Rework Power Fit report: 90 min stability, aligned tables, PSU/fan sections
- Increase stability profile duration from 33 min to 90 min by wiring powerBenchDurationSec() into runBenchmarkPowerCalibration (was discarded) - Collect per-step PSU slot readings, fan RPM/duty, and per-GPU telemetry in ramp loop; add matching fields to NvidiaPowerBenchStep/NvidiaPowerBenchGPU - Rewrite renderPowerBenchReport: replace Per-Slot Results with Single GPU section, rework Ramp Sequence rows=runs/cols=GPUs, add PSU Performance section (conditional on IPMI data), add transposed Single vs All-GPU comparison table in per-GPU sections - Add fmtMDTable helper (benchmark_table.go) and apply to all tables in both power and performance reports so columns align in plain-text view Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -89,136 +89,159 @@ func renderBenchmarkReportWithCharts(result NvidiaBenchmarkResult) string {
|
||||
|
||||
// Perspective 1: Compatibility — hard stops
|
||||
b.WriteString("### 1. Compatibility\n\n")
|
||||
b.WriteString("| GPU | Thermal throttle | Fan duty at throttle | ECC uncorr | Status |\n")
|
||||
b.WriteString("|-----|------------------|----------------------|------------|--------|\n")
|
||||
for _, gpu := range result.GPUs {
|
||||
thermalThrottle := "-"
|
||||
if gpu.Scores.ThermalThrottlePct > 0 {
|
||||
thermalThrottle = fmt.Sprintf("%.1f%%", gpu.Scores.ThermalThrottlePct)
|
||||
{
|
||||
var rows [][]string
|
||||
for _, gpu := range result.GPUs {
|
||||
thermalThrottle := "-"
|
||||
if gpu.Scores.ThermalThrottlePct > 0 {
|
||||
thermalThrottle = fmt.Sprintf("%.1f%%", gpu.Scores.ThermalThrottlePct)
|
||||
}
|
||||
fanAtThrottle := "-"
|
||||
if result.Cooling != nil && result.Cooling.FanDutyCycleAvailable && gpu.Scores.ThermalThrottlePct > 0 {
|
||||
fanAtThrottle = fmt.Sprintf("%.0f%%", result.Cooling.P95FanDutyCyclePct)
|
||||
}
|
||||
ecc := "-"
|
||||
if gpu.ECC.Uncorrected > 0 {
|
||||
ecc = fmt.Sprintf("⛔ %d", gpu.ECC.Uncorrected)
|
||||
}
|
||||
compatStatus := "✓ OK"
|
||||
if gpu.ECC.Uncorrected > 0 || (gpu.Scores.ThermalThrottlePct > 0 && result.Cooling != nil && result.Cooling.FanDutyCycleAvailable && result.Cooling.P95FanDutyCyclePct < 95) {
|
||||
compatStatus = "⛔ HARD STOP"
|
||||
}
|
||||
rows = append(rows, []string{fmt.Sprintf("GPU %d", gpu.Index), thermalThrottle, fanAtThrottle, ecc, compatStatus})
|
||||
}
|
||||
fanAtThrottle := "-"
|
||||
if result.Cooling != nil && result.Cooling.FanDutyCycleAvailable && gpu.Scores.ThermalThrottlePct > 0 {
|
||||
fanAtThrottle = fmt.Sprintf("%.0f%%", result.Cooling.P95FanDutyCyclePct)
|
||||
}
|
||||
ecc := "-"
|
||||
if gpu.ECC.Uncorrected > 0 {
|
||||
ecc = fmt.Sprintf("⛔ %d", gpu.ECC.Uncorrected)
|
||||
}
|
||||
