT_DERIVED,PM_L2_ST_MISS
+ PRESET,PAPI_L3_DCR,NOT_DERIVED,PM_DATA_FROM_L2MISS
+ PRESET,PAPI_L3_DCM,DERIVED_ADD,PM_DATA_FROM_LMEM,PM_DATA_FROM_RMEM
+ PRESET,PAPI_L3_LDM,DERIVED_ADD,PM_DATA_FROM_LMEM,PM_DATA_FROM_RMEM
+ PRESET,PAPI_L1_ICH,NOT_DERIVED,PM_INST_FROM_L1
+ PRESET,PAPI_L1_ICM,NOT_DERIVED,PM_L1_ICACHE_MISS
+ PRESET,PAPI_L2_ICM,NOT_DERIVED,PM_INST_FROM_L2MISS
+-PRESET,PAPI_L2_ICM,NOT_DERIVED,PM_L2_INST_MISS
+#PRESET,PAPI_L2_ICM,NOT_DERIVED,PM_L2_INST_MISS
+ PRESET,PAPI_L2_ICH,NOT_DERIVED,PM_INST_FROM_L2
+ PRESET,PAPI_L3_ICA,NOT_DERIVED,PM_INST_FROM_L2MISS
+ PRESET,PAPI_L3_ICH,NOT_DERIVED,PM_INST_FROM_L3
--- a/SOURCES/papi-rhbz2037417.patch
+++ b/SOURCES/papi-rhbz2037417.patch
@ -0,0 +1,61 @@
+commit 6964aa356fa606f320c7b871123aceb5c1f21999
+Author: Masahiko, Yamada <yamada.masahiko@fujitsu.com>
+Date:   Tue Aug 24 14:17:29 2021 +0900
+
+    Fix the PAPI_FUL_CCY setting for a64fx
+    
+    In a64fx, the maximum number of instruction commits is 4, so the following setting was incorrect.
+    PAPI_FUL_CCY=CPU_CYCLES-0INST_COMMIT-1INST_COMMIT-2INST_COMMIT-3INST_COMMIT-4INST_COMMIT
+    
+    The correct settings are:.
+    PAPI_FUL_CCY=CPU_CYCLES-0INST_COMMIT-1INST_COMMIT-2INST_COMMIT-3INST_COMMIT
+
+diff --git a/src/papi_events.csv b/src/papi_events.csv
+index 4ef647959..74deb712f 100644
+--- a/src/papi_events.csv
+++ b/src/papi_events.csv
+@@ -1934,7 +1934,7 @@ PRESET,PAPI_PRF_DM,DERIVED_SUB,L2D_CACHE_REFILL_PRF,L2D_CACHE_MIBMCH_PRF
+ PRESET,PAPI_MEM_SCY,NOT_DERIVED,LD_COMP_WAIT_L2_MISS
+ PRESET,PAPI_STL_ICY,DERIVED_ADD,STALL_FRONTEND,STALL_BACKEND
+ PRESET,PAPI_STL_CCY,NOT_DERIVED,0INST_COMMIT
+-PRESET,PAPI_FUL_CCY,DERIVED_SUB,CPU_CYCLES,0INST_COMMIT,1INST_COMMIT,2INST_COMMIT,3INST_COMMIT,4INST_COMMIT
+PRESET,PAPI_FUL_CCY,DERIVED_SUB,CPU_CYCLES,0INST_COMMIT,1INST_COMMIT,2INST_COMMIT,3INST_COMMIT
+ PRESET,PAPI_HW_INT,DERIVED_ADD,EXC_IRQ,EXC_FIQ
+ PRESET,PAPI_BR_MSP,NOT_DERIVED,BR_MIS_PRED
+ PRESET,PAPI_BR_PRC,DERIVED_SUB,BR_PRED,BR_MIS_PRED
+commit fbf3b9e3d17c4ec4bd7e33410c44fc5aed57e36f
+Author: Masahiko, Yamada <yamada.masahiko@fujitsu.com>
+Date:   Fri Mar 4 15:41:30 2022 +0900
+
+    Add PAPI idle-related preset events for a64fx
+    
+    For a64fx, add four PAPI idle-related preset events
+    (PAPI_BRU_IDL/PAPI_FXU_IDL/PAPI_FPU_IDL/PAPI_LSU_IDL).
+    
+     PAPI_BRU_IDL = BR_COMP_WAIT
+     PAPI_FXU_IDL = EU_COMP_WAIT - FL_COMP_WAIT
+     PAPI_FPU_IDL = FL_COMP_WAIT
+     PAPI_LSU_IDL = LD_COMP_WAIT
+    
+    The specifications of BR_COMP_WAIT, EU_COMP_WAIT, FL_COMP_WAIT,
+    and LD_COMP_WAIT can be found in the "14.4. Cycle Accounting"
+    on A64FX_Microarchitecture_Manual_en_1.5.pdf at the following URL:.
+    https://github.com/fujitsu/A64FX/blob/master/doc
+    
+    Signed-off-by: Masahiko, Yamada <yamada.masahiko@fujitsu.com>
+
+diff --git a/src/papi_events.csv b/src/papi_events.csv
+index 74deb712f..1cd498e91 100644
+--- a/src/papi_events.csv
+++ b/src/papi_events.csv
+@@ -1935,6 +1935,10 @@ PRESET,PAPI_MEM_SCY,NOT_DERIVED,LD_COMP_WAIT_L2_MISS
+ PRESET,PAPI_STL_ICY,DERIVED_ADD,STALL_FRONTEND,STALL_BACKEND
+ PRESET,PAPI_STL_CCY,NOT_DERIVED,0INST_COMMIT
+ PRESET,PAPI_FUL_CCY,DERIVED_SUB,CPU_CYCLES,0INST_COMMIT,1INST_COMMIT,2INST_COMMIT,3INST_COMMIT
+PRESET,PAPI_BRU_IDL,NOT_DERIVED,BR_COMP_WAIT
+PRESET,PAPI_FXU_IDL,DERIVED_SUB,EU_COMP_WAIT,FL_COMP_WAIT
+PRESET,PAPI_FPU_IDL,NOT_DERIVED,FL_COMP_WAIT
+PRESET,PAPI_LSU_IDL,NOT_DERIVED,LD_COMP_WAIT
+ PRESET,PAPI_HW_INT,DERIVED_ADD,EXC_IRQ,EXC_FIQ
+ PRESET,PAPI_BR_MSP,NOT_DERIVED,BR_MIS_PRED
+ PRESET,PAPI_BR_PRC,DERIVED_SUB,BR_PRED,BR_MIS_PRED
--- a/SOURCES/papi-rhbz2037426.patch
+++ b/SOURCES/papi-rhbz2037426.patch
@ -0,0 +1,42 @@
+commit b78d7665bc02a0ce17adc6c09ab052064a940937
+Author: Masahiko, Yamada <yamada.masahiko@fujitsu.com>
+Date:   Wed Dec 8 19:39:44 2021 +0900
+
+    Improve the papi_xml_event_info command.
+    
+    Modify the papi_xml_event_info command as follows:.
+    - Test only the event name even if the event has a unit mask.
+    - Test other unit masks in the event even if
+      there is an error in one unit mask in the event.
+    
+    Signed-off-by: Masahiko, Yamada <yamada.masahiko@fujitsu.com>
+
+diff --git a/src/utils/papi_xml_event_info.c b/src/utils/papi_xml_event_info.c
+index 2a777a9fe..c024cc036 100644
+--- a/src/utils/papi_xml_event_info.c
+++ b/src/utils/papi_xml_event_info.c
+@@ -226,9 +226,6 @@ enum_native_events( FILE * f, int cidx)
+ 	   k = i;
+ 	   if ( PAPI_enum_cmp_event( &k, PAPI_NTV_ENUM_UMASKS, cidx ) == PAPI_OK ) {
+ 
+-	      /* Test if event can be added */
+-	      if ( test_event( k ) == PAPI_OK ) {
+-
+ 		 /* add the event */
+ 		 xmlize_event( f, &info, num );
+ 
+@@ -237,13 +234,12 @@ enum_native_events( FILE * f, int cidx)
+ 		    retval = PAPI_get_event_info( k, &info );
+ 		    if ( retval == PAPI_OK ) {
+ 		       if ( test_event( k )!=PAPI_OK ) {
+-			   break;
+			   continue;
+ 		       }
+ 		       xmlize_event( f, &info, -1 );
+ 		    }
+ 		 } while ( PAPI_enum_cmp_event( &k, PAPI_NTV_ENUM_UMASKS, cidx ) == PAPI_OK);
+ 		 fprintf( f, "    </event>\n" );
+-	      }
+ 	   } else {
+               /* this event has no unit masks; test & write the event */
+ 	      if ( test_event( i ) == PAPI_OK ) {
--- a/SOURCES/papi-rhbz2037427.patch
+++ b/SOURCES/papi-rhbz2037427.patch
@ -0,0 +1,140 @@
+commit 2098e8656156084104ab8d1981b53c50d22b8f62
+Author: Masahiko, Yamada <yamada.masahiko@fujitsu.com>
+Date:   Fri Mar 4 13:34:20 2022 +0900
+
+    PAPI_get_hardware_info: improve PAPI_hw_info_t for ARM processors
+    
+    Currently, it is not possible to determine which company the ARM processor
+    was designed by from the PAPI_hw_info_t available in PAPI_get_hardware_info().
