[v1.00] Skeleton for future support for other vector instructions in --accurate-pp

.gitignore

@@ -1 +1,2 @@
 cpufetch
+*.o

Makefile

@@ -15,11 +15,12 @@ ifneq ($(OS),Windows_NT)
 	ifeq ($(arch), $(filter $(arch), x86_64 amd64 i686))
 		SRC_DIR=src/x86/
 		SOURCE += $(COMMON_SRC) $(SRC_DIR)cpuid.c $(SRC_DIR)apic.c $(SRC_DIR)cpuid_asm.c $(SRC_DIR)uarch.c
-		HEADERS += $(COMMON_HDR) $(SRC_DIR)cpuid.h $(SRC_DIR)apic.h $(SRC_DIR)cpuid_asm.h $(SRC_DIR)uarch.h
+		HEADERS += $(COMMON_HDR) $(SRC_DIR)cpuid.h $(SRC_DIR)apic.h $(SRC_DIR)cpuid_asm.h $(SRC_DIR)uarch.h $(SRC_DIR)freq/freq.h
 
                 os := $(shell uname -s)
                 ifeq ($(os), Linux)
-			SOURCE += freq.o
+			SOURCE += $(SRC_DIR)freq/freq.c freq_nov.o freq_sse.o freq_avx.o freq_avx512.o
+			HEADERS += $(SRC_DIR)freq/freq.h
 			CFLAGS += -pthread
                 endif
 		CFLAGS += -DARCH_X86 -std=c99 -fstack-protector-all
@@ -69,8 +70,17 @@ static: $(OUTPUT)
 strict: CFLAGS += -O2 -Werror -fsanitize=undefined -D_FORTIFY_SOURCE=2
 strict: $(OUTPUT)
 
-freq.o: Makefile $(SRC_DIR)freq.c $(SRC_DIR)freq.h
+freq_nov.o: Makefile $(SRC_DIR)freq/freq_nov.c $(SRC_DIR)freq/freq_nov.h
-	$(CC) $(CFLAGS) $(SANITY_FLAGS) -c -mavx -mfma -pthread $(SRC_DIR)freq.c -o freq.o
+	$(CC) $(CFLAGS) $(SANITY_FLAGS) -c -pthread $(SRC_DIR)freq/freq_nov.c -o $@
+
+freq_sse.o: Makefile $(SRC_DIR)freq/freq_sse.c $(SRC_DIR)freq/freq_sse.h
+	$(CC) $(CFLAGS) $(SANITY_FLAGS) -c -msse -pthread $(SRC_DIR)freq/freq_sse.c -o $@
+
+freq_avx.o: Makefile $(SRC_DIR)freq/freq_avx.c $(SRC_DIR)freq/freq_avx.h
+	$(CC) $(CFLAGS) $(SANITY_FLAGS) -c -mavx -mfma -pthread $(SRC_DIR)freq/freq_avx.c -o $@
+
+freq_avx512.o: Makefile $(SRC_DIR)freq/freq_avx512.c $(SRC_DIR)freq/freq_avx512.h
+	$(CC) $(CFLAGS) $(SANITY_FLAGS) -c -mavx512f -mfma -pthread $(SRC_DIR)freq/freq_avx512.c -o $@
 
 $(OUTPUT): Makefile $(SOURCE) $(HEADERS)
 	$(CC) $(CFLAGS) $(SANITY_FLAGS) $(SOURCE) -o $(OUTPUT)
@@ -79,7 +89,7 @@ run: $(OUTPUT)
 	./$(OUTPUT)
 
 clean:
-	@rm -f $(OUTPUT) freq.o
+	@rm -f $(OUTPUT) *.o
 
 install: $(OUTPUT)
 	install -Dm755 "cpufetch"   "$(DESTDIR)$(PREFIX)/bin/cpufetch"

src/x86/cpuid.c

@@ -18,7 +18,7 @@
 #include "../common/args.h"
 #include "apic.h"
 #include "uarch.h"
-#include "freq.h"
+#include "freq/freq.h"
 
