INSERTPS—Insert Scalar Single-Precision Floating-Point ValueInstruction Operand EncodingDescription(register source form)Copy a single-precision scalar floating-point element into a 128-bit vector register. The immediate operand has three fields, where the ZMask bits specify which elements of the destination will be set to zero, the Count_D bits specify which element of the destination will be overwritten with the scalar value, and for vector register sources the Count_S bits specify which element of the source will be copied. When the scalar source is a memory operand the Count_S bits are ignored. (memory source form)Load a floating-point element from a 32-bit memory location and destination operand it into the first source at the location indicated by the Count_D bits of the immediate operand. Store in the destination and zero out destination elements based on the ZMask bits of the immediate operand. 128-bit Legacy SSE version: The first source register is an XMM register. The second source operand is either an XMM register or a 32-bit memory location. The destination is not distinct from the first source XMM register and the upper bits (MAXVL-1:128) of the corresponding register destination are unmodified.VEX.128 and EVEX encoded version: The destination and first source register is an XMM register. The second source operand is either an XMM register or a 32-bit memory location. The upper bits (MAXVL-1:128) of the corre-sponding register destination are zeroed.If VINSERTPS is encoded with VEX.L= 1, an attempt to execute the instruction encoded with VEX.L= 1 will cause an #UD exception.Opcode/InstructionOp / En64/32 bit Mode SupportCPUID Feature FlagDescription66 0F 3A 21 /r ibINSERTPS xmm1, xmm2/m32, imm8AV/VSSE4_1Insert a single-precision floating-point value selected by imm8 from xmm2/m32 into xmm1 at the specified destination element specified by imm8 and zero out destination elements in xmm1 as indicated in imm8.VEX.128.66.0F3A.WIG 21 /r ibVINSERTPS xmm1, xmm2, xmm3/m32, imm8BV/VAVXInsert a single-precision floating-point value selected by imm8 from xmm3/m32 and merge with values in xmm2 at the specified destination element specified by imm8 and write out the result and zero out destination elements in xmm1 as indicated in imm8.EVEX.128.66.0F3A.W0 21 /r ibVINSERTPS xmm1, xmm2, xmm3/m32, imm8CV/VAVX512FInsert a single-precision floating-point value selected by imm8 from xmm3/m32 and merge with values in xmm2 at the specified destination element specified by imm8 and write out the result and zero out destination elements in xmm1 as indicated in imm8.Op/EnTuple TypeOperand 1Operand 2Operand 3Operand 4ANAModRM:reg (r, w)ModRM:r/m (r)Imm8NABNAModRM:reg (w)VEX.vvvv (r)ModRM:r/m (r)Imm8CTuple1 ScalarModRM:reg (w)EVEX.vvvv (r)ModRM:r/m (r)Imm8
This UNOFFICIAL reference was generated from the official Intel® 64 and IA-32 Architectures Software Developer’s Manual by a dumb script. There is no guarantee that some parts aren't mangled or broken and is distributed WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.