+    On ARM processors, the PAPI_hw_info_t obtained with PAPI_get_hardware_info()
+    does not contain information indicating which company was designed.
+    For ARM processors, improve the vendor and vendor_string entries
+    in PAPI_hw_info_t, which can be retrieved with PAPI_get_hardware_info(),
+    to include information indicating which company was designed.
+    
+    Signed-off-by: Masahiko, Yamada <yamada.masahiko@fujitsu.com>
+
+diff --git a/src/components/perf_event/pe_libpfm4_events.c b/src/components/perf_event/pe_libpfm4_events.c
+index 744851ff0..6dcb5e023 100644
+--- a/src/components/perf_event/pe_libpfm4_events.c
+++ b/src/components/perf_event/pe_libpfm4_events.c
+@@ -1248,8 +1248,10 @@ _pe_libpfm4_init(papi_vector_t *component, int cidx,
+ 						    &pinfo,sizeof(pfm_pmu_info_t));
+                         found_default++;
+ 				}
+
+				/* For ARM processors, */
+ 				if ( (pinfo.type==PFM_PMU_TYPE_CORE) &&
+-					( _papi_hwi_system_info.hw_info.vendor == PAPI_VENDOR_ARM)) {
+					( _papi_hwi_system_info.hw_info.vendor >= PAPI_VENDOR_ARM_ARM)) {
+ 					if (strlen(_papi_hwi_system_info.hw_info.model_string) == 0) {
+ 						strSize = sizeof(_papi_hwi_system_info.hw_info.model_string);
+ 						strncpy( _papi_hwi_system_info.hw_info.model_string, pinfo.desc, strSize - 1);
+diff --git a/src/components/perf_event/perf_event.c b/src/components/perf_event/perf_event.c
+index a50194cf6..6985fc4cb 100644
+--- a/src/components/perf_event/perf_event.c
+++ b/src/components/perf_event/perf_event.c
+@@ -137,7 +137,8 @@ pe_vendor_fixups(papi_vector_t *vector)
+   }
+ 
+ 	/* ARM */
+-	if ( _papi_hwi_system_info.hw_info.vendor == PAPI_VENDOR_ARM) {
+	/* If implementer is ARM Limited. */
+	if ( _papi_hwi_system_info.hw_info.vendor == PAPI_VENDOR_ARM_ARM) {
+ 
+ 		/* Some ARMv7 and earlier could not measure	*/
+ 		/* KERNEL and USER separately.			*/
+diff --git a/src/linux-common.c b/src/linux-common.c
+index 99601db86..2527981ad 100644
+--- a/src/linux-common.c
+++ b/src/linux-common.c
+@@ -112,8 +112,20 @@ decode_vendor_string( char *s, int *vendor )
+ 		*vendor = PAPI_VENDOR_IBM;
+ 	else if ( strcasecmp( s, "Cray" ) == 0 )
+ 		*vendor = PAPI_VENDOR_CRAY;
+-	else if ( strcasecmp( s, "ARM" ) == 0 )
+-		*vendor = PAPI_VENDOR_ARM;
+	else if ( strcasecmp( s, "ARM_ARM" ) == 0 )
+		*vendor = PAPI_VENDOR_ARM_ARM;
+	else if ( strcasecmp( s, "ARM_BROADCOM" ) == 0 )
+		*vendor = PAPI_VENDOR_ARM_BROADCOM;
+	else if ( strcasecmp( s, "ARM_CAVIUM" ) == 0 )
+		*vendor = PAPI_VENDOR_ARM_CAVIUM;
+	else if ( strcasecmp( s, "ARM_FUJITSU" ) == 0 )
+		*vendor = PAPI_VENDOR_ARM_FUJITSU;
+	else if ( strcasecmp( s, "ARM_HISILICON") == 0 )
+		*vendor = PAPI_VENDOR_ARM_HISILICON;
+	else if ( strcasecmp( s, "ARM_APM" ) == 0 )
+		*vendor = PAPI_VENDOR_ARM_APM;
+	else if ( strcasecmp( s, "ARM_QUALCOMM" ) == 0 )
+		*vendor = PAPI_VENDOR_ARM_QUALCOMM;
+ 	else if ( strcasecmp( s, "MIPS" ) == 0 )
+ 		*vendor = PAPI_VENDOR_MIPS;
+ 	else if ( strcasecmp( s, "SiCortex" ) == 0 )
+@@ -409,9 +421,38 @@ _linux_get_cpu_info( PAPI_hw_info_t *hwinfo, int *cpuinfo_mhz )
+ 				}
+ 				else {
+ 					/* "CPU implementer" indicates ARM */
+					/* For ARM processors, hwinfo->vendor >= PAPI_VENDOR_ARM_ARM(0x41). */
+					/* If implementer is ARM Limited., hwinfo->vendor == PAPI_VENDOR_ARM_ARM. */
+					/* If implementer is Cavium Inc., hwinfo->vendor == PAPI_VENDOR_ARM_CAVIUM(0x43). */
+ 					s = search_cpu_info( f, "CPU implementer");
+ 					if ( s ) {
+-						strcpy( hwinfo->vendor_string, "ARM" );
+						int tmp;
+						sscanf( s, "%x", &tmp );
+						switch( tmp ) {
+						case PAPI_VENDOR_ARM_ARM:
+							strcpy( hwinfo->vendor_string, "ARM_ARM" );
+							break;
+						case PAPI_VENDOR_ARM_BROADCOM:
+							strcpy( hwinfo->vendor_string, "ARM_BROADCOM" );
+							break;
+						case PAPI_VENDOR_ARM_CAVIUM:
+							strcpy( hwinfo->vendor_string, "ARM_CAVIUM" );
+							break;
+						case PAPI_VENDOR_ARM_FUJITSU:
+							strcpy( hwinfo->vendor_string, "ARM_FUJITSU" );
+							break;
+						case PAPI_VENDOR_ARM_HISILICON:
+							strcpy( hwinfo->vendor_string, "ARM_HISILICON" );
+							break;
+						case PAPI_VENDOR_ARM_APM:
+							strcpy( hwinfo->vendor_string, "ARM_APM" );
+							break;
+						case PAPI_VENDOR_ARM_QUALCOMM:
+							strcpy( hwinfo->vendor_string, "ARM_QUALCOMM" );
+							break;
+						default:
+							strcpy( hwinfo->vendor_string, "ARM_UNKNOWN" );
+						}
+ 					}
+ 				}
+ 			}
+@@ -438,7 +479,7 @@ _linux_get_cpu_info( PAPI_hw_info_t *hwinfo, int *cpuinfo_mhz )
+ 		decode_cpuinfo_power(f,hwinfo);
+ 	}
+ 
+-	if (hwinfo->vendor==PAPI_VENDOR_ARM) {
+	if (hwinfo->vendor>=PAPI_VENDOR_ARM_ARM) {
+ 
+ 		decode_cpuinfo_arm(f,hwinfo);
+ 	}
+diff --git a/src/papi.h b/src/papi.h
+index 14b05da1f..b05b368cb 100644
+--- a/src/papi.h
+++ b/src/papi.h
+@@ -354,6 +354,13 @@ All of the functions in the PerfAPI should use the following set of constants.
+ #define PAPI_VENDOR_FREESCALE 6
+ #define PAPI_VENDOR_ARM     7
+ #define PAPI_VENDOR_MIPS    8
+#define PAPI_VENDOR_ARM_ARM       0x41
+#define PAPI_VENDOR_ARM_BROADCOM  0x42
+#define PAPI_VENDOR_ARM_CAVIUM    0x43
+#define PAPI_VENDOR_ARM_FUJITSU   0x46
+#define PAPI_VENDOR_ARM_HISILICON 0x48
+#define PAPI_VENDOR_ARM_APM       0x50
+#define PAPI_VENDOR_ARM_QUALCOMM  0x51
+ /** @} */
+ 
+ /** @internal 
--- a/SOURCES/papi-thread_init.patch
+++ b/SOURCES/papi-thread_init.patch
@ -0,0 +1,139 @@
+commit 617eeabe0bbfb5357c10b22ebd72b24a4a872e52
+Author: Anthony <adanalis@icl.utk.edu>
+Date:   Mon Jan 6 15:09:42 2020 -0500
+
+    Updated the variables that are used in the debug messages in accordance to a previous commit that made these variables thread safe.
