[llvm] b723d5a - [llvm-exegesis][x86] Add option to prevent use of xmm8-xmm15 upper SSE registers

[Simon Pilgrim via llvm-commits]

Author: Simon Pilgrim
Date: 2022-12-07T17:54:09Z
New Revision: b723d5a625c0135a8c6a72572ba91ddf566e8723

URL: https://github.com/llvm/llvm-project/commit/b723d5a625c0135a8c6a72572ba91ddf566e8723
DIFF: https://github.com/llvm/llvm-project/commit/b723d5a625c0135a8c6a72572ba91ddf566e8723.diff

LOG: [llvm-exegesis][x86] Add option to prevent use of xmm8-xmm15 upper SSE registers

Noticed while trying to use llvm-exegesis to get some accurate capture numbers on some old Atom/Silverment hardware as part of the work with D103695.

These targets' frontends are particularly poor and the use of the xmm8-xmm15 SSE registers results in longer instruction encodings which were affecting the latency/throughput estimates.

Thanks to @lebedev.ri for the --skip-measurements command line argument which made testing much easier!

Differential Revision: https://reviews.llvm.org/D138832

Added: 
    llvm/test/tools/llvm-exegesis/X86/inverse_throughput/inverse_throughput-disable-upper-sse-registers.s

Modified: 
    llvm/docs/CommandGuide/llvm-exegesis.rst
    llvm/tools/llvm-exegesis/lib/X86/Target.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/docs/CommandGuide/llvm-exegesis.rst b/llvm/docs/CommandGuide/llvm-exegesis.rst
index d8f98aa5c3969..1d78f455d1e63 100644
--- a/llvm/docs/CommandGuide/llvm-exegesis.rst
+++ b/llvm/docs/CommandGuide/llvm-exegesis.rst
@@ -213,6 +213,15 @@ OPTIONS
   could occur if the sampling is too frequent. A prime number should be used to
   avoid consistently skipping certain blocks.
 
+.. option:: -x86-disable-upper-sse-registers
+
+  Using the upper xmm registers (xmm8-xmm15) forces a longer instruction encoding
+  which may put greater pressure on the frontend fetch and decode stages,
+  potentially reducing the rate that instructions are dispatched to the backend,
+  particularly on older hardware. Comparing baseline results with this mode
+  enabled can help determine the effects of the frontend and can be used to
+  improve latency and throughput estimates.
+
 .. option:: -repetition-mode=[duplicate|loop|min]
 
  Specify the repetition mode. `duplicate` will create a large, straight line

diff  --git a/llvm/test/tools/llvm-exegesis/X86/inverse_throughput/inverse_throughput-disable-upper-sse-registers.s b/llvm/test/tools/llvm-exegesis/X86/inverse_throughput/inverse_throughput-disable-upper-sse-registers.s
new file mode 100644
index 0000000000000..65921fded8867
--- /dev/null
+++ b/llvm/test/tools/llvm-exegesis/X86/inverse_throughput/inverse_throughput-disable-upper-sse-registers.s
@@ -0,0 +1,10 @@
+# RUN: llvm-exegesis -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mode=inverse_throughput --skip-measurements -x86-disable-upper-sse-registers -opcode-name=ADDPSrr -repetition-mode=loop | FileCheck %s
+
+CHECK:      ---
+CHECK-NEXT: mode:            inverse_throughput
+CHECK-NEXT: key:
+CHECK-NEXT:   instructions:
+CHECK-NEXT:     - 'ADDPSrr [[LHS0:XMM[0-7]]] [[LHS0]] [[RHS0:XMM[0-7]]]'
+CHECK-NEXT:     - 'ADDPSrr [[LHS1:XMM[0-7]]] [[LHS1]] [[RHS1:XMM[0-7]]]'
+CHECK-NEXT:     - 'ADDPSrr [[LHS2:XMM[0-7]]] [[LHS2]] [[RHS2:XMM[0-7]]]'
+CHECK-NEXT:     - 'ADDPSrr [[LHS3:XMM[0-7]]] [[LHS3]] [[RHS3:XMM[0-7]]]'

diff  --git a/llvm/tools/llvm-exegesis/lib/X86/Target.cpp b/llvm/tools/llvm-exegesis/lib/X86/Target.cpp
index 6ecb6b17f2071..8ab6a67662118 100644
--- a/llvm/tools/llvm-exegesis/lib/X86/Target.cpp
+++ b/llvm/tools/llvm-exegesis/lib/X86/Target.cpp
@@ -54,6 +54,11 @@ static cl::opt<unsigned> LbrSamplingPeriod(
     cl::desc("The sample period (nbranches/sample), used for LBR sampling"),
     cl::cat(BenchmarkOptions), cl::init(0));
 
+static cl::opt<bool>
+    DisableUpperSSERegisters("x86-disable-upper-sse-registers",
+                             cl::desc("Disable XMM8-XMM15 register usage"),
+                             cl::cat(BenchmarkOptions), cl::init(false));
+
 // FIXME: Validates that repetition-mode is loop if LBR is requested.
 
 // Returns a non-null reason if we cannot handle the memory references in this
@@ -708,6 +713,11 @@ class ExegesisX86Target : public ExegesisTarget {
                                const APInt &Value) const override;
 
   ArrayRef<unsigned> getUnavailableRegisters() const override {
+    if (DisableUpperSSERegisters)
+      return makeArrayRef(kUnavailableRegistersSSE,
+                          sizeof(kUnavailableRegistersSSE) /
+                              sizeof(kUnavailableRegistersSSE[0]));
+
     return makeArrayRef(kUnavailableRegisters,
                         std::size(kUnavailableRegisters));
   }
@@ -772,6 +782,7 @@ class ExegesisX86Target : public ExegesisTarget {
   }
 
   static const unsigned kUnavailableRegisters[4];
+  static const unsigned kUnavailableRegistersSSE[12];
 };
 
 // We disable a few registers that cannot be encoded on instructions with a REX
@@ -779,6 +790,12 @@ class ExegesisX86Target : public ExegesisTarget {
 const unsigned ExegesisX86Target::kUnavailableRegisters[4] = {X86::AH, X86::BH,
                                                               X86::CH, X86::DH};
 
+// Optionally, also disable the upper (x86_64) SSE registers to reduce frontend
+// decoder load.
+const unsigned ExegesisX86Target::kUnavailableRegistersSSE[12] = {
+    X86::AH,    X86::BH,    X86::CH,    X86::DH,    X86::XMM8,  X86::XMM9,
+    X86::XMM10, X86::XMM11, X86::XMM12, X86::XMM13, X86::XMM14, X86::XMM15};
+
 // We're using one of R8-R15 because these registers are never hardcoded in
 // instructions (e.g. MOVS writes to EDI, ESI, EDX), so they have less
 // conflicts.