[v0.98][PPC] Add altivec detection and peak performance output

src/common/printer.c

@@ -64,6 +64,8 @@ enum {
 #ifdef ARCH_X86
   ATTRIBUTE_AVX,
   ATTRIBUTE_FMA,
+#elif ARCH_PPC
+  ATTRIBUTE_ALTIVEC,
 #elif ARCH_ARM
   ATTRIBUTE_FEATURES,
 #endif
@@ -91,7 +93,9 @@ static const char* ATTRIBUTE_FIELDS [] = {
 #ifdef ARCH_X86
   "AVX:",
   "FMA:",
-#elif defined(ARCH_ARM) || defined(ARCH_PPC)
+#elif ARCH_PPC
+  "Altivec: ",
+#elif defined(ARCH_ARM)
   "Features: ",
 #endif
   "L1i Size:",
@@ -572,13 +576,14 @@ bool print_cpufetch_ppc(struct cpuInfo* cpu, STYLE s, struct colors* cs) {
   char* n_cores = get_str_topology(cpu, cpu->topo, false);
   char* n_cores_dual = get_str_topology(cpu, cpu->topo, true);
   char* cpu_name = get_str_cpu_name(cpu);
+  char* altivec = get_str_altivec(cpu);
 
   /*
   char* l1i = get_str_l1i(cpu->cach);
   char* l1d = get_str_l1d(cpu->cach);
   char* l2 = get_str_l2(cpu->cach);
-  char* l3 = get_str_l3(cpu->cach);
-  char* pp = get_str_peak_performance(cpu,cpu->topo,get_freq(cpu->freq));*/
+  char* l3 = get_str_l3(cpu->cach);*/
+  char* pp = get_str_peak_performance(cpu,cpu->topo,get_freq(cpu->freq));
 
   setAttribute(art,ATTRIBUTE_NAME,cpu_name);
   /*
@@ -597,17 +602,15 @@ bool print_cpufetch_ppc(struct cpuInfo* cpu, STYLE s, struct colors* cs) {
   else {
     setAttribute(art,ATTRIBUTE_NCORES, n_cores);
   }
+  setAttribute(art,ATTRIBUTE_ALTIVEC, altivec);
   /*
-  setAttribute(art,ATTRIBUTE_AVX,avx);
-  setAttribute(art,ATTRIBUTE_FMA,fma);  
   setAttribute(art,ATTRIBUTE_L1i,l1i);
   setAttribute(art,ATTRIBUTE_L1d,l1d);
   setAttribute(art,ATTRIBUTE_L2,l2);
   if(l3 != NULL) {
     setAttribute(art,ATTRIBUTE_L3,l3);
-  }
+  }*/
   setAttribute(art,ATTRIBUTE_PEAK,pp);
-  */
 
   if(art->n_attributes_set > NUMBER_OF_LINES) {
     printBug("The number of attributes set is bigger than the max that can be displayed");

src/common/printer.h

@@ -7,7 +7,9 @@ typedef int STYLE;
 
 #ifdef ARCH_X86
   #include "../x86/cpuid.h"
-#else
+#elif ARCH_PPC
+  #include "../ppc/ppc.h"
+#elif ARCH_ARM
   #include "../arm/midr.h"
 #endif
 

src/ppc/ppc.c

@@ -3,8 +3,10 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
+#include <assert.h>
 
 #include "ppc.h"
+#include "uarch.h"
 #include "udev.h"
 #include "../common/udev.h"
 
@@ -146,12 +148,54 @@ struct cpuInfo* get_cpu_info() {
   cpu->cach = get_cache_info(cpu);
   cpu->topo = get_topology_info(cpu, cpu->cach);
 
+  feat->altivec = has_altivec(cpu->arch);
+
   if(cpu->cach == NULL || cpu->topo == NULL) {
     return NULL;
   }
   return cpu;
 }
 
+char* get_str_altivec(struct cpuInfo* cpu) {
+  char* string = calloc(4, sizeof(char));
+
+  if(cpu->feat->altivec) strcpy(string, "Yes");
+  else strcpy(string, "No");
+
+  return string;
+}
+
+char* get_str_peak_performance(struct cpuInfo* cpu, struct topology* topo, int64_t freq) {
+  /*
+   * Not sure about this
+   * PP(SP) = N_CORES * FREQUENCY * 4(If altivec)
+   */
+
+  //7 for GFLOP/s and 6 for digits,eg 412.14
+  uint32_t size = 7+6+1+1;
+  assert(strlen(STRING_UNKNOWN)+1 <= size);
+  char* string = malloc(sizeof(char)*size);
+
+  //First check we have consistent data
+  if(freq == UNKNOWN_FREQ) {
+    snprintf(string,strlen(STRING_UNKNOWN)+1,STRING_UNKNOWN);
+    return string;
+  }
+
+  struct features* feat = cpu->feat;
+  double flops = topo->physical_cores * topo->sockets * (freq*1000000);
+  if(feat->altivec) flops = flops*4;
+
+  if(flops >= (double)1000000000000.0)
+    snprintf(string,size,"%.2f TFLOP/s",flops/1000000000000);
+  else if(flops >= 1000000000.0)
+    snprintf(string,size,"%.2f GFLOP/s",flops/1000000000);
+  else
+    snprintf(string,size,"%.2f MFLOP/s",flops/1000000);
+
+  return string;
+}
+
 char* get_str_topology(struct cpuInfo* cpu, struct topology* topo, bool dual_socket) {
   char* string;
   if(topo->smt_supported > 1) {

src/ppc/ppc.h

@@ -5,6 +5,8 @@
 
 struct topology* get_topology_info(struct cpuInfo* cpu, struct cache* cach);
 struct cpuInfo* get_cpu_info();
+char* get_str_altivec(struct cpuInfo* cpu);
+char* get_str_peak_performance(struct cpuInfo* cpu, struct topology* topo, int64_t freq);
 void print_debug(struct cpuInfo* cpu);
 
 #endif

src/ppc/uarch.c

@@ -219,6 +219,23 @@ struct uarch* get_uarch_from_pvr(uint32_t pvr) {
   return arch;
 }
 
+bool has_altivec(struct uarch* arch) {
+  switch(arch->uarch) {
+    case UARCH_PPC970FX:
+    case UARCH_PPC970MP:
+    case UARCH_CELLBE:
+    case UARCH_POWER6:
+    case UARCH_POWER7:
+    case UARCH_POWER7PLUS:
+    case UARCH_POWER8:
+    case UARCH_POWER9:
+    case UARCH_POWER10:
+      return true;
+    default:
+      return false;
+  }
+}
+
 char* get_str_uarch(struct cpuInfo* cpu) {
   return cpu->arch->uarch_str;    
 }

src/ppc/uarch.h

@@ -7,6 +7,7 @@
 struct uarch;
 
 struct uarch* get_uarch_from_pvr(uint32_t pvr);
+bool has_altivec(struct uarch* arch);
 char* get_str_uarch(struct cpuInfo* cpu);
 char* get_str_process(struct cpuInfo* cpu);
 void free_uarch_struct(struct uarch* arch);