+
+diff --git a/src/papi_internal.c b/src/papi_internal.c
+index f0e457bf7..69b2914d0 100644
+--- a/src/papi_internal.c
+++ b/src/papi_internal.c
+@@ -114,7 +114,7 @@ _papi_hwi_free_papi_event_string() {
+ 
+ void
+ _papi_hwi_set_papi_event_code (unsigned int event_code, int update_flag) {
+-	INTDBG("new event_code: %#x, update_flag: %d, previous event_code: %#x\n", event_code, update_flag, papi_event_code);
+	INTDBG("new event_code: %#x, update_flag: %d, previous event_code: %#x\n", event_code, update_flag, _papi_hwi_my_thread->tls_papi_event_code);
+ 
+ 	// if call is just to reset and start over, set both flags to show nothing saved yet
+ 	if (update_flag < 0) {
+@@ -131,7 +131,7 @@ _papi_hwi_set_papi_event_code (unsigned int event_code, int update_flag) {
+ }
+ unsigned int
+ _papi_hwi_get_papi_event_code () {
+-	INTDBG("papi_event_code: %#x\n", papi_event_code);
+	INTDBG("papi_event_code: %#x\n", _papi_hwi_my_thread->tls_papi_event_code);
+ 	return _papi_hwi_my_thread->tls_papi_event_code;
+ }
+ /* Get the index into the ESI->NativeInfoArray for the current PAPI event code */
+From 3cc3b6679e1ace7516c3037105ad16410ce7d3db Mon Sep 17 00:00:00 2001
+From: William Cohen <wcohen@redhat.com>
+Date: Wed, 12 Aug 2020 10:12:59 -0400
+Subject: [PATCH] Initialize component globals before threads globals
+
+An earlier commit (979e80136) swapped the order of initializing
+globals and threads.  This caused issues with the perf_event, appio,
+and stealtime components which could be observed with the
+all_native_events, appio_test_pthreads, and stealtime_basic tests
+respectively.  The component initialization needs to be performed
+before the thread initialization.
+
+The order of initialization has been changed back to initializing the
+component then the threads.  One complication is that papi_internal.c
+had functions (_papi_hwi_set_papi_event_code and
+_papi_hwi_get_papi_event_code) that required thread local storage that
+was being setup in commit 979e80136 by the thread initialization.
+This was the original reason for swapping the order of initialization
+of component and thread.  Using __thread on the file scope
+declarations of the variables allow the original order of
+initialization.
+---
+ src/papi.c          | 10 +++++-----
+ src/papi_internal.c | 21 +++++++++++++--------
+ 2 files changed, 18 insertions(+), 13 deletions(-)
+
+diff --git a/src/papi.c b/src/papi.c
+index 33cc29935..107a15044 100644
+--- a/src/papi.c
+++ b/src/papi.c
+@@ -1151,19 +1151,19 @@ PAPI_library_init( int version )
+ 	   papi_return( init_retval );
+ 	}
+ 
+-	/* Initialize thread globals, including the main threads  */
+	/* Initialize component globals */
+ 
+-	tmp = _papi_hwi_init_global_threads(  );
+	tmp = _papi_hwi_init_global(  );
+ 	if ( tmp ) {
+ 		init_retval = tmp;
+ 		_papi_hwi_shutdown_global_internal(  );
+-   	_in_papi_library_init_cnt--;
+		_in_papi_library_init_cnt--;
+ 		papi_return( init_retval );
+ 	}
+ 
+-	/* Initialize component globals */
+	/* Initialize thread globals, including the main threads  */
+ 
+-	tmp = _papi_hwi_init_global(  );
+	tmp = _papi_hwi_init_global_threads(  );
+ 	if ( tmp ) {
+ 		init_retval = tmp;
+ 		_papi_hwi_shutdown_global_internal(  );
+diff --git a/src/papi_internal.c b/src/papi_internal.c
+index 5a1ccd433..bdf30f875 100644
+--- a/src/papi_internal.c
+++ b/src/papi_internal.c
+@@ -115,27 +115,32 @@ _papi_hwi_free_papi_event_string() {
+ 	return;
+ }
+ 
+// A place to keep the current papi event code so some component functions can fetch its value
+// The current event code can be stored here prior to component calls and cleared after the component returns
+static THREAD_LOCAL_STORAGE_KEYWORD unsigned int papi_event_code = -1;
+static THREAD_LOCAL_STORAGE_KEYWORD int papi_event_code_changed = -1;
+
+ void
+ _papi_hwi_set_papi_event_code (unsigned int event_code, int update_flag) {
+-	INTDBG("new event_code: %#x, update_flag: %d, previous event_code: %#x\n", event_code, update_flag, _papi_hwi_my_thread->tls_papi_event_code);
+	INTDBG("new event_code: %#x, update_flag: %d, previous event_code: %#x\n", event_code, update_flag, papi_event_code);
+ 
+ 	// if call is just to reset and start over, set both flags to show nothing saved yet
+ 	if (update_flag < 0) {
+-		_papi_hwi_my_thread->tls_papi_event_code_changed = -1;
+-		_papi_hwi_my_thread->tls_papi_event_code = -1;
+		papi_event_code_changed = -1;
+		papi_event_code = -1;
+ 		return;
+ 	}
+ 
+ 	// if 0, it is being set prior to calling a component, if >0 it is being changed by the component
+-	_papi_hwi_my_thread->tls_papi_event_code_changed = update_flag;
+	papi_event_code_changed = update_flag;
+ 	// save the event code passed in
+-	_papi_hwi_my_thread->tls_papi_event_code = event_code;
+	papi_event_code = event_code;
+ 	return;
+ }
+ unsigned int
+ _papi_hwi_get_papi_event_code () {
+-	INTDBG("papi_event_code: %#x\n", _papi_hwi_my_thread->tls_papi_event_code);
+-	return _papi_hwi_my_thread->tls_papi_event_code;
+	INTDBG("papi_event_code: %#x\n", papi_event_code);
+	return papi_event_code;
+ }
+ /* Get the index into the ESI->NativeInfoArray for the current PAPI event code */
+ int
+@@ -560,7 +565,7 @@ _papi_hwi_native_to_eventcode(int cidx, int event_code, int ntv_idx, const char
+ 
+   int result;
+ 
+-  if (_papi_hwi_my_thread->tls_papi_event_code_changed > 0) {
+  if (papi_event_code_changed > 0) {
+ 	  result = _papi_hwi_get_papi_event_code();
+ 	  INTDBG("EXIT: papi_event_code: %#x set by the component\n", result);
+ 	  return result;
+-- 
+2.26.2
+
--- a/SOURCES/papi-zen.patch
+++ b/SOURCES/papi-zen.patch
@ -0,0 +1,302 @@
+commit 20890adcb59a1c1648cb70be65332c03a3781e1a
+Author: Anthony Castaldo <TonyCastaldo@icl.utk.edu>