compatStatus := "✓ OK"
|
||||
if gpu.ECC.Uncorrected > 0 || (gpu.Scores.ThermalThrottlePct > 0 && result.Cooling != nil && result.Cooling.FanDutyCycleAvailable && result.Cooling.P95FanDutyCyclePct < 95) {
|
||||
compatStatus = "⛔ HARD STOP"
|
||||
}
|
||||
fmt.Fprintf(&b, "| GPU %d | %s | %s | %s | %s |\n",
|
||||
gpu.Index, thermalThrottle, fanAtThrottle, ecc, compatStatus)
|
||||
b.WriteString(fmtMDTable([]string{"GPU", "Thermal throttle", "Fan duty at throttle", "ECC uncorr", "Status"}, rows))
|
||||
b.WriteString("\n")
|
||||
}
|
||||
b.WriteString("\n")
|
||||
|
||||
// Perspective 2: Thermal headroom
|
||||
b.WriteString("### 2. Thermal Headroom\n\n")
|
||||
b.WriteString("| GPU | p95 temp | Slowdown limit | Shutdown limit | Headroom | Thermal throttle | Status |\n")
|
||||
b.WriteString("|-----|----------|----------------|----------------|----------|------------------|--------|\n")
|
||||
for _, gpu := range result.GPUs {
|
||||
shutdownTemp := gpu.ShutdownTempC
|
||||
if shutdownTemp <= 0 {
|
||||
shutdownTemp = 90
|
||||
{
|
||||
var rows [][]string
|
||||
for _, gpu := range result.GPUs {
|
||||
shutdownTemp := gpu.ShutdownTempC
|
||||
if shutdownTemp <= 0 {
|
||||
shutdownTemp = 90
|
||||
}
|
||||
slowdownTemp := gpu.SlowdownTempC
|
||||
if slowdownTemp <= 0 {
|
||||
slowdownTemp = 80
|
||||
}
|
||||
headroom := gpu.Scores.TempHeadroomC
|
||||
thermalStatus := "✓ OK"
|
||||
switch {
|
||||
case headroom < 10:
|
||||
thermalStatus = "⛔ CRITICAL"
|
||||
case gpu.Steady.P95TempC >= slowdownTemp:
|
||||
thermalStatus = "⚠ WARNING"
|
||||
}
|
||||
throttlePct := "-"
|
||||
if gpu.Scores.ThermalThrottlePct > 0 {
|
||||
throttlePct = fmt.Sprintf("%.1f%%", gpu.Scores.ThermalThrottlePct)
|
||||
}
|
||||
rows = append(rows, []string{
|
||||
fmt.Sprintf("GPU %d", gpu.Index),
|
||||
fmt.Sprintf("%.1f°C", gpu.Steady.P95TempC),
|
||||
fmt.Sprintf("%.0f°C", slowdownTemp),
|
||||
fmt.Sprintf("%.0f°C", shutdownTemp),
|
||||
fmt.Sprintf("%.1f°C", headroom),
|
||||
throttlePct,
|
||||
thermalStatus,
|
||||
})
|
||||
}
|
||||
slowdownTemp := gpu.SlowdownTempC
|
||||
if slowdownTemp <= 0 {
|
||||
slowdownTemp = 80
|
||||
}
|
||||
headroom := gpu.Scores.TempHeadroomC
|
||||
thermalStatus := "✓ OK"
|
||||
switch {
|
||||
case headroom < 10:
|
||||
thermalStatus = "⛔ CRITICAL"
|
||||
case gpu.Steady.P95TempC >= slowdownTemp:
|
||||
thermalStatus = "⚠ WARNING"
|
||||
}
|
||||
throttlePct := "-"
|
||||
if gpu.Scores.ThermalThrottlePct > 0 {
|
||||
throttlePct = fmt.Sprintf("%.1f%%", gpu.Scores.ThermalThrottlePct)
|
||||
}
|
||||
fmt.Fprintf(&b, "| GPU %d | %.1f°C | %.0f°C | %.0f°C | %.1f°C | %s | %s |\n",
|
||||
gpu.Index, gpu.Steady.P95TempC, slowdownTemp, shutdownTemp, headroom, throttlePct, thermalStatus)
|
||||
