[LoopVectorize][PowerPC] Estimate int and float register pressure separately in loop-vectorize

In loop-vectorize, interleave count and vector factor depend on target register number. Currently, it does not
estimate different register pressure for different register class separately(especially for scalar type,
float type should not be on the same position with int type), so it's not accurate. Specifically,
it causes too many times interleaving/unrolling, result in too many register spills in loop body and hurting performance.

So we need classify the register classes in IR level, and importantly these are abstract register classes,
and are not the target register class of backend provided in td file. It's used to establish the mapping between
the types of IR values and the number of simultaneous live ranges to which we'd like to limit for some set of those types.

For example, POWER target, register num is special when VSX is enabled. When VSX is enabled, the number of int scalar register is 32(GPR),
float is 64(VSR), but for int and float vector register both are 64(VSR). So there should be 2 kinds of register class when vsx is enabled,
and 3 kinds of register class when VSX is NOT enabled.

It runs on POWER target, it makes big(+~30%) performance improvement in one specific bmk(503.bwaves_r) of spec2017 and no other obvious degressions.

Differential revision: https://reviews.llvm.org/D67148

llvm-svn: 374017

3 files changed, 214 insertions, 10 deletions

diff --git a/llvm/test/Transforms/LoopVectorize/PowerPC/reg-usage.ll b/llvm/test/Transforms/LoopVectorize/PowerPC/reg-usage.ll
new file mode 100644
index 00000000000..7c48d6400eb
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/PowerPC/reg-usage.ll
@@ -0,0 +1,178 @@
+; RUN: opt < %s -debug-only=loop-vectorize -loop-vectorize -vectorizer-maximize-bandwidth -O2 -mtriple=powerpc64-unknown-linux -S -mcpu=pwr8 2>&1 | FileCheck %s --check-prefixes=CHECK,CHECK-PWR8
+; RUN: opt < %s -debug-only=loop-vectorize -loop-vectorize -vectorizer-maximize-bandwidth -O2 -mtriple=powerpc64le-unknown-linux -S -mcpu=pwr9 2>&1 | FileCheck %s --check-prefixes=CHECK,CHECK-PWR9
+
+@a = global [1024 x i8] zeroinitializer, align 16
+@b = global [1024 x i8] zeroinitializer, align 16
+
+define i32 @foo() {
+;
+; CHECK-LABEL: foo
+
+; CHECK:      LV(REG): VF = 8
+; CHECK-NEXT: LV(REG): Found max usage: 2 item
+; CHECK-NEXT: LV(REG): RegisterClass: PPC::GPRRC, 2 registers
+; CHECK-NEXT: LV(REG): RegisterClass: PPC::VSXRC, 7 registers
+; CHECK-NEXT: LV(REG): Found invariant usage: 0 item
+; CHECK:      LV(REG): VF = 16
+; CHECK-NEXT: LV(REG): Found max usage: 2 item
+; CHECK-NEXT: LV(REG): RegisterClass: PPC::GPRRC, 2 registers
+; CHECK-NEXT: LV(REG): RegisterClass: PPC::VSXRC, 13 registers
+; CHECK-NEXT: LV(REG): Found invariant usage: 0 item
+
+; CHECK-PWR8:      LV(REG): VF = 16
+; CHECK-PWR8-NEXT: LV(REG): Found max usage: 2 item
+; CHECK-PWR8-NEXT: LV(REG): RegisterClass: PPC::GPRRC, 2 registers
+; CHECK-PWR8-NEXT: LV(REG): RegisterClass: PPC::VSXRC, 13 registers
+; CHECK-PWR8-NEXT: LV(REG): Found invariant usage: 0 item