+Date:   Thu Jan 16 16:43:51 2020 -0500
+
+    Added two machine types to papi_events.csv to be in line with
+    libpfm4 update to support amd64_fam17h_zen1 and zen2.
+
+diff --git a/src/papi_events.csv b/src/papi_events.csv
+index 97446ad2c..8e96adfbd 100644
+--- a/src/papi_events.csv
+++ b/src/papi_events.csv
+@@ -396,6 +396,8 @@ PRESET,PAPI_FSQ_INS,NOT_DERIVED,RETIRED_SSE_AVX_OPERATIONS:SINGLE_DIV_OPS:DOUBLE
+ #
+ #
+ CPU,amd64_fam17h
+CPU,amd64_fam17h_zen1
+CPU,amd64_fam17h_zen2
+ #
+ PRESET,PAPI_TOT_INS,NOT_DERIVED,RETIRED_INSTRUCTIONS
+ PRESET,PAPI_TOT_CYC,NOT_DERIVED,CYCLES_NOT_IN_HALT
+
+commit ae449f73abd0849f05ab3e1f3a64bde0c670c645
+Author: Anthony <adanalis@icl.utk.edu>
+Date:   Fri Jul 17 12:05:14 2020 -0400
+
+    Separated the cache preset events of AMD Zen1 and Zen2 and added some more.
+
+diff --git a/src/papi_events.csv b/src/papi_events.csv
+index 8e96adfbd..2325bd4dc 100644
+--- a/src/papi_events.csv
+++ b/src/papi_events.csv
+@@ -397,7 +397,6 @@ PRESET,PAPI_FSQ_INS,NOT_DERIVED,RETIRED_SSE_AVX_OPERATIONS:SINGLE_DIV_OPS:DOUBLE
+ #
+ CPU,amd64_fam17h
+ CPU,amd64_fam17h_zen1
+-CPU,amd64_fam17h_zen2
+ #
+ PRESET,PAPI_TOT_INS,NOT_DERIVED,RETIRED_INSTRUCTIONS
+ PRESET,PAPI_TOT_CYC,NOT_DERIVED,CYCLES_NOT_IN_HALT
+@@ -434,6 +433,27 @@ PRESET,PAPI_FML_INS,NOT_DERIVED,RETIRED_SSE_AVX_OPERATIONS:SP_MULT_FLOPS:DP_MULT
+ PRESET,PAPI_FAD_INS,NOT_DERIVED,RETIRED_SSE_AVX_OPERATIONS:SP_ADD_SUB_FLOPS:DP_ADD_SUB_FLOPS
+ PRESET,PAPI_FDV_INS,NOT_DERIVED,RETIRED_SSE_AVX_OPERATIONS:SP_DIV_FLOPS:DP_DIV_FLOPS,NOTE,"Counts both divide and square root instructions"
+ PRESET,PAPI_FSQ_INS,NOT_DERIVED,RETIRED_SSE_AVX_OPERATIONS:SP_DIV_FLOPS:DP_DIV_FLOPS,NOTE,"Counts both divide and square root instructions"
+# Events discovered via CAT
+PRESET,PAPI_L2_DCM,NOT_DERIVED,CORE_TO_L2_CACHEABLE_REQUEST_ACCESS_STATUS:LS_RD_BLK_C
+PRESET,PAPI_L2_DCR,NOT_DERIVED,REQUESTS_TO_L2_GROUP1:RD_BLK_L
+PRESET,PAPI_L2_DCH,NOT_DERIVED,CORE_TO_L2_CACHEABLE_REQUEST_ACCESS_STATUS:LS_RD_BLK_L_HIT_X
+#
+#
+CPU,amd64_fam17h_zen2
+# Events copied from zen1 that also exist on zen2
+PRESET,PAPI_TLB_DM,NOT_DERIVED,L1_DTLB_MISS:TLB_RELOAD_1G_L2_MISS:TLB_RELOAD_2M_L2_MISS:TLB_RELOAD_COALESCED_PAGE_MISS:TLB_RELOAD_4K_L2_MISS:TLB_RELOAD_1G_L2_HIT:TLB_RELOAD_2M_L2_HIT:TLB_RELOAD_COALESCED_PAGE_HIT:TLB_RELOAD_4K_L2_HIT
+PRESET,PAPI_TLB_IM,DERIVED_ADD,L1_ITLB_MISS_L2_ITLB_HIT,L1_ITLB_MISS_L2_ITLB_MISS:IF1G:IF2M:IF4K
+PRESET,PAPI_BR_TKN,NOT_DERIVED,RETIRED_TAKEN_BRANCH_INSTRUCTIONS
+PRESET,PAPI_BR_MSP,NOT_DERIVED,RETIRED_BRANCH_INSTRUCTIONS_MISPREDICTED
+PRESET,PAPI_TOT_INS,NOT_DERIVED,RETIRED_INSTRUCTIONS
+PRESET,PAPI_BR_INS,NOT_DERIVED,RETIRED_BRANCH_INSTRUCTIONS
+PRESET,PAPI_TOT_CYC,NOT_DERIVED,CYCLES_NOT_IN_HALT
+# Events discovered via CAT
+PRESET,PAPI_L1_DCA,NOT_DERIVED,perf::PERF_COUNT_HW_CACHE_L1D:ACCESS
+PRESET,PAPI_L2_DCM,NOT_DERIVED,CORE_TO_L2_CACHEABLE_REQUEST_ACCESS_STATUS:LS_RD_BLK_C
+PRESET,PAPI_L2_DCR,NOT_DERIVED,REQUESTS_TO_L2_GROUP1:RD_BLK_L
+PRESET,PAPI_L2_DCH,NOT_DERIVED,CORE_TO_L2_CACHEABLE_REQUEST_ACCESS_STATUS:LS_RD_BLK_L_HIT_X
+
+ #
+ #
+ CPU,Intel architectural PMU
+commit ccc22b5dda46fea8933d99950c3e30b5298cdd1d
+Author: Heike Jagode <jagode@icl.utk.edu>
+Date:   Thu Sep 24 13:33:38 2020 -0400
+
+    Added presets for floating-point operations (FP_OPS, DP_OPS, SP_OPS)
+    for AMD zen2.
+    
+    PPR (under section 2.1.15.3. -- https://www.amd.com/system/files/TechDocs/54945_3.03_ppr_ZP_B2_pub.zip)
+    explains that FLOP events require MergeEvent support, which was included
+    in the 5.6 kernel.
+    
+    ===>>> Hence, a kernel version 5.6 or greater is required.
+    
+    NOTE: without the MergeEvent support in the kernel,
+          there is no guarantee that the SSE/AVX FLOP
+          events produce any useful data whatsoever.
+    
+    These events have been tested and verified for
+    scalar flops, SSE, AVX, and FMA:
+    
+    (1) for one AVX instruction (e.g. _mm256_add_pd()),
+        the RETIRED_SSE_AVX_FLOPS:ADD_SUB_FLOPS event returns
+        a count of 4 (in the case of double precision), and
+        a count of 8 (in the case of single precision).
+    
+    (2) for one AVX FMA instruction (e.g. _mm256_macc_pd()),
+        the RETIRED_SSE_AVX_FLOPS:MAC_FLOPS event returns
+        a count of 8 (in the case of double precision), and
+        a count of 16 (in the case of single precision).
+    
+    (3) for one SSE instruction (e.g. _mm_mul_pd()),
+        the RETIRED_SSE_AVX_FLOPS:MULT_FLOPS event returns
+        a count of 2 (in the case of double precision), and
+        a count of 4 (in the case of single precision).
+
+diff --git a/src/papi_events.csv b/src/papi_events.csv
+index 2325bd4dc..2ff3e4d16 100644
+--- a/src/papi_events.csv
+++ b/src/papi_events.csv
+@@ -454,8 +454,19 @@ PRESET,PAPI_L2_DCM,NOT_DERIVED,CORE_TO_L2_CACHEABLE_REQUEST_ACCESS_STATUS:LS_RD_
+ PRESET,PAPI_L2_DCR,NOT_DERIVED,REQUESTS_TO_L2_GROUP1:RD_BLK_L
+ PRESET,PAPI_L2_DCH,NOT_DERIVED,CORE_TO_L2_CACHEABLE_REQUEST_ACCESS_STATUS:LS_RD_BLK_L_HIT_X
+ 
+-#
+-#
+# New FLOP event on zen2
+# PPR (under section 2.1.15.3. --
+# https://www.amd.com/system/files/TechDocs/54945_3.03_ppr_ZP_B2_pub.zip)
+# explains that FLOP events require MergeEvent support, which was included 
+# in the 5.6 kernel. 
+# Hence, a kernel version 5.6 or greater is required.
+# NOTE: without the MergeEvent support in the kernel, there is no guarantee
+# that this SSE/AVX FLOP event produces any useful data whatsoever.  
+PRESET,PAPI_FP_OPS,NOT_DERIVED,RETIRED_SSE_AVX_FLOPS:ANY
+PRESET,PAPI_DP_OPS,NOT_DERIVED,RETIRED_SSE_AVX_FLOPS:ANY
+PRESET,PAPI_SP_OPS,NOT_DERIVED,RETIRED_SSE_AVX_FLOPS:ANY
+
+
+ CPU,Intel architectural PMU