b.WriteString(fmtMDTable([]string{"GPU", "p95 temp", "Slowdown limit", "Shutdown limit", "Headroom", "Thermal throttle", "Status"}, rows))
|
||||
b.WriteString("\n")
|
||||
}
|
||||
b.WriteString("\n")
|
||||
|
||||
// Perspective 3: Power delivery
|
||||
b.WriteString("### 3. Power Delivery\n\n")
|
||||
b.WriteString("| GPU | Power cap throttle | Power stability | Fan duty (p95) | Status |\n")
|
||||
b.WriteString("|-----|-------------------|-----------------|----------------|--------|\n")
|
||||
for _, gpu := range result.GPUs {
|
||||
powerCap := "-"
|
||||
if gpu.Scores.PowerCapThrottlePct > 0 {
|
||||
powerCap = fmt.Sprintf("%.1f%%", gpu.Scores.PowerCapThrottlePct)
|
||||
{
|
||||
var rows [][]string
|
||||
for _, gpu := range result.GPUs {
|
||||
powerCap := "-"
|
||||
if gpu.Scores.PowerCapThrottlePct > 0 {
|
||||
powerCap = fmt.Sprintf("%.1f%%", gpu.Scores.PowerCapThrottlePct)
|
||||
}
|
||||
fanDuty := "-"
|
||||
if result.Cooling != nil && result.Cooling.FanDutyCycleAvailable {
|
||||
fanDuty = fmt.Sprintf("%.0f%%", result.Cooling.P95FanDutyCyclePct)
|
||||
}
|
||||
powerStatus := "✓ OK"
|
||||
if gpu.Scores.PowerCapThrottlePct > 5 {
|
||||
powerStatus = "⚠ POWER LIMITED"
|
||||
}
|
||||
rows = append(rows, []string{
|
||||
fmt.Sprintf("GPU %d", gpu.Index),
|
||||
powerCap,
|
||||
fmt.Sprintf("%.1f", gpu.Scores.PowerSustainScore),
|
||||
fanDuty,
|
||||
powerStatus,
|
||||
})
|
||||
}
|
||||
fanDuty := "-"
|
||||
if result.Cooling != nil && result.Cooling.FanDutyCycleAvailable {
|
||||
fanDuty = fmt.Sprintf("%.0f%%", result.Cooling.P95FanDutyCyclePct)
|
||||
}
|
||||
powerStatus := "✓ OK"
|
||||
if gpu.Scores.PowerCapThrottlePct > 5 {
|
||||
powerStatus = "⚠ POWER LIMITED"
|
||||
}
|
||||
fmt.Fprintf(&b, "| GPU %d | %s | %.1f | %s | %s |\n",
|
||||
gpu.Index, powerCap, gpu.Scores.PowerSustainScore, fanDuty, powerStatus)
|
||||
b.WriteString(fmtMDTable([]string{"GPU", "Power cap throttle", "Power stability", "Fan duty (p95)", "Status"}, rows))
|
||||
b.WriteString("\n")
|
||||
}
|
||||
b.WriteString("\n")
|
||||
|
||||
// Perspective 4: Performance
|
||||
b.WriteString("### 4. Performance\n\n")
|
||||
b.WriteString("| GPU | Compute TOPS | Synthetic | Mixed | Mixed Eff. | TOPS/SM/GHz |\n")
|
||||
b.WriteString("|-----|--------------|-----------|-------|------------|-------------|\n")
|
||||
for _, gpu := range result.GPUs {
|
||||
synthetic := "-"
|
||||
if gpu.Scores.SyntheticScore > 0 {
|
||||
synthetic = fmt.Sprintf("%.2f", gpu.Scores.SyntheticScore)
|
||||
{
|
||||
var rows [][]string
|
||||
for _, gpu := range result.GPUs {
|
||||
synthetic := "-"
|
||||
if gpu.Scores.SyntheticScore > 0 {
|
||||
synthetic = fmt.Sprintf("%.2f", gpu.Scores.SyntheticScore)
|
||||
}
|
||||
mixed := "-"
|
||||
