Add saturating subtraction with a SIMD encoding

This includes the new instructions `ssub_sat` and `usub_sat` and only encodes the i8x16 and i16x8 types; these are what is needed for implementing the SIMD spec (see https://github.com/WebAssembly/simd/blob/master/proposals/simd/SIMD.md#saturating-integer-subtraction).

cranelift/codegen/meta/src/isa/x86/encodings.rs

@@ -480,6 +480,7 @@ pub(crate) fn define(
     let sqrt = shared.by_name("sqrt");
     let sshr = shared.by_name("sshr");
     let sshr_imm = shared.by_name("sshr_imm");
+    let ssub_sat = shared.by_name("ssub_sat");
     let stack_addr = shared.by_name("stack_addr");
     let store = shared.by_name("store");
     let store_complex = shared.by_name("store_complex");
@@ -501,6 +502,7 @@ pub(crate) fn define(
     let uload8_complex = shared.by_name("uload8_complex");
     let ushr = shared.by_name("ushr");
     let ushr_imm = shared.by_name("ushr_imm");
+    let usub_sat = shared.by_name("usub_sat");
     let vconst = shared.by_name("vconst");
     let x86_bsf = x86.by_name("x86_bsf");
     let x86_bsr = x86.by_name("x86_bsr");
@@ -1965,6 +1967,24 @@ pub(crate) fn define(
         e.enc_32_64(isub, rec_fa.opcodes(*opcodes));
     }
 
+    // SIMD integer saturating subtraction
+    e.enc_32_64(
+        ssub_sat.bind_vector_from_lane(I8, sse_vector_size),
+        rec_fa.opcodes(&PSUBSB),
+    );
+    e.enc_32_64(
+        ssub_sat.bind_vector_from_lane(I16, sse_vector_size),
+        rec_fa.opcodes(&PSUBSW),
+    );
+    e.enc_32_64(
+        usub_sat.bind_vector_from_lane(I8, sse_vector_size),
+        rec_fa.opcodes(&PSUBUSB),
+    );
+    e.enc_32_64(
+        usub_sat.bind_vector_from_lane(I16, sse_vector_size),
+        rec_fa.opcodes(&PSUBUSW),
+    );
+
     // SIMD integer multiplication: the x86 ISA does not have instructions for multiplying I8x16
     // and I64x2 and these are (at the time of writing) not necessary for WASM SIMD.
     for (ty, opcodes, isap) in &[

cranelift/codegen/meta/src/isa/x86/opcodes.rs

@@ -326,6 +326,22 @@ pub static PSUBD: [u8; 3] = [0x66, 0x0f, 0xfa];
 /// Subtract packed quadword integers in xmm2/m128 from xmm1 (SSE2).
 pub static PSUBQ: [u8; 3] = [0x66, 0x0f, 0xfb];
 
+/// Subtract packed signed byte integers in xmm2/m128 from packed signed byte integers in xmm1
+/// and saturate results (SSE2).
+pub static PSUBSB: [u8; 3] = [0x66, 0x0f, 0xe8];
+
+/// Subtract packed signed word integers in xmm2/m128 from packed signed word integers in xmm1
+/// and saturate results (SSE2).
+pub static PSUBSW: [u8; 3] = [0x66, 0x0f, 0xe9];
+
+/// Subtract packed unsigned byte integers in xmm2/m128 from packed unsigned byte integers in xmm1
+/// and saturate results (SSE2).
+pub static PSUBUSB: [u8; 3] = [0x66, 0x0f, 0xd8];
+
+/// Subtract packed unsigned word integers in xmm2/m128 from packed unsigned word integers in xmm1
+/// and saturate results (SSE2).
+pub static PSUBUSW: [u8; 3] = [0x66, 0x0f, 0xd9];
+
 /// Push r{16,32,64}.
 pub static PUSH_REG: [u8; 1] = [0x50];