+ CPU,ix86arch
+ #
+
+commit 35f93252a6e222299c03f2c94912334488e76b02
+Author: Heike Jagode <jagode@icl.utk.edu>
+Date:   Thu Sep 24 18:40:59 2020 -0400
+
+    Added presets for floating-point instructions (FP_INS, VEC_DP, VEC_SP)
+    for AMD zen2.
+    
+    For unoptimized code (like native MMM), these events may include
+    non-numeric floating-point instructions, e.g. MOVSD: move or merge
+    scalar double-precision floating-point value instructions.
+    
+    Tested with:
+    1) SSE double: _mm_mul_pd / _mm_add_pd
+    2) SSE single: _mm_mul_ps / _mm_add_ps
+    3) AVX double: _mm256_mul_pd / _mm256_add_pd
+    4) AVX single: _mm256_mul_ps / _mm256_add_ps
+    5) FMA double: _mm256_macc_pd
+    6) FMA single: _mm256_macc_pd
+
+diff --git a/src/papi_events.csv b/src/papi_events.csv
+index 2ff3e4d16..60a64564d 100644
+--- a/src/papi_events.csv
+++ b/src/papi_events.csv
+@@ -465,6 +465,11 @@ PRESET,PAPI_L2_DCH,NOT_DERIVED,CORE_TO_L2_CACHEABLE_REQUEST_ACCESS_STATUS:LS_RD_
+ PRESET,PAPI_FP_OPS,NOT_DERIVED,RETIRED_SSE_AVX_FLOPS:ANY
+ PRESET,PAPI_DP_OPS,NOT_DERIVED,RETIRED_SSE_AVX_FLOPS:ANY
+ PRESET,PAPI_SP_OPS,NOT_DERIVED,RETIRED_SSE_AVX_FLOPS:ANY
+# Floating-point instructions (including non-numeric floating-point instructions,
+# e.g. Move or Merge Scalar Double-Precision Floating-Point values)
+PAPI_FP_INS,NOT_DERIVED,RETIRED_MMX_FP_INSTRUCTIONS:SSE_INSTR:MMX_INSTR:X87_INSTR
+PAPI_VEC_DP,NOT_DERIVED,RETIRED_MMX_FP_INSTRUCTIONS:SSE_INSTR:MMX_INSTR:X87_INSTR
+PAPI_VEC_SP,NOT_DERIVED,RETIRED_MMX_FP_INSTRUCTIONS:SSE_INSTR:MMX_INSTR:X87_INSTR
+ 
+ 
+ CPU,Intel architectural PMU
+
+commit 344f6493425d865577508ff32b6f65516b1b4394
+Author: Heike Jagode <jagode@icl.utk.edu>
+Date:   Thu Sep 24 19:03:31 2020 -0400
+
+    Added missing 'PRESET' to csv file.
+
+diff --git a/src/papi_events.csv b/src/papi_events.csv
+index 60a64564d..724d520f0 100644
+--- a/src/papi_events.csv
+++ b/src/papi_events.csv
+@@ -467,9 +467,9 @@ PRESET,PAPI_DP_OPS,NOT_DERIVED,RETIRED_SSE_AVX_FLOPS:ANY
+ PRESET,PAPI_SP_OPS,NOT_DERIVED,RETIRED_SSE_AVX_FLOPS:ANY
+ # Floating-point instructions (including non-numeric floating-point instructions,
+ # e.g. Move or Merge Scalar Double-Precision Floating-Point values)
+-PAPI_FP_INS,NOT_DERIVED,RETIRED_MMX_FP_INSTRUCTIONS:SSE_INSTR:MMX_INSTR:X87_INSTR
+-PAPI_VEC_DP,NOT_DERIVED,RETIRED_MMX_FP_INSTRUCTIONS:SSE_INSTR:MMX_INSTR:X87_INSTR
+-PAPI_VEC_SP,NOT_DERIVED,RETIRED_MMX_FP_INSTRUCTIONS:SSE_INSTR:MMX_INSTR:X87_INSTR
+PRESET,PAPI_FP_INS,NOT_DERIVED,RETIRED_MMX_FP_INSTRUCTIONS:SSE_INSTR:MMX_INSTR:X87_INSTR
+PRESET,PAPI_VEC_DP,NOT_DERIVED,RETIRED_MMX_FP_INSTRUCTIONS:SSE_INSTR:MMX_INSTR:X87_INSTR
+PRESET,PAPI_VEC_SP,NOT_DERIVED,RETIRED_MMX_FP_INSTRUCTIONS:SSE_INSTR:MMX_INSTR:X87_INSTR
+ 
+ 
+ CPU,Intel architectural PMU
+
+commit 4616aa717c5301a9a478876661eb8ac1f18c0333
+Author: Heike Jagode <jagode@icl.utk.edu>
+Date:   Thu Oct 8 11:36:23 2020 -0400
+
+    For zen2, since FP_OPS counts both single- and double-prec operations
+    correctly, we don't need to confuse the user with additional
+    DP_OPS and SP_OPS events. So, I'm taking them out.
+    
+    Same applies for events counting FP instructions.
+
+diff --git a/src/papi_events.csv b/src/papi_events.csv
+index 724d520f0..9ebf557e1 100644
+--- a/src/papi_events.csv
+++ b/src/papi_events.csv
+@@ -463,13 +463,20 @@ PRESET,PAPI_L2_DCH,NOT_DERIVED,CORE_TO_L2_CACHEABLE_REQUEST_ACCESS_STATUS:LS_RD_
+ # NOTE: without the MergeEvent support in the kernel, there is no guarantee
+ # that this SSE/AVX FLOP event produces any useful data whatsoever.  
+ PRESET,PAPI_FP_OPS,NOT_DERIVED,RETIRED_SSE_AVX_FLOPS:ANY
+-PRESET,PAPI_DP_OPS,NOT_DERIVED,RETIRED_SSE_AVX_FLOPS:ANY
+-PRESET,PAPI_SP_OPS,NOT_DERIVED,RETIRED_SSE_AVX_FLOPS:ANY
+# Since FP_OPS counts both single- and double-prec operations
+# correctly, we don't need to confuse the user with additional
+# DP_OPS and SP_OPS events. So, I'm taking them out.  
+#PRESET,PAPI_DP_OPS,NOT_DERIVED,RETIRED_SSE_AVX_FLOPS:ANY
+#PRESET,PAPI_SP_OPS,NOT_DERIVED,RETIRED_SSE_AVX_FLOPS:ANY
+#
+ # Floating-point instructions (including non-numeric floating-point instructions,
+ # e.g. Move or Merge Scalar Double-Precision Floating-Point values)
+ PRESET,PAPI_FP_INS,NOT_DERIVED,RETIRED_MMX_FP_INSTRUCTIONS:SSE_INSTR:MMX_INSTR:X87_INSTR
+-PRESET,PAPI_VEC_DP,NOT_DERIVED,RETIRED_MMX_FP_INSTRUCTIONS:SSE_INSTR:MMX_INSTR:X87_INSTR
+-PRESET,PAPI_VEC_SP,NOT_DERIVED,RETIRED_MMX_FP_INSTRUCTIONS:SSE_INSTR:MMX_INSTR:X87_INSTR
+# Since FP_INS counts both single- and double-prec instuctions
+# correctly, we don't need to confuse the user with additional
+# VEC_DP and VEC_SP events. So, I'm taking them out.  
+#PRESET,PAPI_VEC_DP,NOT_DERIVED,RETIRED_MMX_FP_INSTRUCTIONS:SSE_INSTR:MMX_INSTR:X87_INSTR
+#PRESET,PAPI_VEC_SP,NOT_DERIVED,RETIRED_MMX_FP_INSTRUCTIONS:SSE_INSTR:MMX_INSTR:X87_INSTR
+ 
+ 
+ CPU,Intel architectural PMU
+
+commit 274219e85ba8adcd2e9c78507adf7edb05b71daa
+Author: Sebastian Mobo <smobo@vols.utk.edu>
+Date:   Thu Oct 8 13:40:21 2020 -0400
+
+    Added instruction-cache preset events for the Zen2.
+    
+    Signed-off-by: Anthony <adanalis@icl.utk.edu>
+
+diff --git a/src/papi_events.csv b/src/papi_events.csv
+index 9ebf557e1..fd75f9371 100644
+--- a/src/papi_events.csv
+++ b/src/papi_events.csv
+@@ -453,7 +453,12 @@ PRESET,PAPI_L1_DCA,NOT_DERIVED,perf::PERF_COUNT_HW_CACHE_L1D:ACCESS
+ PRESET,PAPI_L2_DCM,NOT_DERIVED,CORE_TO_L2_CACHEABLE_REQUEST_ACCESS_STATUS:LS_RD_BLK_C
+ PRESET,PAPI_L2_DCR,NOT_DERIVED,REQUESTS_TO_L2_GROUP1:RD_BLK_L
+ PRESET,PAPI_L2_DCH,NOT_DERIVED,CORE_TO_L2_CACHEABLE_REQUEST_ACCESS_STATUS:LS_RD_BLK_L_HIT_X
+-
+#
+PRESET,PAPI_L1_ICM,NOT_DERIVED,REQUESTS_TO_L2_GROUP1:CACHEABLE_IC_READ