+; CHECK-PWR8: Setting best plan to VF=16, UF=4
+
+; CHECK-PWR9:      LV(REG): VF = 8
+; CHECK-PWR9-NEXT: LV(REG): Found max usage: 2 item
+; CHECK-PWR9-NEXT: LV(REG): RegisterClass: PPC::GPRRC, 2 registers
+; CHECK-PWR9-NEXT: LV(REG): RegisterClass: PPC::VSXRC, 7 registers
+; CHECK-PWR9-NEXT: LV(REG): Found invariant usage: 0 item
+; CHECK-PWR9: Setting best plan to VF=8, UF=8
+
+
+entry:
+  br label %for.body
+
+for.cond.cleanup:
+  %add.lcssa = phi i32 [ %add, %for.body ]
+  ret i32 %add.lcssa
+
+for.body:
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %s.015 = phi i32 [ 0, %entry ], [ %add, %for.body ]
+  %arrayidx = getelementptr inbounds [1024 x i8], [1024 x i8]* @a, i64 0, i64 %indvars.iv
+  %0 = load i8, i8* %arrayidx, align 1
+  %conv = zext i8 %0 to i32
+  %arrayidx2 = getelementptr inbounds [1024 x i8], [1024 x i8]* @b, i64 0, i64 %indvars.iv
+  %1 = load i8, i8* %arrayidx2, align 1
+  %conv3 = zext i8 %1 to i32
+  %sub = sub nsw i32 %conv, %conv3
+  %ispos = icmp sgt i32 %sub, -1
+  %neg = sub nsw i32 0, %sub
+  %2 = select i1 %ispos, i32 %sub, i32 %neg
+  %add = add nsw i32 %2, %s.015
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 1024
+  br i1 %exitcond, label %for.cond.cleanup, label %for.body
+}
+
+define i32 @goo() {
+; For indvars.iv used in a computating chain only feeding into getelementptr or cmp,
+; it will not have vector version and the vector register usage will not exceed the
+; available vector register number.
+; CHECK-LABEL: goo
+; CHECK:      LV(REG): VF = 8
+; CHECK-NEXT: LV(REG): Found max usage: 2 item
+; CHECK-NEXT: LV(REG): RegisterClass: PPC::GPRRC, 2 registers
+; CHECK-NEXT: LV(REG): RegisterClass: PPC::VSXRC, 7 registers
+; CHECK-NEXT: LV(REG): Found invariant usage: 0 item
+; CHECK:      LV(REG): VF = 16
+; CHECK-NEXT: LV(REG): Found max usage: 2 item
+; CHECK-NEXT: LV(REG): RegisterClass: PPC::GPRRC, 2 registers
+; CHECK-NEXT: LV(REG): RegisterClass: PPC::VSXRC, 13 registers
+; CHECK-NEXT: LV(REG): Found invariant usage: 0 item
+; CHECK:      LV(REG): VF = 16
+; CHECK-NEXT: LV(REG): Found max usage: 2 item
+; CHECK-NEXT: LV(REG): RegisterClass: PPC::GPRRC, 2 registers
+; CHECK-NEXT: LV(REG): RegisterClass: PPC::VSXRC, 13 registers
+; CHECK-NEXT: LV(REG): Found invariant usage: 0 item
+
+; CHECK: Setting best plan to VF=16, UF=4
+
+entry:
+  br label %for.body
+
+for.cond.cleanup:                                 ; preds = %for.body
+  %add.lcssa = phi i32 [ %add, %for.body ]
+  ret i32 %add.lcssa
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %s.015 = phi i32 [ 0, %entry ], [ %add, %for.body ]
+  %tmp1 = add nsw i64 %indvars.iv, 3
+  %arrayidx = getelementptr inbounds [1024 x i8], [1024 x i8]* @a, i64 0, i64 %tmp1
+  %tmp = load i8, i8* %arrayidx, align 1
+  %conv = zext i8 %tmp to i32
+  %tmp2 = add nsw i64 %indvars.iv, 2
+  %arrayidx2 = getelementptr inbounds [1024 x i8], [1024 x i8]* @b, i64 0, i64 %tmp2
+  %tmp3 = load i8, i8* %arrayidx2, align 1
+  %conv3 = zext i8 %tmp3 to i32
+  %sub = sub nsw i32 %conv, %conv3
+  %ispos = icmp sgt i32 %sub, -1
+  %neg = sub nsw i32 0, %sub
+  %tmp4 = select i1 %ispos, i32 %sub, i32 %neg