 #define CPU_VENDOR_INTEL_STRING "GenuineIntel"
 #define CPU_VENDOR_AMD_STRING   "AuthenticAMD"
@@ -194,8 +194,10 @@ int64_t get_peak_performance(struct cpuInfo* cpu, struct topology* topo, int64_t
 
   int64_t freq;
 #ifdef __linux__
-  if(accurate_pp) freq = measure_avx_frequency(cpu);
+  if(accurate_pp)
-  else freq = max_freq;
+    freq = measure_frequency(cpu);
+  else
+    freq = max_freq;
 #else
   // Silence compiler warning
   (void)(accurate_pp);

src/x86/freq.h

@@ -1,9 +0,0 @@
-#ifndef __FREQ__
-#define __FREQ__
-
-#include <stdint.h>
-#include "../common/cpu.h"
-
-int64_t measure_avx_frequency(struct cpuInfo* cpu);
-
-#endif

src/x86/freq/freq.c

@@ -1,8 +1,13 @@
 #define  _GNU_SOURCE
 #include <stdio.h>
 
+#include "../../common/global.h"
+#include "../uarch.h"
 #include "freq.h"
-#include "../common/global.h"
+#include "freq_nov.h"
+#include "freq_sse.h"
+#include "freq_avx.h"
+#include "freq_avx512.h"
 
 #include <immintrin.h>
 #include <stdlib.h>
@@ -13,10 +18,8 @@
 #include <string.h>
 #include <pthread.h>
 
-#define MEASURE_TIME_SECONDS         5
 #define MAX_NUMBER_THREADS         512
 #define FREQ_VECTOR_SIZE         1<<16
-#define LOOP_ITERS           100000000
 
 struct freq_thread {
   bool end;
@@ -80,44 +83,38 @@ void* measure_freq(void *freq_ptr) {
   return NULL;
 }
 
-void* compute_avx() {
+int64_t measure_frequency(struct cpuInfo* cpu) {
-  bool end = false;
-
-  struct timeval begin, now;
-
-  __m256 a = _mm256_set1_ps(1.5);
-  __m256 b = _mm256_set1_ps(1.2);
-  __m256 c = _mm256_set1_ps(0.0);
-
-  gettimeofday(&begin, NULL);
-  while(!end) {
-    for(uint64_t i=0; i < LOOP_ITERS; i++) {
-      c = _mm256_fmadd_ps(a, b, c);
-    }
-
-    gettimeofday(&now, NULL);
-    double elapsed = (now.tv_sec - begin.tv_sec) + ((now.tv_usec - begin.tv_usec)/1000000.0);
-    end = elapsed >= (double) MEASURE_TIME_SECONDS;
-  }
-
-  FILE* fp = fopen("/dev/null", "w");
-  if(fp == NULL) {
-    printf("fopen: %s", strerror(errno));
-  }
-  else {
-    fprintf(fp, "%f", c[0]);
-    fclose(fp);
-  }
-
-  return NULL;
-}
-
-int64_t measure_avx_frequency(struct cpuInfo* cpu) {
   int ret;
+  int num_spaces;
   struct freq_thread* freq_struct = malloc(sizeof(struct freq_thread));
   freq_struct->end = false;
   freq_struct->measure = false;
 
+  void* (*compute_function)(void*);
+
+  if(cpu->feat->AVX512 && vpus_are_AVX512(cpu)) {
+    printf("cpufetch is measuring the AVX512 frequency...");
+    compute_function = compute_avx512;
+    num_spaces = 45;
+  }
+  else if(cpu->feat->AVX || cpu->feat->AVX2) {
+    printf("cpufetch is measuring the AVX frequency...");
+    compute_function = compute_avx;
+    num_spaces = 42;
+  }
+  else if(cpu->feat->SSE) {
+    printf("cpufetch is measuring the SSE frequency...");
+    compute_function = compute_sse;
+    num_spaces = 42;
+  }
+  else {
+    printf("cpufetch is measuring the frequency (no vector instructions)...");
+    compute_function = compute_nov;
+    num_spaces = 63;
+  }
+
+  fflush(stdout);
+
   pthread_t freq_t;
   if(pthread_create(&freq_t, NULL, measure_freq, freq_struct)) {
     fprintf(stderr, "Error creating thread\n");
@@ -126,7 +123,7 @@ int64_t measure_avx_frequency(struct cpuInfo* cpu) {
 