+#
+PRESET,PAPI_L2_ICR,NOT_DERIVED,REQUESTS_TO_L2_GROUP1:CACHEABLE_IC_READ
+PRESET,PAPI_L2_ICM,NOT_DERIVED,CORE_TO_L2_CACHEABLE_REQUEST_ACCESS_STATUS:IC_FILL_MISS
+PRESET,PAPI_L2_ICH,NOT_DERIVED,CORE_TO_L2_CACHEABLE_REQUEST_ACCESS_STATUS:IC_FILL_HIT_X:IC_FILL_HIT_S
+ # New FLOP event on zen2
+ # PPR (under section 2.1.15.3. --
+ # https://www.amd.com/system/files/TechDocs/54945_3.03_ppr_ZP_B2_pub.zip)
+
+commit 02f34baafb868d183f21bebfd3c46574847b9929
+Author: Swarup Sahoo <swarup-chandra.sahoo@amd.com>
+Date:   Tue May 18 02:51:56 2021 +0530
+
+    Added AMD Zen3 preset events. Refer section 2.1.17.2 of PPR for AMD family 19h model 01h, https://www.amd.com/system/files/TechDocs/55898_pub.zip
+    
+    Signed-off-by: Swarup Sahoo <swarup-chandra.sahoo@amd.com>
+
+diff --git a/src/papi_events.csv b/src/papi_events.csv
+index 4ef647959..d9e9da8a3 100644
+--- a/src/papi_events.csv
+++ b/src/papi_events.csv
+@@ -482,6 +482,33 @@ PRESET,PAPI_FP_INS,NOT_DERIVED,RETIRED_MMX_FP_INSTRUCTIONS:SSE_INSTR:MMX_INSTR:X
+ # VEC_DP and VEC_SP events. So, I'm taking them out.  
+ #PRESET,PAPI_VEC_DP,NOT_DERIVED,RETIRED_MMX_FP_INSTRUCTIONS:SSE_INSTR:MMX_INSTR:X87_INSTR
+ #PRESET,PAPI_VEC_SP,NOT_DERIVED,RETIRED_MMX_FP_INSTRUCTIONS:SSE_INSTR:MMX_INSTR:X87_INSTR
+#
+#
+CPU,amd64_fam19h_zen3
+PRESET,PAPI_TOT_INS,NOT_DERIVED,RETIRED_INSTRUCTIONS
+PRESET,PAPI_TOT_CYC,NOT_DERIVED,CYCLES_NOT_IN_HALT
+PRESET,PAPI_BR_INS,NOT_DERIVED,RETIRED_BRANCH_INSTRUCTIONS
+PRESET,PAPI_BR_TKN,NOT_DERIVED,RETIRED_TAKEN_BRANCH_INSTRUCTIONS
+PRESET,PAPI_BR_MSP,NOT_DERIVED,RETIRED_BRANCH_INSTRUCTIONS_MISPREDICTED
+PRESET,PAPI_TLB_DM,NOT_DERIVED,	L1_DTLB_MISS:TLB_RELOAD_1G_L2_MISS:TLB_RELOAD_2M_L2_MISS:TLB_RELOAD_COALESCED_PAGE_MISS:TLB_RELOAD_4K_L2_MISS:TLB_RELOAD_1G_L2_HIT:TLB_RELOAD_2M_L2_HIT:TLB_RELOAD_COALESCED_PAGE_HIT:TLB_RELOAD_4K_L2_HIT
+PRESET,PAPI_TLB_IM,DERIVED_ADD,L1_ITLB_MISS_L2_ITLB_HIT,L1_ITLB_MISS_L2_ITLB_MISS:COALESCED4K:IF1G:IF2M:IF4K
+PRESET,PAPI_L1_DCA,NOT_DERIVED,LS_DISPATCH:LD_ST_DISPATCH:STORE_DISPATCH:LD_DISPATCH
+PRESET,PAPI_L1_DCM,NOT_DERIVED,REQUESTS_TO_L2_GROUP1:RD_BLK_L:RD_BLK_X:LS_RD_BLK_C_S:CHANGE_TO_X
+PRESET,PAPI_L2_DCM,NOT_DERIVED,CORE_TO_L2_CACHEABLE_REQUEST_ACCESS_STATUS:LS_RD_BLK_C
+PRESET,PAPI_L2_DCR,NOT_DERIVED,REQUESTS_TO_L2_GROUP1:RD_BLK_L:RD_BLK_X:LS_RD_BLK_C_S:CHANGE_TO_X
+PRESET,PAPI_L2_DCH,NOT_DERIVED,CORE_TO_L2_CACHEABLE_REQUEST_ACCESS_STATUS:LS_RD_BLK_C_S:LS_RD_BLK_L_HIT_X:LS_RD_BLK_L_HIT_S:LS_RD_BLK_X
+PRESET,PAPI_L2_ICR,NOT_DERIVED,REQUESTS_TO_L2_GROUP1:CACHEABLE_IC_READ
+PRESET,PAPI_L2_ICA,NOT_DERIVED,REQUESTS_TO_L2_GROUP1:CACHEABLE_IC_READ
+PRESET,PAPI_L2_ICM,NOT_DERIVED,CORE_TO_L2_CACHEABLE_REQUEST_ACCESS_STATUS:IC_FILL_MISS
+PRESET,PAPI_L2_ICH,NOT_DERIVED,CORE_TO_L2_CACHEABLE_REQUEST_ACCESS_STATUS:IC_FILL_HIT_X:IC_FILL_HIT_S
+# RETIRED_SSE_AVX_FLOPS requires MergeEvent support.
+PRESET,PAPI_VEC_INS,NOT_DERIVED,RETIRED_SSE_AVX_FLOPS:ANY
+PRESET,PAPI_FP_INS,NOT_DERIVED,RETIRED_SSE_AVX_FLOPS:ANY
+PRESET,PAPI_FP_OPS,NOT_DERIVED,RETIRED_SSE_AVX_FLOPS:ANY
+PRESET,PAPI_FML_INS,NOT_DERIVED,RETIRED_SSE_AVX_FLOPS:MULT_FLOPS
+PRESET,PAPI_FAD_INS,NOT_DERIVED,RETIRED_SSE_AVX_FLOPS:ADD_SUB_FLOPS
+PRESET,PAPI_FDV_INS,NOT_DERIVED,RETIRED_SSE_AVX_FLOPS:DIV_FLOPS
+PRESET,PAPI_FSQ_INS,NOT_DERIVED,RETIRED_SSE_AVX_FLOPS:DIV_FLOPS
+ 
+ 
+ CPU,Intel architectural PMU
--- a/SPECS/papi.spec
+++ b/SPECS/papi.spec
@ -1,5 +1,3 @@
-# Default to no static libraries
-%{!?with_static: %global with_static 0}
 %bcond_with bundled_libpfm
 # rdma is not available
 %ifarch %{arm}
@ -7,26 +5,26 @@
 %else
 %{!?with_rdma: %global with_rdma 1}
 %endif
-%{!?with_pcp: %global with_pcp 1}
 Summary: Performance Application Programming Interface
 Name: papi
-Version: 6.0.0
-Release: 11%{?dist}
+Version: 5.6.0
+Release: 16%{?dist}
 License: BSD
+Group: Development/System
 Requires: papi-libs = %{version}-%{release}
 URL: http://icl.cs.utk.edu/papi/
-# The upstream papi tar.gz file include iozone source code in it.
-# The license for iozone source code is not compatible, so it needs
-# to be eliminated from the srpm.
-# The iozone code has been removed from the upstream papi git repo
-# so when papi is rebased to a newer version it can be used as is.
-Source0: http://icl.cs.utk.edu/projects/papi/downloads/%{name}-%{version}-noiozone.tar.gz
-Patch1: papi-python3.patch
-Patch2: papi-a64fx.patch
-Patch4: papi-config.patch
-Patch5: papi-nostatic.patch
-Patch6: papi-lto.patch
-BuildRequires: make
+Source0: http://icl.cs.utk.edu/projects/papi/downloads/%{name}-%{version}.tar.gz
+Patch1: papi-ldflags.patch
+Patch2: papi-divzero.patch
+Patch3: papi-rhbz1807346.patch
+Patch4: papi-thread_init.patch
+Patch5: papi-mx.patch
+Patch6: papi-bz1908126.patch
+Patch7: papi-rhbz1918721.patch
+Patch8: papi-rhbz2037417.patch
+Patch9: papi-rhbz2037426.patch
+Patch10: papi-rhbz2037427.patch
+Patch11: papi-zen.patch
 BuildRequires: autoconf
 BuildRequires: doxygen
 BuildRequires: ncurses-devel
@ -35,10 +33,8 @@ BuildRequires: kernel-headers >= 2.6.32
 BuildRequires: chrpath
 BuildRequires: lm_sensors-devel
 %if %{without bundled_libpfm}
-BuildRequires: libpfm-devel >= 4.6.0-1
-%if %{with_static}
-BuildRequires: libpfm-static >= 4.6.0-1
-%endif
+BuildRequires: libpfm-devel >= 4.10.1-3
+BuildRequires: libpfm-static >= 4.10.1-3
 %endif
 # Following required for net component
 BuildRequires: net-tools
@ -47,9 +43,6 @@ BuildRequires: net-tools
 BuildRequires: rdma-core-devel
 BuildRequires: infiniband-diags-devel
 %endif
-%if %{with_pcp}
-BuildRequires: pcp-libs-devel
-%endif
 BuildRequires: perl-generators
 #Right now libpfm does not know anything about s390 and will fail
 ExcludeArch: s390 s390x
@ -60,12 +53,14 @@ running programs.