if gpu.Scores.MixedScore > 0 {
|
||||
mixed = fmt.Sprintf("%.2f", gpu.Scores.MixedScore)
|
||||
}
|
||||
mixedEff := "-"
|
||||
if gpu.Scores.MixedEfficiency > 0 {
|
||||
mixedEff = fmt.Sprintf("%.1f%%", gpu.Scores.MixedEfficiency*100)
|
||||
}
|
||||
topsPerSM := "-"
|
||||
if gpu.Scores.TOPSPerSMPerGHz > 0 {
|
||||
topsPerSM = fmt.Sprintf("%.3f", gpu.Scores.TOPSPerSMPerGHz)
|
||||
}
|
||||
rows = append(rows, []string{
|
||||
fmt.Sprintf("GPU %d", gpu.Index),
|
||||
fmt.Sprintf("**%.2f**", gpu.Scores.CompositeScore),
|
||||
synthetic, mixed, mixedEff, topsPerSM,
|
||||
})
|
||||
}
|
||||
mixed := "-"
|
||||
if gpu.Scores.MixedScore > 0 {
|
||||
mixed = fmt.Sprintf("%.2f", gpu.Scores.MixedScore)
|
||||
b.WriteString(fmtMDTable([]string{"GPU", "Compute TOPS", "Synthetic", "Mixed", "Mixed Eff.", "TOPS/SM/GHz"}, rows))
|
||||
if len(result.PerformanceRampSteps) > 0 {
|
||||
fmt.Fprintf(&b, "\n**Platform power score (scalability):** %.1f%%\n", result.PlatformPowerScore)
|
||||
}
|
||||
mixedEff := "-"
|
||||
if gpu.Scores.MixedEfficiency > 0 {
|
||||
mixedEff = fmt.Sprintf("%.1f%%", gpu.Scores.MixedEfficiency*100)
|
||||
}
|
||||
topsPerSM := "-"
|
||||
if gpu.Scores.TOPSPerSMPerGHz > 0 {
|
||||
topsPerSM = fmt.Sprintf("%.3f", gpu.Scores.TOPSPerSMPerGHz)
|
||||
}
|
||||
fmt.Fprintf(&b, "| GPU %d | **%.2f** | %s | %s | %s | %s |\n",
|
||||
gpu.Index, gpu.Scores.CompositeScore, synthetic, mixed, mixedEff, topsPerSM)
|
||||
b.WriteString("\n")
|
||||
}
|
||||
if len(result.PerformanceRampSteps) > 0 {
|
||||
fmt.Fprintf(&b, "\n**Platform power score (scalability):** %.1f%%\n", result.PlatformPowerScore)
|
||||
}
|
||||
b.WriteString("\n")
|
||||
|
||||
// Perspective 5: Anomaly flags
|
||||
b.WriteString("### 5. Anomalies\n\n")
|
||||
b.WriteString("| GPU | ECC corrected | Sync boost throttle | Power instability | Thermal instability |\n")
|
||||
b.WriteString("|-----|---------------|---------------------|-------------------|---------------------|\n")
|
||||
for _, gpu := range result.GPUs {
|
||||
eccCorr := "-"
|
||||
if gpu.ECC.Corrected > 0 {
|
||||
eccCorr = fmt.Sprintf("⚠ %d", gpu.ECC.Corrected)
|
||||
{
|
||||
var rows [][]string
|
||||
for _, gpu := range result.GPUs {
|
||||
eccCorr := "-"
|
||||
if gpu.ECC.Corrected > 0 {
|
||||
eccCorr = fmt.Sprintf("⚠ %d", gpu.ECC.Corrected)
|
||||
}
|
||||
syncBoost := "-"
|
||||
if gpu.Scores.SyncBoostThrottlePct > 0 {
|
||||
syncBoost = fmt.Sprintf("%.1f%%", gpu.Scores.SyncBoostThrottlePct)
|
||||
}
|
||||
powerVar := "OK"
|
||||
if gpu.Scores.PowerSustainScore < 70 {
|
||||
powerVar = "⚠ unstable"
|
||||
}
|
||||
thermalVar := "OK"
|
||||
if gpu.Scores.ThermalSustainScore < 70 {
|
||||
thermalVar = "⚠ unstable"
|
||||
}
|
||||
