Pull in regalloc2 v0.2.0, with no more separate scratch registers. (#4182)

RA2 recently removed the need for a dedicated scratch register for
cyclic moves (bytecodealliance/regalloc2#51). This has moderate positive
performance impact on function bodies that were register-constrained, as
it means that one more register is available. In Sightglass, I measured
+5-8% on `blake3-scalar`, at least among current benchmarks.

cranelift/codegen/src/isa/aarch64/inst/regs.rs

@@ -209,24 +209,9 @@ pub fn create_reg_env(flags: &settings::Flags) -> MachineEnv {
                 preg(vreg(28)),
                 preg(vreg(29)),
                 preg(vreg(30)),
-                // v31 is the scratch reg, to allow for parallel moves.
+                preg(vreg(31)),
             ],
         ],
-        scratch_by_class: [
-            // We use tmp2 (x17) as the regalloc scratch register,
-            // used to resolve cyclic parallel moves. This is valid
-            // because tmp2 is never live between regalloc-visible
-            // instructions, only within them (i.e. in expansion into
-            // multiple machine instructions when that
-            // occurs). spilltmp is used for moves to/from spillslots,
-            // but tmp2 never is, so it is available for this
-            // purpose. (Its only other use is in prologue stack
-            // checks, and the prologue is prepended after regalloc
-            // runs.)
-            preg(tmp2_reg()),
-            // We use v31 for Float/Vec-class parallel moves.
-            preg(vreg(31)),
-        ],
         fixed_stack_slots: vec![],
     };
 

cranelift/codegen/src/isa/s390x/inst/regs.rs

@@ -102,7 +102,7 @@ pub fn create_machine_env(_flags: &settings::Flags) -> MachineEnv {
                 preg(gpr(10)),
                 preg(gpr(11)),
                 preg(gpr(12)),
-                // no r13; it is our scratch reg.
+                preg(gpr(13)),
                 preg(gpr(14)),
                 // no r15; it is the stack pointer.
             ],
@@ -114,10 +114,9 @@ pub fn create_machine_env(_flags: &settings::Flags) -> MachineEnv {
                 preg(fpr(12)),
                 preg(fpr(13)),
                 preg(fpr(14)),
-                // no f15; it is our scratch reg.
+                preg(fpr(15)),
             ],
         ],
-        scratch_by_class: [preg(gpr(13)), preg(fpr(15))],
         fixed_stack_slots: vec![],
     }
 }

cranelift/codegen/src/isa/x64/inst/regs.rs

@@ -166,7 +166,7 @@ pub(crate) fn create_reg_env_systemv(flags: &settings::Flags) -> MachineEnv {
                 preg(rdx()),
                 preg(r8()),
                 preg(r9()),
-                // N.B.: not r10; it is our scratch reg.
+                preg(r10()),
                 preg(r11()),
             ],
             // Preferred XMMs: all of them.
@@ -186,7 +186,7 @@ pub(crate) fn create_reg_env_systemv(flags: &settings::Flags) -> MachineEnv {
                 preg(xmm12()),
                 preg(xmm13()),
                 preg(xmm14()),
-                // N.B.: not xmm15; it is our scratch reg.
+                preg(xmm15()),
             ],
         ],
         non_preferred_regs_by_class: [
@@ -195,7 +195,6 @@ pub(crate) fn create_reg_env_systemv(flags: &settings::Flags) -> MachineEnv {
             // Non-preferred XMMs: none.
             vec![],
         ],
-        scratch_by_class: [preg(r10()), preg(xmm15())],
         fixed_stack_slots: vec![],
     };
 

cranelift/codegen/src/isa/x64/mod.rs

@@ -425,11 +425,11 @@ mod test {
         // 00000004  41B900000000      mov r9d,0x0
         // 0000000A  83FF02            cmp edi,byte +0x2
         // 0000000D  0F8320000000      jnc near 0x33
-        // 00000013  8BC7              mov eax,edi
-        // 00000015  490F43C1          cmovnc rax,r9
+        // 00000013  8BF7              mov esi,edi
+        // 00000015  490F43F1          cmovnc rsi,r9
         // 00000019  4C8D0D0B000000    lea r9,[rel 0x2b]
-        // 00000020  4963448100        movsxd rax,dword [r9+rax*4+0x0]
-        // 00000025  4901C1            add r9,rax
+        // 00000020  496374B100        movsxd rsi,dword [r9+rsi*4+0x0]
+        // 00000025  4901F1            add r9,rsi
         // 00000028  41FFE1            jmp r9
         // 0000002B  1200              adc al,[rax]
         // 0000002D  0000              add [rax],al
@@ -449,8 +449,8 @@ mod test {
         // 00000050  C3                ret
 
         let golden = vec![
-            85, 72, 137, 229, 65, 185, 0, 0, 0, 0, 131, 255, 2, 15, 131, 32, 0, 0, 0, 139, 199, 73,
-            15, 67, 193, 76, 141, 13, 11, 0, 0, 0, 73, 99, 68, 129, 0, 73, 1, 193, 65, 255, 225,
+            85, 72, 137, 229, 65, 185, 0, 0, 0, 0, 131, 255, 2, 15, 131, 32, 0, 0, 0, 139, 247, 73,
+            15, 67, 241, 76, 141, 13, 11, 0, 0, 0, 73, 99, 116, 177, 0, 73, 1, 241, 65, 255, 225,
             18, 0, 0, 0, 28, 0, 0, 0, 184, 3, 0, 0, 0, 72, 137, 236, 93, 195, 184, 1, 0, 0, 0, 72,
             137, 236, 93, 195, 184, 2, 0, 0, 0, 72, 137, 236, 93, 195,
         ];