 %package libs
 Summary: Libraries for PAPI clients
+Group: Development/System
 %description libs
 This package contains the run-time libraries for any application that wishes
 to use PAPI.

 %package devel
 Summary: Header files for the compiling programs with PAPI
+Group: Development/System
 Requires: papi = %{version}-%{release}
 Requires: papi-libs = %{version}-%{release}
 Requires: pkgconfig
@ -76,67 +71,64 @@ that uses PAPI.

 %package testsuite
 Summary: Set of tests for checking PAPI functionality
+Group: Development/System
 Requires: papi = %{version}-%{release}
 Requires: papi-libs = %{version}-%{release}
 %description testsuite
 PAPI-testsuite includes compiled versions of papi tests to ensure
 that PAPI functions on particular hardware.

-%if %{with_static}
 %package static
 Summary: Static libraries for the compiling programs with PAPI
+Group: Development/System
 Requires: papi = %{version}-%{release}
 %description static
 PAPI-static includes the static versions of the library files for
 the PAPI user-space libraries and interfaces.
-%endif

 %prep
 %setup -q
-%patch1 -p1 -b .python3
-%patch2 -p1 -b .a64fx
-%patch4 -p1
+%patch1 -p1 -b .ldflags
+%patch2 -p1 -b .divzero
+%patch3 -p1 -b .rhbz1807346
+%patch4 -p1 -b .thread_init
 %patch5 -p1
 %patch6 -p1
+%patch7 -p1
+%patch8 -p1
+%patch9 -p1
+%patch10 -p1
+%patch11 -p1