rows = append(rows, []string{fmt.Sprintf("GPU %d", gpu.Index), eccCorr, syncBoost, powerVar, thermalVar})
|
||||
}
|
||||
syncBoost := "-"
|
||||
if gpu.Scores.SyncBoostThrottlePct > 0 {
|
||||
syncBoost = fmt.Sprintf("%.1f%%", gpu.Scores.SyncBoostThrottlePct)
|
||||
}
|
||||
powerVar := "OK"
|
||||
if gpu.Scores.PowerSustainScore < 70 {
|
||||
powerVar = "⚠ unstable"
|
||||
}
|
||||
thermalVar := "OK"
|
||||
if gpu.Scores.ThermalSustainScore < 70 {
|
||||
thermalVar = "⚠ unstable"
|
||||
}
|
||||
fmt.Fprintf(&b, "| GPU %d | %s | %s | %s | %s |\n",
|
||||
gpu.Index, eccCorr, syncBoost, powerVar, thermalVar)
|
||||
b.WriteString(fmtMDTable([]string{"GPU", "ECC corrected", "Sync boost throttle", "Power instability", "Thermal instability"}, rows))
|
||||
b.WriteString("\n")
|
||||
}
|
||||
b.WriteString("\n")
|
||||
|
||||
// ── Per GPU detail ────────────────────────────────────────────────────────
|
||||
b.WriteString("## Per-GPU Details\n\n")
|
||||
@@ -263,12 +286,16 @@ func renderBenchmarkReportWithCharts(result NvidiaBenchmarkResult) string {
|
||||
// Steady-state telemetry
|
||||
if benchmarkTelemetryAvailable(gpu.Steady) {
|
||||
fmt.Fprintf(&b, "**Steady-state telemetry** (%ds):\n\n", int(gpu.Steady.DurationSec))
|
||||
b.WriteString("| | Avg | P95 |\n|---|---|---|\n")
|
||||
fmt.Fprintf(&b, "| Power | %.1f W | %.1f W |\n", gpu.Steady.AvgPowerW, gpu.Steady.P95PowerW)
|
||||
fmt.Fprintf(&b, "| Temperature | %.1f °C | %.1f °C |\n", gpu.Steady.AvgTempC, gpu.Steady.P95TempC)
|
||||
fmt.Fprintf(&b, "| GPU clock | %.0f MHz | %.0f MHz |\n", gpu.Steady.AvgGraphicsClockMHz, gpu.Steady.P95GraphicsClockMHz)
|
||||
fmt.Fprintf(&b, "| Memory clock | %.0f MHz | %.0f MHz |\n", gpu.Steady.AvgMemoryClockMHz, gpu.Steady.P95MemoryClockMHz)
|
||||
fmt.Fprintf(&b, "| GPU utilisation | %.1f %% | — |\n", gpu.Steady.AvgUsagePct)
|
||||
b.WriteString(fmtMDTable(
|
||||
[]string{"", "Avg", "P95"},
|
||||
[][]string{
|
||||
{"Power", fmt.Sprintf("%.1f W", gpu.Steady.AvgPowerW), fmt.Sprintf("%.1f W", gpu.Steady.P95PowerW)},
|
||||
{"Temperature", fmt.Sprintf("%.1f °C", gpu.Steady.AvgTempC), fmt.Sprintf("%.1f °C", gpu.Steady.P95TempC)},
|
||||
{"GPU clock", fmt.Sprintf("%.0f MHz", gpu.Steady.AvgGraphicsClockMHz), fmt.Sprintf("%.0f MHz", gpu.Steady.P95GraphicsClockMHz)},
|
||||
{"Memory clock", fmt.Sprintf("%.0f MHz", gpu.Steady.AvgMemoryClockMHz), fmt.Sprintf("%.0f MHz", gpu.Steady.P95MemoryClockMHz)},
|
||||
{"GPU utilisation", fmt.Sprintf("%.1f %%", gpu.Steady.AvgUsagePct), "—"},
|
||||
},
|
||||
))
|
||||
b.WriteString("\n")
|
||||
} else {
|
||||
b.WriteString("**Steady-state telemetry:** unavailable\n\n")
|
||||
@@ -277,7 +304,7 @@ func renderBenchmarkReportWithCharts(result NvidiaBenchmarkResult) string {
|
||||
// Per-precision stability phases.