   pthread_t* compute_th = malloc(sizeof(pthread_t) * cpu->topo->total_cores);
   for(int i=0; i < cpu->topo->total_cores; i++) {
-    ret = pthread_create(&compute_th[i], NULL, compute_avx, NULL);
+    ret = pthread_create(&compute_th[i], NULL, compute_function, NULL);
 
     if(ret != 0) {
       fprintf(stderr, "Error creating thread\n");
@@ -134,9 +131,6 @@ int64_t measure_avx_frequency(struct cpuInfo* cpu) {
     }
   }
 
-  printf("cpufetch is measuring AVX2 frequency...");
-  fflush(stdout);
-
   sleep_ms(500);
   freq_struct->measure = true;
 
@@ -153,6 +147,6 @@ int64_t measure_avx_frequency(struct cpuInfo* cpu) {
     return -1;
   }
 
-  printf("\r                                       ");
+  printf("\r%*c", num_spaces, ' ');
   return freq_struct->freq;
 }

src/x86/freq/freq.h

@@ -0,0 +1,9 @@
+#ifndef __FREQ__
+#define __FREQ__
+
+#include <stdint.h>
+#include "../../common/cpu.h"
+
+int64_t measure_frequency(struct cpuInfo* cpu);
+
+#endif

src/x86/freq/freq_avx.c

@@ -0,0 +1,46 @@
+#include <stdio.h>
+#include <immintrin.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <sys/time.h>
+#include <time.h>
+#include <errno.h>
+#include <string.h>
+#include <pthread.h>
+#include <stdint.h>
+
+#define MEASURE_TIME_SECONDS         5
+#define LOOP_ITERS           100000000
+
+void* compute_avx() {
+  bool end = false;
+
+  struct timeval begin, now;
+
+  __m256 a = _mm256_set1_ps(1.5);
+  __m256 b = _mm256_set1_ps(1.2);
+  __m256 c = _mm256_set1_ps(0.0);
+
+  gettimeofday(&begin, NULL);
+  while(!end) {
+    for(uint64_t i=0; i < LOOP_ITERS; i++) {
+      c = _mm256_fmadd_ps(a, b, c);
+    }
+
+    gettimeofday(&now, NULL);
+    double elapsed = (now.tv_sec - begin.tv_sec) + ((now.tv_usec - begin.tv_usec)/1000000.0);
+    end = elapsed >= (double) MEASURE_TIME_SECONDS;
+  }
+
+  FILE* fp = fopen("/dev/null", "w");
+  if(fp == NULL) {
+    printf("fopen: %s", strerror(errno));
+  }
+  else {
+    fprintf(fp, "%f", c[0]);
+    fclose(fp);
+  }
+
+  return NULL;
+}
+

src/x86/freq/freq_avx.h

@@ -0,0 +1,6 @@
+#ifndef __FREQ_AVX__
+#define __FREQ_AVX__
+
+void* compute_avx();
+
+#endif

src/x86/freq/freq_avx512.c

@@ -0,0 +1,5 @@
+#include <stdio.h>
+
+void* compute_avx512() {
+  return NULL;
+}

src/x86/freq/freq_avx512.h

@@ -0,0 +1,6 @@
+#ifndef __FREQ_AVX512__
+#define __FREQ_AVX512__
+
+void* compute_avx512();
+
+#endif

src/x86/freq/freq_nov.c

@@ -0,0 +1,5 @@
+#include <stdio.h>
+
+void* compute_nov() {
+  return NULL;
+}

src/x86/freq/freq_nov.h

@@ -0,0 +1,6 @@
+#ifndef __FREQ_NO_VECTOR__
+#define __FREQ_NO_VECTOR__
+
+void* compute_nov();
+
+#endif

src/x86/freq/freq_sse.c

@@ -0,0 +1,5 @@
+#include <stdio.h>
+
+void* compute_sse() {
+  return NULL;
+}

src/x86/freq/freq_sse.h

@@ -0,0 +1,6 @@
+#ifndef __FREQ_SSE__
+#define __FREQ_SSE__
+
+void* compute_sse();
+
+#endif