 %build
-
 %if %{without bundled_libpfm}
 # Build our own copy of libpfm.
 %global libpfm_config --with-pfm-incdir=%{_includedir} --with-pfm-libdir=%{_libdir}
 %endif

-%if %{with_static}
-%global static_lib_config --with-static-lib=yes
-%else
-%global static_lib_config --with-static-lib=no
-%endif
-
-# set up environment variable for the various components
-# cuda
-# host_micpower
-%if  %{with_rdma}
-  export PAPI_INFINIBAND_UMAD_ROOT=/usr
-%endif
-# lmsensors
-export PAPI_LMSENSORS_ROOT=/usr
-#pushd vmware; ./configure; popd
-%if %{with_pcp}
-%global pcp_enable pcp
-export PAPI_PCP_ROOT=/usr
-%endif
-
 cd src
 autoconf
 %configure --with-perf-events \
 %{?libpfm_config} \
-%{?static_lib_config} \
--with-shared-lib=yes --with-shlib --with-shlib-tools \
--with-components="appio coretemp example infiniband lmsensors lustre micpower mx net %{?pcp_enable} rapl stealtime"
+--with-static-lib=yes --with-shared-lib=yes --with-shlib --with-shlib-tools \
+--with-components="appio coretemp example infiniband lmsensors lustre micpower mx net rapl stealtime"
 # implicit enabled components: perf_event perf_event_uncore
 #components currently left out because of build configure/build issues
 # --with-components="bgpm coretemp_freebsd cuda host_micpower nvml vmware"

+pushd components
+#pushd cuda; ./configure; popd
+#pushd host_micpower; ./configure; popd
+%if  %{with_rdma}
+pushd infiniband_umad; %configure; popd
+%endif
+pushd lmsensors; \
+ %configure --with-sensors_incdir=/usr/include/sensors \
+ --with-sensors_libdir=%{_libdir}; \
+ popd
+#pushd vmware; ./configure; popd
+popd
+
 #DBG workaround to make sure libpfm just uses the normal CFLAGS
 DBG="" make %{?_smp_mflags}

@ -158,14 +150,15 @@ chrpath --delete $RPM_BUILD_ROOT%{_libdir}/*.so*
 %{_bindir}/*
 %dir /usr/share/papi
 /usr/share/papi/papi_events.csv
-%doc INSTALL.txt README.md LICENSE.txt RELEASENOTES.txt
+%doc INSTALL.txt README LICENSE.txt RELEASENOTES.txt
 %doc %{_mandir}/man1/*

-%ldconfig_scriptlets libs
+%post libs -p /sbin/ldconfig
+%postun libs -p /sbin/ldconfig

 %files libs
 %{_libdir}/*.so.*
-%doc INSTALL.txt README.md LICENSE.txt RELEASENOTES.txt
+%doc INSTALL.txt README LICENSE.txt RELEASENOTES.txt

 %files devel
 %{_includedir}/*.h
@ -184,71 +177,38 @@ chrpath --delete $RPM_BUILD_ROOT%{_libdir}/*.so*
 /usr/share/papi/components
 /usr/share/papi/testlib

-%if %{with_static}
 %files static
 %{_libdir}/*.a
-%endif

 %changelog
-* Thu Nov 04 2021 William Cohen <wcohen@redhat.com> - 6.0.0-11
- Allow build with LTO enable. rhbz#1986635
+* Fri May 6 2022 William Cohen <wcohen@redhat.com> - 5.6.0-16
+- AMD Zen2/3 support (rhbz2071558)

-* Mon Aug 09 2021 Mohan Boddu <mboddu@redhat.com> - 6.0.0-10
- Rebuilt for IMA sigs, glibc 2.34, aarch64 flags
-  Related: rhbz#1991688
+* Tue Apr 19 2022 William Cohen <wcohen@redhat.com> - 5.6.0-15
+- Fujitsu A64FX improvements. (rhbz2037417,rhbz2037426,rhbz2037427)

-* Wed Jun 16 2021 William Cohen <wcohen@redhat.com> - 6.0.0-9
- Excise iozone code from papi source tarball. Resolves: rhbz#1972870
+* Tue May 25 2021 William Cohen <wcohen@redhat.com> - 5.6.0-14
+- Disable problematic IBM Power9 events.

-* Fri Apr 16 2021 Mohan Boddu <mboddu@redhat.com> - 6.0.0-8
- Rebuilt for RHEL 9 BETA on Apr 15th 2021. Related: rhbz#1947937
+* Tue May 25 2021 William Cohen <wcohen@redhat.com> - 5.6.0-13
+- Add Fujitsu A64FX support.

-* Thu Jan 28 2021 William Cohen <wcohen@redhat.com> - 6.0.0-7
- By default disable genaration of static libraries.
+* Tue May 18 2021 William Cohen <wcohen@redhat.com> - 5.6.0-12
+- Improvements to mx component.

-* Tue Jan 26 2021 Fedora Release Engineering <releng@fedoraproject.org> - 6.0.0-6
- Rebuilt for https://fedoraproject.org/wiki/Fedora_34_Mass_Rebuild
+* Fri Aug 21 2020 William Cohen <wcohen@redhat.com> - 5.6.0-11
+- Correct the handling of multiple threads. (rhbz1807346)

-* Thu Dec 17 2020 William Cohen <wcohen@redhat.com> - 6.0.0-5
- Remove iozone source code. (#1901077)
+* Wed May 27 2020 William Cohen <wcohen@redhat.com> - 5.6.0-10
+- Rebuild with current libpfm-4.10.1.

-* Mon Nov 09 2020 William Cohen <wcohen@redhat.com> - 6.0.0-4
- Add Fujitsu A64FX presets.
-
-* Tue Jul 28 2020 Fedora Release Engineering <releng@fedoraproject.org> - 6.0.0-3
- Rebuilt for https://fedoraproject.org/wiki/Fedora_33_Mass_Rebuild
-
-* Wed Jul 01 2020 Jeff Law <law@redhat.com> - 6.0.0-2
- Disable LTO
-
-* Wed Mar 04 2020 William Cohen <wcohen@redhat.com> - 6.0.0-1
- Rebase to official papi-6.0.0.
-
-* Wed Jan 29 2020 Fedora Release Engineering <releng@fedoraproject.org> - 5.7.0-4
- Rebuilt for https://fedoraproject.org/wiki/Fedora_32_Mass_Rebuild
-
-* Fri Jul 26 2019 Fedora Release Engineering <releng@fedoraproject.org> - 5.7.0-3
- Rebuilt for https://fedoraproject.org/wiki/Fedora_31_Mass_Rebuild
-
-* Mon Mar 04 2019 William Cohen <wcohen@redhat.com> - 5.7.0-2
- Rebase to official papi-5.7.0.
-
-* Mon Feb 18 2019 William Cohen <wcohen@redhat.com> - 5.7.0-1
- Rebase to papi-5.7.0.
-
-* Fri Feb 01 2019 Fedora Release Engineering <releng@fedoraproject.org> - 5.6.0-10
- Rebuilt for https://fedoraproject.org/wiki/Fedora_30_Mass_Rebuild
-
-* Mon Jan 7 2019 William Cohen <wcohen@redhat.com> - 5.6.0-9
+* Tue May 26 2020 William Cohen <wcohen@redhat.com> - 5.6.0-9
 - Correct typo in papi-testsuite description.
 - Add papi-libs for papi-testsuite and papi-devel.

 * Fri Nov 2 2018 Fedora Release Engineering <releng@fedoraproject.org> - 5.6.0-8
 - Pull in patch to avoid division-by-0.

-* Fri Jul 13 2018 Fedora Release Engineering <releng@fedoraproject.org> - 5.6.0-7
- Rebuilt for https://fedoraproject.org/wiki/Fedora_29_Mass_Rebuild
-
 * Thu May 17 2018 William Cohen <wcohen@redhat.com> - 5.6.0-6
 - Dynamically link utilities and tests to papi libraries.