|
||||
if len(gpu.PrecisionSteady) > 0 {
|
||||
b.WriteString("**Per-precision stability:**\n\n")
|
||||
b.WriteString("| Precision | Status | Clock CV | Power CV | Clock Drift | ECC corr | ECC uncorr |\n|-----------|--------|----------|----------|-------------|----------|------------|\n")
|
||||
var precRows [][]string
|
||||
for _, p := range gpu.PrecisionSteady {
|
||||
eccCorr := "—"
|
||||
eccUncorr := "—"
|
||||
@@ -289,10 +316,15 @@ func renderBenchmarkReportWithCharts(result NvidiaBenchmarkResult) string {
|
||||
if strings.TrimSpace(status) == "" {
|
||||
status = "OK"
|
||||
}
|
||||
fmt.Fprintf(&b, "| %s | %s | %.1f%% | %.1f%% | %.1f%% | %s | %s |\n",
|
||||
p.Precision, status, p.Steady.ClockCVPct, p.Steady.PowerCVPct, p.Steady.ClockDriftPct,
|
||||
eccCorr, eccUncorr)
|
||||
precRows = append(precRows, []string{
|
||||
p.Precision, status,
|
||||
fmt.Sprintf("%.1f%%", p.Steady.ClockCVPct),
|
||||
fmt.Sprintf("%.1f%%", p.Steady.PowerCVPct),
|
||||
fmt.Sprintf("%.1f%%", p.Steady.ClockDriftPct),
|
||||
eccCorr, eccUncorr,
|
||||
})
|
||||
}
|
||||
b.WriteString(fmtMDTable([]string{"Precision", "Status", "Clock CV", "Power CV", "Clock Drift", "ECC corr", "ECC uncorr"}, precRows))
|
||||
b.WriteString("\n")
|
||||
} else {
|
||||
// Legacy: show combined-window variance.
|
||||
@@ -315,16 +347,22 @@ func renderBenchmarkReportWithCharts(result NvidiaBenchmarkResult) string {
|
||||
// Precision results
|
||||
if len(gpu.PrecisionResults) > 0 {
|
||||
b.WriteString("**Precision results:**\n\n")
|
||||
b.WriteString("| Precision | TOPS (raw) | Weight | TOPS (fp32-eq) | Lanes | Iterations |\n|-----------|------------|--------|----------------|-------|------------|\n")
|
||||
var presRows [][]string
|
||||
for _, p := range gpu.PrecisionResults {
|
||||
if p.Supported {
|
||||
weightStr := fmt.Sprintf("×%.3g", p.Weight)
|
||||
fmt.Fprintf(&b, "| %s | %.2f | %s | %.2f | %d | %d |\n",
|
||||
p.Name, p.TeraOpsPerSec, weightStr, p.WeightedTeraOpsPerSec, p.Lanes, p.Iterations)
|
||||
presRows = append(presRows, []string{
|
||||
p.Name,
|
||||
fmt.Sprintf("%.2f", p.TeraOpsPerSec),
|
||||
fmt.Sprintf("×%.3g", p.Weight),
|
||||
fmt.Sprintf("%.2f", p.WeightedTeraOpsPerSec),
|
||||
fmt.Sprintf("%d", p.Lanes),
|
||||
fmt.Sprintf("%d", p.Iterations),
|
||||
})
|
||||
} else {
|
||||
fmt.Fprintf(&b, "| %s | — (unsupported) | — | — | — | — |\n", p.Name)
|
||||
presRows = append(presRows, []string{p.Name, "— (unsupported)", "—", "—", "—", "—"})
|
||||
}
|
||||
}
|
||||