+  %add = add nsw i32 %tmp4, %s.015
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 1024
+  br i1 %exitcond, label %for.cond.cleanup, label %for.body
+}
+
+define i64 @bar(i64* nocapture %a) {
+; CHECK-LABEL: bar
+; CHECK:      LV(REG): VF = 2
+; CHECK-NEXT: LV(REG): Found max usage: 2 item
+; CHECK-NEXT: LV(REG): RegisterClass: PPC::VSXRC, 3 registers
+; CHECK-NEXT: LV(REG): RegisterClass: PPC::GPRRC, 1 registers
+; CHECK-NEXT: LV(REG): Found invariant usage: 0 item
+
+; CHECK: Setting best plan to VF=2, UF=12
+
+entry:
+  br label %for.body
+
+for.cond.cleanup:
+  %add2.lcssa = phi i64 [ %add2, %for.body ]
+  ret i64 %add2.lcssa
+
+for.body:
+  %i.012 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %s.011 = phi i64 [ 0, %entry ], [ %add2, %for.body ]
+  %arrayidx = getelementptr inbounds i64, i64* %a, i64 %i.012
+  %0 = load i64, i64* %arrayidx, align 8
+  %add = add nsw i64 %0, %i.012
+  store i64 %add, i64* %arrayidx, align 8
+  %add2 = add nsw i64 %add, %s.011
+  %inc = add nuw nsw i64 %i.012, 1
+  %exitcond = icmp eq i64 %inc, 1024
+  br i1 %exitcond, label %for.cond.cleanup, label %for.body
+}
+
+@d = external global [0 x i64], align 8
+@e = external global [0 x i32], align 4
+@c = external global [0 x i32], align 4
+
+define void @hoo(i32 %n) {
+; CHECK-LABEL: hoo
+; CHECK:      LV(REG): VF = 4
+; CHECK-NEXT: LV(REG): Found max usage: 2 item
+; CHECK-NEXT: LV(REG): RegisterClass: PPC::GPRRC, 2 registers
+; CHECK-NEXT: LV(REG): RegisterClass: PPC::VSXRC, 2 registers
+; CHECK-NEXT: LV(REG): Found invariant usage: 0 item
+; CHECK:      LV(REG): VF = 1
+; CHECK-NEXT: LV(REG): Found max usage: 1 item
+; CHECK-NEXT: LV(REG): RegisterClass: PPC::GPRRC, 2 registers
+; CHECK-NEXT: LV(REG): Found invariant usage: 0 item
+; CHECK: Setting best plan to VF=1, UF=12
+
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds [0 x i64], [0 x i64]* @d, i64 0, i64 %indvars.iv
+  %tmp = load i64, i64* %arrayidx, align 8
+  %arrayidx1 = getelementptr inbounds [0 x i32], [0 x i32]* @e, i64 0, i64 %tmp
+  %tmp1 = load i32, i32* %arrayidx1, align 4
+  %arrayidx3 = getelementptr inbounds [0 x i32], [0 x i32]* @c, i64 0, i64 %indvars.iv
+  store i32 %tmp1, i32* %arrayidx3, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 10000
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
diff --git a/llvm/test/Transforms/LoopVectorize/X86/reg-usage-debug.ll b/llvm/test/Transforms/LoopVectorize/X86/reg-usage-debug.ll
index 8205092deff..b6254a4f8aa 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/reg-usage-debug.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/reg-usage-debug.ll
@@ -22,7 +22,11 @@ target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
 ; CHECK: LV: Checking a loop in "test_g"
-; CHECK: LV(REG): Found max usage: 2
+; CHECK: LV(REG): Found max usage: 2 item
+; CHECK-NEXT: LV(REG): RegisterClass: Generic::ScalarRC, 2 registers
+; CHECK-NEXT: LV(REG): RegisterClass: Generic::VectorRC, 2 registers
+; CHECK-NEXT: LV(REG): Found invariant usage: 1 item
+; CHECK-NEXT: LV(REG): RegisterClass: Generic::VectorRC, 2 registers
 