b.WriteString(fmtMDTable([]string{"Precision", "TOPS (raw)", "Weight", "TOPS (fp32-eq)", "Lanes", "Iterations"}, presRows))
|
||||
b.WriteString("\n")
|
||||
}
|
||||
|
||||
@@ -346,9 +384,13 @@ func renderBenchmarkReportWithCharts(result NvidiaBenchmarkResult) string {
|
||||
b.WriteString("## Interconnect (NCCL)\n\n")
|
||||
fmt.Fprintf(&b, "**Status:** %s\n\n", result.Interconnect.Status)
|
||||
if result.Interconnect.Supported {
|
||||
b.WriteString("| Metric | Avg | Max |\n|--------|-----|-----|\n")
|
||||
fmt.Fprintf(&b, "| Alg BW | %.1f GB/s | %.1f GB/s |\n", result.Interconnect.AvgAlgBWGBps, result.Interconnect.MaxAlgBWGBps)
|
||||
fmt.Fprintf(&b, "| Bus BW | %.1f GB/s | %.1f GB/s |\n", result.Interconnect.AvgBusBWGBps, result.Interconnect.MaxBusBWGBps)
|
||||
b.WriteString(fmtMDTable(
|
||||
[]string{"Metric", "Avg", "Max"},
|
||||
[][]string{
|
||||
{"Alg BW", fmt.Sprintf("%.1f GB/s", result.Interconnect.AvgAlgBWGBps), fmt.Sprintf("%.1f GB/s", result.Interconnect.MaxAlgBWGBps)},
|
||||
{"Bus BW", fmt.Sprintf("%.1f GB/s", result.Interconnect.AvgBusBWGBps), fmt.Sprintf("%.1f GB/s", result.Interconnect.MaxBusBWGBps)},
|
||||
},
|
||||
))
|
||||
b.WriteString("\n")
|
||||
}
|
||||
for _, note := range result.Interconnect.Notes {
|
||||
@@ -365,14 +407,16 @@ func renderBenchmarkReportWithCharts(result NvidiaBenchmarkResult) string {
|
||||
if !sp.Available {
|
||||
b.WriteString("IPMI power measurement unavailable.\n\n")
|
||||
} else {
|
||||
b.WriteString("| | Value |\n|---|---|\n")
|
||||
fmt.Fprintf(&b, "| Server idle | %.0f W |\n", sp.IdleW)
|
||||
fmt.Fprintf(&b, "| Server under load | %.0f W |\n", sp.LoadedW)
|
||||
fmt.Fprintf(&b, "| Server delta (load − idle) | %.0f W |\n", sp.DeltaW)
|
||||
fmt.Fprintf(&b, "| GPU-reported sum | %.0f W |\n", sp.GPUReportedSumW)
|
||||
if sp.ReportingRatio > 0 {
|
||||
fmt.Fprintf(&b, "| Reporting ratio | %.2f (1.0 = accurate, <0.75 = GPU over-reports) |\n", sp.ReportingRatio)
|
||||
spRows := [][]string{
|
||||
{"Server idle", fmt.Sprintf("%.0f W", sp.IdleW)},
|
||||
{"Server under load", fmt.Sprintf("%.0f W", sp.LoadedW)},
|
||||
{"Server delta (load − idle)", fmt.Sprintf("%.0f W", sp.DeltaW)},
|
||||
{"GPU-reported sum", fmt.Sprintf("%.0f W", sp.GPUReportedSumW)},
|
||||
}
|
||||
if sp.ReportingRatio > 0 {
|
||||
spRows = append(spRows, []string{"Reporting ratio", fmt.Sprintf("%.2f (1.0 = accurate, <0.75 = GPU over-reports)", sp.ReportingRatio)})
|
||||
}
|
||||
b.WriteString(fmtMDTable([]string{"", "Value"}, spRows))
|
||||
b.WriteString("\n")
|
||||
}
|
||||
for _, note := range sp.Notes {
|
||||
@@ -397,15 +441,19 @@ func renderBenchmarkReportWithCharts(result NvidiaBenchmarkResult) string {
|
||||
if cooling := result.Cooling; cooling != nil {
|
||||
b.WriteString("## Cooling\n\n")
|
||||
if cooling.Available {
|
||||
b.WriteString("| Metric | Value |\n|--------|-------|\n")
|
||||
fmt.Fprintf(&b, "| Average fan speed | %.0f RPM |\n", cooling.AvgFanRPM)
|
||||
dutyAvg, dutyP95 := "N/A", "N/A"
|
||||
if cooling.FanDutyCycleAvailable {
|
||||
fmt.Fprintf(&b, "| Average fan duty cycle | %.1f%% |\n", cooling.AvgFanDutyCyclePct)
|
||||
fmt.Fprintf(&b, "| P95 fan duty cycle | %.1f%% |\n", cooling.P95FanDutyCyclePct)
|
||||
} else {
|
||||
b.WriteString("| Average fan duty cycle | N/A |\n")
|
||||
b.WriteString("| P95 fan duty cycle | N/A |\n")
|
||||
dutyAvg = fmt.Sprintf("%.1f%%", cooling.AvgFanDutyCyclePct)
|
||||
dutyP95 = fmt.Sprintf("%.1f%%", cooling.P95FanDutyCyclePct)
|
||||
}
|
||||
b.WriteString(fmtMDTable(
|
||||
[]string{"Metric", "Value"},
|
||||
[][]string{
|
||||
{"Average fan speed", fmt.Sprintf("%.0f RPM", cooling.AvgFanRPM)},
|
||||
{"Average fan duty cycle", dutyAvg},
|
||||
{"P95 fan duty cycle", dutyP95},
|
||||
},
|
||||
))
|
||||
b.WriteString("\n")
|
||||
} else {
|
||||
b.WriteString("Cooling telemetry unavailable.\n\n")
|
||||
@@ -422,12 +470,16 @@ func renderBenchmarkReportWithCharts(result NvidiaBenchmarkResult) string {
|
||||
if len(result.PerformanceRampSteps) > 0 {
|
||||
b.WriteString("## Platform Scalability (Performance Ramp)\n\n")
|
||||
fmt.Fprintf(&b, "**Platform power score:** %.1f%% \n\n", result.PlatformPowerScore)
|
||||
b.WriteString("| k GPUs | GPU Indices | Total Synthetic TOPS | Scalability |\n")
|
||||
b.WriteString("|--------|-------------|----------------------|-------------|\n")
|
||||
var scalRows [][]string
|
||||
for _, step := range result.PerformanceRampSteps {
|
||||
fmt.Fprintf(&b, "| %d | %s | %.2f | %.1f%% |\n",
|
||||
step.StepIndex, joinIndexList(step.GPUIndices), step.TotalSyntheticTOPS, step.ScalabilityPct)
|
||||
scalRows = append(scalRows, []string{
|
||||
fmt.Sprintf("%d", step.StepIndex),
|
||||
joinIndexList(step.GPUIndices),
|
||||
fmt.Sprintf("%.2f", step.TotalSyntheticTOPS),
|
||||
fmt.Sprintf("%.1f%%", step.ScalabilityPct),
|
||||
})
|
||||
}
|
||||
b.WriteString(fmtMDTable([]string{"k GPUs", "GPU Indices", "Total Synthetic TOPS", "Scalability"}, scalRows))
|
||||
b.WriteString("\n")
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user