 define i32 @test_g(i32* nocapture readonly %a, i32 %n) local_unnamed_addr !dbg !6 {
 entry:
@@ -60,7 +64,11 @@ for.end:                                          ; preds = %for.end.loopexit, %
 }
 
 ; CHECK: LV: Checking a loop in "test"
-; CHECK: LV(REG): Found max usage: 2
+; CHECK: LV(REG): Found max usage: 2 item
+; CHECK-NEXT: LV(REG): RegisterClass: Generic::ScalarRC, 2 registers
+; CHECK-NEXT: LV(REG): RegisterClass: Generic::VectorRC, 2 registers
+; CHECK-NEXT: LV(REG): Found invariant usage: 1 item
+; CHECK-NEXT: LV(REG): RegisterClass: Generic::VectorRC, 2 registers
 
 define i32 @test(i32* nocapture readonly %a, i32 %n) local_unnamed_addr {
 entry:
diff --git a/llvm/test/Transforms/LoopVectorize/X86/reg-usage.ll b/llvm/test/Transforms/LoopVectorize/X86/reg-usage.ll
index 9b276aa2bd7..cae9360e061 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/reg-usage.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/reg-usage.ll
@@ -11,9 +11,15 @@ define i32 @foo() {
 ;
 ; CHECK-LABEL: foo
 ; CHECK:      LV(REG): VF = 8
-; CHECK-NEXT: LV(REG): Found max usage: 7
+; CHECK-NEXT: LV(REG): Found max usage: 2 item
+; CHECK-NEXT: LV(REG): RegisterClass: Generic::ScalarRC, 2 registers
+; CHECK-NEXT: LV(REG): RegisterClass: Generic::VectorRC, 7 registers
+; CHECK-NEXT: LV(REG): Found invariant usage: 0 item
 ; CHECK:      LV(REG): VF = 16
-; CHECK-NEXT: LV(REG): Found max usage: 13
+; CHECK-NEXT: LV(REG): Found max usage: 2 item
+; CHECK-NEXT: LV(REG): RegisterClass: Generic::ScalarRC, 2 registers
+; CHECK-NEXT: LV(REG): RegisterClass: Generic::VectorRC, 13 registers
+; CHECK-NEXT: LV(REG): Found invariant usage: 0 item
 
 entry:
   br label %for.body
@@ -47,9 +53,15 @@ define i32 @goo() {
 ; available vector register number.
 ; CHECK-LABEL: goo
 ; CHECK:      LV(REG): VF = 8
-; CHECK-NEXT: LV(REG): Found max usage: 7
+; CHECK-NEXT: LV(REG): Found max usage: 2 item
+; CHECK-NEXT: LV(REG): RegisterClass: Generic::ScalarRC, 2 registers
+; CHECK-NEXT: LV(REG): RegisterClass: Generic::VectorRC, 7 registers
+; CHECK-NEXT: LV(REG): Found invariant usage: 0 item
 ; CHECK:      LV(REG): VF = 16
-; CHECK-NEXT: LV(REG): Found max usage: 13
+; CHECK-NEXT: LV(REG): Found max usage: 2 item
+; CHECK-NEXT: LV(REG): RegisterClass: Generic::ScalarRC, 2 registers
+; CHECK-NEXT: LV(REG): RegisterClass: Generic::VectorRC, 13 registers
+; CHECK-NEXT: LV(REG): Found invariant usage: 0 item
 entry:
   br label %for.body
 
@@ -81,8 +93,11 @@ for.body:                                         ; preds = %for.body, %entry
 define i64 @bar(i64* nocapture %a) {
 ; CHECK-LABEL: bar
 ; CHECK:       LV(REG): VF = 2
-; CHECK:       LV(REG): Found max usage: 3
-;
+; CHECK-NEXT: LV(REG): Found max usage: 2 item
+; CHECK-NEXT: LV(REG): RegisterClass: Generic::VectorRC, 3 registers
+; CHECK-NEXT: LV(REG): RegisterClass: Generic::ScalarRC, 1 registers
+; CHECK-NEXT: LV(REG): Found invariant usage: 0 item
+
 entry:
   br label %for.body
 
@@ -113,8 +128,11 @@ define void @hoo(i32 %n) {
 ; so the max usage of AVX512 vector register will be 2.
 ; AVX512F-LABEL: bar
 ; AVX512F:       LV(REG): VF = 16
-; AVX512F:       LV(REG): Found max usage: 2
-;
+; AVX512F-CHECK: LV(REG): Found max usage: 2 item
+; AVX512F-CHECK: LV(REG): RegisterClass: Generic::ScalarRC, 2 registers
+; AVX512F-CHECK: LV(REG): RegisterClass: Generic::VectorRC, 2 registers
+; AVX512F-CHECK: LV(REG): Found invariant usage: 0 item
+
 entry:
   br label %for.body